diff --git a/docs/Developer-Guide/README.md b/docs/Developer-Guide/README.md
deleted file mode 100644
index 9742ec2..0000000
--- a/docs/Developer-Guide/README.md
+++ /dev/null
@@ -1,172 +0,0 @@
-# SuperClaude Framework Developer Guide
-
-A documentation suite for understanding and extending the SuperClaude Context-Oriented Configuration Framework.
-
-## Documentation Overview
-
-This Developer Guide provides documentation for understanding SuperClaude's context architecture and how to extend it:
-
-### [Contributing Code Guide](contributing-code.md)
-**Purpose**: Guidelines for contributing context files and framework improvements
-**Audience**: Contributors and framework maintainers
-**Key Topics**: Adding context files, naming conventions, documentation standards
-
-### [Context Architecture Guide](technical-architecture.md)
-**Purpose**: Understanding how context files work and are structured
-**Audience**: Anyone wanting to understand or extend SuperClaude
-**Key Topics**: Context file structure, import system, agent/command patterns
-
-### [Verification & Troubleshooting Guide](testing-debugging.md)
-**Purpose**: Verifying installation and troubleshooting context file issues
-**Audience**: Users and maintainers
-**Key Topics**: File verification, common issues, diagnostic commands
-
-### [Documentation Index](documentation-index.md)
-**Purpose**: Comprehensive navigation guide and topic-based organization
-**Audience**: All users seeking efficient information discovery
-**Key Features**: Skill level pathways, cross-references, quality validation, usage guidelines
-
-## Quick Navigation
-
-### For New Contributors
-1. Start with [Contributing Code Guide](contributing-code.md#development-setup) for environment setup
-2. Review [Technical Architecture Guide](technical-architecture.md#architecture-overview) for system understanding
-3. Use [Testing & Debugging Guide](testing-debugging.md#quick-start-testing-tutorial) for testing basics
-
-### For System Architects
-1. Begin with [Technical Architecture Guide](technical-architecture.md) for complete system design
-2. Reference [Contributing Code Guide](contributing-code.md#architecture-overview) for component patterns
-3. Review [Testing & Debugging Guide](testing-debugging.md#integration-testing) for validation frameworks
-
-### For Testing Engineers
-1. Start with [Testing & Debugging Guide](testing-debugging.md) for comprehensive testing procedures
-2. Reference [Contributing Code Guide](contributing-code.md#development-workflow) for development integration
-3. Use [Technical Architecture Guide](technical-architecture.md#quality-framework) for architecture context
-
-## Key Framework Concepts
-
-### Context-Oriented Configuration
-SuperClaude is a collection of `.md` instruction files that Claude Code reads to modify its behavior. It is NOT executing software.
-
-**IMPORTANT**: SuperClaude is NOT a CLI tool or executable software. When you see `/sc:` commands in documentation, these are **context trigger patterns** you type in Claude Code conversations, not terminal commands.
-
-### Agent Context Files
-Specialized instruction sets that provide domain expertise when activated by `@agent-[name]` or automatically by keywords.
-
-### Command Context Files
-Workflow patterns triggered by `/sc:[command]` **context patterns** (not CLI commands) that guide Claude Code through structured development tasks when you type them in Claude Code conversations.
-
-### MCP Integration
-External tools (actual software) that can be configured to provide additional capabilities like documentation lookup or code analysis.
-
-## What SuperClaude Is NOT
-
-- ❌ **Not Software**: No code executes, no processes run
-- ❌ **Not Testable**: Context files are instructions, not functions
-- ❌ **Not Optimizable**: No performance to measure or improve
-- ❌ **Not Persistent**: Each Claude conversation is independent
-
-## Documentation Features
-
-### Cross-Referenced Integration
-All three documents are strategically cross-referenced, enabling seamless navigation between development workflows, architectural understanding, and testing procedures.
-
-### Accessibility & Inclusivity
-- **Screen Reader Support**: Full navigation guidance and diagram descriptions
-- **Skill Level Pathways**: Clear progression from beginner to advanced
-- **Comprehensive Glossaries**: 240+ technical terms with detailed definitions
-- **Learning Resources**: Time estimates and prerequisite guidance
-
-### Consistent Terminology
-Unified technical vocabulary ensures clear communication across all documentation, with key terms defined consistently throughout comprehensive glossaries.
-
-### Comprehensive Code Examples
-All code examples include proper documentation, error handling, and follow consistent formatting standards suitable for production use.
-
-### Security-First Approach
-Security considerations are embedded throughout all documentation, from development practices to testing procedures to architectural design.
-
-### Professional Quality Standards
-- **WCAG 2.1 Compliant**: Full accessibility standards compliance
-- **Technical Accuracy**: All examples tested and verified
-- **Framework Integration**: Documentation quality matches framework sophistication
-- **Community Focus**: Inclusive design for developers of all abilities
-
-## Document Status
-
-✅ **Phase 1 Complete**: Critical issues resolved, basic structure established
-✅ **Phase 2 Complete**: Cross-document consistency, navigation improvements, security integration
-✅ **Phase 3 Complete**: Advanced examples, visual diagrams, enhanced architecture documentation
-✅ **Phase 4 Complete**: Accessibility improvements, comprehensive glossaries, skill level guidance, professional polish
-
-### Accessibility & Quality Enhancements (Phase 4)
-- **240+ Glossary Terms**: Comprehensive technical definitions across all documents
-- **Screen Reader Support**: Full accessibility with navigation guidance and diagram descriptions
-- **Skill Level Pathways**: Clear learning progressions from beginner to advanced
-- **Professional Polish**: Documentation quality aligned with framework sophistication
-
-## Getting Started
-
-### Prerequisites
-- Python 3.8+ (for installation tool)
-- Claude Code installed
-- Optional: Node.js 16+ for MCP servers
-
-### Understanding the Framework
-```bash
-# Check installation
-ls ~/.claude/
-# You'll see context files, not executable code
-
-# View a command context
-cat ~/.claude/commands/implement.md
-# You'll see instructions for Claude, not code
-
-# View an agent context
-cat ~/.claude/agents/python-expert.md
-# You'll see expertise definitions, not programs
-```
-
-### Extending SuperClaude
-1. **Add Commands**: Create new `.md` files in `~/.claude/commands/`
-2. **Add Agents**: Create new `.md` files in `~/.claude/agents/`
-3. **Add Modes**: Create new `.md` files in `~/.claude/modes/`
-
-No compilation, no testing, no deployment - just add context files and Claude Code will read them automatically.
-
-## Support and Resources
-
-### Documentation Issues
-- **Broken Links**: Report cross-reference issues in GitHub issues
-- **Unclear Content**: Request clarification through GitHub discussions
-- **Missing Information**: Suggest improvements through pull requests
-
-### Development Support
-- **Technical Questions**: Use GitHub discussions for architecture and implementation questions
-- **Bug Reports**: Submit detailed issues with reproduction steps
-- **Feature Requests**: Propose enhancements through GitHub issues
-
-### Community Resources
-- **[GitHub Repository](https://github.com/SuperClaude-Org/SuperClaude_Framework)**: Main development and collaboration hub
-
-## Contributing to Documentation
-
-We welcome contributions to improve documentation quality, accuracy, and completeness:
-
-### Documentation Standards
-- **Clarity**: Write for your target audience skill level
-- **Consistency**: Follow established terminology and formatting
-- **Completeness**: Provide working examples and complete procedures
-- **Cross-References**: Link related concepts across documents
-
-### Submission Process
-1. Fork the repository and create a feature branch
-2. Make documentation improvements following our standards
-3. Test all code examples and verify cross-references
-4. Submit pull request with clear description of changes
-
----
-
-**SuperClaude Framework**: Building the future of AI-assisted development through intelligent orchestration and behavioral programming.
-
-For the latest updates and community discussions, visit our [GitHub repository](https://github.com/SuperClaude-Org/SuperClaude_Framework).
\ No newline at end of file
diff --git a/docs/Developer-Guide/contributing-code.md b/docs/Developer-Guide/contributing-code.md
deleted file mode 100644
index d47603c..0000000
--- a/docs/Developer-Guide/contributing-code.md
+++ /dev/null
@@ -1,401 +0,0 @@
-# Contributing Context Files to SuperClaude Framework 🛠️
-
-Welcome to SuperClaude Framework development! This guide provides everything you need to contribute context files and behavioral instructions that enhance Claude Code through structured prompts and MCP server integration.
-
-**Project Purpose**: SuperClaude provides Claude Code with structured context files and behavioral instructions. We're building the next generation of AI-assisted development through intelligent prompt engineering.
-
-## Table of Contents
-
-1. [Development Setup](#development-setup) - Prerequisites and environment
-2. [Architecture Overview](#architecture-overview) - System components and design
-3. [Context File Guidelines](#context-file-guidelines) - Standards and practices
-4. [Development Workflow](#development-workflow) - Git workflow and submissions
-5. [Contributing to Components](#contributing-to-components) - Agents, commands, modes
-6. [File Validation](#file-validation) - Quality assurance
-7. [Getting Help](#getting-help) - Support and resources
-
-## Development Setup
-
-### Prerequisites
-
-**Required:**
-- Python 3.8+ with pip
-- Git for version control
-- Claude Code installed and working
-- Node.js 16+ (for MCP server configuration)
-
-**Environment Setup:**
-```bash
-# Fork SuperClaude_Framework on GitHub first
-git clone https://github.com/YOUR_USERNAME/SuperClaude_Framework.git
-cd SuperClaude_Framework
-
-# Test installation system
-PYTHONPATH=/path/to/SuperClaude_Framework python3 -m setup --help
-
-# Install to development location
-PYTHONPATH=/path/to/SuperClaude_Framework python3 -m setup install --components core
-```
-
-**Validation Check:**
-```bash
-# Verify Python version
-python3 --version # Should be 3.8+
-
-# Check Node.js for MCP configuration
-node --version # Should be 16+
-
-# Test Claude Code integration
-ls ~/.claude/ # Should show Claude Code directory
-```
-
-## Architecture Overview
-
-### Framework Structure
-
-SuperClaude is a **Context-Oriented Configuration Framework** - not executing software, but instruction files that Claude Code reads to modify its behavior.
-
-```
-SuperClaude_Framework/
-├── superclaude/ # Framework components (the source of truth)
-│ ├── Core/ # PRINCIPLES.md, RULES.md, FLAGS.md
-│ ├── Agents/ # 15 specialized domain experts
-│ ├── Commands/ # 21 context trigger patterns (/sc: behavioral instructions)
-│ ├── Modes/ # 6 behavioral modification patterns
-│ └── MCP/ # 6 MCP server configurations
-├── setup/ # Python installation system
-├── docs/ # Documentation (what you're reading)
-└── tests/ # File validation scripts
-```
-
-**Key Concepts:**
-- **Context Files**: .md instruction files that guide Claude Code behavior
-- **Agents**: Domain specialists (e.g., security-engineer.md, python-expert.md)
-- **Commands**: Workflow patterns (e.g., implement.md, analyze.md)
-- **Modes**: Interaction modifiers (e.g., brainstorming, introspection)
-- **MCP Integration**: Configuration for Model Context Protocol servers
-
-### How It Works
-
-```
-User Input → Claude Code → Reads SuperClaude Context → Modified Behavior → Enhanced Output
-```
-
-1. User types `/sc:implement "auth system"` **in Claude Code conversation** (not terminal)
-2. Claude Code reads `superclaude/Commands/implement.md`
-3. Command activates security-engineer agent context
-4. Context7 MCP provides authentication patterns
-5. Claude generates complete, secure implementation
-
-## Context File Guidelines
-
-### File Organization
-
-**Context Files (`.md`):**
-- Write clear, actionable instructions for Claude Code
-- Use frontmatter metadata for configuration
-- Follow existing patterns and naming conventions
-- Test instructions produce expected behaviors
-
-**Installation Scripts (`.py`):**
-- Follow PEP 8 style guidelines
-- Include docstrings for functions and classes
-- Add type hints where beneficial
-- Focus on file copying and configuration
-
-**Example Agent Structure:**
-```markdown
----
-name: new-specialist
-description: Brief description of expertise
-category: specialized|architecture|quality
----
-
-# Agent Name
-
-## Triggers
-- Keywords that activate this agent
-- File types that trigger activation
-
-## Behavioral Mindset
-Core philosophy and approach
-
-## Focus Areas
-- Domain expertise area 1
-- Domain expertise area 2
-
-## Key Actions
-1. Specific behavior pattern
-2. Problem-solving approach
-```
-
-### Context File Standards
-
-**Structure Requirements:**
-- Clear, actionable instructions for Claude Code
-- Specific triggers and activation patterns
-- Examples demonstrating usage
-- Boundaries defining scope
-
-**Quality Standards:**
-- Instructions are testable in Claude Code conversations
-- Examples produce expected behavioral changes
-- Clear activation triggers and context patterns
-- Professional language and formatting
-
-## Development Workflow
-
-### Git Workflow
-
-1. **Fork and Clone:**
- ```bash
- # Fork on GitHub, then:
- git clone https://github.com/YOUR_USERNAME/SuperClaude_Framework.git
- cd SuperClaude_Framework
- git remote add upstream https://github.com/SuperClaude-Org/SuperClaude_Framework.git
- ```
-
-2. **Create Feature Branch:**
- ```bash
- git checkout -b feature/your-feature-name
- # Work on your changes
- git add .
- git commit -m "Add: descriptive commit message"
- ```
-
-3. **Submit Pull Request:**
- ```bash
- git push origin feature/your-feature-name
- # Create PR on GitHub
- ```
-
-### Pull Request Template
-
-```markdown
-## Description
-Brief description of context file changes
-
-## Type of Change
-- [ ] Bug fix in context files
-- [ ] New feature (agent, command, mode)
-- [ ] Documentation improvement
-- [ ] Installation system enhancement
-
-## Testing
-- [ ] Manual testing with Claude Code
-- [ ] Context file validation passes
-- [ ] Examples validated in Claude Code conversations
-
-## Checklist
-- [ ] Files follow SuperClaude conventions
-- [ ] Self-review completed
-- [ ] Documentation updated
-- [ ] No breaking changes to existing context
-```
-
-### Code Review Process
-
-**Manual Review:**
-- Context file clarity and effectiveness
-- Agent/command logic and triggers
-- Documentation accuracy and completeness
-- Integration with existing components
-- Claude Code behavioral testing results
-
-## Contributing to Components
-
-### Adding New Agents
-
-**Agent Development Process:**
-1. Identify domain expertise gap
-2. Create agent file in `superclaude/Agents/`
-3. Define triggers, behaviors, and boundaries
-4. Test with various Claude Code scenarios
-5. Document usage patterns and examples
-
-**Agent Template:**
-```markdown
----
-name: agent-name
-description: Domain expertise description
-category: specialized
-tools: Read, Write, Edit, Bash
----
-
-# Agent Name
-
-## Triggers
-- Specific keywords: domain, expertise, area
-- File patterns: *.domain, specific frameworks
-- Complexity indicators: architectural decisions
-
-## Behavioral Mindset
-- Focus on domain best practices
-- Systematic approach to problem-solving
-- Quality and security considerations
-
-## Focus Areas
-- Core domain expertise
-- Related technical areas
-- Integration patterns
-
-## Key Actions
-1. Analyze requirements within domain context
-2. Apply domain-specific best practices
-3. Coordinate with related specialists
-4. Validate solutions meet domain standards
-```
-
-### Adding New Commands
-
-**Command Structure:**
-```markdown
----
-name: command-name
-description: Command purpose
-category: workflow|utility|analysis
-complexity: basic|standard|advanced
-mcp-servers: [context7, sequential]
-personas: [architect, engineer]
----
-
-# /sc:command-name
-
-## Triggers
-- When to use this command
-- Context indicators
-
-## Usage
-Type in Claude Code conversation:
-```
-/sc:command-name [target] [--options]
-```
-**Note**: This is a context trigger pattern, not a terminal command.
-
-## Workflow Pattern
-1. Initial analysis
-2. Processing steps
-3. Validation and output
-
-## Examples
-Practical usage examples
-```
-
-### Adding New Modes
-
-**Mode Development:**
-- Define activation triggers
-- Specify behavioral modifications
-- Create interaction patterns
-- Test across different Claude Code scenarios
-
-## File Validation
-
-### Context File Validation
-
-**Manual Validation Process:**
-1. Install development version in Claude Code
-2. Test agent/command activation triggers in Claude Code conversations
-3. Verify behavioral modifications occur as expected
-4. Validate context file structure and formatting
-5. Test edge cases and error conditions
-
-**Validation Checklist:**
-- [ ] Context files use valid markdown syntax
-- [ ] Triggers activate correctly in Claude Code
-- [ ] Behavior matches documentation
-- [ ] No conflicts with existing components
-- [ ] Examples produce expected results in Claude Code conversations
-
-### File Structure Validation
-
-```bash
-# Check file structure
-find ~/.claude -name "*.md" | head -10
-
-# Verify context file format
-head ~/.claude/agents/python-expert.md
-
-# Test import system
-grep "@import" ~/.claude/CLAUDE.md
-```
-
-## Getting Help
-
-### Development Support
-
-**Documentation:**
-- [Technical Architecture](technical-architecture.md) - System design details
-- [Verification Guide](testing-debugging.md) - File validation procedures
-
-**Community Channels:**
-- GitHub Issues: Bug reports and feature requests
-- GitHub Discussions: Development questions and ideas
-- Pull Request Reviews: Context file feedback and collaboration
-
-**Code Review Guidelines:**
-- Provide constructive, specific feedback
-- Test changes locally when possible
-- Focus on maintainability and clarity
-- Respect contributor efforts and learning
-
-### Issue Reporting
-
-**Bug Reports:**
-1. Describe expected vs actual behavior in Claude Code
-2. Provide steps to reproduce with context triggers
-3. Include environment details and file versions
-4. Share relevant context file configurations
-
-**Feature Requests:**
-1. Explain the behavioral enhancement being proposed
-2. Describe how users would benefit
-3. Consider integration with existing context patterns
-4. Provide usage examples
-
-## Contributing Guidelines Summary
-
-### Do's
-✅ **Follow existing patterns and conventions**
-✅ **Test context files thoroughly with Claude Code**
-✅ **Write clear, actionable behavioral instructions**
-✅ **Provide working examples**
-✅ **Focus on user experience improvements**
-✅ **Coordinate with related components**
-
-### Don'ts
-❌ **Don't break existing functionality**
-❌ **Don't add untested context modifications**
-❌ **Don't ignore style guidelines**
-❌ **Don't create overly complex behavioral patterns**
-❌ **Don't duplicate existing functionality**
-
-### Quality Standards
-
-**Context Files:**
-- Clear activation triggers
-- Specific behavioral instructions
-- Practical examples
-- Defined scope boundaries
-
-**Documentation:**
-- Accurate and up-to-date
-- Working context examples
-- Clear navigation structure
-- Accessibility considerations
-
-## License and Attribution
-
-**MIT License**: SuperClaude Framework is licensed under the MIT License, providing maximum freedom for use, modification, and distribution.
-
-By contributing to SuperClaude Framework, you agree that your contributions will be licensed under the same MIT License. You retain copyright to your contributions while granting the project perpetual rights to use, modify, and distribute your context files.
-
-## Acknowledgments
-
-SuperClaude Framework exists because of the collaborative effort of developers, users, and contributors who believe in advancing AI-assisted development. Every bug report, feature suggestion, documentation improvement, and context file contribution makes the framework better for everyone.
-
-Your expertise and perspective make SuperClaude Framework better. Whether you're improving context files, adding features, or helping other users, every contribution advances the goal of more effective AI-assisted development.
-
----
-
-**Welcome to the SuperClaude Framework contributor community!** Your contributions help build the future of AI-assisted development through intelligent context and behavioral programming.
diff --git a/docs/Developer-Guide/documentation-index.md b/docs/Developer-Guide/documentation-index.md
deleted file mode 100644
index 53052e6..0000000
--- a/docs/Developer-Guide/documentation-index.md
+++ /dev/null
@@ -1,227 +0,0 @@
-# SuperClaude Framework Developer-Guide Index
-
-## Document Navigation Guide
-
-This index provides comprehensive access to all SuperClaude Framework development documentation, organized by topic and skill level for efficient information discovery.
-
-### Quick Navigation
-
-**For New Contributors**: Start with [Contributing Guide → Setup](contributing-code.md#development-setup)
-
-**For System Understanding**: Begin with [Technical Architecture Guide → Context Architecture](technical-architecture.md#context-file-architecture)
-
-**For Verification**: Start with [Verification Guide → Installation Check](testing-debugging.md#installation-verification)
-
----
-
-## Primary Documentation
-
-### 📋 [Contributing Context Files Guide](contributing-code.md)
-**Purpose**: Complete context file development and contribution guidelines
-**Target Audience**: Framework contributors and context file developers
-**Length**: ~1,000 lines focused on context file reality
-
-**Key Sections**:
-- [Development Setup](contributing-code.md#development-setup) - Environment configuration and prerequisites
-- [Context File Guidelines](contributing-code.md#context-file-guidelines) - Standards and structure
-- [Development Workflow](contributing-code.md#development-workflow) - Git workflow and submission process
-- [Contributing to Components](contributing-code.md#contributing-to-components) - Agent, command, and mode development
-- [File Validation](contributing-code.md#file-validation) - Context file verification methods
-
-### 🏗️ [Context Architecture Guide](technical-architecture.md)
-**Purpose**: Understanding how context files work and are structured
-**Target Audience**: Anyone wanting to understand or extend SuperClaude
-**Length**: ~800 lines focused on context file patterns and Claude Code integration
-
-**Key Sections**:
-- [Context File Architecture](technical-architecture.md#context-file-architecture) - Directory structure and file types
-- [The Import System](technical-architecture.md#the-import-system) - How Claude Code loads context
-- [Agent Context Structure](technical-architecture.md#agent-context-structure) - Domain specialist contexts
-- [Command Context Structure](technical-architecture.md#command-context-structure) - Workflow patterns
-- [How Claude Code Reads Context](technical-architecture.md#how-claude-code-reads-context) - Processing sequence
-- [Extending the Framework](technical-architecture.md#extending-the-framework) - Adding new components
-
-### 🧪 [Verification & Troubleshooting Guide](testing-debugging.md)
-**Purpose**: Verifying installation and troubleshooting context file issues
-**Target Audience**: Users and maintainers
-**Length**: ~500 lines focused on file verification and Claude Code integration
-
-**Key Sections**:
-- [Installation Verification](testing-debugging.md#installation-verification) - Check context file installation
-- [Context File Verification](testing-debugging.md#context-file-verification) - File structure validation
-- [MCP Server Verification](testing-debugging.md#mcp-server-verification) - External tool configuration
-- [Common Issues](testing-debugging.md#common-issues) - Troubleshooting activation problems
-- [Troubleshooting Commands](testing-debugging.md#troubleshooting-commands) - Diagnostic procedures
-
----
-
-## Topic-Based Index
-
-### 🚀 Getting Started
-
-**Complete Beginners**:
-1. [Contributing Guide → Setup](contributing-code.md#development-setup) - Environment setup
-2. [Architecture Guide → Overview](technical-architecture.md#overview) - Understanding context files
-3. [Verification Guide → Installation Check](testing-debugging.md#installation-verification) - Basic verification
-
-**Environment Setup**:
-- [Development Setup](contributing-code.md#development-setup) - Prerequisites and configuration
-- [Installation Verification](testing-debugging.md#installation-verification) - File installation check
-
-### 🏗️ Architecture & Design
-
-**Context File Architecture**:
-- [Context File Architecture](technical-architecture.md#context-file-architecture) - Complete system design
-- [The Import System](technical-architecture.md#the-import-system) - How Claude Code loads context
-- [Agent Context Structure](technical-architecture.md#agent-context-structure) - Domain specialist patterns
-- [Command Context Structure](technical-architecture.md#command-context-structure) - Workflow definitions
-
-**Component Development**:
-- [Contributing to Components](contributing-code.md#contributing-to-components) - Agent, command, mode development
-- [Adding New Agents](contributing-code.md#adding-new-agents) - Domain specialist creation
-- [Adding New Commands](contributing-code.md#adding-new-commands) - Workflow pattern development
-- [Extending the Framework](technical-architecture.md#extending-the-framework) - Framework expansion
-
-### 🧪 Verification & Quality
-
-**File Verification**:
-- [Context File Verification](testing-debugging.md#context-file-verification) - File structure validation
-- [File Validation](contributing-code.md#file-validation) - Context file verification methods
-
-**Troubleshooting**:
-- [Common Issues](testing-debugging.md#common-issues) - Activation and configuration problems
-- [Troubleshooting Commands](testing-debugging.md#troubleshooting-commands) - Diagnostic procedures
-
-### 🔧 Development Workflows
-
-**Context File Development**:
-- [Development Workflow](contributing-code.md#development-workflow) - Git workflow
-- [Context File Guidelines](contributing-code.md#context-file-guidelines) - Standards and practices
-- [Pull Request Process](contributing-code.md#pull-request-template) - Submission process
-
-**Component Development**:
-- [Agent Development](contributing-code.md#adding-new-agents) - Domain specialist creation
-- [Command Development](contributing-code.md#adding-new-commands) - Workflow pattern creation
-- [Mode Development](contributing-code.md#adding-new-modes) - Behavioral modification patterns
-
-### 🛠️ MCP Integration
-
-**MCP Configuration**:
-- [MCP Server Configuration](technical-architecture.md#mcp-server-configuration) - External tool setup
-- [MCP Server Verification](testing-debugging.md#mcp-server-verification) - Configuration validation
-
-### 🚨 Support & Troubleshooting
-
-**Common Issues**:
-- [Commands Not Working](testing-debugging.md#issue-commands-not-working) - Context trigger problems
-- [Agents Not Activating](testing-debugging.md#issue-agents-not-activating) - Activation issues
-- [Context Not Loading](testing-debugging.md#issue-context-not-loading) - Loading problems
-
-**Support Resources**:
-- [Getting Help](contributing-code.md#getting-help) - Support channels
-- [Issue Reporting](contributing-code.md#issue-reporting) - Bug reports and features
-
----
-
-## Skill Level Pathways
-
-### 🟢 Beginner Path (Understanding SuperClaude)
-
-**Week 1: Foundation**
-1. [Architecture Overview](technical-architecture.md#overview) - What SuperClaude is
-2. [Installation Verification](testing-debugging.md#installation-verification) - Check your setup
-3. [Context File Architecture](technical-architecture.md#context-file-architecture) - Directory structure
-
-**Week 2: Basic Usage**
-1. [How Claude Code Reads Context](technical-architecture.md#how-claude-code-reads-context) - Processing sequence
-2. [Common Issues](testing-debugging.md#common-issues) - Troubleshooting basics
-3. [Context File Guidelines](contributing-code.md#context-file-guidelines) - File standards
-
-### 🟡 Intermediate Path (Contributing Context Files)
-
-**Month 1: Context Development**
-1. [Development Setup](contributing-code.md#development-setup) - Environment preparation
-2. [Agent Context Structure](technical-architecture.md#agent-context-structure) - Domain specialists
-3. [Command Context Structure](technical-architecture.md#command-context-structure) - Workflow patterns
-
-**Month 2: Component Creation**
-1. [Adding New Agents](contributing-code.md#adding-new-agents) - Domain specialist development
-2. [Adding New Commands](contributing-code.md#adding-new-commands) - Workflow creation
-3. [File Validation](contributing-code.md#file-validation) - Context verification
-
-### 🔴 Advanced Path (Framework Extension)
-
-**Advanced Understanding**
-1. [The Import System](technical-architecture.md#the-import-system) - Context loading mechanics
-2. [Extending the Framework](technical-architecture.md#extending-the-framework) - Framework expansion
-3. [MCP Server Configuration](technical-architecture.md#mcp-server-configuration) - External tool integration
-
----
-
-## Reference Materials
-
-### 📚 Key Concepts
-
-**Framework Fundamentals**:
-- Context-Oriented Configuration Framework
-- Agent Domain Specialists
-- Command Workflow Patterns
-- Mode Behavioral Modifications
-- MCP Integration Patterns
-
-### 🔗 Cross-References
-
-**Development → Architecture**:
-- [Context File Guidelines](contributing-code.md#context-file-guidelines) → [Context File Architecture](technical-architecture.md#context-file-architecture)
-- [Adding Components](contributing-code.md#contributing-to-components) → [Agent/Command Structure](technical-architecture.md#agent-context-structure)
-
-**Development → Verification**:
-- [Development Workflow](contributing-code.md#development-workflow) → [File Verification](testing-debugging.md#context-file-verification)
-- [File Validation](contributing-code.md#file-validation) → [Installation Verification](testing-debugging.md#installation-verification)
-
-**Architecture → Verification**:
-- [How Claude Code Reads Context](technical-architecture.md#how-claude-code-reads-context) → [Troubleshooting](testing-debugging.md#common-issues)
-- [MCP Configuration](technical-architecture.md#mcp-server-configuration) → [MCP Verification](testing-debugging.md#mcp-server-verification)
-
----
-
-## Quality Standards
-
-### ✅ Documentation Accuracy
-- **Technical Precision**: All examples reflect SuperClaude reality (context files, not software)
-- **Command Accuracy**: Correct Python module execution paths and Claude Code context triggers
-- **No Fiction**: Removed all references to non-existent testing frameworks and performance systems
-
-### ✅ Content Focus
-- **Context Files**: Documentation centers on .md instruction files and Claude Code behavior
-- **File Verification**: Practical approaches to validating context file installation and structure
-- **Real Workflows**: Actual development processes for context file contribution
-
-### ✅ User Experience
-- **Clear Progression**: Skill-based learning paths from understanding to contribution
-- **Practical Examples**: Working context file examples and Claude Code integration
-- **Support Integration**: Clear guidance to help resources for real issues
-
----
-
-## Usage Guidelines
-
-### For Contributors
-1. **Start with**: [Development Setup](contributing-code.md#development-setup)
-2. **Context Development**: Follow [Context File Guidelines](contributing-code.md#context-file-guidelines)
-3. **Validation**: Use [File Validation](contributing-code.md#file-validation)
-4. **Support**: Reference [Getting Help](contributing-code.md#getting-help)
-
-### For Architects
-1. **System Understanding**: [Context File Architecture](technical-architecture.md#context-file-architecture)
-2. **Component Patterns**: [Agent and Command Structure](technical-architecture.md#agent-context-structure)
-3. **Extension**: [Extending the Framework](technical-architecture.md#extending-the-framework)
-4. **Integration**: [MCP Configuration](technical-architecture.md#mcp-server-configuration)
-
-### For Verification
-1. **Installation Check**: [Installation Verification](testing-debugging.md#installation-verification)
-2. **File Validation**: [Context File Verification](testing-debugging.md#context-file-verification)
-3. **Troubleshooting**: [Common Issues](testing-debugging.md#common-issues)
-4. **Diagnostics**: [Troubleshooting Commands](testing-debugging.md#troubleshooting-commands)
-
-This comprehensive index reflects the reality of SuperClaude as a context-oriented configuration framework, focusing on practical context file development and Claude Code integration.
\ No newline at end of file
diff --git a/docs/Developer-Guide/technical-architecture.md b/docs/Developer-Guide/technical-architecture.md
deleted file mode 100644
index 3fb331a..0000000
--- a/docs/Developer-Guide/technical-architecture.md
+++ /dev/null
@@ -1,356 +0,0 @@
-# SuperClaude Context Architecture Guide
-
-## Overview
-
-This guide documents how SuperClaude's Context-Oriented Configuration Framework is structured and how Claude Code interprets these context files to modify its behavior.
-
-**Important**: SuperClaude is NOT standalone software with running processes, execution layers, or performance systems. It is a collection of `.md` instruction files that Claude Code reads to adopt specialized behaviors.
-
-## Table of Contents
-
-1. [Context File Architecture](#context-file-architecture)
-2. [The Import System](#the-import-system)
-3. [Agent Context Structure](#agent-context-structure)
-4. [Command Context Structure](#command-context-structure)
-5. [Mode Context Structure](#mode-context-structure)
-6. [MCP Server Configuration](#mcp-server-configuration)
-7. [How Claude Code Reads Context](#how-claude-code-reads-context)
-8. [Extending the Framework](#extending-the-framework)
-
-## Context File Architecture
-
-### Directory Structure
-
-```
-~/.claude/ (SuperClaude Framework Files Only)
-├── CLAUDE.md # Main context file with imports
-├── FLAGS.md # Flag definitions and triggers
-├── RULES.md # Core behavioral rules
-├── PRINCIPLES.md # Guiding principles
-├── ZIG.md # Zig language integration
-├── MCP_Context7.md # Context7 MCP integration
-├── MCP_Magic.md # Magic MCP integration
-├── MCP_Morphllm.md # Morphllm MCP integration
-├── MCP_Playwright.md # Playwright MCP integration
-├── MCP_Sequential.md # Sequential MCP integration
-├── MCP_Serena.md # Serena MCP integration
-├── MCP_Tavily.md # Tavily MCP integration
-├── MCP_Zig.md # Zig MCP integration
-├── MODE_Brainstorming.md # Collaborative discovery mode
-├── MODE_Business_Panel.md # Business expert panel mode
-├── MODE_DeepResearch.md # Deep research mode
-├── MODE_Introspection.md # Transparent reasoning mode
-├── MODE_Orchestration.md # Tool coordination mode
-├── MODE_Task_Management.md # Task orchestration mode
-├── MODE_Token_Efficiency.md # Compressed communication mode
-├── agents/ # Domain specialist contexts (19 total)
-│ ├── backend-architect.md # Backend expertise
-│ ├── business-panel-experts.md # Business strategy panel
-│ ├── deep-research-agent.md # Deep research expertise
-│ ├── devops-architect.md # DevOps expertise
-│ ├── frontend-architect.md # Frontend expertise
-│ ├── learning-guide.md # Educational expertise
-│ ├── performance-engineer.md # Performance expertise
-│ ├── python-expert.md # Python expertise
-│ ├── quality-engineer.md # Quality assurance expertise
-│ ├── refactoring-expert.md # Code quality expertise
-│ ├── requirements-analyst.md # Requirements expertise
-│ ├── root-cause-analyst.md # Problem diagnosis expertise
-│ ├── security-engineer.md # Security expertise
-│ ├── socratic-mentor.md # Educational expertise
-│ ├── spec-panel-experts.md # Specification review panel
-│ ├── system-architect.md # System design expertise
-│ ├── technical-writer.md # Documentation expertise
-│ ├── test-runner.md # Test execution expertise
-│ └── wave-orchestrator.md # Wave orchestration patterns
-└── commands/ # Workflow pattern contexts
- └── sc/ # SuperClaude command namespace (25 total)
- ├── analyze.md # Analysis patterns
- ├── brainstorm.md # Discovery patterns
- ├── build.md # Build patterns
- ├── business-panel.md # Business expert panel patterns
- ├── cleanup.md # Cleanup patterns
- ├── design.md # Design patterns
- ├── document.md # Documentation patterns
- ├── estimate.md # Estimation patterns
- ├── explain.md # Explanation patterns
- ├── git.md # Git workflow patterns
- ├── help.md # Help and command listing
- ├── implement.md # Implementation patterns
- ├── improve.md # Improvement patterns
- ├── index.md # Index patterns
- ├── load.md # Context loading patterns
- ├── reflect.md # Reflection patterns
- ├── research.md # Deep research patterns
- ├── save.md # Session persistence patterns
- ├── select-tool.md # Tool selection patterns
- ├── spawn.md # Multi-agent patterns
- ├── spec-panel.md # Specification review panel
- ├── task.md # Task management patterns
- ├── test.md # Testing patterns
- ├── troubleshoot.md # Troubleshooting patterns
- └── workflow.md # Workflow planning patterns
-
-Note: Other directories (backups/, logs/, projects/, serena/, etc.) are Claude Code
-operational directories, not part of SuperClaude framework content.
-```
-
-### Context File Types
-
-| File Type | Purpose | Activation | Example |
-|-----------|---------|------------|---------|
-| **Commands** | Define workflow patterns | `/sc:[command]` (context trigger) | User types `/sc:implement` → reads `implement.md` |
-| **Agents** | Provide domain expertise | `@agent-[name]` or auto | `@agent-security` → reads `security-engineer.md` |
-| **Modes** | Modify interaction style | Flags or triggers | `--brainstorm` → activates brainstorming mode |
-| **Core** | Set fundamental rules | Always active | `RULES.md` always loaded |
-
-## The Import System
-
-### How CLAUDE.md Works
-
-The main `CLAUDE.md` file uses an import system to load multiple context files:
-
-```markdown
-# CLAUDE
-
-*MANDATORY*
-@FLAGS.md # Flag definitions and triggers
-@RULES.md # Core behavioral rules
-@PRINCIPLES.md # Guiding principles
-*SECONDARY*
-@MCP_Context7.md # Context7 MCP integration
-@MCP_Magic.md # Magic MCP integration
-@MCP_Morphllm.md # Morphllm MCP integration
-@MCP_Playwright.md # Playwright MCP integration
-@MCP_Sequential.md # Sequential MCP integration
-@MCP_Serena.md # Serena MCP integration
-@MCP_Tavily.md # Tavily MCP integration
-@MCP_Zig.md # Zig MCP integration
-*CRITICAL*
-@MODE_Brainstorming.md # Collaborative discovery mode
-@MODE_Business_Panel.md # Business expert panel mode
-@MODE_DeepResearch.md # Deep research mode
-@MODE_Introspection.md # Transparent reasoning mode
-@MODE_Task_Management.md # Task orchestration mode
-@MODE_Orchestration.md # Tool coordination mode
-@MODE_Token_Efficiency.md # Compressed communication mode
-*LANGUAGE SPECIFIC*
-@ZIG.md # Zig language integration
-```
-
-### Import Processing
-
-1. Claude Code reads `CLAUDE.md`
-2. Encounters `@import` statements
-3. Loads referenced files into context
-4. Builds complete behavioral framework
-5. Applies relevant contexts based on user input
-
-## Agent Context Structure
-
-### Anatomy of an Agent File
-
-Each agent `.md` file follows this structure:
-
-```markdown
----
-name: agent-name
-description: Brief description
-category: specialized|architecture|quality
----
-
-# Agent Name
-
-## Triggers
-- Keywords that activate this agent
-- File types that trigger activation
-- Complexity thresholds
-
-## Behavioral Mindset
-Core philosophy and approach
-
-## Focus Areas
-- Domain expertise area 1
-- Domain expertise area 2
-
-## Key Actions
-1. Specific behavior pattern
-2. Problem-solving approach
-```
-
-### Agent Activation Logic
-
-- **Manual**: User types `@agent-python-expert "task"`
-- **Automatic**: Keywords in request trigger agent loading
-- **Contextual**: File types or patterns activate relevant agents
-
-## Command Context Structure
-
-### Anatomy of a Command File
-
-```markdown
----
-name: command-name
-description: Command purpose
-category: utility|orchestration|analysis
-complexity: basic|enhanced|advanced
-mcp-servers: [context7, sequential]
-personas: [architect, engineer]
----
-
-# /sc:command-name
-
-## Triggers
-- When to use this command
-- Context indicators
-
-## Usage
-/sc:command-name [target] [--options]
-
-## Workflow Pattern
-1. Step 1: Initial action
-2. Step 2: Processing
-3. Step 3: Validation
-
-## Examples
-Practical usage examples
-```
-
-### Command Processing
-
-When user types `/sc:implement "feature"` in Claude Code conversation:
-1. Claude reads `commands/sc/implement.md`
-2. Adopts implementation workflow pattern
-3. May auto-activate related agents
-4. Follows defined workflow steps
-
-## Mode Context Structure
-
-### Behavioral Modes
-
-Modes modify Claude's interaction style:
-
-```markdown
-# MODE_[Name].md
-
-## Activation Triggers
-- Flag: --mode-name
-- Keywords: [triggers]
-- Complexity: threshold
-
-## Behavioral Modifications
-- Communication style changes
-- Decision-making adjustments
-- Output format modifications
-
-## Interaction Patterns
-- How to respond
-- What to prioritize
-```
-
-## MCP Server Configuration
-
-### Configuration Location
-
-MCP servers are configured in `~/.claude.json` (NOT part of SuperClaude context):
-
-```json
-{
- "mcpServers": {
- "context7": {
- "command": "npx",
- "args": ["-y", "@upstash/context7-mcp@latest"]
- },
- "sequential-thinking": {
- "command": "npx",
- "args": ["-y", "sequential-thinking-mcp@latest"]
- }
- }
-}
-```
-
-### MCP Integration
-
-- **MCP Servers**: Actual software providing tools
-- **SuperClaude**: Context that tells Claude when to use them
-- **Activation**: Flags or keywords trigger MCP usage
-
-## How Claude Code Reads Context
-
-### Context Loading Sequence
-
-```
-User Input (in Claude Code): "/sc:analyze src/ --focus security"
- ↓
-1. Parse Command: identify 'analyze' command
- ↓
-2. Load Context: read commands/sc/analyze.md
- ↓
-3. Check Flags: --focus security
- ↓
-4. Auto-Activation: load security-engineer.md
- ↓
-5. Apply Patterns: follow analysis workflow
- ↓
-6. Generate Output: using loaded contexts
-```
-
-### Context Priority
-
-1. **Explicit Commands**: `/sc:` commands take precedence
-2. **Manual Agents**: `@agent-` override auto-activation
-3. **Flags**: Modify behavior of commands/agents
-4. **Auto-Activation**: Based on keywords/context
-5. **Default Behavior**: Standard Claude Code
-
-## Extending the Framework
-
-### Adding New Commands
-
-1. Create `~/.claude/commands/sc/new-command.md`
-2. Define metadata, triggers, and workflow
-3. No code changes needed - just context
-
-### Adding New Agents
-
-1. Create `~/.claude/agents/new-specialist.md`
-2. Define expertise, triggers, and behaviors
-3. Agent becomes available
-
-### Adding New Modes
-
-1. Create `~/.claude/MODE_NewMode.md`
-2. Define activation triggers and modifications
-3. Mode activates based on triggers
-
-### Best Practices
-
-- **Keep Context Focused**: One concept per file
-- **Clear Triggers**: Define when context activates
-- **Workflow Patterns**: Provide step-by-step guidance
-- **Examples**: Include practical usage examples
-- **Metadata**: Use frontmatter for configuration
-
-## Important Clarifications
-
-### What SuperClaude Is NOT
-
-- ❌ **No Execution Engine**: No code runs, no processes execute
-- ❌ **No Performance System**: No optimization possible (it's just text)
-- ❌ **No Detection Engine**: Claude Code does pattern matching
-- ❌ **No Orchestration Layer**: Context files guide, not control
-- ❌ **No Quality Gates**: Just instructional patterns
-
-### What SuperClaude IS
-
-- ✅ **Context Files**: `.md` instructions for Claude Code
-- ✅ **Behavioral Patterns**: Workflows and approaches
-- ✅ **Domain Expertise**: Specialized knowledge contexts
-- ✅ **Configuration**: Settings for actual tools (MCP)
-- ✅ **Framework**: Structured prompt engineering
-
-## Summary
-
-SuperClaude's architecture is intentionally simple: it's a well-organized collection of context files that Claude Code reads to modify its behavior. The power comes from the careful crafting of these contexts and their systematic organization, not from any executing code or running processes.
-
-The framework's elegance lies in its simplicity - by providing Claude Code with structured instructions through context files, we can achieve sophisticated behavioral modifications without any software complexity.
diff --git a/docs/Developer-Guide/testing-debugging.md b/docs/Developer-Guide/testing-debugging.md
deleted file mode 100644
index 15f0caf..0000000
--- a/docs/Developer-Guide/testing-debugging.md
+++ /dev/null
@@ -1,324 +0,0 @@
-# SuperClaude Verification and Troubleshooting Guide
-
-## Overview
-
-This guide covers how to verify your SuperClaude installation and troubleshoot common issues with context files and configurations.
-
-**Important**: SuperClaude is a collection of context files, not executable software. This guide focuses on verifying context files are properly installed and accessible to Claude Code.
-
-## Table of Contents
-
-1. [Installation Verification](#installation-verification)
-2. [Context File Verification](#context-file-verification)
-3. [MCP Server Verification](#mcp-server-verification)
-4. [Common Issues](#common-issues)
-5. [Troubleshooting Commands](#troubleshooting-commands)
-
-## Installation Verification
-
-### Check Installation Status
-
-```bash
-# Verify SuperClaude installation system is available
-python3 -m SuperClaude --version
-# Expected: SuperClaude Framework installation help
-
-# Verify Claude Code CLI integration
-claude --version
-# Expected: Claude Code version info
-
-# Check if context files were installed
-ls ~/.claude/
-# Expected: CLAUDE.md, FLAGS.md, RULES.md, agents/, commands/, modes/
-
-# Verify main context file
-head ~/.claude/CLAUDE.md
-# Expected: Should show import statements
-```
-
-### Verify Directory Structure
-
-```bash
-# Check all directories exist
-for dir in agents commands modes; do
- if [ -d ~/.claude/$dir ]; then
- echo "✅ $dir directory exists"
- ls ~/.claude/$dir | wc -l
- else
- echo "❌ $dir directory missing"
- fi
-done
-```
-
-### Count Installed Components
-
-```bash
-# Should have 14 agents
-ls ~/.claude/agents/*.md | wc -l
-
-# Should have 21 commands
-ls ~/.claude/commands/*.md | wc -l
-
-# Should have 5 modes
-ls ~/.claude/modes/*.md | wc -l
-```
-
-## Context File Verification
-
-### Verify Core Files
-
-```bash
-# Check core context files exist
-for file in CLAUDE.md FLAGS.md RULES.md PRINCIPLES.md; do
- if [ -f ~/.claude/$file ]; then
- echo "✅ $file exists ($(wc -l < ~/.claude/$file) lines)"
- else
- echo "❌ $file missing"
- fi
-done
-```
-
-### Verify Import System
-
-```bash
-# Check CLAUDE.md has correct imports
-grep "@import" ~/.claude/CLAUDE.md
-# Expected output:
-# @import commands/*.md
-# @import agents/*.md
-# @import modes/*.md
-# @import FLAGS.md
-# @import RULES.md
-# @import PRINCIPLES.md
-```
-
-### Check File Integrity
-
-```bash
-# Verify files are readable text files
-file ~/.claude/CLAUDE.md
-# Expected: ASCII text or UTF-8 text
-
-# Check for corruption
-for file in ~/.claude/**/*.md; do
- if file "$file" | grep -q "text"; then
- echo "✅ $file is valid text"
- else
- echo "❌ $file may be corrupted"
- fi
-done
-```
-
-## MCP Server Verification
-
-### Check MCP Configuration
-
-```bash
-# Verify .claude.json exists
-if [ -f ~/.claude.json ]; then
- echo "✅ MCP configuration file exists"
- # Check which servers are configured
- grep -o '"[^"]*":' ~/.claude.json | grep -v mcpServers
-else
- echo "❌ No MCP configuration found"
-fi
-```
-
-### Test MCP Server Availability
-
-```bash
-# Check if Node.js is available (required for MCP)
-node --version
-# Expected: v16.0.0 or higher
-
-# Check if npx is available
-npx --version
-# Expected: Version number
-
-# Test Context7 MCP (if configured)
-npx -y @upstash/context7-mcp@latest --help 2>/dev/null && echo "✅ Context7 available" || echo "❌ Context7 not available"
-```
-
-## Common Issues
-
-### Issue: Commands Not Working
-
-**Symptom**: `/sc:` context triggers don't produce expected Claude Code behavior
-
-**Verification**:
-```bash
-# Check if command file exists
-ls ~/.claude/commands/implement.md
-# If missing, reinstall SuperClaude
-
-# Verify file content
-head -20 ~/.claude/commands/implement.md
-# Should show command metadata and instructions
-```
-
-**Solution**:
-```bash
-# Reinstall commands component
-PYTHONPATH=/path/to/SuperClaude_Framework python3 -m setup install --components commands --force
-```
-
-### Issue: Agents Not Activating
-
-**Symptom**: `@agent-` invocations don't work in Claude Code
-
-**Verification**:
-```bash
-# List all agents
-ls ~/.claude/agents/
-
-# Check specific agent
-cat ~/.claude/agents/python-expert.md | head -20
-```
-
-**Solution**:
-```bash
-# Reinstall agents
-PYTHONPATH=/path/to/SuperClaude_Framework python3 -m setup install --components agents --force
-```
-
-### Issue: Context Not Loading
-
-**Symptom**: Claude Code doesn't seem to read SuperClaude context
-
-**Verification**:
-```bash
-# Check CLAUDE.md is in correct location
-ls -la ~/.claude/CLAUDE.md
-
-# Verify Claude Code can access the directory
-# In Claude Code, check if context is loading properly
-```
-
-**Solution**:
-1. Restart Claude Code
-2. Ensure you're in a project directory
-3. Check file permissions: `chmod 644 ~/.claude/*.md`
-
-### Issue: MCP Servers Not Working
-
-**Symptom**: MCP features unavailable
-
-**Verification**:
-```bash
-# Check Node.js installation
-which node
-
-# Verify .claude.json syntax
-python3 -c "import json; json.load(open('$HOME/.claude.json'))" && echo "✅ Valid JSON" || echo "❌ Invalid JSON"
-```
-
-**Solution**:
-```bash
-# Install Node.js if missing
-# Ubuntu: sudo apt install nodejs npm
-# macOS: brew install node
-# Windows: Download from nodejs.org
-
-# Fix JSON syntax if invalid
-PYTHONPATH=/path/to/SuperClaude_Framework python3 -m setup install --components mcp --force
-```
-
-## Troubleshooting Commands
-
-### Quick Diagnostic
-
-```bash
-#!/bin/bash
-# SuperClaude Quick Diagnostic Script
-
-echo "=== SuperClaude Diagnostic ==="
-echo ""
-
-# Check installation system
-echo "1. Installation System:"
-if command -v SuperClaude &> /dev/null; then
- echo " ✅ SuperClaude installation available"
- python3 -m SuperClaude --version
-else
- echo " ❌ SuperClaude not found - install with: pipx install SuperClaude (or pip install SuperClaude)"
-fi
-
-# Check context files
-echo ""
-echo "2. Context Files:"
-if [ -d ~/.claude ]; then
- echo " ✅ ~/.claude directory exists"
- echo " - Agents: $(ls ~/.claude/agents/*.md 2>/dev/null | wc -l)"
- echo " - Commands: $(ls ~/.claude/commands/*.md 2>/dev/null | wc -l)"
- echo " - Modes: $(ls ~/.claude/modes/*.md 2>/dev/null | wc -l)"
-else
- echo " ❌ ~/.claude directory not found"
-fi
-
-# Check MCP
-echo ""
-echo "3. MCP Configuration:"
-if [ -f ~/.claude.json ]; then
- echo " ✅ MCP configuration exists"
-else
- echo " ❌ No MCP configuration"
-fi
-
-# Check Node.js
-echo ""
-echo "4. Node.js (for MCP):"
-if command -v node &> /dev/null; then
- echo " ✅ Node.js installed: $(node --version)"
-else
- echo " ⚠️ Node.js not installed (optional, needed for MCP)"
-fi
-
-echo ""
-echo "=== Diagnostic Complete ==="
-```
-
-### File Permission Fix
-
-```bash
-# Fix permissions on all context files
-chmod 644 ~/.claude/*.md
-chmod 644 ~/.claude/**/*.md
-chmod 755 ~/.claude ~/.claude/agents ~/.claude/commands ~/.claude/modes
-```
-
-### Complete Reinstall
-
-```bash
-# Backup existing configuration
-cp -r ~/.claude ~/.claude.backup.$(date +%Y%m%d)
-
-# Remove existing installation
-rm -rf ~/.claude
-
-# Reinstall everything
-PYTHONPATH=/path/to/SuperClaude_Framework python3 -m setup install
-
-# Restore any customizations from backup if needed
-```
-
-## Important Notes
-
-### What We're NOT Verifying
-
-- **No Code Execution**: Context files don't execute, so no runtime verification needed
-- **No Performance Metrics**: No code runs, so no performance to measure
-- **No Unit Tests**: Context files are instructions, not functions
-- **No Integration Tests**: Claude Code reads files; verification is behavioral
-
-### What We ARE Verifying
-
-- **File Presence**: Context files exist in correct locations
-- **File Integrity**: Files are valid text and readable
-- **Directory Structure**: Proper organization maintained
-- **Configuration Validity**: JSON files are syntactically correct
-- **Dependencies Available**: Node.js for MCP servers (optional)
-- **Behavioral Testing**: Context files produce expected Claude Code behavior
-
-## Summary
-
-Verification for SuperClaude focuses on ensuring context files are properly installed and accessible to Claude Code. Since SuperClaude is not software but a configuration framework, verification centers on file presence, integrity, and behavioral testing in Claude Code conversations.
\ No newline at end of file
diff --git a/docs/Getting-Started/installation.md b/docs/Getting-Started/installation.md
deleted file mode 100644
index 4f23930..0000000
--- a/docs/Getting-Started/installation.md
+++ /dev/null
@@ -1,514 +0,0 @@
-
-
----
-
-## ⚡ **Quick Installation**
-
-
-
-### **Choose Your Preferred Method**
-
-| Method | Command | Platform | Best For |
-|:------:|---------|:--------:|----------|
-| **🐍 pipx** | `pipx install SuperClaude && SuperClaude install` | Linux/macOS | **✅ Recommended** - Isolated environment |
-| **📦 pip** | `pip install SuperClaude && SuperClaude install` | All | Traditional Python setups |
-| **🌐 npm** | `npm install -g @bifrost_inc/superclaude && superclaude install` | All | Node.js developers |
-| **🔧 Dev** | `git clone ... && pip install -e ".[dev]"` | All | Contributors & developers |
-
-
-
----
-
-## 📋 **Requirements**
-
-
-
-
-
-|
-
-### ✅ **Required**
-
-| Component | Version | Check Command |
-|-----------|---------|---------------|
-| **Python** | 3.8+ | `python3 --version` |
-| **pip** | Latest | `pip --version` |
-| **Claude Code** | Latest | `claude --version` |
-| **Disk Space** | 50MB | `df -h` |
-
- |
-
-
-### 💡 **Optional**
-
-| Component | Purpose | Check Command |
-|-----------|---------|---------------|
-| **Node.js** | MCP Servers | `node --version` |
-| **Git** | Version Control | `git --version` |
-| **pipx** | Isolated Install | `pipx --version` |
-| **RAM** | Performance | 1GB recommended |
-
- |
-
-
-
-
-
-
-🔍 Quick System Check
-
-```bash
-# Run this to check all requirements at once
-python3 --version && echo "✅ Python OK" || echo "❌ Python missing"
-claude --version && echo "✅ Claude Code OK" || echo "❌ Claude Code missing"
-node --version 2>/dev/null && echo "✅ Node.js OK (optional)" || echo "⚠️ Node.js missing (optional)"
-git --version 2>/dev/null && echo "✅ Git OK (optional)" || echo "⚠️ Git missing (optional)"
-```
-
-
-
----
-
-## 🚀 **Installation Methods**
-
-
-
-### **Detailed Installation Instructions**
-
-
-
-### **Method 1: pipx (Recommended)**
-
-
-
-|
-
-```bash
-# Install pipx if not present
-python3 -m pip install --user pipx
-python3 -m pipx ensurepath
-
-# Install SuperClaude
-pipx install SuperClaude
-
-# Run the installer
-SuperClaude install
-```
-
- |
-
-
-**✅ Advantages:**
-- Isolated environment
-- No dependency conflicts
-- Clean uninstall
-- Automatic PATH setup
-
-**📍 Best for:**
-- Linux/macOS users
-- Clean system installs
-- Multiple Python projects
-
- |
-
-
-
-### **Method 2: pip (Traditional)**
-
-
-
-|
-
-```bash
-# Standard installation
-pip install SuperClaude
-
-# Or user installation
-pip install --user SuperClaude
-
-# Run the installer
-SuperClaude install
-```
-
- |
-
-
-**✅ Advantages:**
-- Works everywhere
-- Familiar to Python users
-- Direct installation
-
-**📍 Best for:**
-- Windows users
-- Virtual environments
-- Quick setup
-
- |
-
-
-
-### **Method 3: npm (Cross-platform)**
-
-
-
-|
-
-```bash
-# Global installation
-npm install -g @bifrost_inc/superclaude
-
-# Run the installer
-superclaude install
-```
-
- |
-
-
-**✅ Advantages:**
-- Cross-platform
-- NPM ecosystem
-- JavaScript familiar
-
-**📍 Best for:**
-- Node.js developers
-- NPM users
-- Cross-platform needs
-
- |
-
-
-
-### **Method 4: Development Installation**
-
-
-
-|
-
-```bash
-# Clone repository
-git clone https://github.com/SuperClaude-Org/SuperClaude_Framework.git
-cd SuperClaude_Framework
-
-# Install in development mode
-pip install -e ".[dev]"
-
-# Test installation
-SuperClaude install --dry-run
-```
-
- |
-
-
-**✅ Advantages:**
-- Latest features
-- Contribute to project
-- Full source access
-
-**📍 Best for:**
-- Contributors
-- Custom modifications
-- Testing new features
-
- |
-
-
-
----
-
-## 🎛️ **Installation Options**
-
-
-
-### **Customize Your Installation**
-
-| Option | Command | Description |
-|--------|---------|-------------|
-| **Interactive** | `SuperClaude install` | Guided setup with prompts |
-| **Specific Components** | `SuperClaude install --components core mcp modes` | Install only what you need |
-| **Preview Mode** | `SuperClaude install --dry-run` | See what will be installed |
-| **Force Install** | `SuperClaude install --force --yes` | Skip all confirmations |
-| **List Components** | `SuperClaude install --list-components` | View available components |
-
-
-
----
-
-## ✅ **Verification**
-
-
-
-### **Confirm Successful Installation**
-
-
-
-### **Step 1: Check Installation**
-
-```bash
-# Verify SuperClaude version
-python3 -m SuperClaude --version
-# Expected: SuperClaude 4.1.5
-
-# List installed components
-SuperClaude install --list-components
-# Expected: List of available components
-```
-
-### **Step 2: Test in Claude Code**
-
-```bash
-# Open Claude Code and try these commands:
-/sc:brainstorm "test project" # Should trigger discovery questions
-/sc:analyze README.md # Should provide structured analysis
-@agent-security "review code" # Should activate security specialist
-```
-
-### **Step 3: What's Installed**
-
-
-
-| Location | Contents | Size |
-|----------|----------|------|
-| `~/.claude/` | Framework files | ~50MB |
-| `~/.claude/CLAUDE.md` | Main entry point | ~2KB |
-| `~/.claude/*.md` | Behavioral instructions | ~200KB |
-| `~/.claude/claude-code-settings.json` | MCP configurations | ~5KB |
-
-
-
----
-
-## 🛠️ **Management**
-
-
-
-
-
-| 📦 Update |
-💾 Backup |
-🗑️ Uninstall |
-
-
-|
-
-```bash
-# Update to latest
-pip install --upgrade SuperClaude
-SuperClaude update
-```
-
- |
-
-
-```bash
-# Create backup
-SuperClaude backup --create
-
-# Restore backup
-SuperClaude backup --restore [file]
-```
-
- |
-
-
-```bash
-# Remove framework
-SuperClaude uninstall
-
-# Uninstall package
-pip uninstall SuperClaude
-```
-
- |
-
-
-
-
-
----
-
-## 🔧 **Troubleshooting**
-
-
-❌ PEP 668 Error (Python Package Management)
-
-This error occurs on systems with externally managed Python environments.
-
-**Solutions (in order of preference):**
-
-```bash
-# Option 1: Use pipx (Recommended)
-pipx install SuperClaude
-
-# Option 2: User installation
-pip install --user SuperClaude
-
-# Option 3: Virtual environment
-python3 -m venv superclaude-env
-source superclaude-env/bin/activate # Linux/macOS
-# or
-superclaude-env\Scripts\activate # Windows
-pip install SuperClaude
-
-# Option 4: Force (use with caution)
-pip install --break-system-packages SuperClaude
-```
-
-
-
-
-❌ Command Not Found
-
-If `SuperClaude` command is not found after installation:
-
-```bash
-# Check if package is installed
-python3 -m pip show SuperClaude
-
-# Run using Python module
-python3 -m SuperClaude install
-
-# Add to PATH (if using --user)
-export PATH="$HOME/.local/bin:$PATH"
-echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc # Linux
-echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc # macOS
-```
-
-
-
-
-❌ Claude Code Not Found
-
-If Claude Code is not installed or not in PATH:
-
-1. Download from [https://claude.ai/code](https://claude.ai/code)
-2. Install following platform instructions
-3. Verify with: `claude --version`
-4. Restart terminal after installation
-
-
-
-
-❌ Permission Denied
-
-For permission errors during installation:
-
-```bash
-# Use user installation
-pip install --user SuperClaude
-
-# Or use sudo (not recommended)
-sudo pip install SuperClaude
-
-# Better: use pipx
-pipx install SuperClaude
-```
-
-
-
-
-❌ Missing Python or pip
-
-**Linux (Ubuntu/Debian):**
-```bash
-sudo apt update
-sudo apt install python3 python3-pip python3-venv
-```
-
-**macOS:**
-```bash
-# Install Homebrew first if needed
-brew install python3
-```
-
-**Windows:**
-- Download from [python.org](https://python.org)
-- Check "Add Python to PATH" during installation
-- Restart terminal after installation
-
-
-
----
-
-## 📚 **Next Steps**
-
-
-
-### **Your Learning Journey**
-
-
-
-| 🌱 Start Here |
-🌿 Expand Skills |
-🌲 Master Framework |
-
-
-|
-
-**First Week:**
-- [Quick Start Guide](quick-start.md)
-- [Commands Reference](../User-Guide/commands.md)
-- Try `/sc:brainstorm`
-
- |
-
-
-**Week 2-3:**
-- [Behavioral Modes](../User-Guide/modes.md)
-- [Agents Guide](../User-Guide/agents.md)
-- [Examples Cookbook](../Reference/examples-cookbook.md)
-
- |
-
-
-**Advanced:**
-- [MCP Servers](../User-Guide/mcp-servers.md)
-- [Technical Architecture](../Developer-Guide/technical-architecture.md)
-- [Contributing Code](../Developer-Guide/contributing-code.md)
-
- |
-
-
-
-
-
----
-
-
-
-### **🎉 Installation Complete!**
-
-You now have access to:
-
-
- 21 Commands • 14 AI Agents • 6 Behavioral Modes • 6 MCP Servers
-
-
-**Ready to start?** Try `/sc:brainstorm` in Claude Code for your first SuperClaude experience!
-
-
-
-
-
-
-
-
\ No newline at end of file
diff --git a/docs/Getting-Started/quick-start.md b/docs/Getting-Started/quick-start.md
deleted file mode 100644
index f825ae5..0000000
--- a/docs/Getting-Started/quick-start.md
+++ /dev/null
@@ -1,492 +0,0 @@
-
-
-# 🚀 SuperClaude Quick Start Guide
-
-### **Context Engineering Framework for Claude Code**
-
-
-
-
-
-
-
-> **💡 Key Insight**: SuperClaude doesn't replace Claude Code - it **configures and enhances** it through behavioral context injection
-
-
- How It Works •
- Instant Start •
- Components •
- Workflows •
- When to Use
-
-
-
-
----
-
-
-
-## 📊 **Framework Capabilities**
-
-| **Commands** | **AI Agents** | **Behavioral Modes** | **MCP Servers** |
-|:------------:|:-------------:|:-------------------:|:---------------:|
-| **21** | **14** | **6** | **6** |
-| `/sc:` triggers | Domain specialists | Context adaptation | Tool integration |
-
-
-
----
-
-## 🎯 **How It Works**
-
-
-
-### **Framework Architecture Flow**
-
-```
-┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
-│ User Input │────>│ Claude Code │────>│ Context Files │
-│ /sc:command │ │ Reads Context │ │ (.md behaviors)│
-└─────────────────┘ └──────────────────┘ └─────────────────┘
- │ │
- ▼ ▼
-┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
-│ Enhanced │<─────│ Behavioral │<────│ MCP Servers │
-│ Response │ │ Activation │ │ (if configured) │
-└─────────────────┘ └──────────────────┘ └─────────────────┘
-```
-
-**The Magic**: When you type `/sc:brainstorm`, Claude reads behavioral instructions from installed `.md` files and responds with enhanced capabilities
-
-
-
----
-
-## ⚡ **Instant Start**
-
-
-
-### **5-Minute Journey from Installation to First Command**
-
-
-
-
-
-| 📦 Step 1: Install (Terminal) |
-💬 Step 2: Use (Claude Code) |
-
-
-|
-
-```bash
-# Quick install with pipx
-pipx install SuperClaude && SuperClaude install
-
-# Or traditional pip
-pip install SuperClaude && SuperClaude install
-
-# Or via npm
-npm install -g @bifrost_inc/superclaude && superclaude install
-```
-
- |
-
-
-```text
-# Interactive discovery
-/sc:brainstorm "web app for task management"
-
-# Analyze existing code
-/sc:analyze src/
-
-# Generate implementation
-/sc:implement "user authentication"
-
-# Activate specialist
-@agent-security "review auth flow"
-```
-
- |
-
-
-
-
-🎥 What Happens Behind the Scenes
-
-1. **Context Loading**: Claude Code imports behavioral `.md` files via `CLAUDE.md`
-2. **Pattern Recognition**: Recognizes `/sc:` and `@agent-` trigger patterns
-3. **Behavioral Activation**: Applies corresponding instructions from context files
-4. **MCP Integration**: Uses configured external tools when available
-5. **Response Enhancement**: Follows framework patterns for comprehensive responses
-
-
-
----
-
-## 🔧 **Core Components**
-
-
-
-### **Four Pillars of SuperClaude**
-
-
-
-
-
-### 📝 **Commands**
-21
-
-**Slash Commands**
-
-`/sc:brainstorm`
-`/sc:implement`
-`/sc:analyze`
-`/sc:workflow`
-
-*Workflow automation*
-
- |
-
-
-### 🤖 **Agents**
-14
-
-**AI Specialists**
-
-`@agent-architect`
-`@agent-security`
-`@agent-frontend`
-`@agent-backend`
-
-*Domain expertise*
-
- |
-
-
-### 🎯 **Modes**
-6
-
-**Behavioral Modes**
-
-Brainstorming
-Introspection
-Orchestration
-Task Management
-
-*Context adaptation*
-
- |
-
-
-### 🔌 **MCP**
-6
-
-**Server Integration**
-
-Context7 (docs)
-Sequential (analysis)
-Magic (UI)
-Playwright (testing)
-
-*Enhanced tools*
-
- |
-
-
-
-
-
----
-
-## 📚 **Workflow Patterns**
-
-
-
-### **Complete Development Lifecycle**
-
-
-
-### **🌟 First Project Session**
-
-
-
-| Step |
-Command |
-What Happens |
-
-
-| 1. Discovery |
-/sc:brainstorm "e-commerce app" |
-Interactive requirements exploration |
-
-
-| 2. Load Context |
-/sc:load src/ |
-Import existing project structure |
-
-
-| 3. Analysis |
-/sc:analyze --focus architecture |
-Deep architectural review |
-
-
-| 4. Planning |
-/sc:workflow "payment integration" |
-Generate implementation roadmap |
-
-
-| 5. Implementation |
-/sc:implement "Stripe checkout" |
-Build with best practices |
-
-
-| 6. Validation |
-/sc:test --coverage |
-Comprehensive testing |
-
-
-| 7. Save Session |
-/sc:save "payment-complete" |
-Persist for next session |
-
-
-
-### **🎨 Domain-Specific Workflows**
-
-
-
-| Domain | Trigger | Specialist Activation | MCP Server |
-|--------|---------|----------------------|------------|
-| **Frontend** | UI component request | `@agent-frontend` | Magic |
-| **Backend** | API endpoint creation | `@agent-backend` | Sequential |
-| **Security** | Auth implementation | `@agent-security` | Context7 |
-| **Testing** | E2E test scenarios | `@agent-qa` | Playwright |
-| **DevOps** | Deployment setup | `@agent-devops` | Morphllm |
-
-
-
----
-
-## 🎯 **When to Use**
-
-
-
-### **SuperClaude vs Standard Claude Code**
-
-
-
-| ✅ Use SuperClaude |
-💭 Use Standard Claude |
-
-
-|
-
-**Perfect for:**
-- 🏗️ Building complete software projects
-- 📊 Systematic workflows with quality gates
-- 🔄 Complex, multi-component systems
-- 💾 Long-term projects needing persistence
-- 👥 Team collaboration with standards
-- 🎯 Domain-specific expertise needs
-
-**Examples:**
-- "Build a full-stack application"
-- "Implement secure authentication"
-- "Refactor legacy codebase"
-- "Create comprehensive test suite"
-
- |
-
-
-**Better for:**
-- 💡 Simple questions or explanations
-- ⚡ One-off coding tasks
-- 📚 Learning programming concepts
-- 🧪 Quick prototypes or experiments
-- 🔍 Code snippet generation
-- ❓ General programming help
-
-**Examples:**
-- "Explain how async/await works"
-- "Write a sorting function"
-- "Debug this error message"
-- "Convert this loop to functional"
-
- |
-
-
-
-
-
----
-
-## 🎓 **Learning Path**
-
-
-
-### **Your 4-Week Journey to Mastery**
-
-
-
-| Week |
-Focus |
-Skills |
-Milestone |
-
-
-1 🌱 |
-Core Commands |
-
-• /sc:brainstorm
-• /sc:analyze
-• /sc:implement
- |
-Complete first project |
-
-
-2 🌿 |
-Behavioral Modes |
-
-• Mode combinations
-• Flag usage
-• Context optimization
- |
-Optimize workflows |
-
-
-3 🌿 |
-MCP Servers |
-
-• Server configuration
-• Tool integration
-• Enhanced capabilities
- |
-Full tool utilization |
-
-
-4 🌲 |
-Advanced Patterns |
-
-• Custom workflows
-• Session management
-• Team patterns
- |
-Framework mastery |
-
-
-
-
-
----
-
-## 💡 **Key Insights**
-
-
-
-### **Understanding SuperClaude's Value**
-
-
-
-|
-
-### 🧠 **Not Software**
-**It's a Framework**
-
-SuperClaude is behavioral configuration, not standalone software. Everything runs through Claude Code.
-
- |
-
-
-### 🔄 **Systematic**
-**Not Ad-hoc**
-
-Transforms random requests into structured workflows with quality gates and validation.
-
- |
-
-
-### 🚀 **Progressive**
-**Not Complex**
-
-Start simple with basic commands. Complexity emerges naturally as needed.
-
- |
-
-
-
-
-
----
-
-## 📖 **Next Steps**
-
-
-
-### **Continue Your Learning Journey**
-
-
-
-| 🌱 Beginner |
-🌿 Intermediate |
-🌲 Advanced |
-
-
-|
-
-**First Week:**
-- [Installation Guide](installation.md)
-- [Commands Reference](../User-Guide/commands.md)
-- [Examples Cookbook](../Reference/examples-cookbook.md)
-
-Start with `/sc:brainstorm`
-
- |
-
-
-**Growing Skills:**
-- [Behavioral Modes](../User-Guide/modes.md)
-- [Agents Guide](../User-Guide/agents.md)
-- [Session Management](../User-Guide/session-management.md)
-
-Explore mode combinations
-
- |
-
-
-**Expert Usage:**
-- [MCP Servers](../User-Guide/mcp-servers.md)
-- [Technical Architecture](../Developer-Guide/technical-architecture.md)
-- [Contributing](../Developer-Guide/contributing-code.md)
-
-Create custom workflows
-
- |
-
-
-
-
-
-
-
-
-
-
-
-
-
-
----
-
-
-
-### **🎉 Ready to Transform Your Development Workflow?**
-
-
- Start now with /sc:brainstorm in Claude Code!
-
-
-
- SuperClaude v4.1.5 - Context Engineering for Claude Code
-
-
-
\ No newline at end of file
diff --git a/docs/Reference/README.md b/docs/Reference/README.md
deleted file mode 100644
index 713cddf..0000000
--- a/docs/Reference/README.md
+++ /dev/null
@@ -1,249 +0,0 @@
-# SuperClaude Framework Reference Documentation
-
-**Navigation Hub**: Structured learning paths and technical references for all skill levels.
-
-**Documentation Status**: ✅ **Status: Current** - All content verified for accuracy and completeness.
-
-## How to Use This Reference Library
-
-This documentation is organized for **progressive learning** with multiple entry points:
-
-- **📱 Quick Reference**: Jump to specific solutions for immediate needs
-- **📚 Learning Paths**: Structured progression from beginner to expert
-- **🔍 Problem-Solving**: Targeted troubleshooting and diagnostic guidance
-- **⚡ Performance**: Optimization patterns and advanced techniques
-
-**Verification Standards**: All examples tested, commands validated, patterns proven in real-world usage.
-
----
-
-## Documentation Navigation Matrix
-
-| Document | Purpose | Target Audience | Complexity | |
-|----------|---------|-----------------|------------|-----------------|
-| **[basic-examples.md](./basic-examples.md)** | Copy-paste ready commands and patterns | All users, quick reference | **Basic** | |
-| **[examples-cookbook.md](./examples-cookbook.md)** | Recipe collection hub and organization | All users, navigation | **Reference** | |
-| **[common-issues.md](./common-issues.md)** | Essential troubleshooting and solutions | All users, problem-solving | **Basic** | As needed |
-| **[mcp-server-guide.md](./mcp-server-guide.md)** | MCP server configuration and usage | Technical users, integration | **Intermediate** | |
-
-| **[advanced-patterns.md](./advanced-patterns.md)** | Expert coordination and orchestration | Experienced users | **Advanced** | |
-| **[advanced-workflows.md](./advanced-workflows.md)** | Complex multi-agent orchestration | Expert users | **Advanced** | |
-| **[integration-patterns.md](./integration-patterns.md)** | Framework and system integration | Architects, experts | **Advanced** | |
-| **[troubleshooting.md](./troubleshooting.md)** | Comprehensive diagnostic guide | All levels, deep debugging | **Variable** | As needed |
-| **[diagnostic-reference.md](./diagnostic-reference.md)** | Advanced debugging and analysis | Expert users, complex issues | **Advanced** | |
-
----
-
-## Recommended Learning Paths
-
-### New Users (Week 1 Foundation)
-**Goal**: Establish confident SuperClaude usage with essential workflows
-
-```
-Day 1-2: ../Getting-Started/quick-start.md
- ↓ Foundation building and first commands
-Day 3-4: basic-examples.md
- ↓ Practical application and pattern recognition
-Day 5-7: common-issues.md
- ↓ Problem resolution and confidence building
-```
-
-**Success Metrics**: Can execute basic commands, manage sessions, resolve common issues independently.
-
-### Intermediate Users (Week 2-3 Enhancement)
-**Goal**: Master coordination patterns and technical depth
-
-```
-Week 2: advanced-patterns.md
- ↓ Multi-agent coordination and orchestration mastery
-Week 3: mcp-server-guide.md + advanced-workflows.md
- ↓ Performance excellence and technical configuration
-```
-
-**Success Metrics**: Can orchestrate complex workflows, optimize performance, configure MCP servers.
-
-### Expert Users (Advanced Mastery)
-**Goal**: Complete framework mastery and complex system integration
-
-```
-Phase 1: advanced-workflows.md
- ↓ Complex orchestration and enterprise patterns
-Phase 2: integration-patterns.md
- ↓ Framework integration and architectural mastery
-Phase 3: diagnostic-reference.md
- ↓ Advanced debugging and system analysis
-```
-
-**Success Metrics**: Can design custom workflows, integrate with any framework, diagnose complex issues.
-
-### Problem-Solving Path (As Needed)
-**Goal**: Immediate issue resolution and diagnostic guidance
-
-```
-Quick Issues: common-issues.md
- ↓ Common problems and immediate solutions
-Complex Debugging: troubleshooting.md
- ↓ Comprehensive diagnostic approach
-Advanced Analysis: diagnostic-reference.md
- ↓ Expert-level debugging and analysis
-```
-
----
-
-## Command Quick Reference
-
-### Essential SuperClaude Commands
-
-| Command Pattern | Purpose | Example |
-|----------------|---------|---------|
-| `/sc:load` | Restore session context | `/sc:load project_name` |
-| `/sc:save` | Preserve session state | `/sc:save "milestone checkpoint"` |
-| `--think` | Enable structured analysis | `--think analyze performance bottlenecks` |
-| `--brainstorm` | Collaborative requirement discovery | `--brainstorm new authentication system` |
-| `--task-manage` | Multi-step operation orchestration | `--task-manage refactor user module` |
-
-### Performance & Efficiency Flags
-
-| Flag | Purpose | Best For |
-|------|---------|----------|
-| `--uc` / `--ultracompressed` | Token-efficient communication | Large operations, context pressure |
-| `--orchestrate` | Optimize tool selection | Multi-tool operations, performance needs |
-| `--loop` | Iterative improvement cycles | Code refinement, quality enhancement |
-| `--validate` | Pre-execution risk assessment | Production environments, critical operations |
-
-### MCP Server Activation
-
-| Flag | Server | Best For |
-|------|---------|----------|
-| `--c7` / `--context7` | Context7 | Official documentation, framework patterns |
-| `--seq` / `--sequential` | Sequential | Complex analysis, debugging, system design |
-| `--magic` | Magic | UI components, design systems, frontend work |
-| `--morph` / `--morphllm` | Morphllm | Bulk transformations, pattern-based edits |
-| `--serena` | Serena | Symbol operations, project memory, large codebases |
-| `--play` / `--playwright` | Playwright | Browser testing, E2E scenarios, visual validation |
-
----
-
-## Framework Integration Quick Start
-
-### React/Next.js Projects
-```bash
-# Initialize with React patterns
---c7 --magic "implement Next.js authentication with TypeScript"
-
-# Component development workflow
---magic --think "create responsive dashboard component"
-```
-
-### Node.js/Express Backend
-```bash
-# API development with best practices
---c7 --seq "design RESTful API with Express and MongoDB"
-
-# Performance optimization
---think --orchestrate "optimize database queries and caching"
-```
-
-### Full-Stack Development
-```bash
-# Complete application workflow
---task-manage --all-mcp "build full-stack e-commerce platform"
-
-# Integration testing
---play --seq "implement end-to-end testing strategy"
-```
-
----
-
-## Problem-Solving Quick Reference
-
-### Immediate Issues
-- **Command not working**: Check [common-issues.md](./common-issues.md) → Common SuperClaude Problems
-- **Session lost**: Use `/sc:load` → See [Session Management](../User-Guide/session-management.md)
-- **Flag confusion**: Check [basic-examples.md](./basic-examples.md) → Flag Usage Examples
-
-### Development Blockers
-- **Performance slow**: See [Advanced Workflows](./advanced-workflows.md) → Performance Patterns
-- **Complex debugging**: Use [troubleshooting.md](./troubleshooting.md) → Systematic Debugging
-- **Integration issues**: Check [integration-patterns.md](./integration-patterns.md) → Framework Patterns
-
-### System-Level Issues
-- **Architecture problems**: Use [advanced-workflows.md](./advanced-workflows.md) → System Design
-- **Expert debugging**: Apply [diagnostic-reference.md](./diagnostic-reference.md) → Advanced Analysis
-- **Custom workflow needs**: Study [advanced-patterns.md](./advanced-patterns.md) → Custom Orchestration [advanced-patterns.md](./advanced-patterns.md) → Custom Orchestration
-
----
-
-## Documentation Health & Verification
-
-### Quality Assurance
-- ✅ **Commands Tested**: All examples tested and functional
-- ✅ **Patterns Proven**: Real-world usage validation in production environments
-- ✅ **Cross-References**: Internal links verified and maintained
-- ✅ **Regular Updates**: Documentation synchronized with framework evolution
-
-### Accuracy Standards
-- **Command Syntax**: Verified against latest SuperClaude implementation
-- **Flag Behavior**: Tested in multiple scenarios and environments
-- **MCP Integration**: Confirmed compatibility with current MCP server versions
-- **Performance Claims**: Benchmarked and measured in realistic conditions
-
-### Reporting Issues
-Found outdated information or broken examples?
-
-1. **Quick Fixes**: Check [common-issues.md](./common-issues.md) first
-2. **Documentation Bugs**: Report via project issues with specific file and line
-3. **Missing Patterns**: Suggest additions with use case description
-4. **Verification Requests**: Request re-testing of specific examples
-
----
-
-## Expert Tips for Maximum Productivity
-
-### Daily Workflow Optimization
-1. **Session Management**: Always start with `/sc:load`, end with `/sc:save`
-2. **Flag Combinations**: Combine complementary flags: `--think --c7` for documented analysis
-3. **Progressive Complexity**: Start simple, add sophistication incrementally
-4. **Tool Specialization**: Match tools to tasks: Magic for UI, Sequential for analysis
-
-### Learning Acceleration
-1. **Follow the Paths**: Use recommended learning sequences for structured growth
-2. **Practice Patterns**: Repeat common workflows until they become intuitive
-3. **Experiment Safely**: Use feature branches and checkpoints for exploration
-4. **Community Learning**: Share discoveries and learn from others' approaches
-
-### Troubleshooting Mastery
-1. **Systematic Approach**: Always start with [common-issues.md](./common-issues.md)
-2. **Evidence Gathering**: Use `--think` for complex problem analysis
-3. **Root Cause Focus**: Address underlying issues, not just symptoms
-4. **Documentation First**: Check official docs before experimental solutions
-
----
-
-## Advanced Resources & Integration
-
-### Framework-Specific Guides
-- **React/Next.js**: See [integration-patterns.md](./integration-patterns.md) → React Integration
-- **Vue/Nuxt**: See [integration-patterns.md](./integration-patterns.md) → Vue Ecosystem
-- **Node.js/Express**: See [integration-patterns.md](./integration-patterns.md) → Backend Patterns
-- **Python/Django**: See [integration-patterns.md](./integration-patterns.md) → Python Workflows
-
-### Specialized Workflows
-- **DevOps Integration**: [advanced-workflows.md](./advanced-workflows.md) → CI/CD Patterns
-- **Testing Strategies**: [advanced-patterns.md](./advanced-patterns.md) → Testing Orchestration
-- **Performance Engineering**: [Advanced Patterns](./advanced-patterns.md) → Complex Coordination
-- **Security Implementation**: [integration-patterns.md](./integration-patterns.md) → Security Patterns
-
-### Community & Support
-- **Best Practices**: Continuously updated based on community feedback
-- **Pattern Library**: Growing collection of proven workflow patterns
-- **Expert Network**: Connect with experienced SuperClaude practitioners
-- **Regular Updates**: Documentation evolves with framework capabilities
-
----
-
-**Start Your Journey**: New to SuperClaude? Begin with [Quick Start Guide](../Getting-Started/quick-start.md) for immediate productivity gains.
-
-**Need Answers Now**: Jump to [basic-examples.md](./basic-examples.md) for copy-paste solutions.
-
-**Ready for Advanced**: Explore [advanced-patterns.md](./advanced-patterns.md) for expert-level orchestration.
\ No newline at end of file
diff --git a/docs/Reference/advanced-patterns.md b/docs/Reference/advanced-patterns.md
deleted file mode 100644
index b0256f4..0000000
--- a/docs/Reference/advanced-patterns.md
+++ /dev/null
@@ -1,323 +0,0 @@
-# SuperClaude Advanced Patterns
-
-**Advanced Context Usage Patterns**: Sophisticated combinations of commands, agents, and flags for experienced SuperClaude users working on complex projects.
-
-**Remember**: SuperClaude provides context to Claude Code. All patterns here are about guiding Claude's behavior through context, not executing code or coordinating processes.
-
-## Table of Contents
-
-### Context Combination Patterns
-- [Multi-Agent Context Patterns](#multi-agent-context-patterns) - Combining multiple specialist contexts
-- [Command Sequencing Patterns](#command-sequencing-patterns) - Effective command combinations
-- [Flag Combination Strategies](#flag-combination-strategies) - Advanced flag usage
-
-### Workflow Patterns
-- [Complex Project Patterns](#complex-project-patterns) - Large project approaches
-- [Migration Patterns](#migration-patterns) - Legacy system modernization
-- [Review and Audit Patterns](#review-and-audit-patterns) - Comprehensive analysis
-
-## Multi-Agent Context Patterns
-
-### Combining Specialist Contexts
-
-**Security + Backend Pattern:**
-```bash
-# Security-focused backend development
-@agent-security "define authentication requirements"
-@agent-backend-architect "design API with security requirements"
-/sc:implement "secure API endpoints"
-
-# What happens:
-# 1. Security context loaded first
-# 2. Backend context added
-# 3. Implementation guided by both contexts
-# Note: Contexts combine in Claude's understanding, not in execution
-```
-
-**Frontend + UX + Accessibility Pattern:**
-```bash
-# Comprehensive frontend development
-@agent-frontend-architect "design component architecture"
-/sc:implement "accessible React components" --magic
-@agent-quality-engineer "review accessibility compliance"
-
-# Context layering:
-# - Frontend patterns guide structure
-# - Magic MCP may provide UI components (if configured)
-# - Quality context ensures standards
-```
-
-### Manual vs Automatic Agent Selection
-
-**Explicit Control Pattern:**
-```bash
-# Manually control which contexts load
-@agent-python-expert "implement data pipeline"
-# Only Python context, no auto-activation
-
-# vs Automatic selection
-/sc:implement "Python data pipeline"
-# May activate multiple agents based on keywords
-```
-
-**Override Auto-Selection:**
-```bash
-# Prevent unwanted agent activation
-/sc:implement "simple utility" --no-mcp
-@agent-backend-architect "keep it simple"
-# Limits context to specified agent only
-```
-
-## Command Sequencing Patterns
-
-### Progressive Refinement Pattern
-
-```bash
-# Start broad, then focus
-/sc:analyze project/
-# General analysis
-
-/sc:analyze project/core/ --focus architecture
-# Focused on structure
-
-/sc:analyze project/core/auth/ --focus security --think-hard
-# Deep security analysis
-
-# Each command builds on previous context within the conversation
-```
-
-### Discovery to Implementation Pattern
-
-```bash
-# Complete feature development flow
-/sc:brainstorm "feature idea"
-# Explores requirements
-
-/sc:design "feature architecture"
-# Creates structure
-
-@agent-backend-architect "review design"
-# Expert review
-
-/sc:implement "feature based on design"
-# Implementation follows design
-
-/sc:test --validate
-# Verification approach
-```
-
-### Iterative Improvement Pattern
-
-```bash
-# Multiple improvement passes
-/sc:analyze code/ --focus quality
-# Identify issues
-
-/sc:improve code/ --fix
-# First improvement pass
-
-@agent-refactoring-expert "suggest further improvements"
-# Expert suggestions
-
-/sc:improve code/ --fix --focus maintainability
-# Refined improvements
-```
-
-## Flag Combination Strategies
-
-### Analysis Depth Control
-
-```bash
-# Quick overview
-/sc:analyze . --overview --uc
-# Fast, compressed output
-
-# Standard analysis
-/sc:analyze . --think
-# Structured thinking
-
-# Deep analysis
-/sc:analyze . --think-hard --verbose
-# Comprehensive analysis
-
-# Maximum depth (use sparingly)
-/sc:analyze . --ultrathink
-# Exhaustive analysis
-```
-
-### MCP Server Selection
-
-```bash
-# Selective MCP usage
-/sc:implement "React component" --magic --c7
-# Only Magic and Context7 MCP
-
-# Disable all MCP
-/sc:implement "simple function" --no-mcp
-# Pure Claude context only
-
-# All available MCP
-/sc:analyze complex-system/ --all-mcp
-# Maximum tool availability (if configured)
-```
-
-## Complex Project Patterns
-
-### Large Codebase Analysis
-
-```bash
-# Systematic exploration of large projects
-# Step 1: Structure understanding
-/sc:load project/
-/sc:analyze . --overview --focus architecture
-
-# Step 2: Identify problem areas
-@agent-quality-engineer "identify high-risk modules"
-
-# Step 3: Deep dive into specific areas
-/sc:analyze high-risk-module/ --think-hard --focus quality
-
-# Step 4: Implementation plan
-/sc:workflow "improvement plan based on analysis"
-```
-
-### Multi-Module Development
-
-```bash
-# Developing interconnected modules
-# Frontend module
-/sc:implement "user interface module"
-@agent-frontend-architect "ensure consistency"
-
-# Backend module
-/sc:implement "API module"
-@agent-backend-architect "ensure compatibility"
-
-# Integration layer
-/sc:implement "frontend-backend integration"
-# Context from both previous implementations guides this
-```
-
-### Cross-Technology Projects
-
-```bash
-# Projects with multiple technologies
-# Python backend
-@agent-python-expert "implement FastAPI backend"
-
-# React frontend
-@agent-frontend-architect "implement React frontend"
-
-# DevOps setup
-@agent-devops-architect "create deployment configuration"
-
-# Integration documentation
-/sc:document --type integration
-```
-
-## Migration Patterns
-
-### Legacy System Analysis
-
-```bash
-# Understanding legacy systems
-/sc:load legacy-system/
-/sc:analyze . --focus architecture --verbose
-
-@agent-refactoring-expert "identify modernization opportunities"
-@agent-system-architect "propose migration strategy"
-
-/sc:workflow "create migration plan"
-```
-
-### Incremental Migration
-
-```bash
-# Step-by-step migration approach
-# Phase 1: Analysis
-/sc:analyze legacy-module/ --comprehensive
-
-# Phase 2: Design new architecture
-@agent-system-architect "design modern replacement"
-
-# Phase 3: Implementation
-/sc:implement "modern module with compatibility layer"
-
-# Phase 4: Validation
-/sc:test --focus compatibility
-```
-
-## Review and Audit Patterns
-
-### Security Audit Pattern
-
-```bash
-# Comprehensive security review
-/sc:analyze . --focus security --think-hard
-@agent-security "review authentication and authorization"
-@agent-security "check for OWASP vulnerabilities"
-/sc:document --type security-audit
-```
-
-### Code Quality Review
-
-```bash
-# Multi-aspect quality review
-/sc:analyze src/ --focus quality
-@agent-quality-engineer "review test coverage"
-@agent-refactoring-expert "identify code smells"
-/sc:improve --fix --preview
-```
-
-### Architecture Review
-
-```bash
-# System architecture assessment
-@agent-system-architect "review current architecture"
-/sc:analyze . --focus architecture --think-hard
-@agent-performance-engineer "identify bottlenecks"
-/sc:design "optimization recommendations"
-```
-
-## Important Clarifications
-
-### What These Patterns Actually Do
-
-- ✅ **Guide Claude's Thinking**: Provide structured approaches
-- ✅ **Combine Contexts**: Layer multiple expertise areas
-- ✅ **Improve Output Quality**: Better code generation through better context
-- ✅ **Structure Workflows**: Organize complex tasks
-
-### What These Patterns Don't Do
-
-- ❌ **Execute in Parallel**: Everything is sequential context loading
-- ❌ **Coordinate Processes**: No actual process coordination
-- ❌ **Optimize Performance**: No code runs, so no performance impact
-- ❌ **Persist Between Sessions**: Each conversation is independent
-
-## Best Practices for Advanced Usage
-
-### Context Management
-
-1. **Layer Deliberately**: Add contexts in logical order
-2. **Avoid Overload**: Too many agents can dilute focus
-3. **Use Manual Control**: Override auto-activation when needed
-4. **Maintain Conversation Flow**: Keep related work in same conversation
-
-### Command Efficiency
-
-1. **Progress Logically**: Broad → Specific → Implementation
-2. **Reuse Context**: Later commands benefit from earlier context
-3. **Document Decisions**: Use `/sc:save` for important summaries
-4. **Scope Appropriately**: Focus on manageable chunks
-
-### Flag Usage
-
-1. **Match Task Complexity**: Simple tasks don't need `--ultrathink`
-2. **Control Output**: Use `--uc` for concise results
-3. **Manage MCP**: Only activate needed servers
-4. **Avoid Conflicts**: Don't use contradictory flags
-
-## Summary
-
-Advanced SuperClaude patterns are about sophisticated context management and command sequencing. They help Claude Code generate better outputs by providing richer, more structured context. Remember: all "coordination" and "optimization" happens in how Claude interprets the context, not in any actual execution or parallel processing.
\ No newline at end of file
diff --git a/docs/Reference/advanced-workflows.md b/docs/Reference/advanced-workflows.md
deleted file mode 100644
index f8d7775..0000000
--- a/docs/Reference/advanced-workflows.md
+++ /dev/null
@@ -1,309 +0,0 @@
-# SuperClaude Advanced Workflows Collection
-
-**Status**: ✅ **Status: Current** - Complex command sequences and context combinations for sophisticated projects.
-
-**Advanced Usage Guide**: Patterns for complex projects using multiple commands, agents, and careful context management within Claude Code conversations.
-
-## Overview and Usage Guide
-
-**Purpose**: Advanced SuperClaude patterns for complex, multi-step projects that require careful sequencing of commands and context management.
-
-**Important**: These are conversation patterns, not executing workflows. All work happens within Claude Code based on context provided.
-
-**Key Concepts**:
-- Command sequences within a conversation
-- Context layering through multiple agents
-- Progressive refinement approaches
-- Project phase management (manual, not automated)
-
-## Multi-Context Project Patterns
-
-### Full-Stack Development Sequence
-
-```bash
-# E-commerce platform using multiple contexts
-# Step 1: Architecture context
-@agent-system-architect "design e-commerce architecture"
-
-# Step 2: Security requirements
-@agent-security "define security requirements for payments"
-
-# Step 3: Backend implementation
-/sc:implement "API with authentication and payment processing"
-# Claude uses accumulated context from previous steps
-
-# Step 4: Frontend implementation
-@agent-frontend-architect "design responsive UI"
-/sc:implement "React frontend with TypeScript"
-
-# Step 5: Review
-/sc:analyze . --focus quality
-
-# Note: Each step builds context within the conversation
-# No actual coordination or parallel execution occurs
-```
-
-### Problem-Solving Workflow
-
-```bash
-# Complex troubleshooting approach
-# Step 1: Problem understanding
-/sc:troubleshoot "application performance issues"
-
-# Step 2: Expert analysis
-@agent-performance-engineer "analyze potential bottlenecks"
-@agent-backend-architect "review architecture for issues"
-
-# Step 3: Solution design
-/sc:design "performance improvement plan"
-
-# Step 4: Implementation
-/sc:implement "performance optimizations"
-
-# Context accumulates but doesn't execute
-```
-
-## Complex Project Phases
-
-### Project Initialization Pattern
-
-```bash
-# Starting a new project
-# Discovery phase
-/sc:brainstorm "project concept"
-# Claude explores requirements
-
-# Planning phase
-/sc:design "system architecture"
-@agent-system-architect "review and refine"
-
-# Documentation
-/sc:document --type architecture
-/sc:save "project-plan"
-# Creates summary for your records (not persistent storage)
-```
-
-### Incremental Development Pattern
-
-```bash
-# Building features incrementally
-# Feature 1: Authentication
-/sc:implement "user authentication"
-/sc:test --focus security
-/sc:document --type api
-
-# Feature 2: User Profiles (builds on auth context)
-/sc:implement "user profile management"
-/sc:test --focus functionality
-
-# Feature 3: Admin Dashboard (uses previous context)
-/sc:implement "admin dashboard"
-@agent-frontend-architect "ensure consistency"
-
-# Each feature builds on conversation context
-```
-
-### Migration Project Pattern
-
-```bash
-# Legacy system migration
-# Phase 1: Analysis
-/sc:load legacy-system/
-/sc:analyze . --focus architecture --verbose
-# Claude builds understanding
-
-# Phase 2: Planning
-@agent-system-architect "design migration strategy"
-/sc:workflow "create migration plan"
-
-# Phase 3: Implementation
-/sc:implement "compatibility layer"
-/sc:implement "new system components"
-
-# Phase 4: Validation
-/sc:test --focus compatibility
-/sc:document --type migration
-
-# Manual phases, not automated workflow
-```
-
-## Enterprise-Scale Patterns
-
-### Large Codebase Analysis
-
-```bash
-# Systematic analysis of large projects
-# Overview
-/sc:analyze . --overview
-# Get high-level understanding
-
-# Focused analysis by module
-/sc:analyze auth-module/ --focus security
-/sc:analyze api-module/ --focus quality
-/sc:analyze frontend/ --focus performance
-
-# Synthesis
-@agent-system-architect "synthesize findings"
-/sc:workflow "improvement recommendations"
-
-# Note: Sequential analysis, not parallel
-```
-
-### Multi-Technology Projects
-
-```bash
-# Projects with diverse tech stacks
-# Backend (Python)
-@agent-python-expert "implement FastAPI backend"
-/sc:implement "Python API with async support"
-
-# Frontend (React)
-@agent-frontend-architect "implement React frontend"
-/sc:implement "TypeScript React application"
-
-# Mobile (React Native)
-/sc:implement "React Native mobile app"
-
-# Infrastructure
-@agent-devops-architect "design deployment"
-/sc:implement "Docker configuration"
-
-# Each technology addressed sequentially
-```
-
-## Quality Assurance Workflows
-
-### Comprehensive Review Pattern
-
-```bash
-# Multi-aspect code review
-# Quality review
-/sc:analyze . --focus quality
-@agent-quality-engineer "identify improvements"
-
-# Security review
-/sc:analyze . --focus security
-@agent-security "check for vulnerabilities"
-
-# Architecture review
-@agent-system-architect "evaluate design"
-
-# Performance review
-@agent-performance-engineer "suggest optimizations"
-
-# Consolidated improvements
-/sc:improve . --fix
-
-# Sequential reviews, not parallel analysis
-```
-
-### Testing Strategy Pattern
-
-```bash
-# Comprehensive testing approach
-# Test planning
-/sc:design "testing strategy"
-
-# Unit tests
-/sc:test --type unit
-# Claude generates unit test code
-
-# Integration tests
-/sc:test --type integration
-# Claude generates integration test code
-
-# E2E tests
-/sc:test --type e2e
-# Claude suggests E2E test scenarios
-
-# Documentation
-/sc:document --type testing
-
-# Test code generation, not execution
-```
-
-## Session Management Patterns
-
-### Long Project Sessions
-
-```bash
-# Managing context in long conversations
-# Start with context
-/sc:load project/
-
-# Work progressively
-/sc:implement "feature A"
-/sc:implement "feature B"
-# Context accumulates
-
-# Create checkpoint
-/sc:save "session-checkpoint"
-# Creates summary for your notes
-
-# Continue work
-/sc:implement "feature C"
-
-# Final summary
-/sc:reflect
-# Reviews conversation progress
-```
-
-### Context Refresh Pattern
-
-```bash
-# When conversation gets too long
-# Save current state
-/sc:save "work-complete"
-# Copy output for next conversation
-
-# In new conversation:
-/sc:load project/
-"Previous work: [paste summary]"
-# Manually restore context
-
-# Continue work
-/sc:implement "next feature"
-```
-
-## Important Clarifications
-
-### What These Workflows ARE
-
-- ✅ **Conversation Patterns**: Sequences within a single Claude conversation
-- ✅ **Context Building**: Progressive accumulation of understanding
-- ✅ **Command Sequences**: Ordered use of commands for better results
-- ✅ **Manual Phases**: User-controlled project progression
-
-### What These Workflows ARE NOT
-
-- ❌ **Automated Workflows**: No automatic execution or orchestration
-- ❌ **Parallel Processing**: Everything is sequential
-- ❌ **Persistent Sessions**: Context lost between conversations
-- ❌ **Performance Optimization**: No code executes to optimize
-
-## Best Practices
-
-### Conversation Management
-
-1. **Keep Related Work Together**: Don't split related tasks across conversations
-2. **Build Context Progressively**: Start broad, then focus
-3. **Document Key Decisions**: Use `/sc:save` for important points
-4. **Manage Conversation Length**: Start new conversation if too long
-
-### Command Sequencing
-
-1. **Logical Order**: Analysis → Design → Implementation → Testing
-2. **Context Accumulation**: Later commands benefit from earlier context
-3. **Appropriate Depth**: Match analysis depth to task complexity
-4. **Clear Scope**: Focus commands on specific areas
-
-### Agent Usage
-
-1. **Strategic Activation**: Use agents for specific expertise
-2. **Avoid Overload**: Too many agents can dilute focus
-3. **Manual Control**: Use `@agent-` for precise control
-4. **Context Layering**: Add agents in logical order
-
-## Summary
-
-Advanced workflows in SuperClaude are sophisticated conversation patterns that build context progressively within a single Claude Code session. They help generate better outputs through careful command sequencing and context management, but do not involve any actual workflow execution, parallel processing, or automation. Success comes from understanding how to layer context effectively within Claude's conversation scope.
\ No newline at end of file
diff --git a/docs/Reference/basic-examples.md b/docs/Reference/basic-examples.md
deleted file mode 100644
index b6e10e8..0000000
--- a/docs/Reference/basic-examples.md
+++ /dev/null
@@ -1,553 +0,0 @@
-# SuperClaude Basic Examples Collection
-
-**Status**: ✅ **Status: Current** - Essential commands, single-agent workflows, and common development tasks.
-
-**Quick Reference Guide**: Copy-paste ready examples for beginners, focused on essential SuperClaude usage patterns and fundamental development workflows.
-
-> **📝 Context Note**: These examples show `/sc:` commands and `@agent-` invocations that trigger Claude Code to read specific context files and adopt the behaviors defined there. The sophistication comes from the behavioral instructions, not from executable software.
-
-## Overview and Usage Guide
-
-**Purpose**: Essential SuperClaude commands and patterns for everyday development tasks. Start here for your first SuperClaude experience.
-
-**Target Audience**: New users, developers learning SuperClaude fundamentals, immediate task application
-
-**Usage Pattern**: Copy → Adapt → Execute → Learn from results
-
-**Key Features**:
-- Examples demonstrate core SuperClaude functionality
-- Clear patterns for immediate application
-- Single-focus examples for clear learning
-- Progressive complexity within basic scope
-
-## Essential One-Liner Commands
-
-### Core Development Commands
-
-#### Command: /sc:brainstorm
-**Purpose**: Interactive project discovery and requirements gathering
-**Syntax**: `/sc:brainstorm "project description"`
-**Example**:
-```bash
-/sc:brainstorm "mobile app for fitness tracking"
-# Expected: Socratic dialogue, requirement elicitation, feasibility analysis
-```
-**Behavior**: Triggers interactive discovery dialogue and requirements analysis
-
-#### Command: /sc:analyze
-**Purpose**: Analyze existing codebase for issues and improvements
-**Syntax**: `/sc:analyze [target] --focus [domain]`
-**Example**:
-```bash
-/sc:analyze src/ --focus security
-# Expected: Comprehensive security audit, vulnerability report, improvement suggestions
-```
-**Behavior**: Provides comprehensive security analysis and improvement recommendations
-
-#### Command: /sc:implement
-**Purpose**: Implement a complete feature with best practices
-**Syntax**: `/sc:implement "feature description with requirements"`
-**Example**:
-```bash
-/sc:implement "user authentication with JWT and rate limiting"
-# Expected: Complete auth implementation, security validation, tests included
-```
-**Behavior**: Delivers complete implementation following security and quality standards
-
-#### Command: /sc:troubleshoot
-**Purpose**: Troubleshoot and fix a problem systematically
-**Syntax**: `/sc:troubleshoot "problem description"`
-**Example**:
-```bash
-/sc:troubleshoot "API returns 500 error on user login"
-# Expected: Step-by-step diagnosis, root cause identification, solution ranking
-```
-**Verification**: Activates root-cause-analyst + Sequential reasoning + systematic debugging
-
-#### Command: /sc:test
-**Purpose**: Generate comprehensive tests for existing code
-**Syntax**: `/sc:test [target] --focus [domain]`
-**Example**:
-```bash
-/sc:test --focus quality
-# Expected: Test suite, quality metrics, coverage reporting
-```
-**Verification**: Activates quality-engineer + test automation
-
-### Quick Analysis Commands
-
-#### Command: /sc:analyze (Quality Focus)
-**Purpose**: Project structure and quality overview
-**Syntax**: `/sc:analyze [target] --focus quality`
-**Example**:
-```bash
-/sc:analyze . --focus quality
-```
-**Verification**:
-
-#### Command: /sc:analyze (Security Focus)
-**Purpose**: Security-focused code review
-**Syntax**: `/sc:analyze [target] --focus security [--think]`
-**Example**:
-```bash
-/sc:analyze src/ --focus security --think
-```
-**Verification**:
-
-#### Command: /sc:analyze (Performance Focus)
-**Purpose**: Performance bottleneck identification
-**Syntax**: `/sc:analyze [target] --focus performance`
-**Example**:
-```bash
-/sc:analyze api/ --focus performance
-```
-**Verification**:
-
-#### Command: /sc:analyze (Architecture Focus)
-**Purpose**: Architecture assessment for refactoring
-**Syntax**: `/sc:analyze [target] --focus architecture [--serena]`
-**Example**:
-```bash
-/sc:analyze . --focus architecture --serena
-```
-**Verification**:
-
-## Manual Agent Invocation Examples
-
-### Direct Specialist Activation
-
-#### Pattern: @agent-[specialist]
-**Purpose**: Manually invoke specific domain experts instead of auto-activation
-**Syntax**: `@agent-[specialist] "task or question"`
-
-#### Python Expert
-```bash
-@agent-python-expert "optimize this data processing pipeline for performance"
-# Expected: Python-specific optimizations, async patterns, memory management
-```
-
-#### Security Engineer
-```bash
-@agent-security "review this authentication system for vulnerabilities"
-# Expected: OWASP compliance check, vulnerability assessment, secure coding recommendations
-```
-
-#### Frontend Architect
-```bash
-@agent-frontend-architect "design a responsive component architecture"
-# Expected: Component patterns, state management, accessibility considerations
-```
-
-#### Quality Engineer
-```bash
-@agent-quality-engineer "create comprehensive test coverage for payment module"
-# Expected: Test strategy, unit/integration/e2e tests, edge cases
-```
-
-### Combining Auto and Manual Patterns
-
-#### Pattern: Command + Manual Override
-```bash
-# Step 1: Use command with auto-activation
-/sc:implement "user profile management system"
-# Auto-activates: backend-architect, possibly frontend
-
-# Step 2: Add specific expert review
-@agent-security "review the profile system for data privacy compliance"
-# Manual activation for targeted review
-
-# Step 3: Performance optimization
-@agent-performance-engineer "optimize database queries for profile fetching"
-# Manual activation for specific optimization
-```
-
-#### Pattern: Sequential Specialist Chain
-```bash
-# Design phase
-@agent-system-architect "design microservices architecture for e-commerce"
-
-# Security review
-@agent-security "review architecture for security boundaries"
-
-# Implementation guidance
-@agent-backend-architect "implement service communication patterns"
-
-# DevOps setup
-@agent-devops-architect "configure CI/CD for microservices"
-```
-
-## Basic Usage Patterns
-
-### Discovery → Implementation Pattern
-```bash
-# Step 1: Explore and understand requirements
-/sc:brainstorm "web dashboard for project management"
-# Expected: Requirements discovery, feature prioritization, technical scope
-
-# Step 2: Analyze technical approach
-/sc:analyze "dashboard architecture patterns" --focus architecture --c7
-# Expected: Architecture patterns, technology recommendations, implementation strategy
-
-# Step 3: Implement core functionality
-/sc:implement "React dashboard with task management and team collaboration"
-# Expected: Complete dashboard implementation with modern React patterns
-```
-
-### Development → Quality Pattern
-```bash
-# Step 1: Build the feature
-/sc:implement "user registration with email verification"
-# Expected: Registration system with email integration
-
-# Step 2: Test thoroughly
-/sc:test --focus quality
-# Expected: Comprehensive test coverage and validation
-
-# Step 3: Review and improve
-/sc:analyze . --focus quality && /sc:implement "quality improvements"
-# Expected: Quality assessment and targeted improvements
-```
-
-### Problem → Solution Pattern
-```bash
-# Step 1: Understand the problem
-/sc:troubleshoot "slow database queries on user dashboard"
-# Expected: Systematic problem diagnosis and root cause analysis
-
-# Step 2: Analyze affected components
-/sc:analyze db/ --focus performance
-# Expected: Database performance analysis and optimization opportunities
-
-# Step 3: Implement solutions
-/sc:implement "database query optimization and caching"
-# Expected: Performance improvements with measurable impact
-```
-
-## Getting Started Examples
-
-### Your First Project Analysis
-```bash
-# Complete project understanding workflow
-/sc:load . && /sc:analyze --focus quality
-
-# Expected Results:
-# - Project structure analysis and documentation
-# - Code quality assessment across all files
-# - Architecture overview with component relationships
-# - Security audit and performance recommendations
-
-# Activates: Serena (project loading) + analyzer + security-engineer + performance-engineer
-# Output: Comprehensive project report with actionable insights
-
-
-# Variations for different focuses:
-/sc:analyze src/ --focus quality # Code quality only
-/sc:analyze . --scope file # Quick file analysis
-/sc:analyze backend/ --focus security # Backend security review
-```
-
-### Interactive Requirements Discovery
-```bash
-# Transform vague ideas into concrete requirements
-/sc:brainstorm "productivity app for remote teams"
-
-# Expected Interaction:
-# - Socratic questioning about user needs and pain points
-# - Feature prioritization and scope definition
-# - Technical feasibility assessment
-# - Structured requirements document generation
-
-# Activates: Brainstorming mode + system-architect + requirements-analyst
-# Output: Product Requirements Document (PRD) with clear specifications
-
-# Follow-up commands for progression:
-/sc:analyze "team collaboration architecture" --focus architecture --c7
-/sc:implement "real-time messaging system with React and WebSocket"
-```
-
-### Simple Feature Implementation
-```bash
-# Complete authentication system
-/sc:implement "user login with JWT tokens and password hashing"
-
-# Expected Implementation:
-# - Secure password hashing with bcrypt
-# - JWT token generation and validation
-# - Login/logout endpoints with proper error handling
-# - Frontend login form with validation
-
-# Activates: security-engineer + backend-architect + Context7
-# Output: Production-ready authentication system
-
-
-# Variations for different auth needs:
-/sc:implement "OAuth integration with Google and GitHub"
-/sc:implement "password reset flow with email verification"
-/sc:implement "two-factor authentication with TOTP"
-```
-
-## Common Development Tasks
-
-### API Development Basics
-```bash
-# REST API with CRUD operations
-/sc:implement "Express.js REST API for blog posts with validation"
-# Expected: Complete REST API with proper HTTP methods, validation, error handling
-
-
-# API documentation generation
-/sc:analyze api/ --focus architecture --c7
-# Expected: Comprehensive API documentation with usage examples
-
-
-# API testing setup
-/sc:test --focus api --type integration
-# Expected: Integration test suite for API endpoints
-
-```
-
-### Frontend Component Development
-```bash
-# React component with modern patterns
-/sc:implement "React user profile component with form validation and image upload"
-# Activates: frontend-architect + Magic MCP + accessibility patterns
-# Expected: Modern React component with hooks, validation, accessibility
-
-
-# Component testing
-/sc:test src/components/ --focus quality
-# Expected: Component tests with React Testing Library
-
-
-# Responsive design implementation
-/sc:implement "responsive navigation component with mobile menu"
-# Expected: Mobile-first responsive navigation with accessibility
-
-```
-
-### Database Integration
-```bash
-# Database setup with ORM
-/sc:implement "PostgreSQL integration with Prisma ORM and migrations"
-# Expected: Database schema, ORM setup, migration system
-
-
-# Database query optimization
-/sc:analyze db/ --focus performance
-# Expected: Query performance analysis and optimization suggestions
-
-
-# Data validation and security
-/sc:implement "input validation and SQL injection prevention"
-# Expected: Comprehensive input validation and security measures
-
-```
-
-## Basic Troubleshooting Examples
-
-### Common API Issues
-```bash
-# Performance problems
-/sc:troubleshoot "API response time increased from 200ms to 2 seconds"
-# Activates: root-cause-analyst + performance-engineer + Sequential reasoning
-# Expected: Systematic diagnosis, root cause identification, solution ranking
-
-# Authentication errors
-/sc:troubleshoot "JWT token validation failing for valid users"
-# Expected: Token validation analysis, security assessment, fix implementation
-
-# Database connection issues
-/sc:troubleshoot "database connection pool exhausted under load"
-# Expected: Connection analysis, configuration fixes, scaling recommendations
-```
-
-### Frontend Debugging
-```bash
-# React rendering issues
-/sc:troubleshoot "React components not updating when data changes"
-# Expected: State management analysis, re-rendering optimization, debugging guide
-
-# Performance problems
-/sc:troubleshoot "React app loading slowly with large component tree"
-# Expected: Performance analysis, optimization strategies, code splitting recommendations
-
-# Build failures
-/sc:troubleshoot "webpack build failing with dependency conflicts"
-# Expected: Dependency analysis, conflict resolution, build optimization
-```
-
-### Development Environment Issues
-```bash
-# Setup problems
-/sc:troubleshoot "Node.js application not starting after npm install"
-# Expected: Environment analysis, dependency troubleshooting, configuration fixes
-
-# Testing failures
-/sc:troubleshoot "tests passing locally but failing in CI"
-# Expected: Environment comparison, CI configuration analysis, fix recommendations
-
-# Deployment issues
-/sc:troubleshoot "application crashes on production deployment"
-# Expected: Production environment analysis, configuration validation, deployment fixes
-```
-
-## Copy-Paste Quick Solutions
-
-### Immediate Project Setup
-```bash
-# New React project with TypeScript
-/sc:implement "React TypeScript project with routing, state management, and testing setup"
-@agent-frontend-architect "review and optimize the project structure"
-
-# New Node.js API server
-/sc:implement "Express.js REST API with JWT authentication and PostgreSQL integration"
-@agent-backend-architect "ensure scalability and best practices"
-
-# Python web API
-/sc:implement "FastAPI application with async PostgreSQL and authentication middleware"
-@agent-python-expert "optimize async patterns and dependency injection"
-
-# Next.js full-stack app
-/sc:implement "Next.js 14 application with App Router, TypeScript, and Tailwind CSS"
-@agent-system-architect "design optimal data fetching strategy"
-```
-
-### Quick Quality Improvements
-```bash
-# Code quality enhancement
-/sc:analyze . --focus quality && /sc:implement "code quality improvements"
-@agent-quality-engineer "create quality metrics dashboard"
-
-# Security hardening
-/sc:analyze . --focus security && /sc:implement "security improvements"
-
-# Test coverage improvement
-/sc:test --focus quality && /sc:implement "additional test coverage"
-```
-
-### Common Feature Implementations
-```bash
-# User authentication system
-/sc:implement "complete user authentication with registration, login, and password reset"
-
-# File upload functionality
-/sc:implement "secure file upload with image resizing and cloud storage"
-
-# Real-time features
-/sc:implement "real-time chat with WebSocket and message persistence"
-
-# Payment processing
-/sc:implement "Stripe payment integration with subscription management"
-
-# Email functionality
-/sc:implement "email service with templates and delivery tracking"
-```
-
-## Basic Flag Examples
-
-### Analysis Depth Control
-```bash
-# Quick analysis
-/sc:analyze src/ --scope file
-
-# Standard analysis
-/sc:analyze . --think
-
-# Deep analysis
-/sc:analyze . --think-hard --focus architecture
-
-```
-
-### Focus Area Selection
-```bash
-# Security-focused analysis
-/sc:analyze . --focus security
-
-
-# Implementation with specific focus
-/sc:implement "API optimization" --focus architecture
-
-
-# Quality-focused testing
-/sc:test --focus quality
-
-```
-
-### Tool Integration
-```bash
-# Use Context7 for official patterns
-/sc:implement "React hooks implementation" --c7
-
-
-# Use Serena for project memory
-/sc:analyze . --serena --focus architecture
-
-
-# Efficient token usage
-/sc:analyze large-project/ --uc
-
-```
-
-## Learning Progression Workflow
-
-### Week 1: Foundation
-```bash
-# Day 1-2: Basic commands
-/sc:analyze . --focus quality
-/sc:implement "simple feature"
-/sc:test --focus quality
-
-# Day 3-4: Troubleshooting
-/sc:troubleshoot "specific problem"
-/sc:analyze problem-area/ --focus relevant-domain
-
-# Day 5-7: Integration
-/sc:brainstorm "project idea"
-/sc:implement "core feature"
-/sc:test --focus quality
-```
-
-### Week 2: Patterns
-```bash
-# Workflow patterns
-/sc:brainstorm → /sc:analyze → /sc:implement → /sc:test
-
-# Problem-solving patterns
-/sc:troubleshoot → /sc:analyze → /sc:implement
-
-# Quality patterns
-/sc:analyze → /sc:implement → /sc:test → /sc:analyze
-```
-
-### Week 3-4: Integration
-```bash
-# Multi-step projects
-/sc:brainstorm "larger project"
-/sc:implement "phase 1"
-/sc:test --focus quality
-/sc:implement "phase 2"
-/sc:test --focus integration
-```
-
-## Next Steps
-
-### Ready for Intermediate?
-- Comfortable with all basic commands
-- Can complete simple workflows independently
-- Understanding of agent activation and tool selection
-- Ready for multi-step projects
-
-### Continue Learning:
-- **Advanced Workflows**: Complex orchestration and multi-agent coordination
-- **Integration Patterns**: Framework integration and cross-tool coordination
-- **Best Practices Guide**: Optimization strategies and expert techniques
-
-### Success Indicators:
-- Can solve common development problems independently
-- Understands when to use different flags and focuses
-- Can adapt examples to specific project needs
-- Ready to explore more complex SuperClaude capabilities
-
----
-
-**Remember**: Start simple, practice frequently, and gradually increase complexity. These basic examples form the foundation for all advanced SuperClaude usage.
\ No newline at end of file
diff --git a/docs/Reference/claude-code-history-management.md b/docs/Reference/claude-code-history-management.md
deleted file mode 100644
index de25e16..0000000
--- a/docs/Reference/claude-code-history-management.md
+++ /dev/null
@@ -1,556 +0,0 @@
-# Claude Code Conversation History Management Research
-
-**Research Date**: 2025-10-09
-**Purpose**: Understand .jsonl file structure, performance impact, and establish rotation policy
-
----
-
-## 1. Official Documentation & Purpose
-
-### .jsonl File Structure
-**Location**: `~/.claude/projects/{project-directory}/`
-
-**Data Structure** (from analysis of actual files):
-```json
-{
- "type": "summary|file-history-snapshot|user|assistant|system|tool_use|tool_result|message",
- "timestamp": "ISO-8601 timestamp",
- "cwd": "/absolute/path/to/working/directory",
- "sessionId": "uuid",
- "gitBranch": "branch-name",
- "content": "message content or command",
- "messageId": "uuid for message tracking"
-}
-```
-
-**Key Message Types** (from 2.6MB conversation analysis):
-- `message` (228): Container for conversation messages
-- `assistant` (228): Claude's responses
-- `user` (182): User inputs
-- `tool_use` (137): Tool invocations
-- `tool_result` (137): Tool execution results
-- `text` (74): Text content blocks
-- `file-history-snapshot` (39): File state tracking
-- `thinking` (31): Claude's reasoning process
-- `system` (12): System-level messages
-
-### File History Snapshot Purpose
-```json
-{
- "type": "file-history-snapshot",
- "messageId": "uuid",
- "snapshot": {
- "messageId": "uuid",
- "trackedFileBackups": {},
- "timestamp": "ISO-8601"
- },
- "isSnapshotUpdate": false
-}
-```
-
-**Purpose** (inferred from structure):
-- Tracks file states at specific conversation points
-- Enables undo/redo functionality for file changes
-- Provides rollback capability for edits
-- **Note**: No official documentation found on this feature
-
-### Conversation Loading Behavior
-**Official Best Practices** ([source](https://www.anthropic.com/engineering/claude-code-best-practices)):
-- "All conversations are automatically saved locally with their full message history"
-- "When resuming, the entire message history is restored to maintain context"
-- "Tool usage and results from previous conversations preserved"
-
-**Resume Commands**:
-- `--continue`: Automatically continue most recent conversation
-- `/resume`: Show list of recent sessions and choose one
-- Session ID specification: Resume specific conversation
-
----
-
-## 2. Performance Impact
-
-### Known Issues from GitHub
-
-#### Issue #5024: History Accumulation Causing Performance Issues
-**Status**: Open (Major Issue)
-**URL**: https://github.com/anthropics/claude-code/issues/5024
-
-**Reported Problems**:
-- File sizes growing to "hundreds of MB or more"
-- Slower application startup times
-- System performance degradation
-- No automatic cleanup mechanism
-- One user reported file size of 968KB+ continuously growing
-
-**Current Workaround**:
-- Manual editing of `.claude.json` (risky - can break configurations)
-- `claude history clear` (removes ALL history across ALL projects)
-
-#### Issue #7985: Severe Memory Leak
-**Status**: Critical
-**URL**: https://github.com/anthropics/claude-code/issues/7985
-
-**Reported Problems**:
-- Context accumulation causing massive memory usage
-- Memory leaks with objects not garbage collected
-- One user reported ~570GB of virtual memory usage
-- Long-running sessions become unusable
-
-#### Issue #8839: Conversation Compaction Failure
-**Status**: Regression (after undo/redo feature)
-**URL**: https://github.com/anthropics/claude-code/issues/8839
-
-**Impact**:
-- Claude Code can no longer automatically compact long conversations
-- "Too long" errors after conversation history navigation feature added
-- Conversations become unmanageable without manual intervention
-
-#### Issue #8755: /clear Command Not Working
-**Status**: Bug
-**URL**: https://github.com/anthropics/claude-code/issues/8755
-
-**Impact**:
-- `/clear` command stopped functioning for some users
-- "Clear Conversations" menu option non-functional
-- Users cannot reset context window as recommended
-
-### Actual Performance Data (Your Environment)
-
-**Current State** (as of 2025-10-09):
-- **Total agiletec project**: 33MB (57 conversation files)
-- **Largest file**: 2.6MB (462 lines)
-- **Average file**: ~580KB
-- **Files >1MB**: 3 files
-- **Total across all projects**: ~62MB
-
-**Age Distribution**:
-- Files older than 30 days: 0
-- Files older than 7 days: 4
-- Most files: <7 days old
-
-**Comparison to Other Projects**:
-```
-33M agiletec (57 files) - Most active
-14M SSD-2TB project
-6.3M tokium
-2.6M bunseki
-```
-
----
-
-## 3. Official Retention Policies
-
-### Standard Retention (Consumer)
-**Source**: [Anthropic Privacy Center](https://privacy.claude.com/en/articles/10023548-how-long-do-you-store-my-data)
-
-- **Prompts/Responses**: Up to 30 days in back-end logs
-- **Deleted chats**: Immediately removed from UI, purged within 30 days
-- **API logs**: Reducing to 7 days starting September 15, 2025 (from 30 days)
-
-### Enterprise Controls
-**Source**: [Custom Data Retention Controls](https://privacy.anthropic.com/en/articles/10440198-custom-data-retention-controls-for-claude-enterprise)
-
-- **Minimum retention**: 30 days
-- **Retention start**: Last observed activity (last message or project update)
-- **Custom periods**: Available for organizations
-
-### Local Storage (No Official Policy)
-**Finding**: No official documentation found regarding:
-- Recommended local .jsonl file retention periods
-- Automatic cleanup of old conversations
-- Performance thresholds for file sizes
-- Safe deletion procedures
-
-**Current Tools**:
-- `claude history clear`: Removes ALL history (all projects, destructive)
-- No selective cleanup tools available
-- No archive functionality
-
----
-
-## 4. Best Practices (Official & Community)
-
-### Official Recommendations
-
-#### Context Management
-**Source**: [Claude Code Best Practices](https://www.anthropic.com/engineering/claude-code-best-practices)
-
-**Key Guidelines**:
-1. **Use `/clear` frequently**: "Reset context window between tasks"
-2. **Scope conversations**: "One project or feature per conversation"
-3. **Clear before switching**: "/clear before fixing bugs to prevent context pollution"
-4. **Don't rely on long context**: "Claude's context window can fill with irrelevant conversation"
-
-**Quote**: "During long sessions, Claude's context window can fill with irrelevant conversation, file contents, and commands which can reduce performance, so use the /clear command frequently between tasks to reset the context window."
-
-#### CLAUDE.md Strategy
-- **Persistent context**: Use CLAUDE.md files for stable instructions
-- **Auto-loaded**: "Claude automatically pulls into context when starting"
-- **Hierarchy**: Global (`~/.claude/CLAUDE.md`) → Workspace → Project
-- **Refinement**: "Take time to experiment and determine what produces best results"
-
-#### When to Restart vs /clear
-**Source**: [Community Best Practices](https://claudelog.com/faqs/does-claude-code-store-my-data/)
-
-**Use `/clear` when**:
-- Starting new task/feature
-- Switching between features
-- Context becomes polluted
-- Before bug fixing
-
-**Restart session when**:
-- Switching projects
-- Updating CLAUDE.md files
-- Experiencing session issues
-- Memory usage high
-
-### Community Strategies
-
-#### Conversation Organization
-**Pattern**: "Scope a chat to one project or feature"
-- Start conversation for specific goal
-- Use `/clear` when goal complete
-- Don't mix unrelated tasks in same conversation
-
-#### Context Optimization
-**Pattern**: "Avoid extensive, unrefined context"
-- Iterate on CLAUDE.md effectiveness
-- Remove ineffective instructions
-- Test and refine periodically
-
-#### Incognito Mode for Sensitive Work
-**Pattern**: "Ghost icon for temporary conversations"
-- Not saved to chat history
-- No contribution to context memory
-- Useful for experimental or sensitive work
-
----
-
-## 5. Recommended Rotation Policy
-
-### Immediate Actions (No Risk)
-
-#### 1. Delete Very Old Conversations (>30 days)
-```bash
-# Backup first
-mkdir -p ~/.claude/projects-archive/$(date +%Y-%m)
-
-# Find and archive
-find ~/.claude/projects/ -name "*.jsonl" -mtime +30 -type f \
- -exec mv {} ~/.claude/projects-archive/$(date +%Y-%m)/ \;
-```
-
-**Rationale**:
-- Aligns with Anthropic's 30-day back-end retention
-- Minimal functionality loss (context rarely useful after 30 days)
-- Significant space savings
-
-#### 2. Archive Project-Specific Old Conversations (>14 days)
-```bash
-# Per-project archive
-mkdir -p ~/.claude/projects-archive/agiletec/$(date +%Y-%m)
-
-find ~/.claude/projects/-Users-kazuki-github-agiletec -name "*.jsonl" -mtime +14 -type f \
- -exec mv {} ~/.claude/projects-archive/agiletec/$(date +%Y-%m)/ \;
-```
-
-**Rationale**:
-- 14 days provides buffer for resumed work
-- Most development tasks complete within 2 weeks
-- Easy to restore if needed
-
-### Periodic Maintenance (Weekly)
-
-#### 3. Identify Large Files for Manual Review
-```bash
-# Find files >1MB
-find ~/.claude/projects/ -name "*.jsonl" -type f -size +1M -exec ls -lh {} \;
-
-# Review and archive if not actively used
-```
-
-**Criteria for Archival**:
-- File >1MB and not modified in 7 days
-- Completed feature/project conversations
-- Debugging sessions that are resolved
-
-### Aggressive Cleanup (Monthly)
-
-#### 4. Archive All Inactive Conversations (>7 days)
-```bash
-# Monthly archive
-mkdir -p ~/.claude/projects-archive/$(date +%Y-%m)
-
-find ~/.claude/projects/ -name "*.jsonl" -mtime +7 -type f \
- -exec mv {} ~/.claude/projects-archive/$(date +%Y-%m)/ \;
-```
-
-**When to Use**:
-- Project directory >50MB
-- Startup performance degraded
-- Running low on disk space
-
-### Emergency Cleanup (Performance Issues)
-
-#### 5. Nuclear Option - Keep Only Recent Week
-```bash
-# BACKUP EVERYTHING FIRST
-tar -czf ~/claude-history-backup-$(date +%Y%m%d).tar.gz ~/.claude/projects/
-
-# Keep only last 7 days
-find ~/.claude/projects/ -name "*.jsonl" -mtime +7 -type f -delete
-```
-
-**When to Use**:
-- Claude Code startup >10 seconds
-- Memory usage abnormally high
-- Experiencing Issue #7985 symptoms
-
----
-
-## 6. Proposed Automated Solution
-
-### Shell Script: `claude-history-rotate.sh`
-```bash
-#!/usr/bin/env bash
-# Claude Code Conversation History Rotation
-# Usage: ./claude-history-rotate.sh [--dry-run] [--days N]
-
-set -euo pipefail
-
-DAYS=${DAYS:-30}
-DRY_RUN=false
-ARCHIVE_BASE=~/.claude/projects-archive
-
-# Parse arguments
-while [[ $# -gt 0 ]]; do
- case $1 in
- --dry-run) DRY_RUN=true; shift ;;
- --days) DAYS="$2"; shift 2 ;;
- *) echo "Unknown option: $1"; exit 1 ;;
- esac
-done
-
-# Create archive directory
-ARCHIVE_DIR="$ARCHIVE_BASE/$(date +%Y-%m)"
-mkdir -p "$ARCHIVE_DIR"
-
-# Find old conversations
-OLD_FILES=$(find ~/.claude/projects/ -name "*.jsonl" -mtime "+$DAYS" -type f)
-
-if [[ -z "$OLD_FILES" ]]; then
- echo "No files older than $DAYS days found."
- exit 0
-fi
-
-# Count and size
-FILE_COUNT=$(echo "$OLD_FILES" | wc -l | tr -d ' ')
-TOTAL_SIZE=$(echo "$OLD_FILES" | xargs du -ch | tail -1 | awk '{print $1}')
-
-echo "Found $FILE_COUNT files older than $DAYS days ($TOTAL_SIZE total)"
-
-if [[ "$DRY_RUN" == "true" ]]; then
- echo "DRY RUN - Would archive:"
- echo "$OLD_FILES"
- exit 0
-fi
-
-# Archive files
-echo "$OLD_FILES" | while read -r file; do
- mv "$file" "$ARCHIVE_DIR/"
- echo "Archived: $(basename "$file")"
-done
-
-echo "✓ Archived $FILE_COUNT files to $ARCHIVE_DIR"
-```
-
-### Cron Job Setup (Optional)
-```bash
-# Add to crontab (monthly cleanup)
-# 0 3 1 * * /Users/kazuki/.local/bin/claude-history-rotate.sh --days 30
-
-# Or use launchd on macOS
-cat > ~/Library/LaunchAgents/com.user.claude-history-rotate.plist <<'EOF'
-
-
-
-
- Label
- com.user.claude-history-rotate
- ProgramArguments
-
- /Users/kazuki/.local/bin/claude-history-rotate.sh
- --days
- 30
-
- StartCalendarInterval
-
- Day
- 1
- Hour
- 3
-
-
-
-EOF
-
-launchctl load ~/Library/LaunchAgents/com.user.claude-history-rotate.plist
-```
-
----
-
-## 7. Monitoring & Alerts
-
-### Disk Usage Check Script
-```bash
-#!/usr/bin/env bash
-# claude-history-check.sh
-
-THRESHOLD_MB=100
-PROJECTS_DIR=~/.claude/projects
-
-TOTAL_SIZE_MB=$(du -sm "$PROJECTS_DIR" | awk '{print $1}')
-
-echo "Claude Code conversation history: ${TOTAL_SIZE_MB}MB"
-
-if [[ $TOTAL_SIZE_MB -gt $THRESHOLD_MB ]]; then
- echo "⚠️ WARNING: History size exceeds ${THRESHOLD_MB}MB threshold"
- echo "Consider running: claude-history-rotate.sh --days 30"
-
- # Find largest projects
- echo ""
- echo "Largest projects:"
- du -sm "$PROJECTS_DIR"/*/ | sort -rn | head -5
-fi
-```
-
-### Performance Indicators to Watch
-1. **Startup time**: >5 seconds = investigate
-2. **File sizes**: >2MB per conversation = review
-3. **Total size**: >100MB across all projects = cleanup
-4. **Memory usage**: >2GB during session = Issue #7985
-5. **Conversation length**: >500 message pairs = use `/clear`
-
----
-
-## 8. Key Takeaways & Recommendations
-
-### Critical Findings
-
-✅ **Safe to Delete**:
-- Conversations >30 days old (aligns with Anthropic retention)
-- Completed feature/project conversations
-- Large files (>1MB) not accessed in 14+ days
-
-⚠️ **Caution Required**:
-- Active project conversations (<7 days)
-- Files referenced in recent work
-- Conversations with unfinished tasks
-
-❌ **Known Issues**:
-- No official cleanup tools (Issue #5024)
-- Memory leaks in long sessions (Issue #7985)
-- `/clear` command bugs (Issue #8755)
-- Conversation compaction broken (Issue #8839)
-
-### Recommended Policy for Your Environment
-
-**Daily Practice**:
-- Use `/clear` between major tasks
-- Scope conversations to single features
-- Restart session if >2 hours continuous work
-
-**Weekly Review** (Sunday):
-```bash
-# Check current state
-du -sh ~/.claude/projects/*/
-
-# Archive old conversations (>14 days)
-claude-history-rotate.sh --days 14 --dry-run # Preview
-claude-history-rotate.sh --days 14 # Execute
-```
-
-**Monthly Cleanup** (1st of month):
-```bash
-# Aggressive cleanup (>30 days)
-claude-history-rotate.sh --days 30
-
-# Review large files
-find ~/.claude/projects/ -name "*.jsonl" -size +1M -mtime +7
-```
-
-**Performance Threshold Actions**:
-- Total size >50MB: Archive 30-day-old conversations
-- Total size >100MB: Archive 14-day-old conversations
-- Total size >200MB: Emergency cleanup (7-day retention)
-- Startup >10s: Investigate memory leaks, consider Issue #7985
-
-### Future-Proofing
-
-**Watch for Official Solutions**:
-- `claude history prune` command (requested in #5024)
-- Automatic history rotation feature
-- Configurable retention settings
-- Separate configuration from history storage
-
-**Community Tools**:
-- [cclogviewer](https://github.com/hesreallyhim/awesome-claude-code): View .jsonl files
-- Consider contributing to #5024 discussion
-- Monitor anthropics/claude-code releases
-
----
-
-## 9. References
-
-### Official Documentation
-- [Claude Code Best Practices](https://www.anthropic.com/engineering/claude-code-best-practices)
-- [How Long Do You Store My Data?](https://privacy.claude.com/en/articles/10023548-how-long-do-you-store-my-data)
-- [Custom Data Retention Controls](https://privacy.anthropic.com/en/articles/10440198-custom-data-retention-controls-for-claude-enterprise)
-
-### GitHub Issues
-- [#5024: History accumulation causes performance issues](https://github.com/anthropics/claude-code/issues/5024)
-- [#7985: Severe memory leak](https://github.com/anthropics/claude-code/issues/7985)
-- [#8839: Conversation compaction failure](https://github.com/anthropics/claude-code/issues/8839)
-- [#8755: /clear command not working](https://github.com/anthropics/claude-code/issues/8755)
-
-### Community Resources
-- [Awesome Claude Code](https://github.com/hesreallyhim/awesome-claude-code)
-- [Claude Code Context Guide](https://www.arsturn.com/blog/beyond-prompting-a-guide-to-managing-context-in-claude-code)
-- [ClaudeLog Documentation](https://claudelog.com/)
-
----
-
-## Appendix: Current Environment Statistics
-
-**Generated**: 2025-10-09 04:24 JST
-
-### Project Size Breakdown
-```
-33M -Users-kazuki-github-agiletec (57 files)
-14M -Volumes-SSD-2TB (project count: N/A)
-6.3M -Users-kazuki-github-tokium
-2.6M -Users-kazuki-github-bunseki
-1.9M -Users-kazuki
-1.9M -Users-kazuki-github-superclaude
----
-Total: ~62MB across all projects
-```
-
-### agiletec Project Details
-- **Total conversations**: 57
-- **Largest file**: 2.6MB (d4852655-b760-4311-8f67-26f593f2403f.jsonl)
-- **Files >1MB**: 3 files
-- **Avg file size**: ~580KB
-- **Files >7 days**: 4 files
-- **Files >30 days**: 0 files
-
-### Immediate Recommendation
-**Status**: ✅ Healthy (no immediate action required)
-
-**Reasoning**:
-- Total size (33MB) well below concern threshold (100MB)
-- No files >30 days old
-- Only 4 files >7 days old
-- Largest file (2.6MB) within acceptable range
-
-**Next Review**: 2025-10-16 (weekly check)
diff --git a/docs/Reference/common-issues.md b/docs/Reference/common-issues.md
deleted file mode 100644
index a26cb2d..0000000
--- a/docs/Reference/common-issues.md
+++ /dev/null
@@ -1,79 +0,0 @@
-# SuperClaude Common Issues - Quick Reference 🚀
-
-**Problem Solving Guide**: Most frequent issues with practical solutions.
-
-## Top 5 Quick Fixes (90% of Issues)
-
-### 1. Commands Not Working in Claude Code ⚡
-```
-Problem: /sc:brainstorm doesn't work
-Solution: Restart Claude Code completely
-Test: /sc:brainstorm "test" should ask questions
-```
-
-### 2. Installation Verification
-```bash
-python3 -m SuperClaude --version # Should show 4.1.5
-
-# If not working:
-# For pipx users
-pipx upgrade SuperClaude
-
-# For pip users
-pip install --upgrade SuperClaude
-
-# Then reinstall
-python3 -m SuperClaude install
-```
-
-### 3. Permission Issues
-```bash
-# Permission denied / PEP 668 errors:
-# Option 1: Use pipx (recommended)
-pipx install SuperClaude
-
-# Option 2: Use pip with --user
-pip install --user SuperClaude
-
-# Option 3: Fix permissions
-sudo chown -R $USER ~/.claude
-```
-
-### 4. MCP Server Issues
-```bash
-/sc:analyze . --no-mcp # Test without MCP servers
-node --version # Check Node.js 16+ if needed
-```
-
-### 5. Component Missing
-```bash
-python3 -m SuperClaude install --components core commands agents modes --force
-```
-
-## Platform-Specific Issues
-
-**Windows:**
-```cmd
-set CLAUDE_CONFIG_DIR=%USERPROFILE%\.claude
-python -m SuperClaude install --install-dir "%CLAUDE_CONFIG_DIR%"
-```
-
-**macOS:**
-```bash
-brew install python3 node
-pip3 install SuperClaude
-```
-
-**Linux:**
-```bash
-sudo apt install python3 python3-pip nodejs
-pip3 install SuperClaude
-```
-
-## Verification Checklist
-- [ ] `python3 -m SuperClaude --version` returns 4.1.5
-- [ ] `/sc:brainstorm "test"` works in Claude Code
-- [ ] `SuperClaude install --list-components` shows components
-
-## When Quick Fixes Don't Work
-See [Troubleshooting Guide](troubleshooting.md) for advanced diagnostics.
\ No newline at end of file
diff --git a/docs/Reference/diagnostic-reference.md b/docs/Reference/diagnostic-reference.md
deleted file mode 100644
index 943143b..0000000
--- a/docs/Reference/diagnostic-reference.md
+++ /dev/null
@@ -1,338 +0,0 @@
-# SuperClaude Diagnostic Reference Guide
-
-## Overview
-
-This guide provides procedures for diagnosing issues with SuperClaude context files and configurations. Since SuperClaude is a collection of text files (not running software), diagnostics focus on file verification and configuration checking.
-
-**Important**: There are no processes to monitor, no performance metrics to measure, and no system resources to analyze. SuperClaude is purely configuration files that Claude Code reads.
-
-## Quick Diagnostics
-
-### One-Line Health Check
-
-```bash
-# Quick status check
-ls ~/.claude/CLAUDE.md && echo "✅ SuperClaude installed" || echo "❌ Not installed"
-```
-
-### Basic Diagnostic Commands
-
-```bash
-# Check if SuperClaude is installed
-python3 -m SuperClaude --version
-
-# Count context files
-find ~/.claude -name "*.md" -type f | wc -l
-# Expected: 40+ files
-
-# Check file sizes (context files should have content)
-find ~/.claude -name "*.md" -type f -size 0
-# Expected: No output (no empty files)
-
-# Verify directory structure
-tree -L 2 ~/.claude/
-# Or without tree command:
-ls -la ~/.claude/
-```
-
-## File System Diagnostics
-
-### Context File Verification
-
-```bash
-#!/bin/bash
-# Comprehensive context file check
-
-echo "=== SuperClaude Context File Diagnostic ==="
-
-# Define expected counts
-EXPECTED_AGENTS=14
-EXPECTED_COMMANDS=21
-EXPECTED_MODES=6
-
-# Count actual files
-ACTUAL_AGENTS=$(ls ~/.claude/agents/*.md 2>/dev/null | wc -l)
-ACTUAL_COMMANDS=$(ls ~/.claude/commands/*.md 2>/dev/null | wc -l)
-ACTUAL_MODES=$(ls ~/.claude/modes/*.md 2>/dev/null | wc -l)
-
-# Report findings
-echo "Agents: $ACTUAL_AGENTS/$EXPECTED_AGENTS $([ $ACTUAL_AGENTS -ge $EXPECTED_AGENTS ] && echo ✅ || echo ⚠️)"
-echo "Commands: $ACTUAL_COMMANDS/$EXPECTED_COMMANDS $([ $ACTUAL_COMMANDS -ge $EXPECTED_COMMANDS ] && echo ✅ || echo ⚠️)"
-echo "Modes: $ACTUAL_MODES/$EXPECTED_MODES $([ $ACTUAL_MODES -ge $EXPECTED_MODES ] && echo ✅ || echo ⚠️)"
-
-# Check core files
-for file in CLAUDE.md FLAGS.md RULES.md PRINCIPLES.md; do
- if [ -f ~/.claude/$file ]; then
- SIZE=$(wc -c < ~/.claude/$file)
- echo "$file: $SIZE bytes ✅"
- else
- echo "$file: MISSING ❌"
- fi
-done
-```
-
-### Import System Check
-
-```bash
-# Verify import statements in CLAUDE.md
-echo "=== Import System Check ==="
-if [ -f ~/.claude/CLAUDE.md ]; then
- echo "Imports found in CLAUDE.md:"
- grep "^@import" ~/.claude/CLAUDE.md
-
- # Count import statements
- IMPORT_COUNT=$(grep -c "^@import" ~/.claude/CLAUDE.md)
- echo "Total imports: $IMPORT_COUNT"
-
- if [ $IMPORT_COUNT -ge 5 ]; then
- echo "✅ Import system configured correctly"
- else
- echo "⚠️ Some imports may be missing"
- fi
-else
- echo "❌ CLAUDE.md not found"
-fi
-```
-
-## Configuration Diagnostics
-
-### MCP Server Configuration Check
-
-```bash
-# Check MCP configuration
-echo "=== MCP Configuration Diagnostic ==="
-
-CONFIG_FILE=~/.claude.json
-
-if [ -f "$CONFIG_FILE" ]; then
- echo "✅ Configuration file exists"
-
- # Validate JSON syntax
- if python3 -c "import json; json.load(open('$CONFIG_FILE'))" 2>/dev/null; then
- echo "✅ Valid JSON syntax"
-
- # List configured servers
- echo "Configured MCP servers:"
- python3 -c "
-import json
-with open('$HOME/.claude.json') as f:
- config = json.load(f)
- if 'mcpServers' in config:
- for server in config['mcpServers']:
- print(f' - {server}')
- else:
- print(' No servers configured')
- "
- else
- echo "❌ Invalid JSON syntax in $CONFIG_FILE"
- fi
-else
- echo "⚠️ No MCP configuration file found"
- echo " This is OK if you don't use MCP servers"
-fi
-```
-
-### Permission Diagnostics
-
-```bash
-# Check file permissions
-echo "=== File Permission Check ==="
-
-# Check if files are readable
-UNREADABLE_COUNT=0
-for file in ~/.claude/**/*.md; do
- if [ ! -r "$file" ]; then
- echo "❌ Cannot read: $file"
- ((UNREADABLE_COUNT++))
- fi
-done
-
-if [ $UNREADABLE_COUNT -eq 0 ]; then
- echo "✅ All context files are readable"
-else
- echo "⚠️ Found $UNREADABLE_COUNT unreadable files"
- echo "Fix with: chmod 644 ~/.claude/**/*.md"
-fi
-
-# Check directory permissions
-for dir in ~/.claude ~/.claude/agents ~/.claude/commands ~/.claude/modes; do
- if [ -d "$dir" ]; then
- if [ -x "$dir" ]; then
- echo "✅ $dir is accessible"
- else
- echo "❌ $dir is not accessible"
- fi
- else
- echo "❌ $dir does not exist"
- fi
-done
-```
-
-## Common Issue Diagnostics
-
-### Issue: Commands Not Recognized
-
-```bash
-# Diagnose command issues
-COMMAND="implement" # Change to test different commands
-
-echo "=== Diagnosing command: $COMMAND ==="
-
-FILE=~/.claude/commands/$COMMAND.md
-
-if [ -f "$FILE" ]; then
- echo "✅ Command file exists"
-
- # Check file size
- SIZE=$(wc -c < "$FILE")
- if [ $SIZE -gt 100 ]; then
- echo "✅ File has content ($SIZE bytes)"
- else
- echo "⚠️ File seems too small ($SIZE bytes)"
- fi
-
- # Check for metadata
- if head -10 "$FILE" | grep -q "^---"; then
- echo "✅ Has metadata header"
- else
- echo "⚠️ Missing metadata header"
- fi
-
- # Check for command pattern
- if grep -q "/sc:$COMMAND" "$FILE"; then
- echo "✅ Contains command pattern"
- else
- echo "⚠️ Missing command pattern"
- fi
-else
- echo "❌ Command file not found: $FILE"
- echo "Available commands:"
- ls ~/.claude/commands/ | sed 's/.md$//'
-fi
-```
-
-### Issue: Agent Not Activating
-
-```bash
-# Diagnose agent issues
-AGENT="python-expert" # Change to test different agents
-
-echo "=== Diagnosing agent: $AGENT ==="
-
-FILE=~/.claude/agents/$AGENT.md
-
-if [ -f "$FILE" ]; then
- echo "✅ Agent file exists"
-
- # Check for trigger keywords
- echo "Trigger keywords found:"
- grep -A 5 "## Triggers" "$FILE" | tail -n +2
-
- # Check for metadata
- if head -10 "$FILE" | grep -q "^name:"; then
- echo "✅ Has metadata"
- else
- echo "⚠️ Missing metadata"
- fi
-else
- echo "❌ Agent file not found: $FILE"
- echo "Available agents:"
- ls ~/.claude/agents/ | sed 's/.md$//'
-fi
-```
-
-## Installation Repair
-
-### Quick Fix Script
-
-```bash
-#!/bin/bash
-# SuperClaude Quick Fix Script
-
-echo "=== SuperClaude Quick Fix ==="
-
-# Check for common issues and fix them
-ISSUES_FOUND=0
-
-# Fix permissions
-echo "Fixing file permissions..."
-chmod 644 ~/.claude/*.md 2>/dev/null
-chmod 644 ~/.claude/**/*.md 2>/dev/null
-chmod 755 ~/.claude ~/.claude/agents ~/.claude/commands ~/.claude/modes 2>/dev/null
-
-# Check for missing directories
-for dir in agents commands modes; do
- if [ ! -d ~/.claude/$dir ]; then
- echo "⚠️ Missing directory: $dir"
- echo " Run: SuperClaude install --components $dir"
- ((ISSUES_FOUND++))
- fi
-done
-
-# Check for empty files
-EMPTY_FILES=$(find ~/.claude -name "*.md" -type f -size 0 2>/dev/null)
-if [ -n "$EMPTY_FILES" ]; then
- echo "⚠️ Found empty files:"
- echo "$EMPTY_FILES"
- echo " Run: SuperClaude install --force"
- ((ISSUES_FOUND++))
-fi
-
-if [ $ISSUES_FOUND -eq 0 ]; then
- echo "✅ No issues found"
-else
- echo "Found $ISSUES_FOUND issues - see recommendations above"
-fi
-```
-
-### Complete Reinstallation
-
-```bash
-# Complete clean reinstall
-echo "=== Clean Reinstall ==="
-
-# Backup current installation
-BACKUP_DIR=~/.claude.backup.$(date +%Y%m%d_%H%M%S)
-if [ -d ~/.claude ]; then
- cp -r ~/.claude "$BACKUP_DIR"
- echo "✅ Backed up to $BACKUP_DIR"
-fi
-
-# Remove current installation
-rm -rf ~/.claude
-
-# Reinstall
-SuperClaude install
-
-# Verify installation
-if [ -f ~/.claude/CLAUDE.md ]; then
- echo "✅ Reinstallation successful"
-else
- echo "❌ Reinstallation failed"
- echo "Restoring backup..."
- cp -r "$BACKUP_DIR" ~/.claude
-fi
-```
-
-## What These Diagnostics DON'T Do
-
-### Not Applicable Concepts
-
-- **CPU/Memory Monitoring**: No processes to monitor
-- **Performance Metrics**: No code execution to measure
-- **Network Analysis**: No network operations (except MCP)
-- **Process Management**: No running processes
-- **Resource Optimization**: No resources consumed
-- **Execution Timing**: No code executes
-
-### Focus on What Matters
-
-- **File Presence**: Are context files installed?
-- **File Integrity**: Are files readable and complete?
-- **Configuration Validity**: Is JSON syntax correct?
-- **Directory Structure**: Is organization correct?
-- **Permissions**: Can Claude Code read the files?
-
-## Summary
-
-SuperClaude diagnostics are simple: verify files exist, check they're readable, and ensure configurations are valid. Since it's just text files that Claude Code reads, there's no complex system monitoring or performance analysis needed. If files are present and readable, SuperClaude is working.
\ No newline at end of file
diff --git a/docs/Reference/examples-cookbook.md b/docs/Reference/examples-cookbook.md
deleted file mode 100644
index 42a9d82..0000000
--- a/docs/Reference/examples-cookbook.md
+++ /dev/null
@@ -1,172 +0,0 @@
-# SuperClaude Examples Cookbook
-
-**Status**: ✅ **Status: Current** - Comprehensive collection of practical SuperClaude usage examples organized by complexity and domain.
-
-**Focused Recipe Collections**: The SuperClaude Examples Cookbook has been restructured into three focused collections for better usability and progressive learning.
-
-## Recipe Collections Overview
-
-### [Basic Examples Collection](./basic-examples.md)
-**Essential commands and single-agent workflows**
-- Copy-paste ready commands for immediate use
-- Essential SuperClaude patterns and fundamentals
-- Common development tasks and troubleshooting
-- Perfect starting point for new users
-
-**Best for**: New users, quick task execution, learning fundamentals
-
-### [Advanced Workflows Collection](./advanced-workflows.md)
-**Multi-agent coordination and complex orchestration**
-- Multi-agent collaboration patterns
-- Enterprise-scale project workflows
-- Session management and persistence
-- Complex system development patterns
-
-**Best for**: Experienced users, enterprise projects, complex coordination
-
-### [Integration Patterns Collection](./integration-patterns.md)
-**Framework integration and cross-tool coordination**
-- Framework-specific integration patterns
-- Performance optimization recipes
-- Cross-tool coordination strategies
-- Monitoring and observability patterns
-
-**Best for**: Expert users, system architects, performance optimization
-
-## Quick Navigation Guide
-
-### By Experience Level
-**Beginner**
-→ Start with [Basic Examples](./basic-examples.md)
-- Essential commands and patterns
-- Simple troubleshooting workflows
-- Copy-paste solutions for common tasks
-
-**Intermediate**
-→ Progress to [Advanced Workflows](./advanced-workflows.md)
-- Multi-agent coordination
-- Complex project orchestration
-- Session management patterns
-
-**Expert**
-→ Master [Integration Patterns](./integration-patterns.md)
-- Framework integration strategies
-- Performance optimization recipes
-- Enterprise-scale architecture patterns
-
-### By Use Case
-**Web Development**
-- Frontend: [Basic Examples](./basic-examples.md#frontend-component-development) → [Integration Patterns](./integration-patterns.md#react-ecosystem-integration)
-- Backend: [Basic Examples](./basic-examples.md#api-development-basics) → [Integration Patterns](./integration-patterns.md#nodejs-backend-integration)
-- Full-Stack: [Advanced Workflows](./advanced-workflows.md#complete-e-commerce-platform-development)
-
-**Mobile Development**
-- React Native: [Basic Examples](./basic-examples.md#copy-paste-quick-solutions) → [Integration Patterns](./integration-patterns.md#mobile-and-web-integration)
-- Cross-Platform: [Integration Patterns](./integration-patterns.md#cross-platform-integration-patterns)
-
-**DevOps & Infrastructure**
-- CI/CD: [Basic Examples](./basic-examples.md#copy-paste-quick-solutions) → [Integration Patterns](./integration-patterns.md#devops-and-infrastructure-integration)
-- Monitoring: [Advanced Workflows](./advanced-workflows.md#advanced-monitoring-and-observability) → [Integration Patterns](./integration-patterns.md#monitoring-and-observability-patterns)
-
-**Performance & Security**
-- Security: [Basic Examples](./basic-examples.md#basic-troubleshooting-examples) → [Advanced Workflows](./advanced-workflows.md#enterprise-scale-security-implementation)
-- Performance: [Integration Patterns](./integration-patterns.md#performance-optimization-recipes)
-
-## Verified Commands Reference
-
-**Core Commands**:
-- `/sc:brainstorm` - Interactive requirements discovery
-- `/sc:analyze` - Codebase analysis and assessment
-- `/sc:implement` - Feature implementation with best practices
-- `/sc:troubleshoot` - Systematic problem diagnosis
-- `/sc:test` - Comprehensive testing and validation
-- `/sc:spawn` - Complex multi-agent coordination
-- `/sc:load` / `/sc:save` - Session management
-- `/sc:reflect` - Context analysis and optimization
-
-**Verified Flags**:
-- `--think`, `--think-hard`, `--ultrathink` - Analysis depth control
-- `--uc` - Ultra-compressed token-efficient mode
-- `--orchestrate` - Intelligent coordination mode
-- `--c7`, `--serena`, `--all-mcp` - MCP server integration
-- `--focus [domain]` - Domain-specific optimization
-- `--scope [level]` - Analysis scope control
-
-## Learning Progression Roadmap
-
-### Phase 1: Foundation (Week 1-2)
-1. **Setup**: Complete [Installation Guide](../Getting-Started/installation.md)
-2. **Basics**: Practice [Basic Examples](./basic-examples.md#essential-one-liner-commands)
-3. **Patterns**: Learn [Basic Usage Patterns](./basic-examples.md#basic-usage-patterns)
-4. **Success**: Can execute common development tasks independently
-
-### Phase 2: Coordination (Week 3-6)
-1. **Agents**: Understand [Multi-Agent Patterns](./advanced-workflows.md#multi-agent-collaboration-patterns)
-2. **Workflows**: Practice [Complex Project Workflows](./advanced-workflows.md#complex-project-workflows)
-3. **Orchestration**: Master [Advanced Orchestration](./advanced-workflows.md#advanced-orchestration-patterns)
-4. **Success**: Can coordinate complex multi-step projects
-
-### Phase 3: Integration (Month 2+)
-1. **Frameworks**: Learn [Framework Integration](./integration-patterns.md#framework-integration-patterns)
-2. **Performance**: Master [Optimization Recipes](./integration-patterns.md#performance-optimization-recipes)
-3. **Troubleshooting**: Advanced [Debugging Workflows](./integration-patterns.md#advanced-troubleshooting-workflows)
-4. **Success**: Can integrate SuperClaude with any development stack
-
-### Phase 4: Expertise (Month 3+)
-1. **Architecture**: Design custom integration patterns
-2. **Contribution**: Contribute to SuperClaude framework
-3. **Leadership**: Mentor community and solve complex problems
-4. **Success**: Framework development and community leadership
-
-## Quick Reference Matrix
-
-| Task Type | Beginner | Intermediate | Expert |
-|-----------|----------|--------------|--------|
-| **Analysis** | [Basic Analysis](./basic-examples.md#quick-analysis-commands) | [Multi-Agent Analysis](./advanced-workflows.md#performance-optimization-team) | [Integration Analysis](./integration-patterns.md#distributed-system-debugging) |
-| **Implementation** | [Simple Features](./basic-examples.md#simple-feature-implementation) | [Complex Projects](./advanced-workflows.md#complex-project-workflows) | [Framework Integration](./integration-patterns.md#framework-integration-patterns) |
-| **Testing** | [Basic Testing](./basic-examples.md#copy-paste-quick-solutions) | [Comprehensive Testing](./advanced-workflows.md#advanced-workflows) | [Testing Integration](./integration-patterns.md#advanced-testing-integration) |
-| **Troubleshooting** | [Common Issues](./basic-examples.md#basic-troubleshooting-examples) | [System Debugging](./advanced-workflows.md#advanced-workflows) | [Distributed Debugging](./integration-patterns.md#advanced-troubleshooting-workflows) |
-| **Performance** | [Basic Optimization](./basic-examples.md#quick-quality-improvements) | [System Optimization](./advanced-workflows.md#performance-optimization-strategies) | [Expert Optimization](./integration-patterns.md#performance-optimization-recipes) |
-
-## Success Milestones
-
-### ✅ Basic Proficiency
-- [ ] Can install and configure SuperClaude
-- [ ] Comfortable with 5-10 core commands
-- [ ] Can complete simple workflows independently
-- [ ] Understands basic flag usage
-
-### ✅ Intermediate Mastery
-- [ ] Masters multi-agent coordination
-- [ ] Can orchestrate complex workflows
-- [ ] Understands session management
-- [ ] Comfortable with advanced flag combinations
-
-### ✅ Expert Integration
-- [ ] Can integrate any development framework
-- [ ] Masters performance optimization
-- [ ] Develops custom integration patterns
-- [ ] Contributes to framework development
-
-## Support Resources
-
-**Documentation**:
-- [Commands Reference](../User-Guide/commands.md) - Complete command documentation
-- [Agents Guide](../User-Guide/agents.md) - Multi-agent coordination
-- [MCP Servers](../User-Guide/mcp-servers.md) - Enhanced capabilities
-- [Advanced Workflows](./advanced-workflows.md) - Complex coordination patterns
-
-**Community**:
-- [GitHub Discussions](https://github.com/SuperClaude-Org/SuperClaude_Framework/discussions) - Community support
-- [GitHub Issues](https://github.com/SuperClaude-Org/SuperClaude_Framework/issues) - Bug reports and features
-- [Contributing Guide](../CONTRIBUTING.md) - Framework contribution
-
-**Advanced**:
-- [Technical Architecture](../Developer-Guide/technical-architecture.md) - Deep system understanding
-- [Troubleshooting Guide](./troubleshooting.md) - Common issues and solutions
-
----
-
-**Your Journey**: Start with [Basic Examples](./basic-examples.md), progress through [Advanced Workflows](./advanced-workflows.md), and master [Integration Patterns](./integration-patterns.md). SuperClaude grows with you from simple commands to sophisticated development orchestration.
-
-**Remember**: Every expert was once a beginner. Focus on practical application, experiment with different approaches, and leverage the community for support and learning.
\ No newline at end of file
diff --git a/docs/Reference/integration-patterns.md b/docs/Reference/integration-patterns.md
deleted file mode 100644
index 32fe89e..0000000
--- a/docs/Reference/integration-patterns.md
+++ /dev/null
@@ -1,319 +0,0 @@
-# SuperClaude Integration Patterns Collection
-
-**Status**: ✅ **Status: Current** - Context patterns for framework integration and tool coordination.
-
-**Context Integration Guide**: Patterns for using SuperClaude commands effectively with different frameworks and tools. Remember: SuperClaude provides context to Claude Code - all actual work is done by Claude.
-
-## Overview and Usage Guide
-
-**Purpose**: Effective patterns for using SuperClaude context with various development frameworks and tools.
-
-**What This Is**: Command combinations and flag patterns that work well for specific technologies
-**What This Isn't**: Performance optimization or parallel execution (no code runs)
-
-**Key Principle**: SuperClaude tells Claude Code WHAT to do and HOW to think about it. Claude Code does the actual work.
-
-## Framework Context Patterns
-
-### React Development Patterns
-
-```bash
-# React development with appropriate context
-/sc:implement "React 18 application with TypeScript" --c7
-# Context7 MCP can provide React documentation if available
-# Magic MCP can help with UI components if configured
-
-# What Actually Happens:
-# 1. Claude reads implement.md for implementation patterns
-# 2. --c7 flag suggests using Context7 MCP for documentation
-# 3. Claude generates React code based on these contexts
-
-# Component development pattern
-@agent-frontend-architect "design component architecture"
-/sc:implement "reusable component library"
-
-# Testing pattern for React
-/sc:test --focus react
-# Claude will suggest React Testing Library patterns
-```
-
-### Node.js Backend Patterns
-
-```bash
-# Node.js backend development patterns
-/sc:implement "Express.js API with TypeScript" --c7
-# Claude will create Express API following Node.js patterns
-
-# What This Means:
-# - Claude reads context about backend patterns
-# - Suggests appropriate middleware and structure
-# - NOT running or optimizing any code
-
-# Database integration pattern
-/sc:implement "database models with Prisma"
-@agent-backend-architect "review database schema"
-
-# API testing pattern
-/sc:test --focus api
-# Claude suggests API testing approaches
-```
-
-### Python Development Patterns
-
-```bash
-# Python web development
-/sc:implement "FastAPI application" --c7
-@agent-python-expert "review implementation"
-
-# What Happens:
-# - Claude uses Python-specific context
-# - Follows FastAPI patterns from context
-# - Generates code (doesn't run it)
-
-# Data science context
-/sc:implement "data analysis pipeline"
-@agent-python-expert "optimize pandas operations"
-# Claude provides optimization suggestions (not actual optimization)
-
-# Testing patterns
-/sc:test --focus python
-# Claude suggests pytest patterns
-```
-
-### Full-Stack Development Patterns
-
-```bash
-# Full-stack application pattern
-/sc:brainstorm "full-stack application architecture"
-@agent-system-architect "design system components"
-
-# Frontend implementation
-/sc:implement "React frontend with TypeScript"
-@agent-frontend-architect "review component structure"
-
-# Backend implementation
-/sc:implement "Node.js API with authentication"
-@agent-backend-architect "review API design"
-
-# Integration
-/sc:implement "connect frontend to backend API"
-```
-
-## Tool Coordination Patterns
-
-### Using MCP Servers Effectively
-
-```bash
-# Context7 for documentation
-/sc:explain "React hooks" --c7
-# If Context7 is configured, it may fetch React docs
-
-# Sequential for complex reasoning
-/sc:troubleshoot "complex bug" --seq
-# Sequential MCP helps with structured problem-solving
-
-# Magic for UI components
-/sc:implement "UI components" --magic
-# Magic MCP can help generate modern UI patterns
-
-# No MCP for simple tasks
-/sc:implement "utility function" --no-mcp
-# Uses only Claude's built-in knowledge
-```
-
-### Agent and Command Combinations
-
-```bash
-# Security-focused development
-@agent-security "review authentication requirements"
-/sc:implement "secure authentication system"
-/sc:analyze --focus security
-
-# Quality-focused workflow
-/sc:implement "new feature"
-@agent-quality-engineer "review code quality"
-/sc:test --focus quality
-
-# Architecture-focused approach
-@agent-system-architect "design microservices"
-/sc:design "service boundaries"
-/sc:implement "service communication"
-```
-
-## Common Integration Patterns
-
-### API Development Pattern
-
-```bash
-# Step 1: Design
-/sc:design "REST API structure"
-
-# Step 2: Implementation
-/sc:implement "API endpoints with validation"
-
-# Step 3: Documentation
-/sc:document --type api
-
-# Step 4: Testing
-/sc:test --focus api
-```
-
-### Database Integration Pattern
-
-```bash
-# Schema design
-@agent-backend-architect "design database schema"
-
-# Model implementation
-/sc:implement "database models"
-
-# Migration creation
-/sc:implement "database migrations"
-
-# Query optimization suggestions
-@agent-backend-architect "suggest query optimizations"
-# Note: Claude suggests optimizations, doesn't actually optimize
-```
-
-### Testing Strategy Pattern
-
-```bash
-# Test planning
-/sc:design "testing strategy"
-
-# Unit tests
-/sc:test --type unit
-
-# Integration tests
-/sc:test --type integration
-
-# E2E test suggestions
-/sc:test --type e2e
-# Claude provides test code, not execution
-```
-
-## Technology-Specific Patterns
-
-### React + TypeScript Pattern
-
-```bash
-# Project setup guidance
-/sc:implement "React TypeScript project structure"
-
-# Component development
-/sc:implement "TypeScript React components with props validation"
-
-# State management
-@agent-frontend-architect "recommend state management approach"
-/sc:implement "state management with Zustand/Redux"
-
-# Testing
-/sc:test --focus react --type unit
-```
-
-### Python FastAPI Pattern
-
-```bash
-# API structure
-/sc:implement "FastAPI project structure"
-
-# Endpoint development
-@agent-python-expert "implement async endpoints"
-
-# Database integration
-/sc:implement "SQLAlchemy models with Alembic"
-
-# Testing
-/sc:test --focus python --type integration
-```
-
-### Node.js Microservices Pattern
-
-```bash
-# Architecture design
-@agent-system-architect "design microservices architecture"
-
-# Service implementation
-/sc:implement "user service with Express"
-/sc:implement "auth service with JWT"
-
-# Inter-service communication
-/sc:implement "service communication patterns"
-
-# Testing approach
-/sc:test --focus microservices
-```
-
-## Troubleshooting Patterns
-
-### Debugging Workflow
-
-```bash
-# Problem analysis
-/sc:troubleshoot "describe the issue"
-
-# Root cause investigation
-@agent-root-cause-analyst "analyze symptoms"
-
-# Solution implementation
-/sc:implement "fix based on analysis"
-
-# Verification
-/sc:test --validate
-```
-
-### Code Review Pattern
-
-```bash
-# Code analysis
-/sc:analyze code/ --focus quality
-
-# Security review
-@agent-security "review for vulnerabilities"
-
-# Performance review
-@agent-performance-engineer "suggest improvements"
-# Note: Suggestions only, no actual performance measurement
-
-# Implementation of improvements
-/sc:improve code/ --fix
-```
-
-## Important Clarifications
-
-### What These Patterns DO
-
-- ✅ Provide structured approaches to development tasks
-- ✅ Combine commands and agents effectively
-- ✅ Suggest appropriate tools and frameworks
-- ✅ Guide Claude to generate better code
-
-### What These Patterns DON'T DO
-
-- ❌ Execute code or measure performance
-- ❌ Run tests or deploy applications
-- ❌ Optimize actual execution speed
-- ❌ Provide real monitoring or metrics
-- ❌ Coordinate parallel processes (everything is sequential text)
-
-## Best Practices
-
-### Effective Pattern Usage
-
-1. **Start with context**: Use `/sc:load` to establish project understanding
-2. **Layer expertise**: Combine general commands with specific agents
-3. **Focus appropriately**: Use `--focus` flags for targeted results
-4. **Manage scope**: Work on specific modules rather than entire codebases
-5. **Document decisions**: Use `/sc:save` to create summaries
-
-### Pattern Selection
-
-- **Simple tasks**: Use basic commands without MCP
-- **Complex tasks**: Add appropriate agents and MCP servers
-- **Security-critical**: Always include `@agent-security`
-- **UI development**: Consider `--magic` flag if configured
-- **Documentation needs**: Use `--c7` for framework docs
-
-## Summary
-
-These integration patterns show how to combine SuperClaude commands, agents, and flags effectively for different development scenarios. Remember that all patterns are about providing better context to Claude Code - the actual code generation, not execution, is what Claude does based on these contexts.
\ No newline at end of file
diff --git a/docs/Reference/mcp-server-guide.md b/docs/Reference/mcp-server-guide.md
deleted file mode 100644
index 4e3b0e6..0000000
--- a/docs/Reference/mcp-server-guide.md
+++ /dev/null
@@ -1,755 +0,0 @@
-# MCP Server Troubleshooting Guide
-
-**MCP Server Focus**: Model Context Protocol (MCP) servers provide enhanced capabilities like documentation lookup (Context7), UI generation (Magic), and advanced reasoning (Sequential). This guide covers installation, configuration, and operational troubleshooting for all MCP servers.
-
-**Server-Specific Solutions**: Each MCP server has unique requirements and common failure patterns. This guide provides targeted solutions for each server type and general MCP troubleshooting strategies.
-
-## MCP Server Overview
-
-### Available MCP Servers
-
-**Core MCP Servers:**
-- **Context7**: Official documentation lookup and framework patterns
-- **Sequential**: Multi-step reasoning and complex analysis
-- **Magic**: Modern UI component generation from 21st.dev patterns
-- **Playwright**: Browser automation and E2E testing
-- **Morphllm**: Pattern-based code editing with token optimization
-- **Serena**: Semantic code understanding and project memory
-
-**Server Requirements:**
-- Node.js 16.0.0 or higher
-- npm or yarn package manager
-- Stable network connection for some servers
-- Sufficient system memory (2GB+ recommended)
-
-## Installation and Configuration Issues
-
-### Node.js and npm Problems
-
-#### Issue: Node.js Version Incompatibility
-**Error Message**: `ERROR: MCP servers require Node.js 16+ but found Node.js 14.x`
-
-**Diagnosis**:
-```bash
-node --version
-npm --version
-```
-
-**Solution 1**: Update Node.js (Linux/Ubuntu)
-```bash
-curl -fsSL https://deb.nodesource.com/setup_lts.x | sudo -E bash -
-sudo apt-get install -y nodejs
-```
-
-**Solution 2**: Use Node Version Manager (nvm)
-```bash
-curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash
-source ~/.bashrc
-nvm install node
-nvm use node
-```
-
-**Solution 3**: Manual Node.js installation
-- Download from https://nodejs.org/
-- Follow platform-specific installation instructions
-
-**Verification**:
-```bash
-node --version # Should be 16.0.0+
-npm --version # Should be 8.0.0+
-```
-
-**Issue: npm Permission Problems**
-```bash
-# Error message
-ERROR: EACCES: permission denied, access '/usr/local/lib/node_modules'
-
-# Solution 1: Configure npm for user directory
-mkdir ~/.npm-global
-npm config set prefix '~/.npm-global'
-echo 'export PATH=~/.npm-global/bin:$PATH' >> ~/.profile
-source ~/.profile
-
-# Solution 2: Fix npm permissions
-sudo chown -R $(whoami) $(npm config get prefix)/{lib/node_modules,bin,share}
-
-# Solution 3: Use npx for package execution
-npx @context7/mcp-server --version
-
-# Verification
-npm list -g --depth=0
-npm config get prefix
-```
-
-### MCP Server Installation Failures
-
-**Issue: Context7 MCP Server Installation Failed**
-```bash
-# Error message
-ERROR: Failed to install @context7/mcp-server
-
-# Diagnosis
-npm list -g @context7/mcp-server
-node --version
-
-# Solution 1: Clean npm cache and reinstall
-npm cache clean --force
-npm install -g @context7/mcp-server
-
-# Solution 2: Use alternative registry
-npm install -g @context7/mcp-server --registry https://registry.npmjs.org/
-
-# Solution 3: Manual installation verification
-npm info @context7/mcp-server
-npm install -g @context7/mcp-server@latest
-
-# Verification
-npm list -g @context7/mcp-server
-node -e "console.log('Context7 installation test')"
-```
-
-**Issue: Sequential MCP Server Dependencies Missing**
-```bash
-# Error message
-ERROR: Sequential MCP server missing required dependencies
-
-# Diagnosis
-npm list -g @sequential/mcp-server
-npm list -g | grep -E "typescript|@types"
-
-# Solution 1: Install dependencies explicitly
-npm install -g typescript @types/node
-npm install -g @sequential/mcp-server
-
-# Solution 2: Force reinstall with dependencies
-npm uninstall -g @sequential/mcp-server
-npm install -g @sequential/mcp-server --save-dev
-
-# Solution 3: Check package integrity
-npm audit --global
-npm update -g
-
-# Verification
-npm list -g @sequential/mcp-server
-```
-
-**Issue: Magic UI Generator Installation Problems**
-```bash
-# Error message
-ERROR: @magic/ui-generator installation failed - build dependencies missing
-
-# Diagnosis
-npm list -g @magic/ui-generator
-which gcc make # Check build tools
-
-# Solution 1: Install build dependencies (Linux)
-sudo apt install build-essential python3-dev
-
-# Solution 2: Install build dependencies (macOS)
-xcode-select --install
-
-# Solution 3: Use pre-built binaries
-npm install -g @magic/ui-generator --ignore-scripts
-
-# Verification
-npm list -g @magic/ui-generator
-```
-
-## Connection and Communication Issues
-
-### MCP Server Connection Failures
-
-**Issue: Context7 Server Not Connecting**
-```bash
-# Error message
-ERROR: MCP server 'context7' failed to connect
-
-# Diagnosis
-# Check Node.js installation
-node --version # Should be 16.0.0 or higher
-npm list -g @context7/mcp-server
-
-# Check server configuration
-cat ~/.claude/CLAUDE.md | grep -i context7
-
-# Solution 1: Restart Claude Code session
-# MCP servers restart with Claude Code session restart
-
-# Solution 2: Reconfigure MCP servers
-python3 -m SuperClaude install --components mcp --force
-
-# Solution 3: Manual server testing
-node -e "console.log('Node.js working')"
-npm test @context7/mcp-server
-
-# Solution 4: Check network connectivity
-ping context7-server.example.com # If server requires network
-curl -I https://context7-api.example.com/health # Health check
-
-# Verification
-# Try Context7 functionality in Claude Code
-# Should respond to documentation requests
-```
-
-**Issue: MCP Server Communication Timeout**
-```bash
-# Error message
-ERROR: MCP server request timeout after 30 seconds
-
-# Diagnosis
-# Check network connectivity and server health
-ping 8.8.8.8 # Basic connectivity
-curl -I https://api.example.com/health # API health
-
-# Check system resources
-top
-free -h
-
-# Solution 1: Reduce operation complexity
-# Break complex tasks into smaller parts
-
-# Solution 2: Restart Claude Code session
-# MCP servers restart with Claude Code session restart
-
-# Solution 3: Disable problematic server temporarily
-# Use --no-mcp flag for operations
-
-# Solution 4: Increase timeout (if configurable)
-# Check MCP server configuration files
-
-# Verification
-# Test with simple operations first
-# Gradually increase complexity
-```
-
-**Issue: Multiple MCP Servers Conflicting**
-```bash
-# Error message
-ERROR: MCP server port conflicts detected
-
-# Diagnosis
-netstat -tlnp | grep :8000 # Check port usage
-ps aux | grep -E "context7|sequential|magic"
-
-# Solution 1: Sequential server restart
-# Restart Claude Code to reset all MCP servers
-
-# Solution 2: Configure different ports
-# Edit MCP server configuration files
-# Usually in ~/.claude/ or server-specific directories
-
-# Solution 3: Use selective server activation
-# Use specific server flags instead of --all-mcp
-
-# Verification
-netstat -tlnp | grep -E "8000|8001|8002" # Check port assignments
-```
-
-## Server-Specific Troubleshooting
-
-### Context7 Documentation Server
-
-**Issue: Context7 Not Finding Documentation**
-```bash
-# Symptoms: Context7 activated but returns no documentation
-
-# Diagnosis
-# Test Context7 connection
-node -e "const c7 = require('@context7/mcp-server'); console.log('Context7 loaded');"
-
-# Solution 1: Update Context7 server
-npm update -g @context7/mcp-server
-
-# Solution 2: Clear Context7 cache
-rm -rf ~/.context7/cache/ # If cache directory exists
-
-# Solution 3: Use explicit library keywords
-# Use specific framework names in requests
-
-# Solution 4: Verify internet connection
-curl -I https://docs.react.dev/ # Example API test
-
-# Verification
-# Try specific documentation requests
-# Should return relevant framework information
-```
-
-**Issue: Context7 Returning Outdated Information**
-```bash
-# Symptoms: Context7 returns old documentation versions
-
-# Solution 1: Update Context7 server
-npm uninstall -g @context7/mcp-server
-npm install -g @context7/mcp-server@latest
-
-# Solution 2: Clear documentation cache
-rm -rf ~/.context7/ # Clear cache if exists
-
-# Solution 3: Force documentation refresh
-# Restart Claude Code session completely
-
-# Verification
-# Check documentation dates in responses
-# Should return current framework versions
-```
-
-### Sequential Reasoning Server
-
-**Issue: Sequential Server Internal Errors**
-```bash
-# Error message
-ERROR: Sequential reasoning server encountered internal error
-
-# Diagnosis
-# Check Sequential server logs
-tail -f ~/.claude/logs/sequential-mcp.log # If logs exist
-
-# Check server installation
-npm list -g @sequential/mcp-server
-
-# Solution 1: Restart Claude Code session
-# This restarts all MCP servers including Sequential
-
-# Solution 2: Use alternative reasoning approach
-# Use native Claude reasoning without MCP servers
-
-# Solution 3: Reinstall Sequential MCP
-npm uninstall -g @sequential/mcp-server
-npm install -g @sequential/mcp-server@latest
-
-# Solution 4: Check memory availability
-free -h # Ensure sufficient memory for complex reasoning
-
-# Verification
-# Test with simple analysis tasks first
-# Should provide structured reasoning output
-```
-
-**Issue: Sequential Server Memory Overload**
-```bash
-# Symptoms: Sequential server crashes or becomes unresponsive
-
-# Diagnosis
-top | grep -E "sequential|node"
-free -h
-
-# Solution 1: Reduce analysis complexity
-# Break complex problems into smaller parts
-
-# Solution 2: Increase system memory or swap
-sudo swapon --show # Check swap status
-
-# Solution 3: Use scope limiting
-# Focus analysis on specific components
-
-# Verification
-ps aux | grep sequential # Check process status
-```
-
-### Magic UI Generator
-
-**Issue: Magic Not Generating UI Components**
-```bash
-# Symptoms: UI component requests not producing expected output
-
-# Diagnosis
-# Check Magic server installation
-npm list -g @magic/ui-generator
-cat ~/.claude/CLAUDE.md | grep -i magic
-
-# Solution 1: Verify Magic server installation
-npm list -g @magic/ui-generator
-npm install -g @magic/ui-generator@latest
-
-# Solution 2: Use explicit Magic activation
-# Include "component", "UI", or "interface" keywords
-
-# Solution 3: Check component request format
-# Use descriptive requests for better Magic activation
-
-# Solution 4: Test Magic server directly
-node -e "const magic = require('@magic/ui-generator'); console.log('Magic loaded');"
-
-# Verification
-# Should produce complete UI components with modern patterns
-```
-
-**Issue: Magic Components Not Framework-Compliant**
-```bash
-# Symptoms: Generated components don't match framework patterns
-
-# Solution 1: Use framework-specific keywords
-# Include "React", "Vue", "Angular" in requests
-
-# Solution 2: Combine with Context7
-# Use both Magic and Context7 for framework-compliant components
-
-# Solution 3: Update Magic server
-npm update -g @magic/ui-generator
-
-# Verification
-# Generated components should follow framework conventions
-```
-
-### Playwright Browser Automation
-
-**Issue: Playwright Browser Installation Failures**
-```bash
-# Error message
-ERROR: Playwright browser automation failed - browser not installed
-
-# Diagnosis
-npm list -g playwright
-npx playwright --version
-
-# Solution 1: Install Playwright browsers
-npx playwright install
-npx playwright install-deps
-
-# Solution 2: Install specific browsers
-npx playwright install chromium
-npx playwright install firefox
-npx playwright install webkit
-
-# Solution 3: Fix browser dependencies (Linux)
-sudo apt-get install libnss3 libatk-bridge2.0-0 libdrm2 libgtk-3-0
-
-# Verification
-npx playwright --version
-ls ~/.cache/ms-playwright/ # Check browser installations
-```
-
-**Issue: Playwright Browser Launch Failures**
-```bash
-# Error message
-ERROR: Browser launch failed - display not available
-
-# Diagnosis
-echo $DISPLAY # Check X11 display
-ps aux | grep Xvfb # Check virtual display
-
-# Solution 1: Use headless mode
-# Set headless: true in Playwright configuration
-
-# Solution 2: Install virtual display (Linux)
-sudo apt-get install xvfb
-export DISPLAY=:99
-Xvfb :99 -screen 0 1024x768x24 &
-
-# Solution 3: Use Docker for browser testing
-docker run -it --rm playwright:latest
-
-# Verification
-# Should successfully launch browsers in headless mode
-```
-
-### Morphllm Pattern Editor
-
-**Issue: Morphllm Pattern Application Failures**
-```bash
-# Symptoms: Pattern-based edits not applying correctly
-
-# Diagnosis
-npm list -g @morphllm/mcp-server
-
-# Solution 1: Update Morphllm server
-npm update -g @morphllm/mcp-server
-
-# Solution 2: Use more specific patterns
-# Provide explicit pattern descriptions
-
-# Solution 3: Check file permissions
-ls -la target-files/ # Ensure write permissions
-
-# Verification
-# Pattern edits should be applied consistently across files
-```
-
-### Serena Project Memory
-
-**Issue: Serena Session Persistence Failures**
-```bash
-# Symptoms: Project context not persisting between sessions
-
-# Diagnosis
-ls ~/.claude/sessions/ # Check session storage
-ls ~/.serena/ # Check Serena-specific storage
-
-# Solution 1: Verify session save operations
-# Ensure proper session saving before closing
-
-# Solution 2: Check storage permissions
-ls -la ~/.claude/sessions/
-chmod 755 ~/.claude/sessions/
-
-# Solution 3: Reinstall Serena server
-# Remove existing Serena registration
-claude mcp remove serena
-# Reinstall using uvx
-uvx --from git+https://github.com/oraios/serena serena --help
-# Re-register with Claude
-claude mcp add serena -- uvx --from git+https://github.com/oraios/serena serena start-mcp-server --context ide-assistant
-
-# Verification
-# Session context should persist across Claude Code restarts
-```
-
-## Performance and Optimization
-
-### MCP Server Performance Issues
-
-**Issue: Slow MCP Server Response Times**
-```bash
-# Symptoms: MCP server operations causing delays
-
-# Diagnosis
-# Check MCP server installation and health
-npm list -g | grep -E "context7|sequential|magic|playwright"
-top | grep node
-
-# Solution 1: Selective MCP server usage
-# Use only needed servers for specific tasks
-
-# Solution 2: Restart Claude Code session
-# This restarts all MCP servers fresh
-
-# Solution 3: Local fallback mode
-# Use --no-mcp flag for pure native operations
-
-# Solution 4: Update all MCP servers
-npm update -g
-
-# Verification
-time node -e "console.log('Node.js speed test')"
-# Should complete successfully
-```
-
-**Issue: MCP Server Memory Leaks**
-```bash
-# Symptoms: Increasing memory usage over time
-
-# Diagnosis
-top | grep node # Monitor Node.js processes
-ps aux --sort=-%mem | head -10
-
-# Solution 1: Regular Claude Code session restarts
-# Restart sessions periodically during heavy usage
-
-# Solution 2: Monitor specific servers
-htop # Monitor individual MCP server processes
-
-# Solution 3: Use memory-efficient patterns
-# Avoid keeping large data sets in MCP server memory
-
-# Verification
-free -h # Monitor memory usage trends
-```
-
-### Resource Management
-
-**Issue: Multiple MCP Servers Competing for Resources**
-```bash
-# Symptoms: System slowdown when multiple servers active
-
-# Diagnosis
-top | grep -E "node|mcp"
-iostat 1 3 # Check I/O usage
-
-# Solution 1: Use targeted server activation
-# Activate only needed servers per task
-
-# Solution 2: Increase system resources
-# Add more RAM or CPU cores if possible
-
-# Solution 3: Queue MCP operations
-# Avoid simultaneous heavy operations
-
-# Solution 4: Use MCP server priorities
-# Configure resource allocation in MCP settings
-
-# Verification
-top # Monitor resource usage during operations
-```
-
-## Advanced MCP Configuration
-
-### Custom MCP Server Configuration
-
-**Issue: Default MCP Configuration Not Optimal**
-```bash
-# Symptoms: MCP servers not performing optimally for specific use cases
-
-# Solution 1: Locate configuration files
-find ~/.claude/ -name "*mcp*" -type f
-find ~/.config/ -name "*mcp*" -type f
-
-# Solution 2: Customize server settings
-# Edit server-specific configuration files
-# Common locations: ~/.claude/mcp-config.json
-
-# Solution 3: Environment variable configuration
-export MCP_CONTEXT7_TIMEOUT=60
-export MCP_SEQUENTIAL_MEMORY_LIMIT=2048
-
-# Verification
-# Test with custom configuration
-# Should show improved performance for specific use cases
-```
-
-**Issue: MCP Server Load Balancing**
-```bash
-# Symptoms: Uneven load distribution across MCP servers
-
-# Solution 1: Configure server priorities
-# Edit MCP configuration to balance loads
-
-# Solution 2: Use round-robin server selection
-# Implement rotation logic in server calls
-
-# Solution 3: Monitor server performance
-# Track response times and adjust accordingly
-
-# Verification
-# Observe balanced resource usage across servers
-```
-
-## Debugging and Diagnostics
-
-### MCP Server Health Monitoring
-
-**Comprehensive MCP Health Check:**
-```bash
-# MCP Server System Diagnostics
-echo "=== MCP Server Health Check ==="
-
-# Node.js environment
-echo "Node.js version: $(node --version)"
-echo "npm version: $(npm --version)"
-
-# Server installations
-echo "=== Installed MCP Servers ==="
-npm list -g | grep -E "context7|sequential|magic|playwright|morphllm|serena"
-
-# Process monitoring
-echo "=== Running MCP Processes ==="
-ps aux | grep -E "node.*mcp|mcp.*server" | head -5
-
-# Resource usage
-echo "=== Resource Usage ==="
-echo "Memory: $(free -h | grep Mem | awk '{print $3 "/" $2}')"
-echo "CPU Load: $(uptime | awk -F'load average:' '{print $2}')"
-
-# Network connectivity (if required)
-echo "=== Network Status ==="
-ping -c 1 8.8.8.8 > /dev/null && echo "✅ Network OK" || echo "❌ Network Issue"
-```
-
-**MCP Server Functionality Test:**
-```bash
-# Test each MCP server individually
-echo "=== MCP Server Functionality Test ==="
-
-# Context7 test
-if npm list -g @context7/mcp-server > /dev/null 2>&1; then
- echo "✅ Context7 installed"
-else
- echo "❌ Context7 missing"
-fi
-
-# Sequential test
-if npm list -g @sequential/mcp-server > /dev/null 2>&1; then
- echo "✅ Sequential installed"
-else
- echo "❌ Sequential missing"
-fi
-
-# Magic test
-if npm list -g @magic/ui-generator > /dev/null 2>&1; then
- echo "✅ Magic installed"
-else
- echo "❌ Magic missing"
-fi
-
-# Playwright test
-if npx playwright --version > /dev/null 2>&1; then
- echo "✅ Playwright installed"
-else
- echo "❌ Playwright missing"
-fi
-```
-
-### MCP Server Log Analysis
-
-**Log Collection and Analysis:**
-```bash
-# Collect MCP server logs
-echo "=== MCP Server Logs ==="
-
-# Check common log locations
-find ~/.claude/ -name "*.log" -type f 2>/dev/null
-find /tmp/ -name "*mcp*.log" -type f 2>/dev/null
-find /var/log/ -name "*mcp*.log" -type f 2>/dev/null
-
-# Check npm logs
-npm config get logs-max
-ls ~/.npm/_logs/ 2>/dev/null | tail -5
-
-# System logs for Node.js processes
-journalctl -u node* --since "1 hour ago" 2>/dev/null | tail -10
-```
-
-## Emergency Recovery
-
-### Complete MCP Reset
-
-**Full MCP Server Reset Procedure:**
-```bash
-# Emergency MCP Reset
-echo "=== Emergency MCP Server Reset ==="
-
-# Step 1: Stop all Claude Code sessions
-echo "Stop all Claude Code sessions and wait 30 seconds"
-
-# Step 2: Backup current state
-cp -r ~/.claude ~/.claude.mcp.backup.$(date +%Y%m%d)
-
-# Step 3: Remove all MCP servers
-npm list -g | grep -E "context7|sequential|magic|playwright|morphllm|serena" | awk '{print $2}' | xargs npm uninstall -g
-
-# Step 4: Clear npm cache
-npm cache clean --force
-
-# Step 5: Reinstall MCP servers
-python3 -m SuperClaude install --components mcp --force
-
-# Step 6: Verification
-npm list -g | grep -E "context7|sequential|magic|playwright|morphllm|serena"
-
-# Step 7: Test functionality
-echo "Test MCP servers in Claude Code after restart"
-```
-
-## Related Resources
-
-### MCP-Specific Documentation
-- **Core SuperClaude Guide**: [../User-Guide/mcp-servers.md](../User-Guide/mcp-servers.md) - MCP server overview and usage
-- **Common Issues**: [common-issues.md](./common-issues.md) - General troubleshooting procedures
-- **Diagnostic Reference**: [diagnostic-reference.md](./diagnostic-reference.md) - Advanced diagnostic procedures
-
-### External Resources
-- **Node.js Official**: [https://nodejs.org/](https://nodejs.org/) - Node.js installation and documentation
-- **npm Documentation**: [https://docs.npmjs.com/](https://docs.npmjs.com/) - Package manager documentation
-- **Playwright Guide**: [https://playwright.dev/](https://playwright.dev/) - Browser automation documentation
-
-### Support Channels
-- **GitHub Issues**: [MCP-specific problems](https://github.com/SuperClaude-Org/SuperClaude_Framework/issues)
-- **GitHub Discussions**: [MCP server community support](https://github.com/SuperClaude-Org/SuperClaude_Framework/discussions)
-
----
-
-**MCP Server Priority**: When troubleshooting, address servers in order of dependency: Node.js → npm → individual servers → Claude Code integration. Most MCP issues resolve with proper Node.js setup and server reinstallation.
-
-**Verification Pattern**: After MCP solutions, always verify with:
-- ✅ `node --version` - Should be 16.0.0+
-- ✅ `npm list -g | grep mcp` - Should show installed servers
-- ✅ Test server functionality in Claude Code - Should respond without errors
\ No newline at end of file
diff --git a/docs/Reference/troubleshooting.md b/docs/Reference/troubleshooting.md
deleted file mode 100644
index 267919a..0000000
--- a/docs/Reference/troubleshooting.md
+++ /dev/null
@@ -1,124 +0,0 @@
-# SuperClaude Troubleshooting Guide 🔧
-
-Quick fixes to advanced diagnostics for SuperClaude Framework issues.
-
-## Quick Fixes (90% of problems)
-
-**Installation Verification:**
-```bash
-python3 -m SuperClaude --version # Should show 4.1.5
-SuperClaude install --list-components
-```
-
-**Command Issues:**
-```bash
-# Test in Claude Code:
-/sc:brainstorm "test project" # Should ask discovery questions
-
-# If no response: Restart Claude Code session
-```
-
-**Resolution Checklist:**
-- [ ] Version commands work and show 4.1.5
-- [ ] `/sc:` commands respond in Claude Code
-- [ ] MCP servers listed: `SuperClaude install --list-components | grep mcp`
-
-## Common Issues
-
-### Installation Problems
-
-**Package Installation Fails:**
-```bash
-# For pipx users
-pipx uninstall SuperClaude
-pipx install SuperClaude
-
-# For pip users
-pip uninstall SuperClaude
-pip install --upgrade pip
-pip install SuperClaude
-```
-
-**Permission Denied / PEP 668 Error:**
-```bash
-# Option 1: Use pipx (recommended)
-pipx install SuperClaude
-
-# Option 2: Use pip with --user flag
-pip install --user SuperClaude
-
-# Option 3: Fix permissions
-sudo chown -R $USER ~/.claude
-
-# Option 4: Force installation (use with caution)
-pip install --break-system-packages SuperClaude
-```
-
-**Component Missing:**
-```bash
-python3 -m SuperClaude install --components core commands agents modes --force
-```
-
-### Command Issues
-
-**Commands Not Recognized:**
-1. Restart Claude Code completely
-2. Verify: `python3 -m SuperClaude --version`
-3. Test: `/sc:brainstorm "test"`
-
-**Agents Not Activating:**
-- Use specific keywords: `/sc:implement "secure JWT authentication"`
-- Manual activation: `@agent-security "review auth code"`
-
-**Slow Performance:**
-```bash
-/sc:analyze . --no-mcp # Test without MCP servers
-/sc:analyze src/ --scope file # Limit scope
-```
-
-### MCP Server Issues
-
-**Server Connection Fails:**
-```bash
-ls ~/.claude/.claude.json # Check config exists
-node --version # Verify Node.js 16+
-SuperClaude install --components mcp --force
-```
-
-**API Key Required (Magic/Morphllm):**
-```bash
-export TWENTYFIRST_API_KEY="your_key"
-export MORPH_API_KEY="your_key"
-# Or use: /sc:command --no-mcp
-```
-
-## Advanced Diagnostics
-
-**System Analysis:**
-```bash
-SuperClaude install --diagnose
-cat ~/.claude/logs/superclaude.log | tail -50
-```
-
-**Component Analysis:**
-```bash
-ls -la ~/.claude/ # Check installed files
-grep -r "@" ~/.claude/CLAUDE.md # Verify imports
-```
-
-**Reset Installation:**
-```bash
-SuperClaude backup --create # Backup first
-SuperClaude uninstall
-SuperClaude install --fresh
-```
-
-## Get Help
-
-**Documentation:**
-- [Installation Guide](../Getting-Started/installation.md) - Setup issues
-- [Commands Guide](../User-Guide/commands.md) - Usage issues
-
-**Community:**
-- [GitHub Issues](https://github.com/SuperClaude-Org/SuperClaude_Framework/issues)
-- Include: OS, Python version, error message, steps to reproduce
\ No newline at end of file
diff --git a/docs/User-Guide-jp/agents.md b/docs/User-Guide-jp/agents.md
deleted file mode 100644
index 7b75e26..0000000
--- a/docs/User-Guide-jp/agents.md
+++ /dev/null
@@ -1,1029 +0,0 @@
-# SuperClaude エージェントガイド 🤖
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#superclaude-agents-guide-)
-
-SuperClaude は、Claude Code が専門知識を得るために呼び出すことができる 14 のドメイン スペシャリスト エージェントを提供します。
-
-## 🧪 エージェントのアクティベーションのテスト
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#-testing-agent-activation)
-
-このガイドを使用する前に、エージェントの選択が機能することを確認してください。
-
-```shell
-# Test manual agent invocation
-@agent-python-expert "explain decorators"
-# Example behavior: Python expert responds with detailed explanation
-
-# Test security agent auto-activation
-/sc:implement "JWT authentication"
-# Example behavior: Security engineer should activate automatically
-
-# Test frontend agent auto-activation
-/sc:implement "responsive navigation component"
-# Example behavior: Frontend architect + Magic MCP should activate
-
-# Test systematic analysis
-/sc:troubleshoot "slow API performance"
-# Example behavior: Root-cause analyst + performance engineer activation
-
-# Test combining manual and auto
-/sc:analyze src/
-@agent-refactoring-expert "suggest improvements"
-# Example behavior: Analysis followed by refactoring suggestions
-```
-
-**テストが失敗した場合**: エージェントファイルが存在する`~/.claude/agents/`か、Claude Codeセッションを再起動してください。
-
-## コアコンセプト
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#core-concepts)
-
-### SuperClaude エージェントとは何ですか?
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#what-are-superclaude-agents)
-
-**エージェントは**、Claude Codeの行動を変更するコンテキスト指示として実装された、専門分野のAIドメインエキスパートです。各エージェントは、ドメイン固有の専門知識、行動パターン、問題解決アプローチを含む、ディレクトリ`.md`内に綿密に作成されたファイルです`superclaude/Agents/`。
-
-**重要**: エージェントは別個の AI モデルやソフトウェアではなく、Claude Code が読み取って特殊な動作を採用するコンテキスト構成です。
-
-### エージェントの2つの使用方法
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#two-ways-to-use-agents)
-
-#### 1. @agent- プレフィックスを使用した手動呼び出し
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#1-manual-invocation-with-agent--prefix)
-
-```shell
-# Directly invoke a specific agent
-@agent-security "review authentication implementation"
-@agent-frontend "design responsive navigation"
-@agent-architect "plan microservices migration"
-```
-
-#### 2. 自動アクティベーション(行動ルーティング)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#2-auto-activation-behavioral-routing)
-
-「自動アクティベーション」とは、Claude Codeがリクエスト内のキーワードとパターンに基づいて適切なコンテキストで動作指示を読み取り、エンゲージすることを意味します。SuperClaudeは、Claudeが最適なスペシャリストにルーティングするための動作ガイドラインを提供します。
-
-> **📝 エージェントの「自動アクティベーション」の仕組み**:エージェントのアクティベーションは自動システムロジックではなく、コンテキストファイル内の動作指示です。ドキュメントでエージェントが「自動アクティベート」と記載されている場合、それはClaude Codeが指示を読み取り、リクエスト内のキーワードとパターンに基づいて特定のドメインの専門知識を活用することを意味します。これにより、基盤となるメカニズムを透明化しながら、インテリジェントなルーティング体験を実現します。
-
-```shell
-# These commands auto-activate relevant agents
-/sc:implement "JWT authentication" # → security-engineer auto-activates
-/sc:design "React dashboard" # → frontend-architect auto-activates
-/sc:troubleshoot "memory leak" # → performance-engineer auto-activates
-```
-
-**MCP サーバーは**、Context7 (ドキュメント作成)、Sequential (分析)、Magic (UI)、Playwright (テスト)、Morphllm (コード変換) などの専用ツールを通じて拡張機能を提供します。
-
-**ドメイン スペシャリストは、**狭い専門分野に焦点を絞り、ジェネラリストのアプローチよりも深く正確なソリューションを提供します。
-
-### エージェント選択ルール
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#agent-selection-rules)
-
-**優先順位の階層:**
-
-1. **手動オーバーライド**- @agent-[name] は自動アクティベーションよりも優先されます
-2. **キーワード**- 直接的なドメイン用語は主要なエージェントをトリガーします
-3. **ファイルタイプ**- 拡張子は言語/フレームワークの専門家を活性化します
-4. **複雑性**- 複数ステップのタスクには調整エージェントが関与する
-5. **コンテキスト**- 関連概念は補完的なエージェントをトリガーします
-
-**紛争解決:**
-
-- 手動呼び出し → 指定したエージェントが優先されます
-- 複数のマッチング → マルチエージェントコーディネーション
-- 不明瞭なコンテキスト → 要件アナリストの活性化
-- 複雑性が高い → システムアーキテクトの監視
-- 品質に関する懸念 → 自動QAエージェントの組み込み
-
-**選択決定ツリー:**
-
-```
-Task Analysis →
-├─ Manual @agent-? → Use specified agent
-├─ Single Domain? → Activate primary agent
-├─ Multi-Domain? → Coordinate specialist agents
-├─ Complex System? → Add system-architect oversight
-├─ Quality Critical? → Include security + performance + quality agents
-└─ Learning Focus? → Add learning-guide + technical-writer
-```
-
-## クイックスタートの例
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#quick-start-examples)
-
-### 手動エージェント呼び出し
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#manual-agent-invocation)
-
-```shell
-# Explicitly call specific agents with @agent- prefix
-@agent-python-expert "optimize this data processing pipeline"
-@agent-quality-engineer "create comprehensive test suite"
-@agent-technical-writer "document this API with examples"
-@agent-socratic-mentor "explain this design pattern"
-```
-
-### 自動エージェント調整
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#automatic-agent-coordination)
-
-```shell
-# Commands that trigger auto-activation
-/sc:implement "JWT authentication with rate limiting"
-# → Triggers: security-engineer + backend-architect + quality-engineer
-
-/sc:design "accessible React dashboard with documentation"
-# → Triggers: frontend-architect + learning-guide + technical-writer
-
-/sc:troubleshoot "slow deployment pipeline with intermittent failures"
-# → Triggers: devops-architect + performance-engineer + root-cause-analyst
-
-/sc:audit "payment processing security vulnerabilities"
-# → Triggers: security-engineer + quality-engineer + refactoring-expert
-```
-
-### 手動と自動のアプローチを組み合わせる
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#combining-manual-and-auto-approaches)
-
-```shell
-# Start with command (auto-activation)
-/sc:implement "user profile system"
-
-# Then explicitly add specialist review
-@agent-security "review the profile system for OWASP compliance"
-@agent-performance-engineer "optimize database queries"
-```
-
----
-
-## SuperClaude エージェントチーム 👥
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#the-superclaude-agent-team-)
-
-### アーキテクチャとシステム設計エージェント 🏗️
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#architecture--system-design-agents-%EF%B8%8F)
-
-### システムアーキテクト 🏢
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#system-architect-)
-
-**専門分野**:スケーラビリティとサービスアーキテクチャに重点を置いた大規模分散システム設計
-
-**自動アクティベーション**:
-
-- キーワード: 「アーキテクチャ」、「マイクロサービス」、「スケーラビリティ」、「システム設計」、「分散」
-- コンテキスト: マルチサービスシステム、アーキテクチャ上の決定、テクノロジーの選択
-- 複雑さ: 5 つ以上のコンポーネントまたはドメイン間統合要件
-
-**機能**:
-
-- サービス境界の定義とマイクロサービスの分解
-- テクノロジースタックの選択と統合戦略
-- スケーラビリティ計画とパフォーマンスアーキテクチャ
-- イベント駆動型アーキテクチャとメッセージングパターン
-- データフロー設計とシステム統合
-
-**例**:
-
-1. **Eコマースプラットフォーム**:イベントソーシングを使用して、ユーザー、製品、支払い、通知サービスのマイクロサービスを設計します。
-2. **リアルタイム分析**:ストリーム処理と時系列ストレージによる高スループットデータ取り込みのためのアーキテクチャ
-3. **マルチテナント SaaS** : テナント分離、共有インフラストラクチャ、水平スケーリング戦略を備えたシステム設計
-
-### 成功基準
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#success-criteria)
-
-- [ ] 応答に表れたシステムレベルの思考
-- [ ] サービスの境界と統合パターンについて言及する
-- [ ] スケーラビリティと信頼性の考慮を含む
-- [ ] テクノロジースタックの推奨事項を提供する
-
-**検証:** `/sc:design "microservices platform"`システム アーキテクトをアクティブ化する必要があります。
-**テスト:**出力には、サービスの分解と統合パターンが含まれている必要があります。
-**チェック:**インフラストラクチャに関する懸念事項については、DevOps アーキテクトと調整する必要があります。
-
-**最適な組み合わせ**: devops-architect (インフラストラクチャ)、performance-engineer (最適化)、security-engineer (コンプライアンス)
-
----
-
-### バックエンドアーキテクト ⚙️
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#backend-architect-%EF%B8%8F)
-
-**専門分野**: APIの信頼性とデータの整合性を重視した堅牢なサーバーサイドシステム設計
-
-**自動アクティベーション**:
-
-- キーワード: 「API」、「バックエンド」、「サーバー」、「データベース」、「REST」、「GraphQL」、「エンドポイント」
-- ファイルタイプ: API仕様、サーバー構成、データベーススキーマ
-- コンテキスト: サーバーサイドロジック、データの永続性、API開発
-
-**機能**:
-
-- RESTful および GraphQL API のアーキテクチャと設計パターン
-- データベーススキーマ設計とクエリ最適化戦略
-- 認証、承認、セキュリティの実装
-- エラー処理、ログ記録、監視の統合
-- キャッシュ戦略とパフォーマンスの最適化
-
-**例**:
-
-1. **ユーザー管理 API** : ロールベースのアクセス制御とレート制限を備えた JWT 認証
-2. **支払い処理**: べき等性と監査証跡を備えた PCI 準拠のトランザクション処理
-3. **コンテンツ管理**: キャッシュ、ページネーション、リアルタイム通知を備えた RESTful API
-
-**最適な組み合わせ**: security-engineer (認証/セキュリティ)、performance-engineer (最適化)、quality-engineer (テスト)
-
----
-
-### フロントエンドアーキテクト 🎨
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#frontend-architect-)
-
-**専門分野**: アクセシビリティとユーザーエクスペリエンスを重視した最新の Web アプリケーション アーキテクチャ
-
-**自動アクティベーション**:
-
-- キーワード: 「UI」、「フロントエンド」、「React」、「Vue」、「Angular」、「コンポーネント」、「アクセシビリティ」、「レスポンシブ」
-- ファイルタイプ: .jsx、.vue、.ts (フロントエンド)、.css、.scss
-- コンテキスト: ユーザーインターフェース開発、コンポーネント設計、クライアント側アーキテクチャ
-
-**機能**:
-
-- コンポーネントアーキテクチャと設計システムの実装
-- 状態管理パターン (Redux、Zustand、Pinia)
-- アクセシビリティ準拠(WCAG 2.1)とインクルーシブデザイン
-- パフォーマンスの最適化とバンドル分析
-- プログレッシブウェブアプリとモバイルファースト開発
-
-**例**:
-
-1. **ダッシュボードインターフェース**: リアルタイム更新とレスポンシブなグリッドレイアウトによるアクセスしやすいデータ視覚化
-2. **フォーム システム**: 検証、エラー処理、アクセシビリティ機能を備えた複雑なマルチステップ フォーム
-3. **デザインシステム**: 一貫したスタイルとインタラクションパターンを備えた再利用可能なコンポーネントライブラリ
-
-**最適な組み合わせ**: 学習ガイド (ユーザー ガイダンス)、パフォーマンス エンジニア (最適化)、品質エンジニア (テスト)
-
----
-
-### DevOps アーキテクト 🚀
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#devops-architect-)
-
-**専門分野**: 信頼性の高いソフトウェア配信のためのインフラストラクチャ自動化と展開パイプライン設計
-
-**自動アクティベーション**:
-
-- キーワード: 「デプロイ」、「CI/CD」、「Docker」、「Kubernetes」、「インフラストラクチャ」、「監視」、「パイプライン」
-- ファイルタイプ: Dockerfile、docker-compose.yml、k8s マニフェスト、CI 構成
-- コンテキスト: 導入プロセス、インフラストラクチャ管理、自動化
-
-**機能**:
-
-- 自動テストとデプロイメントを備えた CI/CD パイプライン設計
-- コンテナオーケストレーションとKubernetesクラスタ管理
-- Terraform とクラウド プラットフォームを使用した Infrastructure as Code
-- 監視、ログ記録、および可観測性スタックの実装
-- セキュリティスキャンとコンプライアンスの自動化
-
-**例**:
-
-1. **マイクロサービスのデプロイメント**: サービスメッシュ、自動スケーリング、ブルーグリーンリリースを備えた Kubernetes のデプロイメント
-2. **マルチ環境パイプライン**: 自動テスト、セキュリティスキャン、段階的なデプロイメントを備えた GitOps ワークフロー
-3. **モニタリングスタック**: メトリック、ログ、トレース、アラートシステムによる包括的な監視
-
-**最適な職種**: システム アーキテクト (インフラストラクチャ計画)、セキュリティ エンジニア (コンプライアンス)、パフォーマンス エンジニア (監視)
-
-### 品質・分析エージェント 🔍
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#quality--analysis-agents-)
-
-### セキュリティエンジニア 🔒
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#security-engineer-)
-
-**専門分野**: 脅威モデリングと脆弱性防止に重点を置いたアプリケーション セキュリティ アーキテクチャ
-
-**自動アクティベーション**:
-
-- キーワード: 「セキュリティ」、「認証」、「脆弱性」、「暗号化」、「コンプライアンス」、「OWASP」
-- コンテキスト: セキュリティレビュー、認証フロー、データ保護要件
-- リスク指標: 支払い処理、ユーザーデータ、API アクセス、規制遵守の必要性
-
-**機能**:
-
-- 脅威モデルと攻撃対象領域分析
-- 安全な認証と認可の設計 (OAuth、JWT、SAML)
-- データ暗号化戦略と鍵管理
-- 脆弱性評価と侵入テストのガイダンス
-- セキュリティコンプライアンス(GDPR、HIPAA、PCI-DSS)の実装
-
-**例**:
-
-1. **OAuth 実装**: トークンの更新とロールベースのアクセスによる安全なマルチテナント認証
-2. **API セキュリティ**: レート制限、入力検証、SQL インジェクション防止、セキュリティ ヘッダー
-3. **データ保護**: 保存時/転送時の暗号化、キーローテーション、プライバシーバイデザインアーキテクチャ
-
-**最適な人材**: バックエンド アーキテクト (API セキュリティ)、品質エンジニア (セキュリティ テスト)、根本原因アナリスト (インシデント対応)
-
----
-
-### パフォーマンスエンジニア ⚡
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#performance-engineer-)
-
-**専門分野**:スケーラビリティとリソース効率を重視したシステムパフォーマンスの最適化
-
-**自動アクティベーション**:
-
-- キーワード: 「パフォーマンス」、「遅い」、「最適化」、「ボトルネック」、「レイテンシ」、「メモリ」、「CPU」
-- コンテキスト: パフォーマンスの問題、スケーラビリティの懸念、リソースの制約
-- メトリクス: 応答時間 >500 ミリ秒、メモリ使用量が多い、スループットが低い
-
-**機能**:
-
-- パフォーマンスプロファイリングとボトルネックの特定
-- データベースクエリの最適化とインデックス戦略
-- キャッシュ実装(Redis、CDN、アプリケーションレベル)
-- 負荷テストと容量計画
-- メモリ管理とリソースの最適化
-
-**例**:
-
-1. **API最適化**: キャッシュとクエリの最適化により、応答時間を2秒から200ミリ秒に短縮
-2. **データベースのスケーリング**: リードレプリカ、接続プール、クエリ結果のキャッシュを実装する
-3. **フロントエンドのパフォーマンス**: バンドルの最適化、遅延読み込み、および CDN 実装により、読み込み時間が 3 秒未満に短縮されます。
-
-**最適な組み合わせ**: システム アーキテクト (スケーラビリティ)、DevOps アーキテクト (インフラストラクチャ)、ルート原因アナリスト (デバッグ)
-
----
-
-### 根本原因分析者 🔍
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#root-cause-analyst-)
-
-**専門分野**:証拠に基づく分析と仮説検定を用いた体系的な問題調査
-
-**自動アクティベーション**:
-
-- キーワード: 「バグ」、「問題」、「問題」、「デバッグ」、「調査」、「トラブルシューティング」、「エラー」
-- コンテキスト: システム障害、予期しない動作、複雑な複数コンポーネントの問題
-- 複雑性: 体系的な調査を必要とするシステム間問題
-
-**機能**:
-
-- 体系的なデバッグ方法論と根本原因分析
-- システム間のエラー相関と依存関係のマッピング
-- 障害調査のためのログ分析とパターン認識
-- 複雑な問題に対する仮説形成と検証
-- インシデント対応と事後分析手順
-
-**例**:
-
-1. **データベース接続障害**: 接続プール、ネットワーク タイムアウト、リソース制限にわたる断続的な障害をトレースします。
-2. **支払い処理エラー**: APIログ、データベースの状態、外部サービスの応答を通じてトランザクションの失敗を調査します。
-3. **パフォーマンスの低下**: メトリクスの相関関係、リソースの使用状況、コードの変更を通じて、段階的な速度低下を分析します。
-
-**最適な担当者**: パフォーマンス エンジニア (パフォーマンスの問題)、セキュリティ エンジニア (セキュリティ インシデント)、品質エンジニア (テストの失敗)
-
----
-
-### 品質エンジニア ✅
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#quality-engineer-)
-
-**専門分野**:自動化とカバレッジに重点を置いた包括的なテスト戦略と品質保証
-
-**自動アクティベーション**:
-
-- キーワード: 「テスト」、「テスト」、「品質」、「QA」、「検証」、「カバレッジ」、「自動化」
-- コンテキスト: テスト計画、品質ゲート、検証要件
-- 品質に関する懸念: コードカバレッジ <80%、テスト自動化の欠如、品質の問題
-
-**機能**:
-
-- テスト戦略設計(ユニット、統合、E2E、パフォーマンステスト)
-- テスト自動化フレームワークの実装とCI/CD統合
-- 品質指標の定義と監視(カバレッジ、欠陥率)
-- エッジケースの特定と境界テストのシナリオ
-- アクセシビリティテストとコンプライアンス検証
-
-**例**:
-
-1. **Eコマーステスト**: ユーザーフロー、支払い処理、在庫管理を網羅した包括的なテストスイート
-2. **API テスト**: REST/GraphQL API の自動契約テスト、負荷テスト、セキュリティ テスト
-3. **アクセシビリティ検証**:自動および手動のアクセシビリティ監査による WCAG 2.1 準拠テスト
-
-**最適な職種**: セキュリティ エンジニア (セキュリティ テスト)、パフォーマンス エンジニア (負荷テスト)、フロントエンド アーキテクト (UI テスト)
-
----
-
-### リファクタリングの専門家 🔧
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#refactoring-expert-)
-
-**専門分野**:体系的なリファクタリングと技術的負債管理によるコード品質の改善
-
-**自動アクティベーション**:
-
-- キーワード: 「リファクタリング」、「クリーンコード」、「技術的負債」、「SOLID」、「保守性」、「コード臭」
-- コンテキスト: レガシーコードの改善、アーキテクチャの更新、コード品質の問題
-- 品質指標: 複雑性が高い、コードの重複がある、テスト範囲が狭い
-
-**機能**:
-
-- SOLID原則の適用と設計パターンの実装
-- コードの臭いの特定と体系的な排除
-- レガシーコードの近代化戦略と移行計画
-- 技術的負債の評価と優先順位付けのフレームワーク
-- コード構造の改善とアーキテクチャのリファクタリング
-
-**例**:
-
-1. **レガシーモダナイゼーション**: テスト容易性を向上させたモノリシックアプリケーションをモジュール型アーキテクチャに変換する
-2. **デザインパターン**: 支払い処理に戦略パターンを実装して結合を減らし、拡張性を向上させる
-3. **コードのクリーンアップ**: 重複したコードを削除し、命名規則を改善し、再利用可能なコンポーネントを抽出します。
-
-**最適な組み合わせ**: system-architect (アーキテクチャの改善)、quality-engineer (テスト戦略)、python-expert (言語固有のパターン)
-
-### 専門開発エージェント 🎯
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#specialized-development-agents-)
-
-### Python エキスパート 🐍
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#python-expert-)
-
-**専門分野**: 最新のフレームワークとパフォーマンスを重視した、本番環境対応の Python 開発
-
-**自動アクティベーション**:
-
-- キーワード: 「Python」、「Django」、「FastAPI」、「Flask」、「asyncio」、「pandas」、「pytest」
-- ファイルタイプ: .py、requirements.txt、pyproject.toml、Pipfile
-- コンテキスト: Python 開発タスク、API 開発、データ処理、テスト
-
-**機能**:
-
-- 最新のPythonアーキテクチャパターンとフレームワークの選択
-- asyncio と並行未来を用いた非同期プログラミング
-- プロファイリングとアルゴリズムの改善によるパフォーマンスの最適化
-- pytest、フィクスチャ、テスト自動化によるテスト戦略
-- pip、poetry、Docker を使用したパッケージ管理とデプロイメント
-
-**例**:
-
-1. **FastAPI マイクロサービス**: Pydantic 検証、依存性注入、OpenAPI ドキュメントを備えた高性能非同期 API
-2. **データ パイプライン**: エラー処理、ログ記録、大規模データセットの並列処理を備えた Pandas ベースの ETL
-3. **Django アプリケーション**: カスタム ユーザー モデル、API エンドポイント、包括的なテスト カバレッジを備えたフルスタック Web アプリ
-
-**最適な職種**: バックエンド アーキテクト (API 設計)、品質エンジニア (テスト)、パフォーマンス エンジニア (最適化)
-
----
-
-### 要件アナリスト 📝
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#requirements-analyst-)
-
-**専門分野**:体系的なステークホルダー分析による要件発見と仕様策定
-
-**自動アクティベーション**:
-
-- キーワード: 「要件」、「仕様」、「PRD」、「ユーザーストーリー」、「機能」、「スコープ」、「ステークホルダー」
-- 背景: プロジェクトの開始、不明確な要件、スコープ定義の必要性
-- 複雑さ: 複数の利害関係者が関わるプロジェクト、不明確な目標、相反する要件
-
-**機能**:
-
-- ステークホルダーへのインタビューやワークショップを通じた要件抽出
-- 受け入れ基準と完了の定義を含むユーザーストーリーの記述
-- 機能仕様と非機能仕様のドキュメント
-- ステークホルダー分析と要件優先順位付けフレームワーク
-- スコープ管理と変更管理プロセス
-
-**例**:
-
-1. **製品要件ドキュメント**: ユーザー ペルソナ、機能仕様、成功指標を含む、フィンテック モバイル アプリの包括的な PRD
-2. **API仕様**: エラー処理、セキュリティ、パフォーマンス基準を含む支払い処理APIの詳細な要件
-3. **移行要件**: データ移行、ユーザートレーニング、ロールバック手順を含むレガシーシステムの近代化要件
-
-**最適な組み合わせ**: システムアーキテクト (技術的実現可能性)、テクニカルライター (ドキュメント作成)、学習ガイド (ユーザーガイダンス)
-
-### コミュニケーションと学習エージェント 📚
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#communication--learning-agents-)
-
-### テクニカルライター 📚
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#technical-writer-)
-
-**専門分野**: 視聴者分析と明確さを重視した技術文書作成とコミュニケーション
-
-**自動アクティベーション**:
-
-- キーワード: 「ドキュメント」、「Readme」、「API ドキュメント」、「ユーザー ガイド」、「テクニカル ライティング」、「マニュアル」
-- コンテキスト: ドキュメントのリクエスト、API ドキュメント、ユーザー ガイド、技術的な説明
-- ファイルタイプ: .md、.rst、API 仕様、ドキュメント ファイル
-
-**機能**:
-
-- 技術文書のアーキテクチャと情報設計
-- さまざまなスキルレベルに合わせたオーディエンス分析とコンテンツターゲティング
-- 動作例と統合ガイダンスを含む API ドキュメント
-- ステップバイステップの手順とトラブルシューティングを記載したユーザーガイドの作成
-- アクセシビリティ基準の適用と包括的な言語の使用
-
-**例**:
-
-1. **APIドキュメント**: 認証、エンドポイント、例、SDK統合ガイドを含む包括的なREST APIドキュメント
-2. **ユーザーマニュアル**: スクリーンショット、トラブルシューティング、FAQセクションを含むステップバイステップのインストールおよび構成ガイド
-3. **技術仕様**: 図、データフロー、実装の詳細を含むシステムアーキテクチャドキュメント
-
-**最適な組み合わせ**: requirements-analyst (仕様の明確化)、learning-guide (教育コンテンツ)、frontend-architect (UI ドキュメント)
-
----
-
-### 学習ガイド 🎓
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#learning-guide-)
-
-**専門分野**:スキル開発とメンターシップに重点を置いた教育コンテンツの設計と漸進的学習
-
-**自動アクティベーション**:
-
-- キーワード: 「説明」、「学習」、「チュートリアル」、「初心者」、「指導」、「教育」、「トレーニング」
-- コンテキスト: 教育的なリクエスト、概念の説明、スキル開発、学習パス
-- 複雑さ: 段階的な分解と段階的な理解を必要とする複雑なトピック
-
-**機能**:
-
-- 段階的なスキル開発を伴う学習パスの設計
-- 類推と例による複雑な概念の説明
-- 実践的な演習を含むインタラクティブなチュートリアルの作成
-- スキル評価と能力評価のフレームワーク
-- メンターシップ戦略と個別学習アプローチ
-
-**例**:
-
-1. **プログラミングチュートリアル**: 実践的な演習、コード例、段階的な複雑さを備えたインタラクティブな React チュートリアル
-2. **概念の説明**: 視覚的な図と練習問題を使った実際の例を通してデータベースの正規化を説明します
-3. **スキル評価**:実践的なプロジェクトとフィードバックによるフルスタック開発のための包括的な評価フレームワーク
-
-**最適な対象者**: テクニカルライター (教育ドキュメント)、フロントエンドアーキテクト (インタラクティブ学習)、要件アナリスト (学習目標)
-
----
-
-## エージェントの調整と統合 🤝
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#agent-coordination--integration-)
-
-### 調整パターン
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#coordination-patterns)
-
-**アーキテクチャチーム**:
-
-- **フルスタック開発**:フロントエンドアーキテクト + バックエンドアーキテクト + セキュリティエンジニア + 品質エンジニア
-- **システム設計**: システムアーキテクト + DevOps アーキテクト + パフォーマンスエンジニア + セキュリティエンジニア
-- **レガシーモダナイゼーション**:リファクタリング専門家 + システムアーキテクト + 品質エンジニア + テクニカルライター
-
-**品質チーム**:
-
-- **セキュリティ監査**: セキュリティエンジニア + 品質エンジニア + 根本原因アナリスト + 要件アナリスト
-- **パフォーマンス最適化**: パフォーマンスエンジニア + システムアーキテクト + DevOps アーキテクト + 根本原因アナリスト
-- **テスト戦略**: 品質エンジニア + セキュリティエンジニア + パフォーマンスエンジニア + フロントエンドアーキテクト
-
-**コミュニケーションチーム**:
-
-- **ドキュメンテーションプロジェクト**: テクニカルライター + 要件アナリスト + 学習ガイド + ドメインエキスパート
-- **学習プラットフォーム**: 学習ガイド + フロントエンドアーキテクト + テクニカルライター + 品質エンジニア
-- **APIドキュメント**: バックエンドアーキテクト + テクニカルライター + セキュリティエンジニア + 品質エンジニア
-
-### MCP サーバー統合
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#mcp-server-integration)
-
-**MCP サーバーによる拡張機能**:
-
-- **コンテキスト7** : すべての建築家と専門家のための公式ドキュメントパターン
-- **シーケンシャル**: 根本原因アナリスト、システムアーキテクト、パフォーマンスエンジニア向けの多段階分析
-- **マジック**:フロントエンドアーキテクト、学習ガイドインタラクティブコンテンツのためのUI生成
-- **Playwright** : 品質エンジニア向けのブラウザテスト、フロントエンドアーキテクト向けのアクセシビリティ検証
-- **Morphllm** : refactoring-expert のコード変換、python-expert の一括変更
-- **Serena** : すべてのエージェントのプロジェクトメモリ、セッション間のコンテキスト保存
-
-### エージェントのアクティベーションのトラブルシューティング
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#troubleshooting-agent-activation)
-
-## トラブルシューティング
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#troubleshooting)
-
-トラブルシューティングのヘルプについては、以下を参照してください。
-
-- [よくある問題](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/common-issues.md)- よくある問題に対するクイック修正
-- [トラブルシューティングガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/troubleshooting.md)- 包括的な問題解決
-
-### よくある問題
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#common-issues)
-
-- **エージェントのアクティベーションなし**: ドメインキーワード「セキュリティ」、「パフォーマンス」、「フロントエンド」を使用します
-- **間違ったエージェントが選択されました**: エージェントのドキュメントでトリガーキーワードを確認してください
-- **エージェントが多すぎる場合**:主要ドメインのキーワードに焦点を当てるか、`/sc:focus [domain]`
-- **エージェントが連携していない**: タスクの複雑さを増やすか、マルチドメインキーワードを使用する
-- **エージェントの専門知識の不一致**: より具体的な技術用語を使用する
-
-### 即時修正
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#immediate-fixes)
-
-- **エージェントの強制アクティベーション**: リクエストで明示的なドメインキーワードを使用する
-- **エージェントの選択をリセット**: エージェントの状態をリセットするには、Claude Code セッションを再起動します。
-- **エージェントのパターンを確認する**: エージェントのドキュメントでトリガーキーワードを確認する
-- **基本的なアクティベーションをテストする**:`/sc:implement "security auth"`セキュリティエンジニアのテストを試みる
-
-### エージェント固有のトラブルシューティング
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#agent-specific-troubleshooting)
-
-**セキュリティエージェントなし:**
-
-```shell
-# Problem: Security concerns not triggering security-engineer
-# Quick Fix: Use explicit security keywords
-"implement authentication" # Generic - may not trigger
-"implement JWT authentication security" # Explicit - triggers security-engineer
-"secure user login with encryption" # Security focus - triggers security-engineer
-```
-
-**パフォーマンスエージェントなし:**
-
-```shell
-# Problem: Performance issues not triggering performance-engineer
-# Quick Fix: Use performance-specific terminology
-"make it faster" # Vague - may not trigger
-"optimize slow database queries" # Specific - triggers performance-engineer
-"reduce API latency and bottlenecks" # Performance focus - triggers performance-engineer
-```
-
-**アーキテクチャエージェントなし:**
-
-```shell
-# Problem: System design not triggering architecture agents
-# Quick Fix: Use architectural keywords
-"build an app" # Generic - triggers basic agents
-"design microservices architecture" # Specific - triggers system-architect
-"scalable distributed system design" # Architecture focus - triggers system-architect
-```
-
-**間違ったエージェントの組み合わせ:**
-
-```shell
-# Problem: Getting frontend agent for backend tasks
-# Quick Fix: Use domain-specific terminology
-"create user interface" # May trigger frontend-architect
-"create REST API endpoints" # Specific - triggers backend-architect
-"implement server-side authentication" # Backend focus - triggers backend-architect
-```
-
-### サポートレベル
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#support-levels)
-
-**クイックフィックス:**
-
-- エージェントトリガーテーブルから明示的なドメインキーワードを使用する
-- Claude Codeセッションを再起動してみてください
-- 混乱を避けるために単一のドメインに焦点を当てる
-
-**詳細なヘルプ:**
-
-- エージェントのインストールに関する問題については、[一般的な問題ガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/common-issues.md)を参照してください。
-- 対象エージェントのトリガーキーワードを確認する
-
-**専門家によるサポート:**
-
-- 使用`SuperClaude install --diagnose`
-- 協調分析については[診断リファレンスガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/diagnostic-reference.md)を参照してください
-
-**コミュニティサポート:**
-
-- [GitHub Issues](https://github.com/SuperClaude-Org/SuperClaude_Framework/issues)で問題を報告してください[](https://github.com/SuperClaude-Org/SuperClaude_Framework/issues)
-- 予想されるエージェントのアクティベーションと実際のエージェントのアクティベーションの例を含める
-
-### 成功の検証
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#success-validation)
-
-エージェントの修正を適用した後、次のようにテストします。
-
-- [ ] ドメイン固有のリクエストは適切なエージェントをアクティブ化します(セキュリティ → セキュリティ エンジニア)
-- [ ] 複雑なタスクはマルチエージェント調整(3 つ以上のエージェント)をトリガーします
-- [ ] エージェントの専門知識がタスク要件に一致している(API → バックエンドアーキテクト)
-- [ ] 適切な場合に品質エージェントが自動的に含められます(セキュリティ、パフォーマンス、テスト)
-- [ ] 回答はドメインの専門知識と専門知識を示す
-
-## クイックトラブルシューティング(レガシー)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#quick-troubleshooting-legacy)
-
-- **エージェントが有効化されていない場合**→ ドメインキーワード「セキュリティ」、「パフォーマンス」、「フロントエンド」を使用します
-- **エージェントが間違っている**→ エージェントのドキュメントでトリガーキーワードを確認してください
-- **エージェントが多すぎる**→ 主要ドメインのキーワードに焦点を絞る
-- **エージェントが連携していない**→ タスクの複雑さを増やすか、マルチドメインキーワードを使用する
-
-**エージェントがアクティブ化されない?**
-
-1. **キーワードを確認する**: ドメイン固有の用語を使用する (例: セキュリティ エンジニアの場合は「ログイン」ではなく「認証」)
-2. **コンテキストを追加**: ファイルの種類、フレームワーク、または特定のテクノロジーを含める
-3. **複雑さの増大**:マルチドメインの問題はより多くのエージェントをトリガーします
-4. **使用例**: エージェントの専門知識に合った具体的なシナリオを参照する
-
-**エージェントが多すぎますか?**
-
-- 主要なドメインのニーズにキーワードを集中させる
-- `/sc:focus [domain]`範囲を制限するために使用する
-- 特定のエージェントから始めて、必要に応じて拡張します
-
-**エージェントが間違っていますか?**
-
-- エージェントのドキュメントでトリガーキーワードを確認する
-- 対象ドメインに対してより具体的な用語を使用する
-- 明示的な要件または制約を追加する
-
-## クイックリファレンス 📋
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#quick-reference-)
-
-### エージェントトリガー検索
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#agent-trigger-lookup)
-
-|トリガータイプ|キーワード/パターン|活性化エージェント|
-|---|---|---|
-|**安全**|「認証」、「セキュリティ」、「脆弱性」、「暗号化」|セキュリティエンジニア|
-|**パフォーマンス**|「遅い」、「最適化」、「ボトルネック」、「レイテンシー」|パフォーマンスエンジニア|
-|**フロントエンド**|「UI」、「React」、「Vue」、「コンポーネント」、「レスポンシブ」|フロントエンドアーキテクト|
-|**バックエンド**|「API」、「サーバー」、「データベース」、「REST」、「GraphQL」|バックエンドアーキテクト|
-|**テスト**|「テスト」、「QA」、「検証」、「カバレッジ」|品質エンジニア|
-|**デブオプス**|「デプロイ」、「CI/CD」、「Docker」、「Kubernetes」|DevOpsアーキテクト|
-|**建築**|「アーキテクチャ」、「マイクロサービス」、「スケーラビリティ」|システムアーキテクト|
-|**パイソン**|「.py」、「Django」、「FastAPI」、「asyncio」|Pythonエキスパート|
-|**問題**|「バグ」、「問題」、「デバッグ」、「トラブルシューティング」|根本原因分析者|
-|**コード品質**|「リファクタリング」、「クリーンコード」、「技術的負債」|リファクタリングの専門家|
-|**ドキュメント**|「ドキュメント」、「Readme」、「APIドキュメント」|テクニカルライター|
-|**学ぶ**|「説明する」、「チュートリアル」、「初心者」、「教える」|学習ガイド|
-|**要件**|「要件」、「PRD」、「仕様」|要件アナリスト|
-
-### コマンドエージェントマッピング
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#command-agent-mapping)
-
-|指示|主な薬剤|サポートエージェント|
-|---|---|---|
-|`/sc:implement`|ドメインアーキテクト(フロントエンド、バックエンド)|セキュリティエンジニア、品質エンジニア|
-|`/sc:analyze`|品質エンジニア、セキュリティエンジニア|パフォーマンスエンジニア、根本原因アナリスト|
-|`/sc:troubleshoot`|根本原因分析者|ドメインスペシャリスト、パフォーマンスエンジニア|
-|`/sc:improve`|リファクタリングの専門家|品質エンジニア、パフォーマンスエンジニア|
-|`/sc:document`|テクニカルライター|ドメインスペシャリスト、学習ガイド|
-|`/sc:design`|システムアーキテクト|ドメインアーキテクト、要件アナリスト|
-|`/sc:test`|品質エンジニア|セキュリティエンジニア、パフォーマンスエンジニア|
-|`/sc:explain`|学習ガイド|テクニカルライター、ドメインスペシャリスト|
-
-### 効果的な薬剤の組み合わせ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#effective-agent-combinations)
-
-**開発ワークフロー**:
-
-- Web アプリケーション: フロントエンド アーキテクト + バックエンド アーキテクト + セキュリティ エンジニア + 品質エンジニア + DevOps アーキテクト
-- API開発: バックエンドアーキテクト + セキュリティエンジニア + テクニカルライター + 品質エンジニア
-- データ プラットフォーム: Python エキスパート + パフォーマンス エンジニア + セキュリティ エンジニア + システム アーキテクト
-
-**分析ワークフロー**:
-
-- セキュリティ監査: セキュリティエンジニア + 品質エンジニア + 根本原因アナリスト + テクニカルライター
-- パフォーマンス調査: パフォーマンスエンジニア + 根本原因アナリスト + システムアーキテクト + DevOps アーキテクト
-- レガシー評価: リファクタリング専門家 + システムアーキテクト + 品質エンジニア + セキュリティエンジニア + テクニカルライター
-
-**コミュニケーションワークフロー**:
-
-- 技術ドキュメント: テクニカルライター + 要件アナリスト + ドメインエキスパート + 学習ガイド
-- 教育コンテンツ: 学習ガイド + テクニカルライター + フロントエンドアーキテクト + 品質エンジニア
-
-## ベストプラクティス💡
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#best-practices-)
-
-### はじめに(シンプルなアプローチ)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#getting-started-simple-approach)
-
-**自然言語ファースト:**
-
-1. **目標を記述する**: ドメイン固有のキーワードを含む自然言語を使用する
-2. **信頼の自動アクティベーション**: システムが適切なエージェントに自動的にルーティングできるようにします
-3. **パターンから学ぶ**: さまざまなリクエストタイプに対してどのエージェントがアクティブになるかを観察する
-4. **反復と改良**: 専門エージェントを追加するために詳細度を追加します
-
-### エージェントの選択の最適化
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#optimizing-agent-selection)
-
-**効果的なキーワードの使用法:**
-
-- **特定 > 汎用**: セキュリティエンジニアの場合は「ログイン」の代わりに「認証」を使用します
-- **技術用語**: フレームワーク名、テクノロジー、具体的な課題など
-- **コンテキストヒント**: ファイルの種類、プロジェクトの範囲、複雑さの指標について言及する
-- **品質キーワード**: 包括的なカバレッジのために「セキュリティ」、「パフォーマンス」、「アクセシビリティ」を追加します
-
-**リクエストの最適化の例:**
-
-```shell
-# Generic (limited agent activation)
-"Fix the login feature"
-
-# Optimized (multi-agent coordination)
-"Implement secure JWT authentication with rate limiting and accessibility compliance"
-# → Triggers: security-engineer + backend-architect + frontend-architect + quality-engineer
-```
-
-### 一般的な使用パターン
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#common-usage-patterns)
-
-**開発ワークフロー:**
-
-```shell
-# Full-stack feature development
-/sc:implement "responsive user dashboard with real-time notifications"
-# → frontend-architect + backend-architect + performance-engineer
-
-# API development with documentation
-/sc:create "REST API for payment processing with comprehensive docs"
-# → backend-architect + security-engineer + technical-writer + quality-engineer
-
-# Performance optimization investigation
-/sc:troubleshoot "slow database queries affecting user experience"
-# → performance-engineer + root-cause-analyst + backend-architect
-```
-
-**分析ワークフロー:**
-
-```shell
-# Security assessment
-/sc:analyze "authentication system for GDPR compliance vulnerabilities"
-# → security-engineer + quality-engineer + requirements-analyst
-
-# Code quality review
-/sc:review "legacy codebase for modernization opportunities"
-# → refactoring-expert + system-architect + quality-engineer + technical-writer
-
-# Learning and explanation
-/sc:explain "microservices patterns with hands-on examples"
-# → system-architect + learning-guide + technical-writer
-```
-
-### 高度なエージェント調整
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#advanced-agent-coordination)
-
-**マルチドメインプロジェクト:**
-
-- **幅広く始める**:システムレベルのキーワードから始めて、建築エージェントの関心を引く
-- **特異性の追加**: 専門エージェントを活性化するためにドメイン固有のニーズを含める
-- **品質統合**: セキュリティ、パフォーマンス、テストの観点を自動的に含めます
-- **ドキュメントの包含**: 包括的なカバレッジのために学習またはドキュメントのニーズを追加します
-
-**エージェントの選択に関するトラブルシューティング:**
-
-**問題: 間違ったエージェントがアクティブ化される**
-
-- 解決策: より具体的なドメイン用語を使用する
-- 例:「データベース最適化」→ パフォーマンスエンジニア + バックエンドアーキテクト
-
-**問題: エージェントが足りない**
-
-- 解決策: 複雑性指標とクロスドメインキーワードを増やす
-- 例: リクエストに「セキュリティ」、「パフォーマンス」、「ドキュメント」を追加する
-
-**問題: エージェントが多すぎる**
-
-- 解決策: 特定の技術用語を含む主要ドメインに焦点を当てる
-- 例: スコープを制限するには「/sc:focus backend」を使用します
-
-### 品質重視の開発
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#quality-driven-development)
-
-**セキュリティ第一のアプローチ:** 開発リクエストには常にセキュリティに関する考慮事項を含め、ドメインスペシャリストとともにセキュリティエンジニアを自動的に関与させます。
-
-**パフォーマンス統合:** パフォーマンス キーワード (「高速」、「効率的」、「スケーラブル」) を含めて、最初からパフォーマンス エンジニアの調整を確実にします。
-
-**アクセシビリティ コンプライアンス:** 「accessible」、「WCAG」、または「inclusive」を使用して、フロントエンド開発にアクセシビリティ検証を自動的に含めます。
-
-**ドキュメント文化:** テクニカルライターの自動的な参加と知識の移転のリクエストに「ドキュメント化」、「説明」、または「チュートリアル」を追加します。
-
----
-
-## エージェントインテリジェンスを理解する🧠
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#understanding-agent-intelligence-)
-
-### エージェントを効果的にする要素
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#what-makes-agents-effective)
-
-**ドメイン専門知識**: 各エージェントは、それぞれのドメインに特有の専門的な知識パターン、行動アプローチ、問題解決方法論を備えています。
-
-**コンテキスト アクティベーション**: エージェントは、キーワードだけでなくリクエストのコンテキストを分析して、関連性とエンゲージメント レベルを判断します。
-
-**協調的インテリジェンス**: 複数のエージェントの調整により、個々のエージェントの能力を超える相乗的な結果が生まれます。
-
-**適応学習**: リクエストパターンと成功した調整結果に基づいてエージェントの選択が改善されます。
-
-### エージェント vs. 従来のAI
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#agent-vs-traditional-ai)
-
-**従来のアプローチ**: 単一のAIが、さまざまなレベルの専門知識を持つすべてのドメインを処理します。 **エージェントアプローチ**: 専門のエキスパートが、深いドメイン知識と集中的な問題解決で協力します。
-
-**利点**:
-
-- ドメイン固有のタスクにおける高い精度
-- より洗練された問題解決方法論
-- 専門家によるレビューによる品質保証の向上
-- 協調的な多角的分析
-
-### システムを信頼し、パターンを理解する
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#trust-the-system-understand-the-patterns)
-
-**期待すること**:
-
-- 適切なドメイン専門家への自動ルーティング
-- 複雑なタスクのためのマルチエージェント調整
-- 自動QAエージェントの組み込みによる品質統合
-- 教育エージェントの活性化による学習機会
-
-**心配する必要がないこと**:
-
-- エージェントの手動選択または構成
-- 複雑なルーティングルールやエージェント管理
-- エージェントの構成または調整
-- エージェントとのやり取りを細かく管理する
-
----
-
-## 関連リソース 📚
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#related-resources-)
-
-### 必須ドキュメント
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#essential-documentation)
-
-- **[コマンドガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md)**- 最適なエージェント調整をトリガーするSuperClaudeコマンドをマスターする
-- **[MCP サーバー](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md)**- 専用ツールの統合によるエージェント機能の強化
-- **[セッション管理](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md)**- 永続的なエージェントコンテキストによる長期ワークフロー
-
-### 高度な使用法
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#advanced-usage)
-
-- **[行動モード](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md)**- エージェントの調整を強化するためのコンテキスト最適化
-- **[はじめに](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Getting-Started/quick-start.md)**- エージェントの最適化のための専門家のテクニック
-- **[例のクックブック](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/examples-cookbook.md)**- 現実世界のエージェントの調整パターン
-
-### 開発リソース
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#development-resources)
-
-- **[技術アーキテクチャ](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Developer-Guide/technical-architecture.md)**- SuperClaude のエージェント システム設計を理解する
-- **[貢献](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Developer-Guide/contributing-code.md)**- エージェントの機能と調整パターンの拡張
-
----
-
-## エージェントとしての道のり 🚀
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md#your-agent-journey-)
-
-**第1週:自然な使用法** 自然な言語による説明から始めましょう。どのエージェントが、そしてなぜアクティブになるのかに注目しましょう。プロセスを考えすぎずに、キーワードのパターンに対する直感を養います。
-
-**第2~3週:パターン認識**
-エージェントの連携パターンを観察します。複雑さとドメインキーワードがエージェントの選択にどのような影響を与えるかを理解します。連携を向上させるために、リクエストの表現を最適化します。
-
-**2ヶ月目以降:エキスパートコーディネーション** 最適なエージェントの組み合わせをトリガーするマルチドメインリクエストをマスターします。トラブルシューティング手法を活用して効果的なエージェント選定を行います。複雑なワークフローには高度なパターンを使用します。
-
-**SuperClaudeのメリット:** 14名の専門AIエキスパートが、シンプルな自然言語によるリクエストに連携して対応します。設定や管理は不要で、ニーズに合わせて拡張できるインテリジェントな連携を実現します。
-
-🎯**インテリジェントエージェントコーディネーションを体験する準備はできましたか?まずは`/sc:implement`、専門的な AI コラボレーションの魔法を発見してください。**
\ No newline at end of file
diff --git a/docs/User-Guide-jp/commands.md b/docs/User-Guide-jp/commands.md
deleted file mode 100644
index 05d2b7f..0000000
--- a/docs/User-Guide-jp/commands.md
+++ /dev/null
@@ -1,415 +0,0 @@
-# SuperClaude コマンドガイド
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#superclaude-commands-guide)
-
-`/sc:*`SuperClaude は、ワークフロー用コマンドと`@agent-*`スペシャリスト用コマンドの 21 個の Claude Code コマンドを提供します。
-
-## コマンドの種類
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#command-types)
-
-|タイプ|使用場所|形式|例|
-|---|---|---|---|
-|**スラッシュコマンド**|クロード・コード|`/sc:[command]`|`/sc:implement "feature"`|
-|**エージェント**|クロード・コード|`@agent-[name]`|`@agent-security "review"`|
-|**インストール**|ターミナル|`SuperClaude [command]`|`SuperClaude install`|
-
-## クイックテスト
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#quick-test)
-
-```shell
-# Terminal: Verify installation
-python3 -m SuperClaude --version
-# Claude Code CLI verification: claude --version
-
-# Claude Code: Test commands
-/sc:brainstorm "test project" # Should ask discovery questions
-/sc:analyze README.md # Should provide analysis
-```
-
-**ワークフロー**:`/sc:brainstorm "idea"`→→`/sc:implement "feature"``/sc:test`
-
-## 🎯 SuperClaude コマンドの理解
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#-understanding-superclaude-commands)
-
-## SuperClaudeの仕組み
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#how-superclaude-works)
-
-SuperClaude は、Claude Code が特殊な動作を実行するために読み込む動作コンテキストファイルを提供します。 と入力すると`/sc:implement`、Claude Code は`implement.md`コンテキストファイルを読み込み、その動作指示に従います。
-
-**SuperClaude コマンドはソフトウェアによって実行されるのではなく**、フレームワークから特殊な命令ファイルを読み取ることで Claude コードの動作を変更するコンテキスト トリガーです。
-
-### コマンドの種類:
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#command-types-1)
-
-- **スラッシュコマンド**(`/sc:*`):ワークフローパターンと動作モードをトリガーする
-- **エージェントの呼び出し**(`@agent-*`):特定のドメインスペシャリストを手動で起動する
-- **フラグ**(`--think`、`--safe-mode`):コマンドの動作と深さを変更する
-
-### コンテキストメカニズム:
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#the-context-mechanism)
-
-1. **ユーザー入力**: 入力する`/sc:implement "auth system"`
-2. **コンテキスト読み込み**: クロードコード読み取り`~/.claude/superclaude/Commands/implement.md`
-3. **行動の採用**:クロードはドメインの専門知識、ツールの選択、検証パターンを適用します
-4. **強化された出力**: セキュリティ上の考慮事項とベストプラクティスを備えた構造化された実装
-
-**重要なポイント**: これにより、従来のソフトウェア実行ではなくコンテキスト管理を通じて洗練された開発ワークフローが作成されます。
-
-### インストールコマンドと使用コマンド
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#installation-vs-usage-commands)
-
-**🖥️ ターミナルコマンド**(実際の CLI ソフトウェア):
-
-- `SuperClaude install`- フレームワークコンポーネントをインストールします
-- `SuperClaude update`- 既存のインストールを更新します
-- `SuperClaude uninstall`- フレームワークのインストールを削除します
-- `python3 -m SuperClaude --version`- インストール状態を確認する
-
-**💬 クロード コード コマンド**(コンテキスト トリガー):
-
-- `/sc:brainstorm`- 要件検出コンテキストをアクティブ化します
-- `/sc:implement`- 機能開発コンテキストをアクティブ化します
-- `@agent-security`- セキュリティスペシャリストのコンテキストをアクティブ化します
-- すべてのコマンドはClaude Codeチャットインターフェース内でのみ機能します
-
-> **クイック スタート**: `/sc:brainstorm "your project idea"`→ `/sc:implement "feature name"`→を試して`/sc:test`、コア ワークフローを体験してください。
-
-## 🧪 セットアップのテスト
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#-testing-your-setup)
-
-### 🖥️ ターミナル検証(ターミナル/CMDで実行)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#%EF%B8%8F-terminal-verification-run-in-terminalcmd)
-
-```shell
-# Verify SuperClaude is working (primary method)
-python3 -m SuperClaude --version
-# Example output: SuperClaude 4.1.5
-
-# Claude Code CLI version check
-claude --version
-
-# Check installed components
-python3 -m SuperClaude install --list-components | grep mcp
-# Example output: Shows installed MCP components
-```
-
-### 💬 クロードコードテスト(クロードコードチャットに入力)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#-claude-code-testing-type-in-claude-code-chat)
-
-```
-# Test basic /sc: command
-/sc:brainstorm "test project"
-# Example behavior: Interactive requirements discovery starts
-
-# Test command help
-/sc:help
-# Example behavior: List of available commands
-```
-
-**テストが失敗した場合**:[インストールガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Getting-Started/installation.md)または[トラブルシューティングを確認してください](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#troubleshooting)
-
-### 📝 コマンドクイックリファレンス
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#-command-quick-reference)
-
-|コマンドタイプ|走る場所|形式|目的|例|
-|---|---|---|---|---|
-|**🖥️ インストール**|ターミナル/CMD|`SuperClaude [command]`|セットアップとメンテナンス|`SuperClaude install`|
-|**🔧 構成**|ターミナル/CMD|`python3 -m SuperClaude [command]`|高度な設定|`python3 -m SuperClaude --version`|
-|**💬 スラッシュコマンド**|クロード・コード|`/sc:[command]`|ワークフロー自動化|`/sc:implement "feature"`|
-|**🤖 エージェントの呼び出し**|クロード・コード|`@agent-[name]`|手動スペシャリストの有効化|`@agent-security "review"`|
-|**⚡ 強化されたフラグ**|クロード・コード|`/sc:[command] --flags`|行動修正|`/sc:analyze --think-hard`|
-
-> **注意**:すべての`/sc:`コマンドと`@agent-`呼び出しは、ターミナルではなくClaude Codeチャット内で動作します。これらのコマンドと呼び出しは、Claude CodeがSuperClaudeフレームワークから特定のコンテキストファイルを読み取るようにトリガーします。
-
-## 目次
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#table-of-contents)
-
-- [必須コマンド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#essential-commands)- ここから始めましょう(8つのコアコマンド)
-- [一般的なワークフロー](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#common-workflows)- 機能するコマンドの組み合わせ
-- [完全なコマンドリファレンス](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#full-command-reference)- カテゴリ別に整理された全21個のコマンド
-- [トラブルシューティング](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#troubleshooting)- よくある問題と解決策
-- [コマンドインデックス](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#command-index)- カテゴリ別にコマンドを検索
-
----
-
-## 必須コマンド
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#essential-commands)
-
-**即時の生産性向上のためのコアワークフロー コマンド:**
-
-### `/sc:brainstorm`- プロジェクト発見
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#scbrainstorm---project-discovery)
-
-**目的**: 対話型の要件検出とプロジェクト計画
-**構文**:`/sc:brainstorm "your idea"` `[--strategy systematic|creative]`
-
-**ユースケース**:
-
-- 新しいプロジェクトの計画:`/sc:brainstorm "e-commerce platform"`
-- 機能の探索:`/sc:brainstorm "user authentication system"`
-- 問題解決:`/sc:brainstorm "slow database queries"`
-
-### `/sc:implement`- 機能開発
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#scimplement---feature-development)
-
-**目的**: インテリジェントなスペシャリストルーティングによるフルスタック機能の実装
-**構文**:`/sc:implement "feature description"` `[--type frontend|backend|fullstack] [--focus security|performance]`
-
-**ユースケース**:
-
-- 認証:`/sc:implement "JWT login system"`
-- UI コンポーネント:`/sc:implement "responsive dashboard"`
-- API:`/sc:implement "REST user endpoints"`
-- データベース:`/sc:implement "user schema with relationships"`
-
-### `/sc:analyze`- コード評価
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#scanalyze---code-assessment)
-
-**目的**: 品質、セキュリティ、パフォーマンスにわたる包括的なコード分析
-**構文**:`/sc:analyze [path]` `[--focus quality|security|performance|architecture]`
-
-**ユースケース**:
-
-- プロジェクトの健全性:`/sc:analyze .`
-- セキュリティ監査:`/sc:analyze --focus security`
-- パフォーマンスレビュー:`/sc:analyze --focus performance`
-
-### `/sc:troubleshoot`- 問題診断
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#sctroubleshoot---problem-diagnosis)
-
-**目的**: 根本原因分析による体系的な問題診断
-**構文**:`/sc:troubleshoot "issue description"` `[--type build|runtime|performance]`
-
-**ユースケース**:
-
-- ランタイムエラー:`/sc:troubleshoot "500 error on login"`
-- ビルドの失敗:`/sc:troubleshoot --type build`
-- パフォーマンスの問題:`/sc:troubleshoot "slow page load"`
-
-### `/sc:test`- 品質保証
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#sctest---quality-assurance)
-
-**目的**: カバレッジ分析による包括的なテスト
-**構文**:`/sc:test` `[--type unit|integration|e2e] [--coverage] [--fix]`
-
-**ユースケース**:
-
-- 完全なテストスイート:`/sc:test --coverage`
-- ユニットテスト:`/sc:test --type unit --watch`
-- E2E検証:`/sc:test --type e2e`
-
-### `/sc:improve`- コード強化
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#scimprove---code-enhancement)
-
-**目的**: 体系的なコードの改善と最適化を適用する
-**構文**:`/sc:improve [path]` `[--type performance|quality|security] [--preview]`
-
-**ユースケース**:
-
-- 一般的な改善点:`/sc:improve src/`
-- パフォーマンスの最適化:`/sc:improve --type performance`
-- セキュリティ強化:`/sc:improve --type security`
-
-### `/sc:document`- ドキュメント生成
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#scdocument---documentation-generation)
-
-**目的**: コードとAPIの包括的なドキュメントを生成する
-**構文**:`/sc:document [path]` `[--type api|user-guide|technical] [--format markdown|html]`
-
-**ユースケース**:
-
-- APIドキュメント:`/sc:document --type api`
-- ユーザーガイド:`/sc:document --type user-guide`
-- 技術ドキュメント:`/sc:document --type technical`
-
-### `/sc:workflow`- 実装計画
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#scworkflow---implementation-planning)
-
-**目的**: 要件から構造化された実装計画を生成する
-**構文**:`/sc:workflow "feature description"` `[--strategy agile|waterfall] [--format markdown]`
-
-**ユースケース**:
-
-- 機能計画:`/sc:workflow "user authentication"`
-- スプリント計画:`/sc:workflow --strategy agile`
-- アーキテクチャ計画:`/sc:workflow "microservices migration"`
-
----
-
-## 一般的なワークフロー
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#common-workflows)
-
-**実証済みのコマンドの組み合わせ:**
-
-### 新しいプロジェクトのセットアップ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#new-project-setup)
-
-```shell
-/sc:brainstorm "project concept" # Define requirements
-/sc:design "system architecture" # Create technical design
-/sc:workflow "implementation plan" # Generate development roadmap
-```
-
-### 機能開発
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#feature-development)
-
-```shell
-/sc:implement "feature name" # Build the feature
-/sc:test --coverage # Validate with tests
-/sc:document --type api # Generate documentation
-```
-
-### コード品質の改善
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#code-quality-improvement)
-
-```shell
-/sc:analyze --focus quality # Assess current state
-/sc:improve --preview # Preview improvements
-/sc:test --coverage # Validate changes
-```
-
-### バグ調査
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#bug-investigation)
-
-```shell
-/sc:troubleshoot "issue description" # Diagnose the problem
-/sc:analyze --focus problem-area # Deep analysis
-/sc:improve --fix --safe-mode # Apply targeted fixes
-```
-
-## 完全なコマンドリファレンス
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#full-command-reference)
-
-### 開発コマンド
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#development-commands)
-
-|指示|目的|最適な用途|
-|---|---|---|
-|**ワークフロー**|実施計画|プロジェクトロードマップ、スプリント計画|
-|**埋め込む**|機能開発|フルスタック機能、API開発|
-|**建てる**|プロジェクトのコンパイル|CI/CD、プロダクションビルド|
-|**デザイン**|システムアーキテクチャ|API仕様、データベーススキーマ|
-
-### 分析コマンド
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#analysis-commands)
-
-|指示|目的|最適な用途|
-|---|---|---|
-|**分析する**|コード評価|品質監査、セキュリティレビュー|
-|**トラブルシューティング**|問題診断|バグ調査、パフォーマンスの問題|
-|**説明する**|コードの説明|学習、コードレビュー|
-
-### 品質コマンド
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#quality-commands)
-
-|指示|目的|最適な用途|
-|---|---|---|
-|**改善する**|コード強化|パフォーマンスの最適化、リファクタリング|
-|**掃除**|技術的負債|デッドコードの削除、整理|
-|**テスト**|品質保証|テスト自動化、カバレッジ分析|
-|**書類**|ドキュメント|APIドキュメント、ユーザーガイド|
-
-### プロジェクト管理
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#project-management)
-
-|指示|目的|最適な用途|
-|---|---|---|
-|**見積もり**|プロジェクト見積もり|タイムライン計画、リソース割り当て|
-|**タスク**|タスク管理|複雑なワークフロー、タスク追跡|
-|**スポーン**|メタオーケストレーション|大規模プロジェクト、並列実行|
-
-### ユーティリティコマンド
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#utility-commands)
-
-|指示|目的|最適な用途|
-|---|---|---|
-|**ギット**|バージョン管理|コミット管理、ブランチ戦略|
-|**索引**|コマンド検出|機能の探索、コマンドの検索|
-
-### セッションコマンド
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#session-commands)
-
-|指示|目的|最適な用途|
-|---|---|---|
-|**負荷**|コンテキストの読み込み|セッションの初期化、プロジェクトのオンボーディング|
-|**保存**|セッションの永続性|チェックポイント、コンテキスト保存|
-|**反映する**|タスクの検証|進捗評価、完了検証|
-|**選択ツール**|ツールの最適化|パフォーマンスの最適化、ツールの選択|
-
----
-
-## コマンドインデックス
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#command-index)
-
-**機能別:**
-
-- **計画**:ブレインストーミング、設計、ワークフロー、見積もり
-- **開発**:実装、ビルド、git
-- **分析**:分析、トラブルシューティング、説明
-- **品質**: 改善、クリーンアップ、テスト、ドキュメント化
-- **管理**: タスク、スポーン、ロード、保存、反映
-- **ユーティリティ**: インデックス、選択ツール
-
-**複雑さ別:**
-
-- **初心者**:ブレインストーミング、実装、分析、テスト
-- **中級**:ワークフロー、設計、改善、ドキュメント
-- **上級**:スポーン、タスク、選択ツール、リフレクト
-
-## トラブルシューティング
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#troubleshooting)
-
-**コマンドの問題:**
-
-- **コマンドが見つかりません**: インストールを確認してください:`python3 -m SuperClaude --version`
-- **応答なし**: Claude Codeセッションを再開する
-- **処理遅延**: `--no-mcp`MCPサーバーなしでテストするために使用します
-
-**クイックフィックス:**
-
-- セッションをリセット:`/sc:load`再初期化する
-- ステータスを確認:`SuperClaude install --list-components`
-- ヘルプ:[トラブルシューティングガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/troubleshooting.md)
-
-## 次のステップ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#next-steps)
-
-- [フラグガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md)- コマンドの動作を制御する
-- [エージェントガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md)- スペシャリストのアクティベーション
-- [例のクックブック](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/examples-cookbook.md)- 実際の使用パターン
\ No newline at end of file
diff --git a/docs/User-Guide-jp/flags.md b/docs/User-Guide-jp/flags.md
deleted file mode 100644
index 2233aec..0000000
--- a/docs/User-Guide-jp/flags.md
+++ /dev/null
@@ -1,388 +0,0 @@
-# SuperClaude フラグガイド 🏁
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#superclaude-flags-guide-)
-
-**ほとんどのフラグは自動的にアクティブになります**。Claude Code は、リクエスト内のキーワードとパターンに基づいて適切なコンテキストを実行するための動作指示を読み取ります。
-
-## 必須の自動アクティベーションフラグ(ユースケースの90%)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#essential-auto-activation-flags-90-of-use-cases)
-
-### コア分析フラグ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#core-analysis-flags)
-
-|フラグ|起動時|何をするのか|
-|---|---|---|
-|`--think`|5つ以上のファイルまたは複雑な分析|標準的な構造化分析(約4Kトークン)|
-|`--think-hard`|アーキテクチャ分析、システム依存関係|強化されたツールによる詳細な分析(約1万トークン)|
-|`--ultrathink`|重要なシステムの再設計、レガシーシステムの近代化|すべてのツールで最大深度分析(約32Kトークン)|
-
-### MCP サーバーフラグ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#mcp-server-flags)
-
-|フラグ|サーバ|目的|自動トリガー|
-|---|---|---|---|
-|`--c7`/`--context7`|コンテキスト7|公式ドキュメント、フレームワークパターン|ライブラリのインポート、フレームワークに関する質問|
-|`--seq`/`--sequential`|一連|多段階推論、デバッグ|複雑なデバッグ、システム設計|
-|`--magic`|魔法|UIコンポーネント生成|`/ui`コマンド、フロントエンドキーワード|
-|`--play`/`--playwright`|劇作家|ブラウザテスト、E2E検証|テスト要求、視覚的検証|
-|`--morph`/`--morphllm`|モルフィム|一括変換、パターン編集|一括操作、スタイルの強制|
-|`--serena`|セレナ|プロジェクトメモリ、シンボル操作|シンボル操作、大規模なコードベース|
-
-### 動作モードフラグ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#behavioral-mode-flags)
-
-|フラグ|起動時|何をするのか|
-|---|---|---|
-|`--brainstorm`|漠然とした要望、探索キーワード|共同発見のマインドセット|
-|`--introspect`|自己分析、エラー回復|推論プロセスを透明性を持って公開する|
-|`--task-manage`|>3ステップ、複雑なスコープ|委任を通じて調整する|
-|`--orchestrate`|マルチツール操作、パフォーマンスニーズ|ツールの選択と並列実行の最適化|
-|`--token-efficient`/`--uc`|コンテキスト >75%、効率性のニーズ|シンボル強化通信、30~50%削減|
-
-### 実行制御フラグ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#execution-control-flags)
-
-|フラグ|起動時|何をするのか|
-|---|---|---|
-|`--loop`|「改善する」「磨く」「洗練する」というキーワード|反復的な強化サイクル|
-|`--safe-mode`|生産、リソース使用率85%以上|最大限の検証、慎重な実行|
-|`--validate`|リスク >0.7、本番環境|実行前のリスク評価|
-|`--delegate`|>7 ディレクトリまたは >50 ファイル|サブエージェント並列処理|
-
-## コマンド固有のフラグ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#command-specific-flags)
-
-### 分析コマンドフラグ(`/sc:analyze`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#analysis-command-flags-scanalyze)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--focus`|特定のドメインをターゲットとする|`security`、、、、`performance``quality``architecture`|
-|`--depth`|分析の徹底性|`quick`、`deep`|
-|`--format`|出力形式|`text`、、`json``report`|
-
-### ビルドコマンドフラグ(`/sc:build`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#build-command-flags-scbuild)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--type`|ビルド構成|`dev`、、`prod``test`|
-|`--clean`|ビルド前にクリーンアップ|ブール値|
-|`--optimize`|最適化を有効にする|ブール値|
-|`--verbose`|詳細な出力|ブール値|
-
-### 設計コマンドフラグ(`/sc:design`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#design-command-flags-scdesign)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--type`|設計目標|`architecture`、、、、`api``component``database`|
-|`--format`|出力形式|`diagram`、、`spec``code`|
-
-### コマンドフラグの説明(`/sc:explain`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#explain-command-flags-scexplain)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--level`|複雑さのレベル|`basic`、、`intermediate``advanced`|
-|`--format`|説明スタイル|`text`、、`examples``interactive`|
-|`--context`|ドメインコンテキスト|任意のドメイン(例:`react`、`security`)|
-
-### コマンドフラグの改善(`/sc:improve`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#improve-command-flags-scimprove)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--type`|改善の焦点|`quality`、、、、、`performance``maintainability``style``security`|
-|`--safe`|保守的なアプローチ|ブール値|
-|`--interactive`|ユーザーガイダンス|ブール値|
-|`--preview`|実行せずに表示する|ブール値|
-
-### タスクコマンドフラグ(`/sc:task`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#task-command-flags-sctask)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--strategy`|タスクアプローチ|`systematic`、、`agile``enterprise`|
-|`--parallel`|並列実行|ブール値|
-|`--delegate`|サブエージェントの調整|ブール値|
-
-### ワークフローコマンドフラグ(`/sc:workflow`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#workflow-command-flags-scworkflow)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--strategy`|ワークフローアプローチ|`systematic`、、`agile``enterprise`|
-|`--depth`|分析の深さ|`shallow`、、`normal``deep`|
-|`--parallel`|並列調整|ブール値|
-
-### コマンドフラグのトラブルシューティング ( `/sc:troubleshoot`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#troubleshoot-command-flags-sctroubleshoot)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--type`|問題カテゴリ|`bug`、、、、`build``performance``deployment`|
-|`--trace`|トレース分析を含める|ブール値|
-|`--fix`|修正を適用する|ブール値|
-
-### クリーンアップコマンドフラグ(`/sc:cleanup`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#cleanup-command-flags-sccleanup)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--type`|クリーンアップ対象|`code`、、、、`imports``files``all`|
-|`--safe`/`--aggressive`|清掃強度|ブール値|
-|`--interactive`|ユーザーガイダンス|ブール値|
-|`--preview`|実行せずに表示する|ブール値|
-
-### コマンドフラグの推定(`/sc:estimate`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#estimate-command-flags-scestimate)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--type`|焦点を推定する|`time`、、`effort``complexity`|
-|`--unit`|時間単位|`hours`、、`days``weeks`|
-|`--breakdown`|詳細な内訳|ブール値|
-
-### インデックスコマンドフラグ(`/sc:index`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#index-command-flags-scindex)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--type`|インデックスターゲット|`docs`、、、、`api``structure``readme`|
-|`--format`|出力形式|`md`、、`json``yaml`|
-
-### コマンドフラグを反映する ( `/sc:reflect`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#reflect-command-flags-screflect)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--type`|反射スコープ|`task`、、`session``completion`|
-|`--analyze`|分析を含める|ブール値|
-|`--validate`|完全性を検証する|ブール値|
-
-### スポーンコマンドフラグ(`/sc:spawn`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#spawn-command-flags-scspawn)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--strategy`|調整アプローチ|`sequential`、、`parallel``adaptive`|
-|`--depth`|分析の深さ|`normal`、`deep`|
-
-### Gitコマンドフラグ(`/sc:git`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#git-command-flags-scgit)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--smart-commit`|コミットメッセージを生成する|ブール値|
-|`--interactive`|ガイド付き操作|ブール値|
-
-### 選択ツールコマンドフラグ ( `/sc:select-tool`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#select-tool-command-flags-scselect-tool)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--analyze`|ツール分析|ブール値|
-|`--explain`|選択の説明|ブール値|
-
-### テストコマンドフラグ(`/sc:test`)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#test-command-flags-sctest)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--coverage`|カバー範囲を含める|ブール値|
-|`--type`|テストの種類|`unit`、、`integration``e2e`|
-|`--watch`|ウォッチモード|ブール値|
-
-## 高度な制御フラグ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#advanced-control-flags)
-
-### 範囲と焦点
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#scope-and-focus)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--scope`|分析境界|`file`、、、、`module``project``system`|
-|`--focus`|ドメインターゲティング|`performance`、、、、、、`security``quality``architecture``accessibility``testing`|
-
-### 実行制御
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#execution-control)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--concurrency [n]`|並列オペレーションを制御する|1-15|
-|`--iterations [n]`|改善サイクル|1-10|
-|`--all-mcp`|すべてのMCPサーバーを有効にする|ブール値|
-|`--no-mcp`|ネイティブツールのみ|ブール値|
-
-### システムフラグ(SuperClaude インストール)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#system-flags-superclaude-installation)
-
-|フラグ|目的|価値観|
-|---|---|---|
-|`--verbose`/`-v`|詳細ログ|ブール値|
-|`--quiet`/`-q`|出力を抑制する|ブール値|
-|`--dry-run`|操作をシミュレーションする|ブール値|
-|`--force`|チェックをスキップする|ブール値|
-|`--yes`/`-y`|自動確認|ブール値|
-|`--install-dir`|ターゲットディレクトリ|パス|
-|`--legacy`|レガシースクリプトを使用する|ブール値|
-|`--version`|バージョンを表示|ブール値|
-|`--help`|ヘルプを表示|ブール値|
-
-## 一般的な使用パターン
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#common-usage-patterns)
-
-### フロントエンド開発
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#frontend-development)
-
-```shell
-/sc:implement "responsive dashboard" --magic --c7
-/sc:design component-library --type component --format code
-/sc:test ui-components/ --magic --play
-/sc:improve legacy-ui/ --magic --morph --validate
-```
-
-### バックエンド開発
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#backend-development)
-
-```shell
-/sc:analyze api/ --focus performance --seq --think
-/sc:design payment-api --type api --format spec
-/sc:troubleshoot "API timeout" --type performance --trace
-/sc:improve auth-service --type security --validate
-```
-
-### 大規模プロジェクト
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#large-projects)
-
-```shell
-/sc:analyze . --ultrathink --all-mcp --safe-mode
-/sc:workflow enterprise-system --strategy enterprise --depth deep
-/sc:cleanup . --type all --safe --interactive
-/sc:estimate "migrate to microservices" --type complexity --breakdown
-```
-
-### 品質とメンテナンス
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#quality--maintenance)
-
-```shell
-/sc:improve src/ --type quality --safe --interactive
-/sc:cleanup imports --type imports --preview
-/sc:reflect --type completion --validate
-/sc:git commit --smart-commit
-```
-
-## フラグインタラクション
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#flag-interactions)
-
-### 互換性のある組み合わせ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#compatible-combinations)
-
-- `--think`+ `--c7`: ドキュメント付き分析
-- `--magic`+ `--play`: テスト付きのUI生成
-- `--serena`+ `--morph`: 変換によるプロジェクトメモリ
-- `--safe-mode`+ `--validate`: 最大限の安全性
-- `--loop`+ `--validate`: 検証を伴う反復的な改善
-
-### 競合するフラグ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#conflicting-flags)
-
-- `--all-mcp`個別のMCPフラグと比較(どちらか一方を使用)
-- `--no-mcp`任意のMCPフラグと比較(--no-mcpが優先)
-- `--safe`vs `--aggressive`(クリーンアップ強度)
-- `--quiet`vs `--verbose`(出力レベル)
-
-### 関係の自動有効化
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#auto-enabling-relationships)
-
-- `--safe-mode`自動的`--uc`に有効になり、`--validate`
-- `--ultrathink`すべてのMCPサーバーを自動的に有効にする
-- `--think-hard`自動的に有効になります`--seq`+`--c7`
-- `--magic`UIに重点を置いたエージェントを起動する
-
-## トラブルシューティングフラグ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#troubleshooting-flags)
-
-### よくある問題
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#common-issues)
-
-- **ツールが多すぎる**:`--no-mcp`ネイティブツールのみでテストする
-- **操作が遅すぎます**:`--uc`出力を圧縮するために追加します
-- **検証ブロッキング**:開発で`--validate`は代わりに使用してください`--safe-mode`
-- **コンテキスト圧力**:`--token-efficient`使用率が75%を超えると自動的にアクティブ化されます
-
-### デバッグフラグ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#debug-flags)
-
-```shell
-/sc:analyze . --verbose # Shows decision logic and flag activation
-/sc:select-tool "operation" --explain # Explains tool selection process
-/sc:reflect --type session --analyze # Reviews current session decisions
-```
-
-### クイックフィックス
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#quick-fixes)
-
-```shell
-/sc:analyze . --help # Shows available flags for command
-/sc:analyze . --no-mcp # Native execution only
-/sc:cleanup . --preview # Shows what would be cleaned
-```
-
-## フラグの優先ルール
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#flag-priority-rules)
-
-1. **安全第一**: `--safe-mode`> `--validate`> 最適化フラグ
-2. **明示的なオーバーライド**: ユーザーフラグ > 自動検出
-3. **深度階層**:`--ultrathink`> `--think-hard`>`--think`
-4. **MCP制御**:`--no-mcp`すべてのMCPフラグを上書きします
-5. **スコープの優先順位**: システム > プロジェクト > モジュール > ファイル
-
-## 関連リソース
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md#related-resources)
-
-- [コマンドガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md)- これらのフラグを使用するコマンド
-- [MCP サーバーガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md)- MCP フラグのアクティブ化について
-- [セッション管理](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md)- 永続セッションでのフラグの使用
\ No newline at end of file
diff --git a/docs/User-Guide-jp/mcp-servers.md b/docs/User-Guide-jp/mcp-servers.md
deleted file mode 100644
index 284a05f..0000000
--- a/docs/User-Guide-jp/mcp-servers.md
+++ /dev/null
@@ -1,319 +0,0 @@
-# SuperClaude MCP サーバーガイド 🔌
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#superclaude-mcp-servers-guide-)
-
-## 概要
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#overview)
-
-MCP(モデルコンテキストプロトコル)サーバーは、専用ツールを通じてClaude Codeの機能を拡張します。SuperClaudeは6つのMCPサーバーを統合し、タスクに応じてサーバーをいつ起動するかをClaudeに指示します。
-
-### 🔍 現実チェック
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#-reality-check)
-
-- **MCPサーバーとは**: 追加ツールを提供する外部Node.jsプロセス
-- **含まれていないもの**:SuperClaude 機能が組み込まれている
-- **アクティベーションの仕組み**: クロードは状況に応じて適切なサーバーを使用するための指示を読み上げます
-- **提供されるもの**:Claude Codeのネイティブ機能を拡張する実際のツール
-
-**コアサーバー:**
-
-- **context7** : 公式ライブラリドキュメントとパターン
-- **段階的思考**:多段階の推論と分析
-- **マジック**:モダンなUIコンポーネント生成
-- **プレイライト**:ブラウザ自動化とE2Eテスト
-- **morphllm-fast-apply** : パターンベースのコード変換
-- **serena** : セマンティックコード理解とプロジェクトメモリ
-
-## クイックスタート
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#quick-start)
-
-**セットアップの確認**:MCPサーバーは自動的に起動します。インストールとトラブルシューティングについては、[「インストールガイド」](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Getting-Started/installation.md)と[「トラブルシューティング」](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/troubleshooting.md)を参照してください。
-
-**自動アクティベーションロジック:**
-
-|リクエストに含まれるもの|アクティブ化されたサーバー|
-|---|---|
-|ライブラリのインポート、API名|**コンテキスト7**|
-|`--think`、デバッグ|**連続思考**|
-|`component`、`UI`、 フロントエンド|**魔法**|
-|`test`、、`e2e``browser`|**劇作家**|
-|複数ファイルの編集、リファクタリング|**morphllm-高速適用**|
-|大規模プロジェクト、セッション|**セレナ**|
-
-## サーバーの詳細
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#server-details)
-
-### コンテキスト7 📚
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#context7-)
-
-**目的**: 公式ライブラリドキュメントへのアクセス **トリガー**: インポートステートメント、フレームワークキーワード、ドキュメントリクエスト **要件**: Node.js 16+、APIキーなし
-
-```shell
-# Automatic activation
-/sc:implement "React authentication system"
-# → Provides official React patterns
-
-# Manual activation
-/sc:analyze auth-system/ --c7
-```
-
-### 連続思考 🧠
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#sequential-thinking-)
-
-**目的**: 構造化された多段階の推論と体系的な分析 **トリガー**: 複雑なデバッグ、`--think`フラグ、アーキテクチャ分析 **要件**: Node.js 16+、APIキーなし
-
-```shell
-# Automatic activation
-/sc:troubleshoot "API performance issues"
-# → Enables systematic root cause analysis
-
-# Manual activation
-/sc:analyze --think-hard architecture/
-```
-
-### 魔法✨
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#magic-)
-
-**目的**: 21st.dev パターンからのモダン UI コンポーネント生成 **トリガー**: UI リクエスト、`/ui`コマンド、コンポーネント開発 **要件**: Node.js 16+、TWENTYFIRST_API_KEY()
-
-```shell
-# Automatic activation
-/sc:implement "responsive dashboard component"
-# → Generates accessible UI with modern patterns
-
-# API key setup
-export TWENTYFIRST_API_KEY="your_key_here"
-```
-
-### 劇作家🎭
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#playwright-)
-
-**目的**: 実際のブラウザ自動化とE2Eテスト **トリガー**: ブラウザテスト、E2Eシナリオ、視覚的検証 **要件**: Node.js 16以上、APIキーなし
-
-```shell
-# Automatic activation
-/sc:test --type e2e "user login flow"
-# → Enables browser automation testing
-
-# Manual activation
-/sc:validate "accessibility compliance" --play
-```
-
-### morphllm-fast-apply 🔄
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#morphllm-fast-apply-)
-
-**目的**: 効率的なパターンベースのコード変換 **トリガー**: 複数ファイルの編集、リファクタリング、フレームワークの移行 **要件**: Node.js 16+、MORPH_API_KEY
-
-```shell
-# Automatic activation
-/sc:improve legacy-codebase/ --focus maintainability
-# → Applies consistent patterns across files
-
-# API key setup
-export MORPH_API_KEY="your_key_here"
-```
-
-### セレナ🧭
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#serena-)
-
-**目的**: プロジェクトメモリを使用したセマンティックコード理解 **トリガー**: シンボル操作、大規模コードベース、セッション管理 **要件**: Python 3.9+、UV パッケージマネージャー、API キーなし
-
-```shell
-# Automatic activation
-/sc:load existing-project/
-# → Builds project understanding and memory
-
-# Manual activation
-/sc:refactor "extract UserService" --serena
-```
-
-## 構成
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#configuration)
-
-**MCP 構成ファイル ( `~/.claude.json`):**
-
-```json
-{
- "mcpServers": {
- "context7": {
- "command": "npx",
- "args": ["-y", "@upstash/context7-mcp@latest"]
- },
- "sequential-thinking": {
- "command": "npx",
- "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
- },
- "magic": {
- "command": "npx",
- "args": ["@21st-dev/magic"],
- "env": {"TWENTYFIRST_API_KEY": "${TWENTYFIRST_API_KEY}"}
- },
- "playwright": {
- "command": "npx",
- "args": ["@playwright/mcp@latest"]
- },
- "morphllm-fast-apply": {
- "command": "npx",
- "args": ["@morph-llm/morph-fast-apply"],
- "env": {"MORPH_API_KEY": "${MORPH_API_KEY}"}
- },
- "serena": {
- "command": "uvx",
- "args": ["--from", "git+https://github.com/oraios/serena", "serena", "start-mcp-server", "--context", "ide-assistant"]
- }
- }
-}
-```
-
-## 使用パターン
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#usage-patterns)
-
-**サーバー制御:**
-
-```shell
-# Enable specific servers
-/sc:analyze codebase/ --c7 --seq
-
-# Disable all MCP servers
-/sc:implement "simple function" --no-mcp
-
-# Enable all servers
-/sc:design "complex architecture" --all-mcp
-```
-
-**マルチサーバー調整:**
-
-```shell
-# Full-stack development
-/sc:implement "e-commerce checkout"
-# → Sequential: workflow analysis
-# → Context7: payment patterns
-# → Magic: UI components
-# → Serena: code organization
-# → Playwright: E2E testing
-```
-
-## トラブルシューティング
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#troubleshooting)
-
-**よくある問題:**
-
-- **サーバーが接続されていません**: Node.js を確認してください: `node --version`(v16 以上が必要)
-- **Context7 が失敗しました**: キャッシュをクリアしてください:`npm cache clean --force`
-- **Magic/Morphllm エラー**: API キーがない場合に発生する可能性があります (有料サービス)
-- **サーバーのタイムアウト**: Claude Codeセッションを再起動します
-
-**クイックフィックス:**
-
-```shell
-# Reset connections
-# Restart Claude Code session
-
-# Check dependencies
-node --version # Should show v16+
-
-# Test without MCP
-/sc:command --no-mcp
-
-# Check configuration
-ls ~/.claude.json
-```
-
-**API キーの設定:**
-
-```shell
-# For Magic server (required for UI generation)
-export TWENTYFIRST_API_KEY="your_key_here"
-
-# For Morphllm server (required for bulk transformations)
-export MORPH_API_KEY="your_key_here"
-
-# Add to shell profile for persistence
-echo 'export TWENTYFIRST_API_KEY="your_key"' >> ~/.bashrc
-echo 'export MORPH_API_KEY="your_key"' >> ~/.bashrc
-```
-
-**環境変数の使用法:**
-
-- ✅ `TWENTYFIRST_API_KEY`- Magic MCP サーバー機能に必要
-- ✅ `MORPH_API_KEY`- Morphllm MCP サーバー機能に必要
-- ❌ ドキュメント内のその他の環境変数 - 例のみ、フレームワークでは使用されません
-- 📝 どちらも有料のサービスAPIキーですが、フレームワークはそれらなしでも動作します
-
-## サーバーの組み合わせ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#server-combinations)
-
-**APIキーなし(無料)** :
-
-- コンテキスト7 + シーケンシャルシンキング + 劇作家 + セレナ
-
-**1 APIキー**:
-
-- プロフェッショナルなUI開発に魔法を加える
-
-**2つのAPIキー**:
-
-- 大規模リファクタリングのために morphllm-fast-apply を追加
-
-**一般的なワークフロー:**
-
-- **学習**:コンテキスト7 + シーケンシャルシンキング
-- **Web開発**:マジック + context7 + プレイライト
-- **エンタープライズリファクタリング**:serena + morphllm + sequential-thinking
-- **複雑な分析**:シーケンシャルシンキング + コンテキスト7 + セレナ
-
-## 統合
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#integration)
-
-**SuperClaude コマンドを使用する場合:**
-
-- 分析コマンドは自動的にSequential + Serenaを使用します
-- 実装コマンドはMagic + Context7を使用する
-- テストコマンドにはPlaywright + Sequentialを使用する
-
-**動作モードの場合:**
-
-- ブレインストーミングモード:発見のためのシーケンシャル
-- タスク管理:永続性のための Serena
-- オーケストレーションモード: 最適なサーバーの選択
-
-**パフォーマンスコントロール:**
-
-- システム負荷に基づく自動リソース管理
-- 同時実行制御: `--concurrency N`(1-15)
-- 制約下での優先度ベースのサーバー選択
-
-## 関連リソース
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md#related-resources)
-
-**必読:**
-
-- [コマンドガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md)- MCPサーバーをアクティブ化するコマンド
-- [クイックスタートガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Getting-Started/quick-start.md)- MCP セットアップガイド
-
-**高度な使用法:**
-
-- [行動モード](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md)- モード-MCP調整
-- [エージェントガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md)- エージェントとMCPの統合
-- [セッション管理](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md)- Serena ワークフロー
-
-**技術リファレンス:**
-
-- [例のクックブック](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/examples-cookbook.md)- MCP ワークフローパターン
-- [技術アーキテクチャ](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Developer-Guide/technical-architecture.md)- 統合の詳細
\ No newline at end of file
diff --git a/docs/User-Guide-jp/modes.md b/docs/User-Guide-jp/modes.md
deleted file mode 100644
index 6811ef1..0000000
--- a/docs/User-Guide-jp/modes.md
+++ /dev/null
@@ -1,726 +0,0 @@
-# SuperClaude 行動モードガイド 🧠
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#superclaude-behavioral-modes-guide-)
-
-## ✅ クイック検証
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#-quick-verification)
-
-コマンドを使用してモードをテストします`/sc:`。モードはタスクの複雑さに基づいて自動的にアクティブになります。コマンドの完全なリファレンスについては、[コマンドガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md)をご覧ください。
-
-## クイックリファレンステーブル
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#quick-reference-table)
-
-|モード|目的|自動トリガー|重要な行動|最適な用途|
-|---|---|---|---|---|
-|**🧠 ブレインストーミング**|インタラクティブな発見|「ブレインストーミング」、「たぶん」、漠然とした要望|ソクラテス式の質問、要件の抽出|新しいプロジェクトの計画、不明確な要件|
-|**🔍 内省**|メタ認知分析|エラー回復、「推論の分析」|透明な思考マーカー(🤔、🎯、💡)|デバッグ、学習、最適化|
-|**📋 タスク管理**|複雑な調整|>3ステップ、>2ディレクトリ|相の崩壊、記憶の持続|多段階操作、プロジェクト管理|
-|**🎯 オーケストレーション**|インテリジェントなツール選択|複数のツールを使用した操作、高いリソース使用率|最適なツールルーティング、並列実行|複雑な分析、パフォーマンスの最適化|
-|**⚡ トークン効率**|圧縮通信|コンテキスト使用率が高い、`--uc`フラグ|シンボルシステム、推定30~50%のトークン削減|リソースの制約、大規模な操作|
-
----
-
-## はじめに(2分の概要)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#getting-started-2-minute-overview)
-
-**モードは動作指示を通じてアクティブ化されます**- Claude Code はコンテキスト ファイルを読み取り、タスクのパターンと複雑さに基づいてどのモード動作を採用するかを決定します。
-
-**簡単な例:**
-
-```shell
-# Automatic activation examples
-/sc:brainstorm "mobile app" # → Socratic discovery questions
-/sc:implement "auth system" # → Multi-phase coordination
-"--uc analyze large-codebase/" # → Compressed symbol output
-```
-
-**手動フラグを使用する場合:**
-
-- 特定の動作が必要: `--brainstorm`、、`--introspect``--uc`
-- 学習/デバッグのための自動検出をオーバーライドする
-- 特定の制約(メモリ、時間、明瞭性)に合わせて最適化する
-
----
-
-## モードの詳細
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#mode-details)
-
-### 🧠 ブレインストーミングモード - インタラクティブな発見
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#-brainstorming-mode---interactive-discovery)
-
-**目的**: 共同作業による発見を通じて、漠然としたアイデアを構造化された要件に変換します。
-
-**自動アクティベーショントリガー:**
-
-- 漠然としたプロジェクトリクエスト:「...を構築したい」、「...を作成しようと考えている」
-- 探索キーワード: ブレインストーミング、探索、議論、理解、不明
-- 不確実性指標:「たぶん」、「おそらく」、「できるかもしれない」
-- 手動フラグ: `--brainstorm`、`--bs`
-
-**行動の変化:**
-
-- **ソクラテス式質問**:隠れた要件を明らかにするために掘り下げた質問をする
-- **非推定的アプローチ**:推定を避け、発見の方向性を導く
-- **協力的なパートナーシップ**:指示的な相談ではなく、探索的に協力します
-- **要件統合**:洞察を構造化された技術概要に変換します
-- **クロスセッションメモリ**:フォローアップの議論のために発見のコンテキストを維持する
-
-**経験例:**
-
-```
-Standard Approach: "I'll build a user authentication system with JWT tokens..."
-Brainstorming Approach:
-"🤔 Let's explore this together:
- - What specific user problems does auth solve for your app?
- - Who are your users and what's their technical comfort level?
- - Any existing systems or social logins to integrate with?
- - What security/compliance requirements do you have?
- 📝 Outcome: Detailed auth requirements brief ready for implementation"
-```
-
-#### 成功基準
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#success-criteria)
-
-- [ ] すぐに解決策を提示するのではなく、質問で応答する
-- [ ] 質問はユーザーのニーズ、技術的制約、ビジネス目標を探ります
-- [ ] 発見プロセス全体を通じて協力的な姿勢を維持する
-- [ ] 結果として構造化された要件または技術概要を作成します
-
-**検証:** `/sc:brainstorm "web app"`ユーザー、機能、テクノロジーについて質問する必要があります。
-**テスト:**漠然としたリクエストは、推測ではなく発見のための質問を引き起こす必要があります。
-**チェック:**モードは、同じ会話内のフォローアップの質問でも維持される必要があります。
-
-**最適な組み合わせ:**
-
-- **→ タスク管理**:要件の発見 → 体系的な実装計画
-- **→ オーケストレーション**:要件の明確化 → 実装に最適なツールの選択
-- **手動オーバーライド**: `--brainstorm`「明確な」要件であっても強制的に検出するために使用します
-
----
-
-### 🔍 内省モード - メタ認知分析
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#-introspection-mode---meta-cognitive-analysis)
-
-**目的**: 学習の最適化と透明な意思決定のための推論プロセスを公開します。
-
-**自動アクティベーショントリガー:**
-
-- 自己分析の要求:「自分の推論を分析する」、「決定を振り返る」
-- エラー回復シナリオと調査を必要とする予期しない結果
-- 複数の実行可能なアプローチによる複雑な問題解決
-- 最適化の機会のためのパターン認識の必要性
-- 手動フラグ:`--introspect`
-
-**行動の変化:**
-
-- **推論の透明性**: 思考プロセスを明確なマーカーで公開します (🤔、🎯、⚡、📊、💡)
-- **意思決定分析**:選択ロジックを評価し、代替アプローチを検討する
-- **パターン認識**:繰り返される行動と改善の機会を特定します
-- **メタ学習**:継続的なフレームワーク改善のための洞察を抽出
-- **フレームワークコンプライアンス**: SuperClaude原則と品質ゲートに照らしてアクションを検証します
-
-**経験例:**
-
-```
-Standard Approach: "I'll analyze this code structure and suggest improvements..."
-Introspective Approach:
-"🧠 Meta-Analysis: Why did I choose structural analysis over functional flow?
- 🎯 Decision Logic: Saw class hierarchy → assumed OOP pattern dominance
- 🔄 Alternative Considered: Data flow analysis might reveal hidden dependencies
- 📊 Evidence Check: File imports suggest functional composition, not OOP
- 💡 Learning: Need to analyze imports before choosing analysis strategy
- ⚡ Correction: Switching to functional flow analysis approach"
-```
-
-**最適な組み合わせ:**
-
-- **→ タスク管理**: 複雑なフェーズの決定に透明な推論を提供します
-- **任意のモード**: 他のモードの操作に推論の透明性レイヤーを追加します
-- **手動オーバーライド**:`--introspect`学習セッションやワークフローのデバッグに使用します
-
----
-
-### 📋 タスク管理モード - 複雑な調整
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#-task-management-mode---complex-coordination)
-
-**目的**: 複数ステップの操作のためのセッション永続性を備えた階層的なタスク構成。
-
-**自動アクティベーショントリガー:**
-
-- 3 つ以上の調整されたステップを必要とする操作
-- 複数のファイル/ディレクトリ スコープ (ディレクトリが 2 つ以上、またはファイル数が 3 つ以上)
-- フェーズとチェックポイントを必要とする複雑な依存関係
-- 品質改善の要望:磨き、洗練、強化
-- 手動フラグ: `--task-manage`、`--delegate`
-
-**行動の変化:**
-
-- **階層的計画**:複雑な作業を計画→フェーズ→タスク→ToDo構造に分割します
-- **セッションの永続性**: 中断があってもプロジェクトのコンテキストと進行状況を維持します
-- **メモリ統合**: 状態保存のために write_memory/read_memory を使用する
-- **進捗オーケストレーション**: 追跡のためにメモリ更新とTodoWriteを調整する
-- **品質ゲート**:フェーズ間の体系的な検証チェックポイントを実装します
-
-**経験例:**
-
-```
-Standard Approach: "I'll implement user authentication..." → Direct implementation
-Task Management Approach:
-"📋 Multi-Phase Implementation Plan:
- 🎯 Phase 1: Security Requirements Analysis (Session 1)
- 🎯 Phase 2: API Design & Documentation (Session 2)
- 🎯 Phase 3: Implementation & Testing (Session 3-4)
- 🎯 Phase 4: Integration & Validation (Session 5)
- 💾 Session persistence: Resume context automatically
- ✓ Quality gates: Validation before each phase transition"
-```
-
-**最適な組み合わせ:**
-
-- **ブレインストーミング→**:要件発見と体系的な実装
-- **+ オーケストレーション**: 最適なツール選択によるタスク調整
-- **+ イントロスペクション**:複雑なフェーズの決定のための透過的な推論
-
----
-
-### 🎯 オーケストレーションモード - インテリジェントなツール選択
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#-orchestration-mode---intelligent-tool-selection)
-
-**目的**: インテリジェントなツールルーティングと並列調整を通じてタスクの実行を最適化します。
-
-**自動アクティベーショントリガー:**
-
-- 高度な調整を必要とするマルチツール操作
-- パフォーマンス制約(リソース使用量が多い)
-- 並列実行の機会(3つ以上の独立したファイル/操作)
-- 複数の有効なツールアプローチによる複雑なルーティング決定
-
-**行動の変化:**
-
-- **インテリジェントツールルーティング**:各タスクタイプに最適なMCPサーバーとネイティブツールを選択します。
-- **リソース認識**: システムの制約と可用性に基づいてアプローチを適応させます
-- **並列最適化**: 同時実行のための独立した操作を識別します
-- **調整の焦点**:調整された実行を通じてツールの選択と使用を最適化します
-- **アダプティブフォールバック**: 優先オプションが利用できない場合にツールを適切に切り替えます
-
-**経験例:**
-
-```
-Standard Approach: Sequential file-by-file analysis and editing
-Orchestration Approach:
-"🎯 Multi-Tool Coordination Strategy:
- 🔍 Phase 1: Serena (semantic analysis) + Sequential (architecture review)
- ⚡ Phase 2: Morphllm (pattern edits) + Magic (UI components)
- 🧪 Phase 3: Playwright (testing) + Context7 (documentation patterns)
- 🔄 Parallel execution: 3 tools working simultaneously
-\"
-```
-
-**最適な組み合わせ:**
-
-- **タスク管理 →** : 複雑な多段階計画のためのツール調整を提供します
-- **+ トークン効率**: 圧縮通信による最適なツール選択
-- **複雑なタスク**: インテリジェントなツールルーティングを追加して実行を強化
-
----
-
-### ⚡ トークン効率モード - 圧縮通信
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#-token-efficiency-mode---compressed-communication)
-
-**目的**: 情報の品質を維持しながら、シンボル システムを通じて推定 30 ~ 50% のトークン削減を実現します。
-
-**自動アクティベーショントリガー:**
-
-- 高いコンテキストの使用が限界に近づいています
-- 資源効率が求められる大規模運用
-- ユーザー明示フラグ: `--uc`、`--ultracompressed`
-- 複数の出力を持つ複雑な分析ワークフロー
-
-**行動の変化:**
-
-- **シンボルコミュニケーション**: ロジックフロー、ステータス、技術ドメインに視覚的なシンボルを使用します
-- **技術略語**:繰り返される技術用語のコンテキスト認識圧縮
-- **構造化された密度**: 冗長な段落よりも箇条書き、表、簡潔な書式
-- **情報保存**: 圧縮しても95%以上の情報品質を維持
-- **構造化されたフォーマット**: 明確さとタスクの完了のために整理されています
-
-**経験例:**
-
-```
-Standard Approach: "The authentication system implementation shows a security vulnerability in the user validation function that needs immediate attention..."
-Token Efficient Approach:
-"🛡️ Security Alert:
- auth.js:45 → user val() → critical vuln
- 📊 Impact: ❌ token bypass possible
- ⚡ Action: fix validation + audit ∵ high sev
- 🔧 Est: 2h impl + 1h test"
-```
-
-**最適な組み合わせ:**
-
-- **任意のモード**: モード固有の動作を維持しながら圧縮レイヤーを追加します
-- **オーケストレーション →** : 圧縮されたツール調整とステータス更新
-- **手動オーバーライド**:`--uc`コンテキストのプレッシャーや効率が優先される場合に使用します
-
----
-
-### 🎨 標準モード - バランスのとれたデフォルト
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#-standard-mode---balanced-default)
-
-**目的**: 簡単な開発タスクに対して明確でプロフェッショナルなコミュニケーションを提供します。
-
-**自動アクティベーショントリガー:**
-
-- 複雑さの指標のない、シンプルで明確に定義されたタスク
-- 明確な要件を備えた単一ファイル操作
-- 基本的な説明と標準的な開発ワークフロー
-- 他のモードトリガーは検出されません(デフォルトのフォールバック)
-
-**行動の変化:**
-
-- **プロフェッショナルなコミュニケーション**:明確で簡潔な技術用語
-- **中程度の詳細**: ほとんどの開発タスクに適したバランスの取れた情報の深さ
-- **標準ツール選択**: ネイティブのClaude機能と基本ツールを使用
-- **品質重視**: 複雑なオーケストレーションのオーバーヘッドなしでコードの品質を維持
-- **応答的な適応**:複雑さが増すと、特化したモードに切り替える準備ができています
-
-**経験例:**
-
-```
-Standard Approach: Consistent, professional baseline for all tasks
-"I'll implement the login function with proper error handling:
-
- 1. Validate user input (email format, password requirements)
- 2. Authenticate against database with secure hashing
- 3. Generate JWT token with appropriate expiration
- 4. Return success response with user data
-
- The implementation will follow security best practices and include comprehensive error handling."
-```
-
-**最適な組み合わせ:**
-
-- **→ 任意のモード**: 他のモードを強化する基準として機能します
-- **モード切り替え**: 必要に応じて自動的に特殊モードに切り替えます
-- **明確さの優先**: 最適化よりも分かりやすいコミュニケーションが重要な場合
-
----
-
-## 高度な使用法
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#advanced-usage)
-
-### モードの組み合わせ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#mode-combinations)
-
-**マルチモードワークフロー:**
-
-```shell
-# Discovery → Planning → Implementation
-/sc:brainstorm "microservices architecture" --task-manage
-# → Brainstorming: requirement discovery
-# → Task Management: multi-phase coordination
-
-# Analysis with transparency and efficiency
-/sc:analyze legacy-system/ --introspect --uc
-# → Introspection: transparent reasoning
-# → Token Efficiency: compressed output
-```
-
-### 手動モード制御
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#manual-mode-control)
-
-**特定の動作を強制する:**
-
-- `--brainstorm`: あらゆるタスクで共同発見を強制
-- `--introspect`: あらゆるモードに推論の透明性を追加
-- `--task-manage`: 階層的な調整を可能にする
-- `--orchestrate`: ツール選択と並列実行を最適化
-- `--uc`: 効率化のために通信を圧縮する
-
-**オーバーライドの例:**
-
-```shell
-# Force brainstorming on "clear" requirements
-/sc:implement "user login" --brainstorm
-
-# Add reasoning transparency to debugging
-# 認証問題を透明な推理でデバッグ
-
-# Enable task management for simple operations
-# システマチックなタスク管理でスタイルファイルを更新
-```
-
-### モードの境界と優先順位
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#mode-boundaries-and-priority)
-
-**モードがアクティブになると:**
-
-1. **複雑さの閾値**: >3ファイル → タスク管理
-2. **リソースの圧力**:コンテキスト使用率が高い → トークン効率
-3. **複数のツールが必要**: 複雑な分析 → オーケストレーション
-4. **不確実性**:漠然とした要件 → ブレインストーミング
-5. **エラー回復**:問題 → イントロスペクション
-
-**優先ルール:**
-
-- **安全第一**:品質と検証は常に効率よりも優先されます
-- **ユーザーの意図**: 手動フラグは自動検出を上書きします
-- **コンテキスト適応**: 複雑さに基づいてモードをスタック
-- **リソース管理**:プレッシャー下では効率モードが活性化する
-
----
-
-## 実世界の例
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#real-world-examples)
-
-### 完全なワークフローの例
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#complete-workflow-examples)
-
-**新規プロジェクト開発:**
-
-```shell
-# Phase 1: Discovery (Brainstorming Mode auto-activates)
-"I want to build a productivity app"
-→ 🤔 Socratic questions about users, features, platform choice
-→ 📝 Structured requirements brief
-
-# Phase 2: Planning (Task Management Mode auto-activates)
-/sc:implement "core productivity features"
-→ 📋 Multi-phase breakdown with dependencies
-→ 🎯 Phase coordination with quality gates
-
-# Phase 3: Implementation (Orchestration Mode coordinates tools)
-/sc:implement "frontend and backend systems"
-→ 🎯 Magic (UI) + Context7 (patterns) + Sequential (architecture)
-→ ⚡ Parallel execution optimization
-```
-
-**複雑な問題のデバッグ:**
-
-```shell
-# Problem analysis (Introspection Mode auto-activates)
-"Users getting intermittent auth failures"
-→ 🤔 Transparent reasoning about potential causes
-→ 🎯 Hypothesis formation and evidence gathering
-→ 💡 Pattern recognition across similar issues
-
-# Systematic resolution (Task Management coordinates)
-# 認証システムを包括的に修正
-→ 📋 Phase 1: Root cause analysis
-→ 📋 Phase 2: Solution implementation
-→ 📋 Phase 3: Testing and validation
-```
-
-### モードの組み合わせパターン
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#mode-combination-patterns)
-
-**非常に複雑なシナリオ:**
-
-```shell
-# Large refactoring with multiple constraints
-/sc:improve legacy-system/ --introspect --uc --orchestrate
-→ 🔍 Transparent reasoning (Introspection)
-→ ⚡ Compressed communication (Token Efficiency)
-→ 🎯 Optimal tool coordination (Orchestration)
-→ 📋 Systematic phases (Task Management auto-activates)
-```
-
----
-
-## クイックリファレンス
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#quick-reference)
-
-### モード起動パターン
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#mode-activation-patterns)
-
-|トリガータイプ|入力例|モードが有効|主要な動作|
-|---|---|---|---|
-|**漠然とした要求**|「アプリを作りたい」|🧠 ブレインストーミング|ソクラテス式の発見的質問|
-|**複雑なスコープ**|>3 つのファイルまたは >2 つのディレクトリ|📋 タスク管理|位相調整|
-|**マルチツールの必要性**|分析 + 実装|🎯 オーケストレーション|ツールの最適化|
-|**エラー回復**|「期待通りに動作していません」|🔍 内省|透明な推論|
-|**リソースの圧力**|高コンテキスト使用|⚡ トークン効率|シンボル圧縮|
-|**簡単なタスク**|「この機能を修正する」|🎨 標準|明確で直接的なアプローチ|
-
-### 手動オーバーライドコマンド
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#manual-override-commands)
-
-```shell
-# Force specific mode behaviors
-/sc:command --brainstorm # Collaborative discovery
-/sc:command --introspect # Reasoning transparency
-/sc:command --task-manage # Hierarchical coordination
-/sc:command --orchestrate # Tool optimization
-/sc:command --uc # Token compression
-
-# Combine multiple modes
-/sc:command --introspect --uc # Transparent + efficient
-/sc:command --task-manage --orchestrate # Coordinated + optimized
-```
-
----
-
-## トラブルシューティング
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#troubleshooting)
-
-トラブルシューティングのヘルプについては、以下を参照してください。
-
-- [よくある問題](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/common-issues.md)- よくある問題に対するクイック修正
-- [トラブルシューティングガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/troubleshooting.md)- 包括的な問題解決
-
-### よくある問題
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#common-issues)
-
-- **モードがアクティブ化されていません**: 手動フラグを使用してください: `--brainstorm`、、`--introspect``--uc`
-- **間違ったモードがアクティブです**: リクエスト内の複雑なトリガーとキーワードを確認してください
-- **予期しないモード切り替え**:タスクの進行に基づく通常の動作
-- **実行への影響**: モードはツールの使用を最適化するものであり、実行には影響しないはずです。
-- **モードの競合**:[フラグガイドでフラグの優先順位ルールを確認してください](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md)
-
-### 即時修正
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#immediate-fixes)
-
-- **特定のモードを強制**:`--brainstorm`またはのような明示的なフラグを使用する`--task-manage`
-- **リセットモードの動作**: モード状態をリセットするには、Claude Code セッションを再起動します。
-- **モードインジケーターを確認する**: 応答に🤔、🎯、📋の記号があるかどうかを確認します
-- **複雑さを検証**: 単純なタスクは標準モードを使用し、複雑なタスクは自動的に切り替わります
-
-### モード固有のトラブルシューティング
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#mode-specific-troubleshooting)
-
-**ブレインストーミングモードの問題:**
-
-```shell
-# Problem: Mode gives solutions instead of asking questions
-# Quick Fix: Check request clarity and use explicit flag
-/sc:brainstorm "web app" --brainstorm # Force discovery mode
-"I have a vague idea about..." # Use uncertainty language
-"Maybe we could build..." # Trigger exploration
-```
-
-**タスク管理モードの問題:**
-
-```shell
-# Problem: Simple tasks getting complex coordination
-# Quick Fix: Reduce scope or use simpler commands
-/sc:implement "function" --no-task-manage # Disable coordination
-/sc:troubleshoot bug.js # Use basic commands
-# Check if task really is complex (>3 files, >2 directories)
-```
-
-**トークン効率モードの問題:**
-
-```shell
-# Problem: Output too compressed or unclear
-# Quick Fix: Disable compression for clarity
-/sc:command --no-uc # Disable compression
-/sc:command --verbose # Force detailed output
-# Use when clarity is more important than efficiency
-```
-
-**イントロスペクションモードの問題:**
-
-```shell
-# Problem: Too much meta-commentary, not enough action
-# Quick Fix: Disable introspection for direct work
-/sc:command --no-introspect # Direct execution
-# Use introspection only for learning and debugging
-```
-
-**オーケストレーション モードの問題:**
-
-```shell
-# Problem: Tool coordination causing confusion
-# Quick Fix: Simplify tool usage
-/sc:command --no-mcp # Native tools only
-/sc:command --simple # Basic execution
-# Check if task complexity justifies orchestration
-```
-
-### エラーコードリファレンス
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#error-code-reference)
-
-|モードエラー|意味|クイックフィックス|
-|---|---|---|
-|**B001**|ブレインストーミングが起動できませんでした|`--brainstorm`明示的なフラグを使用する|
-|**T001**|タスク管理のオーバーヘッド|`--no-task-manage`簡単なタスクに使用する|
-|**U001**|トークン効率が強すぎる|使用`--verbose`または`--no-uc`|
-|**I001**|イントロスペクションモードが停止しました|`--no-introspect`直接行動に使う|
-|**O001**|オーケストレーション調整に失敗|使用`--no-mcp`または`--simple`|
-|**M001**|モードの競合が検出されました|フラグの優先順位のルールを確認する|
-|**M002**|モード切り替えループ|状態をリセットするにはセッションを再起動してください|
-|**M003**|モードが認識されません|SuperClaudeを更新するかスペルをチェックする|
-
-### プログレッシブサポートレベル
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#progressive-support-levels)
-
-**レベル 1: クイックフィックス (< 2 分)**
-
-- 自動モード選択を無効にするには手動フラグを使用します
-- タスクの複雑さが期待されるモードの動作と一致しているかどうかを確認する
-- Claude Codeセッションを再起動してみてください
-
-**レベル2: 詳細なヘルプ(5~15分)**
-
-```shell
-# Mode-specific diagnostics
-/sc:help modes # List all available modes
-/sc:reflect --type mode-status # Check current mode state
-# Review request complexity and triggers
-```
-
-- モードのインストールに関する問題については、[一般的な問題ガイドを](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/common-issues.md)参照してください。
-
-**レベル3: 専門家によるサポート(30分以上)**
-
-```shell
-# Deep mode analysis
-SuperClaude install --diagnose
-# Check mode activation patterns
-# Review behavioral triggers and thresholds
-```
-
-- 行動モード分析については[診断リファレンスガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/diagnostic-reference.md)を参照してください
-
-**レベル4: コミュニティサポート**
-
-- [GitHub Issues](https://github.com/SuperClaude-Org/SuperClaude_Framework/issues)でのモードの問題の報告[](https://github.com/SuperClaude-Org/SuperClaude_Framework/issues)
-- 予期しないモード動作の例を含める
-- 望ましいモードと実際のモードのアクティベーションを説明する
-
-### 成功の検証
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#success-validation)
-
-モード修正を適用した後、次のようにテストします。
-
-- [ ] シンプルなリクエストには標準モード(明確で直接的な応答)を使用します
-- [ ] 複雑な要求は適切なモード(調整、推論)を自動的にアクティブ化します
-- [ ] 手動フラグは自動検出を正しく上書きします
-- [ ] モードインジケーター(🤔、🎯、📋)は予想通りに表示されます
-- [ ] さまざまなモードでパフォーマンスは良好です
-
-## クイックトラブルシューティング(レガシー)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#quick-troubleshooting-legacy)
-
-- **モードがアクティブ化されない**→手動フラグを使用: `--brainstorm`、、`--introspect``--uc`
-- **間違ったモードがアクティブです**→ リクエスト内の複雑なトリガーとキーワードを確認してください
-- **予期せぬモード切り替え**→ タスクの進行に基づく通常の動作
-- **実行への影響**→ モードはツールの使用を最適化するものであり、実行には影響しないはずです
-- **モードの競合→**[フラグガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md)でフラグの優先順位ルールを確認してください[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md)
-
-## よくある質問
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#frequently-asked-questions)
-
-**Q: どのモードがアクティブになっているかはどうすればわかりますか?** A: 通信パターンで次のインジケーターを確認してください。
-
-- 🤔発見の質問 → ブレインストーミング
-- 🎯 推論の透明性 → 内省
-- フェーズの内訳 → タスク管理
-- ツール調整 → オーケストレーション
-- シンボル圧縮 → トークン効率
-
-**Q: 特定のモードを強制できますか?** A: はい、手動フラグを使用して自動検出をオーバーライドします。
-
-```shell
-/sc:command --brainstorm # Force discovery
-/sc:command --introspect # Add transparency
-/sc:command --task-manage # Enable coordination
-/sc:command --uc # Compress output
-```
-
-**Q: モードは実行に影響しますか?** A: モードは調整を通じてツールの使用を最適化します。
-
-- **トークン効率**: 30~50%のコンテキスト削減
-- **オーケストレーション**:並列処理
-- **タスク管理**:体系的な計画を通じて手戻りを防止
-
-**Q: モードは連携して動作しますか?** A: はい、モードは互いに補完し合うように設計されています。
-
-- **タスク管理は**他のモードを調整します
-- **トークン効率は**あらゆるモードの出力を圧縮する
-- **イントロスペクションは**あらゆるワークフローに透明性をもたらします
-
----
-
-## まとめ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#summary)
-
-SuperClaude の 5 つの行動モードは、ユーザーのニーズに自動的に適合する**インテリジェントな適応システムを作成します。**
-
-- **🧠 ブレインストーミング**:漠然としたアイデアを明確な要件に変換する
-- **🔍 イントロスペクション**:学習とデバッグのための透過的な推論を提供します
-- **📋 タスク管理**:複雑な複数ステップの操作を調整します
-- **🎯 オーケストレーション**: ツールの選択と並列実行を最適化します
-- **⚡ トークン効率**: 明瞭さを保ちながらコミュニケーションを圧縮する
-- **🎨 標準**: 単純なタスクに対してプロフェッショナルな基準を維持します
-
-**重要な洞察**:モードについて考える必要はありません。モードは透過的に動作し、開発エクスペリエンスを向上させます。達成したいことを説明するだけで、SuperClaudeはニーズに合わせてアプローチを自動的に調整します。
-
----
-
-## 関連ガイド
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/modes.md#related-guides)
-
-**学習の進捗:**
-
-**🌱 エッセンシャル(第1週)**
-
-- [クイックスタートガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Getting-Started/quick-start.md)- モードの有効化例
-- [コマンドリファレンス](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md)- コマンドは自動的にモードをアクティブ化します
-- [インストールガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Getting-Started/installation.md)- 動作モードの設定
-
-**🌿中級(第2~3週)**
-
-- [エージェントガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/agents.md)- モードとスペシャリストの連携方法
-- [フラグガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/flags.md)- 手動モードの制御と最適化
-- [例文集](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/examples-cookbook.md)- モードパターンの実践
-
-**🌲 上級(2ヶ月目以降)**
-
-- [MCP サーバー](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md)- 拡張機能を備えたモード統合
-- [セッション管理](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md)- タスク管理モードのワークフロー
-- [はじめに](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Getting-Started/quick-start.md)- モードの使用パターン
-
-**🔧 エキスパート**
-
-- [技術アーキテクチャ](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Developer-Guide/technical-architecture.md)- モード実装の詳細
-- [コードの貢献](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Developer-Guide/contributing-code.md)- モードの機能を拡張する
-
-**モード固有のガイド:**
-
-- **ブレインストーミング**:[要件発見パターン](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/Reference/examples-cookbook.md#requirements)
-- **タスク管理**:[セッション管理ガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md)
-- **オーケストレーション**: [MCP サーバー ガイド](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/mcp-servers.md)
-- **トークン効率**:[コマンドの基礎](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/commands.md#token-efficiency)
\ No newline at end of file
diff --git a/docs/User-Guide-jp/session-management.md b/docs/User-Guide-jp/session-management.md
deleted file mode 100644
index e9c9fe6..0000000
--- a/docs/User-Guide-jp/session-management.md
+++ /dev/null
@@ -1,414 +0,0 @@
-# セッション管理ガイド
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#session-management-guide)
-
-SuperClaude は、Serena MCP サーバーを通じて永続的なセッション管理を提供し、Claude Code の会話全体にわたる真のコンテキスト保存と長期的なプロジェクト継続性を実現します。
-
-## 永続メモリを使用したコアセッションコマンド
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#core-session-commands-with-persistent-memory)
-
-### `/sc:load`- 永続メモリによるコンテキストの読み込み
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#scload---context-loading-with-persistent-memory)
-
-**目的**: 以前のセッションからのプロジェクトコンテキストと永続メモリを使用してセッションを初期化します。MCP
-**統合**: Serena MCP をトリガーして、保存されたプロジェクトメモリを読み取ります。
-**構文**:`/sc:load [project_path]`
-
-**何が起こるのですか**:
-
-- Serena MCPは以前のセッションから永続メモリファイルを読み取ります
-- プロジェクトのコンテキストは保存されたメモリから復元されます
-- 過去の決定、パターン、進捗状況が読み込まれます
-- セッション状態は履歴コンテキストで初期化されます
-
-**ユースケース**:
-
-```shell
-# Load existing project context from persistent memory
-/sc:load src/
-
-# Resume specific project work with full history
-/sc:load "authentication-system"
-
-# Initialize with codebase analysis and previous insights
-/sc:load . --analyze
-```
-
-### `/sc:save`- メモリへのセッションの永続性
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#scsave---session-persistence-to-memory)
-
-**目的**: 現在のセッション状態と決定を永続メモリ
-**MCP に保存します。統合**: Serena MCP をトリガーしてメモリ ファイルに書き込みます。
-**構文**:`/sc:save "session_description"`
-
-**何が起こるのですか**:
-
-- 現在の状況と決定はセレナのメモリに書き込まれます
-- プロジェクトの状態と進捗は会話を通じて維持されます
-- 重要な洞察とパターンは将来のセッションのために保存されます
-- セッション概要はタイムスタンプ付きで作成され、検索に利用できます
-
-**ユースケース**:
-
-```shell
-# Save completed feature work for future reference
-/sc:save "user authentication implemented with JWT"
-
-# Checkpoint during complex work
-/sc:save "API design phase complete, ready for implementation"
-
-# Store architectural decisions permanently
-/sc:save "microservices architecture decided, service boundaries defined"
-```
-
-### `/sc:reflect`- メモリコンテキストによる進捗状況の評価
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#screflect---progress-assessment-with-memory-context)
-
-**目的**: 保存されたメモリに対して現在の進行状況を分析し、セッションの完全性を検証する
-**MCP 統合**: Serena MCP を使用して、保存されたメモリと現在の状態を比較する
-**構文**:`/sc:reflect [--scope project|session]`
-
-**何が起こるのですか**:
-
-- セレナMCPは過去の記憶と現在の文脈を読み取ります
-- 進捗は保存された目標とマイルストーンに対して評価されます
-- 歴史的背景に基づいてギャップと次のステップが特定される
-- セッションの完全性はプロジェクトメモリに対して検証されます
-
-**ユースケース**:
-
-```shell
-# Assess project progress against stored milestones
-/sc:reflect --scope project
-
-# Validate current session completeness
-/sc:reflect
-
-# Check if ready to move to next phase based on memory
-/sc:reflect --scope session
-```
-
-## 永続メモリアーキテクチャ
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#persistent-memory-architecture)
-
-### Serena MCP が真の永続性を実現する方法
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#how-serena-mcp-enables-true-persistence)
-
-**メモリストレージ**:
-
-- 構造化メモリファイルとして保存されるセッションコンテキスト
-- プロジェクトの決定とアーキテクチャパターンは永久に保存されます
-- コード分析の結果と洞察は会話を通じて保持されます
-- 進捗状況の追跡とマイルストーンのデータは長期にわたって維持されます
-
-**セッション間の継続性**:
-
-- 以前のセッションのコンテキストが新しい会話で自動的に利用可能
-- 決定と根拠は会話を通じて保存され、アクセス可能
-- 過去のパターンと解決策からの学習を維持
-- 一貫したプロジェクト理解が永久に維持される
-
-**メモリタイプ**:
-
-- **プロジェクトの思い出**:長期プロジェクトの文脈とアーキテクチャ
-- **セッションの記憶**:具体的な会話の結果と決定
-- **パターンメモリ**:再利用可能なソリューションとアーキテクチャパターン
-- **進捗の思い出**:マイルストーンの追跡と完了ステータス
-
-## 永続性を備えたセッションライフサイクルパターン
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#session-lifecycle-patterns-with-persistence)
-
-### 新しいプロジェクトの初期化
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#new-project-initialization)
-
-```shell
-# 1. Start fresh project
-/sc:brainstorm "e-commerce platform requirements"
-
-# 2. Save initial decisions to persistent memory
-/sc:save "project scope and requirements defined"
-
-# 3. Begin implementation planning
-/sc:workflow "user authentication system"
-
-# 4. Save architectural decisions permanently
-/sc:save "auth architecture: JWT + refresh tokens + rate limiting"
-```
-
-### 既存の作業の再開(クロス会話)
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#resuming-existing-work-cross-conversation)
-
-```shell
-# 1. Load previous context from persistent memory
-/sc:load "e-commerce-project"
-
-# 2. Assess current state against stored progress
-/sc:reflect --scope project
-
-# 3. Continue with next phase using stored context
-/sc:implement "payment processing integration"
-
-# 4. Save progress checkpoint to memory
-/sc:save "payment system integrated with Stripe API"
-```
-
-### 長期プロジェクト管理
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#long-term-project-management)
-
-```shell
-# Weekly checkpoint pattern with persistence
-/sc:load project-name
-/sc:reflect --scope project
-# ... work on features ...
-/sc:save "week N progress: features X, Y, Z completed"
-
-# Phase completion pattern with memory
-/sc:reflect --scope project
-/sc:save "Phase 1 complete: core authentication and user management"
-/sc:workflow "Phase 2: payment and order processing"
-```
-
-## クロス会話の継続性
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#cross-conversation-continuity)
-
-### 粘り強く新しい会話を始める
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#starting-new-conversations-with-persistence)
-
-新しい Claude Code 会話を開始すると、永続メモリ システムによって次のことが可能になります。
-
-1. **自動コンテキスト復元**
-
- ```shell
- /sc:load project-name
- # Automatically restores all previous context, decisions, and progress
- ```
-
-2. **進歩の継続**
-
- - 以前のセッションの決定はすぐに利用可能
- - アーキテクチャパターンとコードの洞察は保存されます
- - プロジェクトの履歴と根拠が維持される
-3. **インテリジェントなコンテキスト構築**
-
- - Serena MCPは、現在の作業に基づいて関連するメモリを提供します
- - 過去のソリューションとパターンが新しい実装に影響を与える
- - プロジェクトの進捗状況が追跡され、理解される
-
-### メモリ最適化
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#memory-optimization)
-
-**有効なメモリ使用量**:
-
-- 説明的かつ検索可能なメモリ名を使用する
-- プロジェクトのフェーズとタイムスタンプのコンテキストを含める
-- 特定の機能やアーキテクチャ上の決定を参照する
-- 将来の検索を直感的にする
-
-**記憶内容戦略**:
-
-- 結果だけでなく、意思決定と根拠も保存する
-- 検討した代替アプローチを含める
-- 統合パターンと依存関係を文書化する
-- 学習内容と洞察を将来の参考のために保存する
-
-**メモリライフサイクル管理**:
-
-- 古くなったメモリの定期的なクリーンアップ
-- 関連するセッション記憶の統合
-- 完了したプロジェクトフェーズのアーカイブ
-- 時代遅れのアーキテクチャ上の決定の削減
-
-## 永続セッションのベストプラクティス
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#best-practices-for-persistent-sessions)
-
-### セッション開始プロトコル
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#session-start-protocol)
-
-1. `/sc:load`既存のプロジェクトの場合は常に
-2. `/sc:reflect`記憶から現在の状態を理解するために使用する
-3. 永続的なコンテキストと保存されたパターンに基づいて作業を計画する
-4. 過去の決定とアーキテクチャの選択に基づいて構築する
-
-### セッション終了プロトコル
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#session-end-protocol)
-
-1. `/sc:reflect`保存された目標に対する完全性を評価するために使用します
-2. 重要な決定を`/sc:save`将来のセッションのために保存する
-3. 次のステップと未解決の質問を記憶に記録する
-4. 将来のシームレスな継続のためにコンテキストを保存する
-
-### 記憶品質の維持
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#memory-quality-maintenance)
-
-- 簡単に思い出せるように、分かりやすく説明的なメモリ名を使用する
-- 決定事項と代替アプローチに関する背景情報を含める
-- 特定のコードの場所とパターンを参照する
-- セッション間でメモリ構造の一貫性を維持する
-
-## 他のSuperClaude機能との統合
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#integration-with-other-superclaude-features)
-
-### MCP サーバー調整
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#mcp-server-coordination)
-
-- **Serena MCP** : 永続メモリインフラストラクチャを提供します
-- **シーケンシャルMCP** : 保存されたメモリを使用して複雑な分析を強化します
-- **Context7 MCP** : 保存されたパターンとドキュメント化のアプローチを参照します
-- **Morphllm MCP** : 保存されたリファクタリングパターンを一貫して適用します
-
-### エージェントとメモリの連携
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#agent-collaboration-with-memory)
-
-- エージェントは強化されたコンテキストのために永続的なメモリにアクセスします
-- 以前の専門家の決定は保存され、参照されます
-- 共有メモリを介したセッション間エージェント調整
-- プロジェクトの履歴に基づいた一貫した専門家の推奨
-
-### 永続性を備えたコマンド統合
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#command-integration-with-persistence)
-
-- すべての`/sc:`コマンドは永続的なコンテキストを参照し、そのコンテキストに基づいて構築できます。
-- 以前のコマンド出力と決定はセッション間で利用可能
-- ワークフローパターンは保存され、再利用できる
-- 実装履歴は将来の指揮決定を導く
-
-## 永続セッションのトラブルシューティング
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#troubleshooting-persistent-sessions)
-
-### よくある問題
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#common-issues)
-
-**メモリが読み込まれません**:
-
-- Serena MCP が正しく構成され、実行されていることを確認します。
-- メモリファイルの権限とアクセス可能性を確認する
-- プロジェクトの命名規則の一貫性を確保する
-- メモリファイルの整合性とフォーマットを検証する
-
-**セッション間のコンテキスト損失**:
-
-- `/sc:save`セッションを終了する前に必ず使用してください
-- 簡単に検索できるように、わかりやすいメモリ名を使用する
-- メモリの完全性を定期的`/sc:reflect`に検証する
-- 重要なメモリファイルを定期的にバックアップする
-
-**メモリの競合**:
-
-- バージョン管理にはタイムスタンプ付きのメモリ名を使用する
-- 古くなった記憶の定期的なクリーンアップ
-- プロジェクトとセッションのメモリを明確に分離
-- セッション間で一貫したメモリ命名規則
-
-### クイックフィックス
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#quick-fixes)
-
-**セッション状態をリセット**:
-
-```shell
-/sc:load --fresh # Start without previous context
-/sc:reflect # Assess current state
-```
-
-**メモリクリーンアップ**:
-
-```shell
-/sc:reflect --cleanup # Remove obsolete memories
-/sc:save --consolidate # Merge related memories
-```
-
-**コンテキスト回復**:
-
-```shell
-/sc:load --recent # Load most recent memories
-/sc:reflect --repair # Identify and fix context gaps
-```
-
-## 高度な永続セッションパターン
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#advanced-persistent-session-patterns)
-
-### 複数フェーズのプロジェクト
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#multi-phase-projects)
-
-- 整理のためにフェーズ固有のメモリ命名を使用する
-- フェーズ全体でアーキテクチャ上の決定の継続性を維持する
-- 永続メモリによるクロスフェーズ依存関係の追跡
-- 歴史的背景を考慮した漸進的な複雑性管理
-
-### チームコラボレーション
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#team-collaboration)
-
-- 共有メモリの規則と命名規則
-- チームのコンテキストにおける意思決定根拠の保存
-- すべてのチームメンバーがアクセスできる統合パターンのドキュメント
-- メモリを介した一貫したコードスタイルとアーキテクチャの適用
-
-### 長期メンテナンス
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#long-term-maintenance)
-
-- 完了したプロジェクトのメモリアーカイブ戦略
-- 蓄積された記憶によるパターンライブラリの開発
-- 時間をかけて構築された再利用可能なソリューションドキュメント
-- 永続的なメモリ蓄積による知識ベースの構築
-
-## 永続セッション管理の主な利点
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#key-benefits-of-persistent-session-management)
-
-### プロジェクトの継続性
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#project-continuity)
-
-- 複数の会話にわたるシームレスな作業継続
-- Claude Codeセッション間でコンテキストが失われることはありません
-- 保存されたアーキテクチャ上の決定と技術的根拠
-- 長期的なプロジェクトの進捗追跡
-
-### 生産性の向上
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#enhanced-productivity)
-
-- プロジェクトのコンテキストを再度説明する必要性が減少
-- 起動時間が速く、作業を継続できる
-- 過去の洞察とパターンに基づいて
-- 累積的なプロジェクト知識の成長
-
-### 品質の一貫性
-
-[](https://github.com/khayashi4337/SuperClaude_Framework/blob/master/docs/User-Guide/session-management.md#quality-consistency)
-
-- セッション間で一貫したアーキテクチャパターン
-- コード品質の決定と標準の保持
-- 再利用可能なソリューションとベストプラクティス
-- 技術的負債の認識を維持
-
----
-
-**重要なポイント**: Serena MCP によるセッション管理により、SuperClaude は単一の会話の支援から永続的なプロジェクト パートナーシップへと変わり、すべての開発フェーズと Claude Code の会話にわたってコンテキスト、決定、学習が維持されます。
\ No newline at end of file
diff --git a/docs/User-Guide-kr/agents.md b/docs/User-Guide-kr/agents.md
deleted file mode 100644
index 5186093..0000000
--- a/docs/User-Guide-kr/agents.md
+++ /dev/null
@@ -1,865 +0,0 @@
-# SuperClaude 에이전트 가이드 🤖
-
-SuperClaude는 Claude Code가 전문 지식을 위해 호출할 수 있는 15개의 도메인 전문 에이전트를 제공합니다.
-
-## 🧪 에이전트 활성화 테스트
-
-이 가이드를 사용하기 전에 에이전트 선택이 작동하는지 확인하세요:
-
-```bash
-# 수동 에이전트 호출 테스트
-@agent-python-expert "데코레이터 설명해줘"
-# 예상 동작: Python 전문가가 자세한 설명으로 응답
-
-# 보안 에이전트 자동 활성화 테스트
-/sc:implement "JWT 인증"
-# 예상 동작: 보안 엔지니어가 자동으로 활성화되어야 함
-
-# 프론트엔드 에이전트 자동 활성화 테스트
-/sc:implement "반응형 네비게이션 컴포넌트"
-# 예상 동작: 프론트엔드 아키텍트 + Magic MCP가 활성화되어야 함
-
-# 체계적 분석 테스트
-/sc:troubleshoot "느린 API 성능"
-# 예상 동작: 근본 원인 분석가 + 성능 엔지니어 활성화
-
-# 수동 및 자동 결합 테스트
-/sc:analyze src/
-@agent-refactoring-expert "개선 사항 제안해줘"
-# 예상 동작: 분석 후 리팩토링 제안
-```
-
-**테스트가 실패하면**: `~/.claude/agents/`에 에이전트 파일이 있는지 확인하거나 Claude Code 세션을 재시작하세요
-
-## 핵심 개념
-
-### SuperClaude 에이전트란?
-
-**에이전트**는 Claude Code의 동작을 수정하는 컨텍스트 지시문으로 구현된 전문 AI 도메인 전문가입니다. 각 에이전트는 `superclaude/Agents/` 디렉토리에 있는 신중하게 작성된 `.md` 파일로, 도메인별 전문 지식, 행동 패턴, 문제 해결 접근 방식을 포함합니다.
-
-**중요**: 에이전트는 별도의 AI 모델이나 소프트웨어가 아닙니다 - Claude Code가 읽어 전문화된 행동을 채택하는 컨텍스트 구성입니다.
-
-### 에이전트 사용 방법 2가지
-
-#### 1. @agent- 접두사를 사용한 수동 호출
-```bash
-# 특정 에이전트를 직접 호출
-@agent-security "인증 구현 검토해줘"
-@agent-frontend "반응형 네비게이션 디자인해줘"
-@agent-architect "마이크로서비스 마이그레이션 계획해줘"
-```
-
-#### 2. 자동 활성화 (행동 라우팅)
-"자동 활성화"는 Claude Code가 요청의 키워드와 패턴에 따라 적절한 컨텍스트를 참여시키기 위해 행동 지침을 읽는 것을 의미합니다. SuperClaude는 Claude가 가장 적절한 전문가에게 라우팅하기 위해 따르는 행동 가이드라인을 제공합니다.
-
-> **📝 에이전트 "자동 활성화" 작동 방식**:
-> 에이전트 활성화는 자동 시스템 로직이 아닙니다 - 컨텍스트 파일의 행동 지침입니다.
-> 문서에서 에이전트가 "자동 활성화"된다고 할 때, Claude Code가 요청의 키워드와 패턴을 기반으로
-> 특정 도메인 전문 지식을 참여시키는 지침을 읽는다는 의미입니다. 이는 기본 메커니즘에 대해
-> 투명하면서도 지능적인 라우팅 경험을 만듭니다.
-
-```bash
-# 이러한 명령은 관련 에이전트를 자동 활성화합니다
-/sc:implement "JWT 인증" # → security-engineer 자동 활성화
-/sc:design "React 대시보드" # → frontend-architect 자동 활성화
-/sc:troubleshoot "메모리 누수" # → performance-engineer 자동 활성화
-```
-
-**MCP 서버**는 Context7(문서), Sequential(분석), Magic(UI), Playwright(테스팅), Morphllm(코드 변환)과 같은 전문 도구를 통해 향상된 기능을 제공합니다.
-
-**도메인 전문가**는 일반적인 접근 방식보다 더 깊고 정확한 솔루션을 제공하기 위해 좁은 전문 영역에 집중합니다.
-
-### 에이전트 선택 규칙
-
-**우선순위 계층:**
-1. **수동 재정의** - @agent-[name]이 자동 활성화보다 우선합니다
-2. **키워드** - 직접적인 도메인 용어가 주요 에이전트를 트리거합니다
-3. **파일 유형** - 확장자가 언어/프레임워크 전문가를 활성화합니다
-4. **복잡성** - 다단계 작업이 조정 에이전트를 참여시킵니다
-5. **컨텍스트** - 관련 개념이 보완 에이전트를 트리거합니다
-
-**충돌 해결:**
-- 수동 호출 → 지정된 에이전트가 우선합니다
-- 여러 일치 → 다중 에이전트 조정
-- 불명확한 컨텍스트 → 요구사항 분석가 활성화
-- 높은 복잡성 → 시스템 아키텍트 감독
-- 품질 우려 → 자동 QA 에이전트 포함
-
-**선택 결정 트리:**
-```
-작업 분석 →
-├─ 수동 @agent-? → 지정된 에이전트 사용
-├─ 단일 도메인? → 주요 에이전트 활성화
-├─ 다중 도메인? → 전문 에이전트 조정
-├─ 복잡한 시스템? → system-architect 감독 추가
-├─ 품질 중요? → security + performance + quality 에이전트 포함
-└─ 학습 중심? → learning-guide + technical-writer 추가
-```
-
-## 빠른 시작 예제
-
-### 수동 에이전트 호출
-```bash
-# @agent- 접두사로 특정 에이전트를 명시적으로 호출
-@agent-python-expert "이 데이터 처리 파이프라인 최적화해줘"
-@agent-quality-engineer "포괄적인 테스트 스위트 만들어줘"
-@agent-technical-writer "이 API를 예제와 함께 문서화해줘"
-@agent-socratic-mentor "이 디자인 패턴 설명해줘"
-```
-
-### 자동 에이전트 조정
-```bash
-# 자동 활성화를 트리거하는 명령
-/sc:implement "속도 제한이 있는 JWT 인증"
-# → 트리거: security-engineer + backend-architect + quality-engineer
-
-/sc:design "접근 가능한 React 대시보드와 문서"
-# → 트리거: frontend-architect + learning-guide + technical-writer
-
-/sc:troubleshoot "간헐적 실패가 있는 느린 배포 파이프라인"
-# → 트리거: devops-architect + performance-engineer + root-cause-analyst
-
-/sc:audit "결제 처리 보안 취약점"
-# → 트리거: security-engineer + quality-engineer + refactoring-expert
-```
-
-### 수동 및 자동 접근 방식 결합
-```bash
-# 명령으로 시작 (자동 활성화)
-/sc:implement "사용자 프로필 시스템"
-
-# 그런 다음 전문가 검토를 명시적으로 추가
-@agent-security "프로필 시스템의 OWASP 규정 준수 검토해줘"
-@agent-performance-engineer "데이터베이스 쿼리 최적화해줘"
-```
-
----
-
-## SuperClaude 에이전트 팀 👥
-
-### 아키텍처 및 시스템 설계 에이전트 🏗️
-
-### system-architect 🏢
-**전문 분야**: 확장성과 서비스 아키텍처에 중점을 둔 대규모 분산 시스템 설계
-
-**자동 활성화**:
-- 키워드: "architecture", "microservices", "scalability", "system design", "distributed"
-- 컨텍스트: 다중 서비스 시스템, 아키텍처 결정, 기술 선택
-- 복잡성: >5개 컴포넌트 또는 교차 도메인 통합 요구사항
-
-**역량**:
-- 서비스 경계 정의 및 마이크로서비스 분해
-- 기술 스택 선택 및 통합 전략
-- 확장성 계획 및 성능 아키텍처
-- 이벤트 기반 아키텍처 및 메시징 패턴
-- 데이터 흐름 설계 및 시스템 통합
-
-**예제**:
-1. **전자상거래 플랫폼**: 이벤트 소싱을 사용한 사용자, 제품, 결제, 알림 서비스를 위한 마이크로서비스 설계
-2. **실시간 분석**: 스트림 처리 및 시계열 저장소를 갖춘 고처리량 데이터 수집 아키텍처
-3. **다중 테넌트 SaaS**: 테넌트 격리, 공유 인프라, 수평 확장 전략을 갖춘 시스템 설계
-
-### 성공 기준
-- [ ] 응답에서 시스템 수준 사고가 명확함
-- [ ] 서비스 경계 및 통합 패턴 언급
-- [ ] 확장성 및 신뢰성 고려사항 포함
-- [ ] 기술 스택 권장사항 제공
-
-**검증:** `/sc:design "마이크로서비스 플랫폼"`은 system-architect를 활성화해야 함
-**테스트:** 출력에 서비스 분해 및 통합 패턴이 포함되어야 함
-**확인:** 인프라 문제에 대해 devops-architect와 조정해야 함
-
-**최적의 협업 대상**: devops-architect(인프라), performance-engineer(최적화), security-engineer(규정 준수)
-
----
-
-### backend-architect ⚙️
-**전문 분야**: API 신뢰성과 데이터 무결성을 강조하는 견고한 서버 측 시스템 설계
-
-**자동 활성화**:
-- 키워드: "API", "backend", "server", "database", "REST", "GraphQL", "endpoint"
-- 파일 유형: API 스펙, 서버 설정, 데이터베이스 스키마
-- 컨텍스트: 서버 측 로직, 데이터 지속성, API 개발
-
-**역량**:
-- RESTful 및 GraphQL API 아키텍처 및 디자인 패턴
-- 데이터베이스 스키마 설계 및 쿼리 최적화 전략
-- 인증, 권한 부여 및 보안 구현
-- 오류 처리, 로깅 및 모니터링 통합
-- 캐싱 전략 및 성능 최적화
-
-**예제**:
-1. **사용자 관리 API**: JWT 인증, 역할 기반 액세스 제어 및 속도 제한
-2. **결제 처리**: PCI 규정 준수 트랜잭션 처리, 멱등성 및 감사 추적
-3. **콘텐츠 관리**: 캐싱, 페이지네이션, 실시간 알림을 갖춘 RESTful API
-
-**최적의 협업 대상**: security-engineer(인증/보안), performance-engineer(최적화), quality-engineer(테스팅)
-
----
-
-### frontend-architect 🎨
-**전문 분야**: 접근성과 사용자 경험에 중점을 둔 현대적인 웹 애플리케이션 아키텍처
-
-**자동 활성화**:
-- 키워드: "UI", "frontend", "React", "Vue", "Angular", "component", "accessibility", "responsive"
-- 파일 유형: .jsx, .vue, .ts(프론트엔드), .css, .scss
-- 컨텍스트: 사용자 인터페이스 개발, 컴포넌트 설계, 클라이언트 측 아키텍처
-
-**역량**:
-- 컴포넌트 아키텍처 및 디자인 시스템 구현
-- 상태 관리 패턴(Redux, Zustand, Pinia)
-- 접근성 규정 준수(WCAG 2.1) 및 포용적 디자인
-- 성능 최적화 및 번들 분석
-- 프로그레시브 웹 앱 및 모바일 우선 개발
-
-**예제**:
-1. **대시보드 인터페이스**: 실시간 업데이트 및 반응형 그리드 레이아웃을 갖춘 접근 가능한 데이터 시각화
-2. **폼 시스템**: 검증, 오류 처리, 접근성 기능을 갖춘 복잡한 다단계 폼
-3. **디자인 시스템**: 일관된 스타일링 및 상호작용 패턴을 갖춘 재사용 가능한 컴포넌트 라이브러리
-
-**최적의 협업 대상**: learning-guide(사용자 안내), performance-engineer(최적화), quality-engineer(테스팅)
-
----
-
-### devops-architect 🚀
-**전문 분야**: 안정적인 소프트웨어 전달을 위한 인프라 자동화 및 배포 파이프라인 설계
-
-**자동 활성화**:
-- 키워드: "deploy", "CI/CD", "Docker", "Kubernetes", "infrastructure", "monitoring", "pipeline"
-- 파일 유형: Dockerfile, docker-compose.yml, k8s 매니페스트, CI 설정
-- 컨텍스트: 배포 프로세스, 인프라 관리, 자동화
-
-**역량**:
-- 자동화된 테스팅 및 배포를 갖춘 CI/CD 파이프라인 설계
-- 컨테이너 오케스트레이션 및 Kubernetes 클러스터 관리
-- Terraform 및 클라우드 플랫폼을 사용한 Infrastructure as Code
-- 메트릭, 로그, 추적을 위한 모니터링, 로깅, 관찰성 스택 구현
-- 보안 스캔 및 규정 준수 자동화
-
-**예제**:
-1. **마이크로서비스 배포**: 서비스 메시, 자동 확장, blue-green 릴리스를 갖춘 Kubernetes 배포
-2. **다중 환경 파이프라인**: 자동화된 테스팅, 보안 스캔, 단계별 배포를 갖춘 GitOps 워크플로우
-3. **모니터링 스택**: 메트릭, 로그, 추적, 알림 시스템을 갖춘 포괄적인 관찰성
-
-**최적의 협업 대상**: system-architect(인프라 계획), security-engineer(규정 준수), performance-engineer(모니터링)
-
----
-
-### deep-research-agent 🔬
-**전문 분야**: 적응형 전략과 다중 홉 추론을 사용한 포괄적인 연구
-
-**자동 활성화**:
-- 키워드: "research", "investigate", "discover", "explore", "find out", "search for", "latest", "current"
-- 명령어: `/sc:research`가 자동으로 이 에이전트를 활성화
-- 컨텍스트: 철저한 조사가 필요한 복잡한 쿼리, 최신 정보 필요, 사실 확인
-- 복잡성: 여러 도메인에 걸쳐 있거나 반복적 탐색이 필요한 질문
-
-**역량**:
-- **적응형 계획 전략**: Planning(직접), Intent(먼저 명확화), Unified(협업)
-- **다중 홉 추론**: 최대 5단계 - 엔티티 확장, 시간적 진행, 개념적 심화, 인과 관계 체인
-- **자기 성찰 메커니즘**: 각 주요 단계 후 진행 상황 평가 및 재계획 트리거
-- **증거 관리**: 명확한 인용, 관련성 점수, 불확실성 인정
-- **도구 오케스트레이션**: Tavily(검색), Playwright(JavaScript 콘텐츠), Sequential(추론)을 사용한 병렬 우선 실행
-- **학습 통합**: Serena 메모리를 통한 패턴 인식 및 전략 재사용
-
-**연구 깊이 수준**:
-- **Quick**: 기본 검색, 1홉, 요약 출력
-- **Standard**: 확장 검색, 2-3홉, 구조화된 보고서(기본값)
-- **Deep**: 포괄적 검색, 3-4홉, 상세 분석
-- **Exhaustive**: 최대 깊이, 5홉, 완전한 조사
-
-**예제**:
-1. **기술 연구**: `/sc:research "최신 React Server Components 패턴"` → 구현 예제를 포함한 포괄적인 기술 연구
-2. **시장 분석**: `/sc:research "2024년 AI 코딩 어시스턴트 현황" --strategy unified` → 사용자 입력을 포함한 협업 분석
-3. **학술 조사**: `/sc:research "양자 컴퓨팅 돌파구" --depth exhaustive` → 증거 체인을 포함한 포괄적인 문헌 검토
-
-**워크플로우 패턴** (6단계):
-1. **이해** (5-10%): 쿼리 복잡성 평가
-2. **계획** (10-15%): 전략 선택 및 병렬 기회 식별
-3. **TodoWrite** (5%): 적응형 작업 계층 구조 생성(3-15개 작업)
-4. **실행** (50-60%): 병렬 검색 및 추출
-5. **추적** (지속적): 진행 상황 및 신뢰도 모니터링
-6. **검증** (10-15%): 증거 체인 확인
-
-**출력**: 보고서는 `claudedocs/research_[topic]_[timestamp].md`에 저장됨
-
-**최적의 협업 대상**: system-architect(기술 연구), learning-guide(교육 연구), requirements-analyst(시장 연구)
-
-### 품질 및 분석 에이전트 🔍
-
-### security-engineer 🔒
-**전문 분야**: 위협 모델링 및 취약점 예방에 중점을 둔 애플리케이션 보안 아키텍처
-
-**자동 활성화**:
-- 키워드: "security", "auth", "authentication", "vulnerability", "encryption", "compliance", "OWASP"
-- 컨텍스트: 보안 검토, 인증 흐름, 데이터 보호 요구사항
-- 위험 지표: 결제 처리, 사용자 데이터, API 액세스, 규정 준수 필요
-
-**역량**:
-- 위협 모델링 및 공격 표면 분석
-- 안전한 인증 및 권한 부여 설계(OAuth, JWT, SAML)
-- 데이터 암호화 전략 및 키 관리
-- 취약점 평가 및 침투 테스트 지침
-- 보안 규정 준수(GDPR, HIPAA, PCI-DSS) 구현
-
-**예제**:
-1. **OAuth 구현**: 토큰 새로 고침 및 역할 기반 액세스를 갖춘 안전한 다중 테넌트 인증
-2. **API 보안**: 속도 제한, 입력 검증, SQL 인젝션 방지, 보안 헤더
-3. **데이터 보호**: 저장/전송 중 암호화, 키 순환, 프라이버시 바이 디자인 아키텍처
-
-**최적의 협업 대상**: backend-architect(API 보안), quality-engineer(보안 테스팅), root-cause-analyst(사고 대응)
-
----
-
-### performance-engineer ⚡
-**전문 분야**: 확장성과 리소스 효율성에 중점을 둔 시스템 성능 최적화
-
-**자동 활성화**:
-- 키워드: "performance", "slow", "optimization", "bottleneck", "latency", "memory", "CPU"
-- 컨텍스트: 성능 문제, 확장성 우려, 리소스 제약
-- 메트릭: 응답 시간 >500ms, 높은 메모리 사용량, 낮은 처리량
-
-**역량**:
-- 성능 프로파일링 및 병목 현상 식별
-- 데이터베이스 쿼리 최적화 및 인덱싱 전략
-- 캐싱 구현(Redis, CDN, 애플리케이션 레벨)
-- 부하 테스트 및 용량 계획
-- 메모리 관리 및 리소스 최적화
-
-**예제**:
-1. **API 최적화**: 캐싱 및 쿼리 최적화를 통해 응답 시간을 2초에서 200ms로 단축
-2. **데이터베이스 확장**: 읽기 복제본, 연결 풀링, 쿼리 결과 캐싱 구현
-3. **프론트엔드 성능**: 번들 최적화, 지연 로딩, CDN 구현으로 <3초 로드 시간 달성
-
-**최적의 협업 대상**: system-architect(확장성), devops-architect(인프라), root-cause-analyst(디버깅)
-
----
-
-### root-cause-analyst 🔍
-**전문 분야**: 증거 기반 분석 및 가설 테스트를 사용한 체계적인 문제 조사
-
-**자동 활성화**:
-- 키워드: "bug", "issue", "problem", "debugging", "investigation", "troubleshoot", "error"
-- 컨텍스트: 시스템 장애, 예상치 못한 동작, 복잡한 다중 컴포넌트 문제
-- 복잡성: 체계적인 조사가 필요한 교차 시스템 문제
-
-**역량**:
-- 체계적인 디버깅 방법론 및 근본 원인 분석
-- 시스템 전반의 오류 상관 관계 및 종속성 매핑
-- 실패 조사를 위한 로그 분석 및 패턴 인식
-- 복잡한 문제에 대한 가설 형성 및 테스트
-- 사고 대응 및 사후 분석 절차
-
-**예제**:
-1. **데이터베이스 연결 실패**: 연결 풀, 네트워크 타임아웃, 리소스 제한 전반의 간헐적 실패 추적
-2. **결제 처리 오류**: API 로그, 데이터베이스 상태, 외부 서비스 응답을 통한 트랜잭션 실패 조사
-3. **성능 저하**: 메트릭 상관 관계, 리소스 사용량, 코드 변경을 통한 점진적인 둔화 분석
-
-**최적의 협업 대상**: performance-engineer(성능 문제), security-engineer(보안 사고), quality-engineer(테스트 실패)
-
----
-
-### quality-engineer ✅
-**전문 분야**: 자동화 및 커버리지에 중점을 둔 포괄적인 테스팅 전략 및 품질 보증
-
-**자동 활성화**:
-- 키워드: "test", "testing", "quality", "QA", "validation", "coverage", "automation"
-- 컨텍스트: 테스트 계획, 품질 게이트, 검증 요구사항
-- 품질 우려: 코드 커버리지 <80%, 테스트 자동화 부족, 품질 문제
-
-**역량**:
-- 테스트 전략 설계(단위, 통합, e2e, 성능 테스팅)
-- 테스트 자동화 프레임워크 구현 및 CI/CD 통합
-- 품질 메트릭 정의 및 모니터링(커버리지, 결함률)
-- 엣지 케이스 식별 및 경계 테스팅 시나리오
-- 접근성 테스팅 및 규정 준수 검증
-
-**예제**:
-1. **전자상거래 테스팅**: 사용자 흐름, 결제 처리, 재고 관리를 다루는 포괄적인 테스트 스위트
-2. **API 테스팅**: REST/GraphQL API에 대한 자동화된 계약 테스팅, 부하 테스팅, 보안 테스팅
-3. **접근성 검증**: 자동화 및 수동 접근성 감사를 통한 WCAG 2.1 규정 준수 테스팅
-
-**최적의 협업 대상**: security-engineer(보안 테스팅), performance-engineer(부하 테스팅), frontend-architect(UI 테스팅)
-
----
-
-### refactoring-expert 🔧
-**전문 분야**: 체계적인 리팩토링 및 기술 부채 관리를 통한 코드 품질 개선
-
-**자동 활성화**:
-- 키워드: "refactor", "clean code", "technical debt", "SOLID", "maintainability", "code smell"
-- 컨텍스트: 레거시 코드 개선, 아키텍처 업데이트, 코드 품질 문제
-- 품질 지표: 높은 복잡성, 중복 코드, 낮은 테스트 커버리지
-
-**역량**:
-- SOLID 원칙 적용 및 디자인 패턴 구현
-- 코드 냄새 식별 및 체계적인 제거
-- 레거시 코드 현대화 전략 및 마이그레이션 계획
-- 기술 부채 평가 및 우선순위 프레임워크
-- 코드 구조 개선 및 아키텍처 리팩토링
-
-**예제**:
-1. **레거시 현대화**: 모놀리식 애플리케이션을 테스트 가능성이 향상된 모듈형 아키텍처로 변환
-2. **디자인 패턴**: 결제 처리에 Strategy 패턴 구현으로 결합도 감소 및 확장성 향상
-3. **코드 정리**: 중복 코드 제거, 명명 규칙 개선, 재사용 가능한 컴포넌트 추출
-
-**최적의 협업 대상**: system-architect(아키텍처 개선), quality-engineer(테스팅 전략), python-expert(언어별 패턴)
-
-### 전문 개발 에이전트 🎯
-
-### python-expert 🐍
-**전문 분야**: 현대적인 프레임워크와 성능을 강조하는 프로덕션급 Python 개발
-
-**자동 활성화**:
-- 키워드: "Python", "Django", "FastAPI", "Flask", "asyncio", "pandas", "pytest"
-- 파일 유형: .py, requirements.txt, pyproject.toml, Pipfile
-- 컨텍스트: Python 개발 작업, API 개발, 데이터 처리, 테스팅
-
-**역량**:
-- 현대적인 Python 아키텍처 패턴 및 프레임워크 선택
-- asyncio 및 concurrent futures를 사용한 비동기 프로그래밍
-- 프로파일링 및 알고리즘 개선을 통한 성능 최적화
-- pytest, 픽스처, 테스트 자동화를 사용한 테스팅 전략
-- pip, poetry, Docker를 사용한 패키지 관리 및 배포
-
-**예제**:
-1. **FastAPI 마이크로서비스**: Pydantic 검증, 의존성 주입, OpenAPI 문서를 갖춘 고성능 비동기 API
-2. **데이터 파이프라인**: 대규모 데이터셋에 대한 오류 처리, 로깅, 병렬 처리를 갖춘 Pandas 기반 ETL
-3. **Django 애플리케이션**: 사용자 정의 사용자 모델, API 엔드포인트, 포괄적인 테스트 커버리지를 갖춘 풀스택 웹 앱
-
-**최적의 협업 대상**: backend-architect(API 설계), quality-engineer(테스팅), performance-engineer(최적화)
-
----
-
-### requirements-analyst 📝
-**전문 분야**: 체계적인 이해관계자 분석을 통한 요구사항 발견 및 사양 개발
-
-**자동 활성화**:
-- 키워드: "requirements", "specification", "PRD", "user story", "functional", "scope", "stakeholder"
-- 컨텍스트: 프로젝트 시작, 불명확한 요구사항, 범위 정의 필요
-- 복잡성: 다중 이해관계자 프로젝트, 불명확한 목표, 상충하는 요구사항
-
-**역량**:
-- 이해관계자 인터뷰 및 워크숍을 통한 요구사항 도출
-- 승인 기준 및 완료 정의를 갖춘 사용자 스토리 작성
-- 기능 및 비기능 사양 문서화
-- 이해관계자 분석 및 요구사항 우선순위 프레임워크
-- 범위 관리 및 변경 제어 프로세스
-
-**예제**:
-1. **제품 요구사항 문서**: 사용자 페르소나, 기능 사양, 성공 메트릭을 포함한 핀테크 모바일 앱 포괄적 PRD
-2. **API 사양**: 오류 처리, 보안, 성능 기준을 갖춘 결제 처리 API에 대한 상세 요구사항
-3. **마이그레이션 요구사항**: 데이터 마이그레이션, 사용자 교육, 롤백 절차를 갖춘 레거시 시스템 현대화 요구사항
-
-**최적의 협업 대상**: system-architect(기술적 실현 가능성), technical-writer(문서화), learning-guide(사용자 안내)
-
-### 커뮤니케이션 및 학습 에이전트 📚
-
-### technical-writer 📚
-**전문 분야**: 대상 분석 및 명확성에 중점을 둔 기술 문서화 및 커뮤니케이션
-
-**자동 활성화**:
-- 키워드: "documentation", "readme", "API docs", "user guide", "technical writing", "manual"
-- 컨텍스트: 문서화 요청, API 문서화, 사용자 가이드, 기술 설명
-- 파일 유형: .md, .rst, API 스펙, 문서 파일
-
-**역량**:
-- 기술 문서화 아키텍처 및 정보 설계
-- 다양한 기술 수준에 대한 대상 분석 및 콘텐츠 타겟팅
-- 작동 예제 및 통합 지침을 포함한 API 문서화
-- 단계별 절차 및 문제 해결을 포함한 사용자 가이드 작성
-- 접근성 표준 적용 및 포용적 언어 사용
-
-**예제**:
-1. **API 문서화**: 인증, 엔드포인트, 예제, SDK 통합 가이드를 포함한 포괄적인 REST API 문서
-2. **사용자 매뉴얼**: 스크린샷, 문제 해결, FAQ 섹션을 포함한 단계별 설치 및 구성 가이드
-3. **기술 사양**: 다이어그램, 데이터 흐름, 구현 세부사항을 포함한 시스템 아키텍처 문서
-
-**최적의 협업 대상**: requirements-analyst(사양 명확성), learning-guide(교육 콘텐츠), frontend-architect(UI 문서화)
-
----
-
-### learning-guide 🎓
-**전문 분야**: 기술 개발 및 멘토십에 중점을 둔 교육 콘텐츠 설계 및 점진적 학습
-
-**자동 활성화**:
-- 키워드: "explain", "learn", "tutorial", "beginner", "teaching", "education", "training"
-- 컨텍스트: 교육 요청, 개념 설명, 기술 개발, 학습 경로
-- 복잡성: 단계별 분해 및 점진적 이해가 필요한 복잡한 주제
-
-**역량**:
-- 점진적 기술 개발을 갖춘 학습 경로 설계
-- 유추 및 예제를 통한 복잡한 개념 설명
-- 실습 연습을 포함한 대화형 튜토리얼 생성
-- 기술 평가 및 역량 평가 프레임워크
-- 멘토십 전략 및 개인화된 학습 접근법
-
-**예제**:
-1. **프로그래밍 튜토리얼**: 실습 연습, 코드 예제, 점진적 복잡성을 포함한 대화형 React 튜토리얼
-2. **개념 설명**: 시각적 다이어그램 및 연습 문제를 포함한 실제 예제를 통한 데이터베이스 정규화 설명
-3. **기술 평가**: 실제 프로젝트 및 피드백을 포함한 풀스택 개발을 위한 포괄적인 평가 프레임워크
-
-**최적의 협업 대상**: technical-writer(교육 문서화), frontend-architect(대화형 학습), requirements-analyst(학습 목표)
-
----
-
-## 에이전트 조정 및 통합 🤝
-
-### 조정 패턴
-
-**아키텍처 팀**:
-- **풀스택 개발**: frontend-architect + backend-architect + security-engineer + quality-engineer
-- **시스템 설계**: system-architect + devops-architect + performance-engineer + security-engineer
-- **레거시 현대화**: refactoring-expert + system-architect + quality-engineer + technical-writer
-
-**품질 팀**:
-- **보안 감사**: security-engineer + quality-engineer + root-cause-analyst + requirements-analyst
-- **성능 최적화**: performance-engineer + system-architect + devops-architect + root-cause-analyst
-- **테스팅 전략**: quality-engineer + security-engineer + performance-engineer + frontend-architect
-
-**커뮤니케이션 팀**:
-- **문서화 프로젝트**: technical-writer + requirements-analyst + learning-guide + 도메인 전문가
-- **학습 플랫폼**: learning-guide + frontend-architect + technical-writer + quality-engineer
-- **API 문서화**: backend-architect + technical-writer + security-engineer + quality-engineer
-
-### MCP 서버 통합
-
-**MCP 서버를 통한 향상된 기능**:
-- **Context7**: 모든 아키텍트 및 전문가를 위한 공식 문서화 패턴
-- **Sequential**: root-cause-analyst, system-architect, performance-engineer를 위한 다단계 분석
-- **Magic**: frontend-architect, learning-guide 대화형 콘텐츠를 위한 UI 생성
-- **Playwright**: quality-engineer를 위한 브라우저 테스팅, frontend-architect를 위한 접근성 검증
-- **Morphllm**: refactoring-expert를 위한 코드 변환, python-expert를 위한 대량 변경
-- **Serena**: 모든 에이전트를 위한 프로젝트 메모리, 세션 전반의 컨텍스트 보존
-
-### 에이전트 활성화 문제 해결
-
-## 문제 해결
-
-문제 해결 도움말은 다음을 참조하세요:
-- [일반적인 문제](../Reference/common-issues.md) - 자주 발생하는 문제에 대한 빠른 수정
-- [문제 해결 가이드](../Reference/troubleshooting.md) - 포괄적인 문제 해결
-
-### 일반적인 문제
-- **에이전트 활성화 없음**: 도메인 키워드 사용: "security", "performance", "frontend"
-- **잘못된 에이전트 선택**: 에이전트 문서의 트리거 키워드 확인
-- **너무 많은 에이전트**: 주요 도메인에 키워드 집중 또는 `/sc:focus [domain]` 사용
-- **에이전트가 조정하지 않음**: 작업 복잡성 증가 또는 다중 도메인 키워드 사용
-- **에이전트 전문 지식 불일치**: 더 구체적인 기술 용어 사용
-
-### 즉각적인 수정
-- **에이전트 활성화 강제**: 요청에 명시적 도메인 키워드 사용
-- **에이전트 선택 재설정**: Claude Code 세션을 재시작하여 에이전트 상태 재설정
-- **에이전트 패턴 확인**: 에이전트 문서의 트리거 키워드 검토
-- **기본 활성화 테스트**: `/sc:implement "security auth"`로 security-engineer 테스트
-
-### 에이전트별 문제 해결
-
-**보안 에이전트 없음:**
-```bash
-# 문제: 보안 우려가 security-engineer를 트리거하지 않음
-# 빠른 수정: 명시적 보안 키워드 사용
-"implement authentication" # 일반적 - 트리거하지 않을 수 있음
-"implement JWT authentication security" # 명시적 - security-engineer 트리거
-"secure user login with encryption" # 보안 중심 - security-engineer 트리거
-```
-
-**성능 에이전트 없음:**
-```bash
-# 문제: 성능 문제가 performance-engineer를 트리거하지 않음
-# 빠른 수정: 성능별 용어 사용
-"make it faster" # 모호함 - 트리거하지 않을 수 있음
-"optimize slow database queries" # 구체적 - performance-engineer 트리거
-"reduce API latency and bottlenecks" # 성능 중심 - performance-engineer 트리거
-```
-
-**아키텍처 에이전트 없음:**
-```bash
-# 문제: 시스템 설계가 아키텍처 에이전트를 트리거하지 않음
-# 빠른 수정: 아키텍처 키워드 사용
-"build an app" # 일반적 - 기본 에이전트 트리거
-"design microservices architecture" # 구체적 - system-architect 트리거
-"scalable distributed system design" # 아키텍처 중심 - system-architect 트리거
-```
-
-**잘못된 에이전트 조합:**
-```bash
-# 문제: 백엔드 작업에 프론트엔드 에이전트 활성화
-# 빠른 수정: 도메인별 용어 사용
-"create user interface" # frontend-architect를 트리거할 수 있음
-"create REST API endpoints" # 구체적 - backend-architect 트리거
-"implement server-side authentication" # 백엔드 중심 - backend-architect 트리거
-```
-
-### 지원 수준
-
-**빠른 수정:**
-- 에이전트 트리거 테이블의 명시적 도메인 키워드 사용
-- Claude Code 세션 재시작 시도
-- 혼란을 피하기 위해 단일 도메인에 집중
-
-**상세 도움말:**
-- 에이전트 설치 문제는 [일반적인 문제 가이드](../Reference/common-issues.md) 참조
-- 대상 에이전트의 트리거 키워드 검토
-
-**전문가 지원:**
-- `SuperClaude install --diagnose` 사용
-- 조정 분석은 [진단 참조 가이드](../Reference/diagnostic-reference.md) 참조
-
-**커뮤니티 지원:**
-- [GitHub Issues](https://github.com/SuperClaude-Org/SuperClaude_Framework/issues)에서 문제 보고
-- 예상 대비 실제 에이전트 활성화 예제 포함
-
-### 성공 검증
-
-에이전트 수정 적용 후 테스트:
-- [ ] 도메인별 요청이 올바른 에이전트 활성화 (security → security-engineer)
-- [ ] 복잡한 작업이 다중 에이전트 조정 트리거 (3개 이상 에이전트)
-- [ ] 에이전트 전문 지식이 작업 요구사항과 일치 (API → backend-architect)
-- [ ] 적절한 경우 품질 에이전트 자동 포함 (security, performance, testing)
-- [ ] 응답에 도메인 전문 지식 및 전문 지식 표시
-
-## 빠른 문제 해결 (레거시)
-- **에이전트 활성화 없음** → 도메인 키워드 사용: "security", "performance", "frontend"
-- **잘못된 에이전트** → 에이전트 문서의 트리거 키워드 확인
-- **너무 많은 에이전트** → 주요 도메인에 키워드 집중
-- **에이전트가 조정하지 않음** → 작업 복잡성 증가 또는 다중 도메인 키워드 사용
-
-**에이전트가 활성화되지 않나요?**
-1. **키워드 확인**: 도메인별 용어 사용 (예: security-engineer의 경우 "login"이 아닌 "authentication")
-2. **컨텍스트 추가**: 파일 유형, 프레임워크 또는 특정 기술 포함
-3. **복잡성 증가**: 다중 도메인 문제가 더 많은 에이전트 트리거
-4. **예제 사용**: 에이전트 전문 지식과 일치하는 구체적인 시나리오 참조
-
-**너무 많은 에이전트?**
-- 주요 도메인 필요에 키워드 집중
-- `/sc:focus [domain]`을 사용하여 범위 제한
-- 특정 에이전트로 시작하고 필요에 따라 확장
-
-**잘못된 에이전트?**
-- 에이전트 문서의 트리거 키워드 검토
-- 대상 도메인에 더 구체적인 용어 사용
-- 명시적 요구사항 또는 제약조건 추가
-
-## 빠른 참조 📋
-
-### 에이전트 트리거 조회
-
-| 트리거 유형 | 키워드/패턴 | 활성화된 에이전트 |
-|-------------|-------------------|------------------|
-| **보안** | "auth", "security", "vulnerability", "encryption" | security-engineer |
-| **성능** | "slow", "optimization", "bottleneck", "latency" | performance-engineer |
-| **프론트엔드** | "UI", "React", "Vue", "component", "responsive" | frontend-architect |
-| **백엔드** | "API", "server", "database", "REST", "GraphQL" | backend-architect |
-| **테스팅** | "test", "QA", "validation", "coverage" | quality-engineer |
-| **DevOps** | "deploy", "CI/CD", "Docker", "Kubernetes" | devops-architect |
-| **아키텍처** | "architecture", "microservices", "scalability" | system-architect |
-| **Python** | ".py", "Django", "FastAPI", "asyncio" | python-expert |
-| **문제** | "bug", "issue", "debugging", "troubleshoot" | root-cause-analyst |
-| **코드 품질** | "refactor", "clean code", "technical debt" | refactoring-expert |
-| **문서화** | "documentation", "readme", "API docs" | technical-writer |
-| **학습** | "explain", "tutorial", "beginner", "teaching" | learning-guide |
-| **요구사항** | "requirements", "PRD", "specification" | requirements-analyst |
-| **연구** | "research", "investigate", "latest", "current" | deep-research-agent |
-
-### 명령어-에이전트 매핑
-
-| 명령어 | 주요 에이전트 | 지원 에이전트 |
-|---------|----------------|-------------------|
-| `/sc:implement` | 도메인 아키텍트 (frontend, backend) | security-engineer, quality-engineer |
-| `/sc:analyze` | quality-engineer, security-engineer | performance-engineer, root-cause-analyst |
-| `/sc:troubleshoot` | root-cause-analyst | 도메인 전문가, performance-engineer |
-| `/sc:improve` | refactoring-expert | quality-engineer, performance-engineer |
-| `/sc:document` | technical-writer | 도메인 전문가, learning-guide |
-| `/sc:design` | system-architect | 도메인 아키텍트, requirements-analyst |
-| `/sc:test` | quality-engineer | security-engineer, performance-engineer |
-| `/sc:explain` | learning-guide | technical-writer, 도메인 전문가 |
-| `/sc:research` | deep-research-agent | 기술 전문가, learning-guide |
-
-### 효과적인 에이전트 조합
-
-**개발 워크플로우**:
-- 웹 애플리케이션: frontend-architect + backend-architect + security-engineer + quality-engineer + devops-architect
-- API 개발: backend-architect + security-engineer + technical-writer + quality-engineer
-- 데이터 플랫폼: python-expert + performance-engineer + security-engineer + system-architect
-
-**분석 워크플로우**:
-- 보안 감사: security-engineer + quality-engineer + root-cause-analyst + technical-writer
-- 성능 조사: performance-engineer + root-cause-analyst + system-architect + devops-architect
-- 레거시 평가: refactoring-expert + system-architect + quality-engineer + security-engineer + technical-writer
-
-**커뮤니케이션 워크플로우**:
-- 기술 문서화: technical-writer + requirements-analyst + 도메인 전문가 + learning-guide
-- 교육 콘텐츠: learning-guide + technical-writer + frontend-architect + quality-engineer
-
-## 모범 사례 💡
-
-### 시작하기 (간단한 접근법)
-
-**자연어 우선:**
-1. **목표 설명**: 도메인별 키워드를 사용한 자연어 사용
-2. **자동 활성화 신뢰**: 시스템이 자동으로 적절한 에이전트로 라우팅하도록 허용
-3. **패턴에서 학습**: 다양한 요청 유형에 대해 어떤 에이전트가 활성화되는지 관찰
-4. **반복 및 개선**: 추가 전문 에이전트를 참여시키기 위해 구체성 추가
-
-### 에이전트 선택 최적화
-
-**효과적인 키워드 사용:**
-- **구체적 > 일반적**: security-engineer를 위해 "login" 대신 "authentication" 사용
-- **기술 용어**: 프레임워크 이름, 기술, 특정 과제 포함
-- **컨텍스트 단서**: 파일 유형, 프로젝트 범위, 복잡성 지표 언급
-- **품질 키워드**: 포괄적인 커버리지를 위해 "security", "performance", "accessibility" 추가
-
-**요청 최적화 예제:**
-```bash
-# 일반적 (제한된 에이전트 활성화)
-"로그인 기능 수정"
-
-# 최적화됨 (다중 에이전트 조정)
-"속도 제한 및 접근성 규정 준수를 갖춘 안전한 JWT 인증 구현"
-# → 트리거: security-engineer + backend-architect + frontend-architect + quality-engineer
-```
-
-### 일반적인 사용 패턴
-
-**개발 워크플로우:**
-```bash
-# 풀스택 기능 개발
-/sc:implement "실시간 알림이 있는 반응형 사용자 대시보드"
-# → frontend-architect + backend-architect + performance-engineer
-
-# 문서화를 포함한 API 개발
-/sc:create "포괄적인 문서가 있는 결제 처리를 위한 REST API"
-# → backend-architect + security-engineer + technical-writer + quality-engineer
-
-# 성능 최적화 조사
-/sc:troubleshoot "사용자 경험에 영향을 미치는 느린 데이터베이스 쿼리"
-# → performance-engineer + root-cause-analyst + backend-architect
-```
-
-**분석 워크플로우:**
-```bash
-# 보안 평가
-/sc:analyze "GDPR 규정 준수 취약점에 대한 인증 시스템"
-# → security-engineer + quality-engineer + requirements-analyst
-
-# 코드 품질 검토
-/sc:review "현대화 기회를 위한 레거시 코드베이스"
-# → refactoring-expert + system-architect + quality-engineer + technical-writer
-
-# 학습 및 설명
-/sc:explain "실습 예제가 있는 마이크로서비스 패턴"
-# → system-architect + learning-guide + technical-writer
-```
-
-### 고급 에이전트 조정
-
-**다중 도메인 프로젝트:**
-- **광범위하게 시작**: 아키텍처 에이전트를 참여시키기 위해 시스템 수준 키워드로 시작
-- **구체성 추가**: 전문 에이전트를 활성화하기 위해 도메인별 필요 포함
-- **품질 통합**: 보안, 성능, 테스팅 관점 자동 포함
-- **문서화 포함**: 포괄적인 커버리지를 위해 학습 또는 문서화 필요 추가
-
-**에이전트 선택 문제 해결:**
-
-**문제: 잘못된 에이전트 활성화**
-- 해결책: 더 구체적인 도메인 용어 사용
-- 예제: "database optimization" → performance-engineer + backend-architect
-
-**문제: 에이전트가 충분하지 않음**
-- 해결책: 복잡성 지표 및 교차 도메인 키워드 증가
-- 예제: 요청에 "security", "performance", "documentation" 추가
-
-**문제: 에이전트가 너무 많음**
-- 해결책: 구체적인 기술 용어로 주요 도메인에 집중
-- 예제: 범위를 제한하기 위해 "/sc:focus backend" 사용
-
-### 품질 중심 개발
-
-**보안 우선 접근법:**
-도메인 전문가와 함께 security-engineer를 자동으로 참여시키기 위해 개발 요청에 항상 보안 고려사항을 포함하세요.
-
-**성능 통합:**
-처음부터 performance-engineer 조정을 보장하기 위해 성능 키워드("빠른", "효율적", "확장 가능")를 포함하세요.
-
-**접근성 규정 준수:**
-프론트엔드 개발에서 접근성 검증을 자동으로 포함하기 위해 "accessible", "WCAG" 또는 "inclusive"를 사용하세요.
-
-**문서화 문화:**
-자동 technical-writer 포함 및 지식 전달을 위해 요청에 "documented", "explained" 또는 "tutorial"을 추가하세요.
-
----
-
-## 에이전트 지능 이해 🧠
-
-### 에이전트를 효과적으로 만드는 것
-
-**도메인 전문 지식**: 각 에이전트는 도메인별 전문 지식 패턴, 행동 접근법, 문제 해결 방법론을 가지고 있습니다.
-
-**컨텍스트 활성화**: 에이전트는 키워드뿐만 아니라 요청 컨텍스트를 분석하여 관련성 및 참여 수준을 결정합니다.
-
-**협업 지능**: 다중 에이전트 조정은 개별 에이전트 능력을 초과하는 시너지 효과를 생성합니다.
-
-**적응형 학습**: 에이전트 선택은 요청 패턴 및 성공적인 조정 결과를 기반으로 향상됩니다.
-
-### 에이전트 vs. 전통적인 AI
-
-**전통적인 접근법**: 단일 AI가 다양한 수준의 전문 지식으로 모든 도메인을 처리
-**에이전트 접근법**: 전문가들이 깊은 도메인 지식과 집중된 문제 해결로 협업
-
-**이점**:
-- 도메인별 작업에서 더 높은 정확도
-- 더 정교한 문제 해결 방법론
-- 전문가 검토를 통한 더 나은 품질 보증
-- 조정된 다중 관점 분석
-
-### 시스템을 신뢰하고 패턴을 이해하세요
-
-**기대할 수 있는 것**:
-- 적절한 도메인 전문가에게 자동 라우팅
-- 복잡한 작업에 대한 다중 에이전트 조정
-- 자동 QA 에이전트 포함을 통한 품질 통합
-- 교육 에이전트 활성화를 통한 학습 기회
-
-**걱정하지 않아도 되는 것**:
-- 수동 에이전트 선택 또는 구성
-- 복잡한 라우팅 규칙 또는 에이전트 관리
-- 에이전트 구성 또는 조정
-- 에이전트 상호작용 마이크로 관리
-
----
-
-## 관련 리소스 📚
-
-### 필수 문서
-- **[명령어 가이드](commands.md)** - 최적의 에이전트 조정을 트리거하는 SuperClaude 명령어 마스터
-- **[MCP 서버](mcp-servers.md)** - 전문 도구 통합을 통한 향상된 에이전트 기능
-- **[세션 관리](session-management.md)** - 영구 에이전트 컨텍스트를 사용한 장기 워크플로우
-
-### 고급 사용
-- **[행동 모드](modes.md)** - 향상된 에이전트 조정을 위한 컨텍스트 최적화
-- **[시작하기](../Getting-Started/quick-start.md)** - 에이전트 최적화를 위한 전문가 기법
-- **[예제 모음](../Reference/examples-cookbook.md)** - 실제 에이전트 조정 패턴
-
-### 개발 리소스
-- **[기술 아키텍처](../Developer-Guide/technical-architecture.md)** - SuperClaude의 에이전트 시스템 설계 이해
-- **[기여하기](../Developer-Guide/contributing-code.md)** - 에이전트 기능 및 조정 패턴 확장
-
----
-
-## 에이전트 여정 🚀
-
-**1주차: 자연스러운 사용**
-자연어 설명으로 시작하세요. 어떤 에이전트가 활성화되는지, 그리고 그 이유를 주목하세요. 프로세스를 과도하게 생각하지 않고 키워드 패턴에 대한 직관을 구축하세요.
-
-**2-3주차: 패턴 인식**
-에이전트 조정 패턴을 관찰하세요. 복잡성과 도메인 키워드가 에이전트 선택에 어떻게 영향을 미치는지 이해하세요. 더 나은 조정을 위해 요청 문구를 최적화하기 시작하세요.
-
-**2개월 이상: 전문가 조정**
-최적의 에이전트 조합을 트리거하는 다중 도메인 요청을 마스터하세요. 효과적인 에이전트 선택을 위한 문제 해결 기법을 활용하세요. 복잡한 워크플로우를 위한 고급 패턴을 사용하세요.
-
-**SuperClaude 이점:**
-간단하고 자연스러운 언어 요청을 통해 조정된 응답으로 작동하는 14명의 전문 AI 전문가의 힘을 경험하세요. 구성도, 관리도 필요 없이, 필요에 따라 확장되는 지능적인 협업만 있습니다.
-
-🎯 **지능적인 에이전트 조정을 경험할 준비가 되셨나요? `/sc:implement`로 시작하여 전문 AI 협업의 마법을 발견하세요.**
-
diff --git a/docs/User-Guide-kr/commands.md b/docs/User-Guide-kr/commands.md
deleted file mode 100644
index c383a5c..0000000
--- a/docs/User-Guide-kr/commands.md
+++ /dev/null
@@ -1,367 +0,0 @@
-# SuperClaude 명령어 가이드
-
-SuperClaude는 Claude Code를 위한 25개의 명령어를 제공합니다: 워크플로우를 위한 `/sc:*` 명령어와 전문가를 위한 `@agent-*`.
-
-## 명령어 유형
-
-| 유형 | 사용 위치 | 형식 | 예제 |
-|------|------------|--------|---------|
-| **슬래시 명령어** | Claude Code | `/sc:[명령어]` | `/sc:implement "기능"` |
-| **에이전트** | Claude Code | `@agent-[이름]` | `@agent-security "검토"` |
-| **설치** | 터미널 | `SuperClaude [명령어]` | `SuperClaude install` |
-
-## 빠른 테스트
-```bash
-# 터미널: 설치 확인
-python3 -m SuperClaude --version
-# Claude Code CLI 확인: claude --version
-
-# Claude Code: 명령어 테스트
-/sc:brainstorm "테스트 프로젝트" # 발견 질문을 해야 함
-/sc:analyze README.md # 분석을 제공해야 함
-```
-
-**워크플로우**: `/sc:brainstorm "아이디어"` → `/sc:implement "기능"` → `/sc:test`
-
-## 🎯 SuperClaude 명령어 이해하기
-
-## SuperClaude 작동 방식
-
-SuperClaude는 Claude Code가 읽어 전문화된 동작을 채택하는 행동 컨텍스트 파일을 제공합니다. `/sc:implement`를 입력하면 Claude Code는 `implement.md` 컨텍스트 파일을 읽고 행동 지침을 따릅니다.
-
-**SuperClaude 명령어는 소프트웨어로 실행되지 않습니다** - 프레임워크의 전문 지침 파일을 읽어 Claude Code의 동작을 수정하는 컨텍스트 트리거입니다.
-
-### 명령어 유형:
-- **슬래시 명령어** (`/sc:*`): 워크플로우 패턴 및 행동 모드 트리거
-- **에이전트 호출** (`@agent-*`): 특정 도메인 전문가를 수동으로 활성화
-- **플래그** (`--think`, `--safe-mode`): 명령어 동작 및 깊이 수정
-
-### 컨텍스트 메커니즘:
-1. **사용자 입력**: `/sc:implement "인증 시스템"` 입력
-2. **컨텍스트 로딩**: Claude Code가 `~/.claude/superclaude/Commands/implement.md` 읽음
-3. **동작 채택**: Claude가 도메인 전문 지식, 도구 선택, 검증 패턴 적용
-4. **향상된 출력**: 보안 고려사항 및 모범 사례를 갖춘 구조화된 구현
-
-**핵심 포인트**: 이는 전통적인 소프트웨어 실행이 아닌 컨텍스트 관리를 통해 정교한 개발 워크플로우를 만듭니다.
-
-### 설치 vs 사용 명령어
-
-**🖥️ 터미널 명령어** (실제 CLI 소프트웨어):
-- `SuperClaude install` - 프레임워크 컴포넌트 설치
-- `SuperClaude update` - 기존 설치 업데이트
-- `SuperClaude uninstall` - 프레임워크 설치 제거
-- `python3 -m SuperClaude --version` - 설치 상태 확인
-
-**💬 Claude Code 명령어** (컨텍스트 트리거):
-- `/sc:brainstorm` - 요구사항 발견 컨텍스트 활성화
-- `/sc:implement` - 기능 개발 컨텍스트 활성화
-- `@agent-security` - 보안 전문가 컨텍스트 활성화
-- 모든 명령어는 Claude Code 채팅 인터페이스 내에서만 작동
-
-> **빠른 시작**: 핵심 워크플로우를 경험하려면 `/sc:brainstorm "프로젝트 아이디어"` → `/sc:implement "기능 이름"` → `/sc:test`를 시도해보세요.
-
-## 🧪 설정 테스트
-
-### 🖥️ 터미널 확인 (터미널/CMD에서 실행)
-```bash
-# SuperClaude 작동 확인 (주요 방법)
-python3 -m SuperClaude --version
-# 예상 출력: SuperClaude 4.1.5
-
-# Claude Code CLI 버전 확인
-claude --version
-
-# 설치된 컴포넌트 확인
-python3 -m SuperClaude install --list-components | grep mcp
-# 예상 출력: 설치된 MCP 컴포넌트 표시
-```
-
-### 💬 Claude Code 테스트 (Claude Code 채팅에 입력)
-```
-# 기본 /sc: 명령어 테스트
-/sc:brainstorm "테스트 프로젝트"
-# 예상 동작: 대화형 요구사항 발견 시작
-
-# 명령어 도움말 테스트
-/sc:help
-# 예상 동작: 사용 가능한 명령어 목록
-```
-
-**테스트가 실패하면**: [설치 가이드](../Getting-Started/installation.md) 또는 [문제 해결](#troubleshooting) 확인
-
-### 📝 명령어 빠른 참조
-
-| 명령어 유형 | 실행 위치 | 형식 | 목적 | 예제 |
-|-------------|--------------|--------|---------|----------|
-| **🖥️ 설치** | 터미널/CMD | `SuperClaude [명령어]` | 설정 및 유지보수 | `SuperClaude install` |
-| **🔧 구성** | 터미널/CMD | `python3 -m SuperClaude [명령어]` | 고급 구성 | `python3 -m SuperClaude --version` |
-| **💬 슬래시 명령어** | Claude Code | `/sc:[명령어]` | 워크플로우 자동화 | `/sc:implement "기능"` |
-| **🤖 에이전트 호출** | Claude Code | `@agent-[이름]` | 수동 전문가 활성화 | `@agent-security "검토"` |
-| **⚡ 향상된 플래그** | Claude Code | `/sc:[명령어] --플래그` | 동작 수정 | `/sc:analyze --think-hard` |
-
-> **기억하세요**: 모든 `/sc:` 명령어와 `@agent-` 호출은 터미널이 아닌 Claude Code 채팅 내에서 작동합니다. 이들은 Claude Code가 SuperClaude 프레임워크에서 특정 컨텍스트 파일을 읽도록 트리거합니다.
-
-## 목차
-
-- [필수 명령어](#필수-명령어) - 여기서 시작하세요 (8개 핵심 명령어)
-- [일반적인 워크플로우](#일반적인-워크플로우) - 작동하는 명령어 조합
-- [전체 명령어 참조](#전체-명령어-참조) - 카테고리별로 정리된 25개 명령어
-- [문제 해결](#문제-해결) - 일반적인 문제 및 해결책
-- [명령어 인덱스](#명령어-인덱스) - 카테고리별로 명령어 찾기
-
----
-
-## 필수 명령어
-
-**즉각적인 생산성을 위한 핵심 워크플로우 명령어:**
-
-### `/sc:brainstorm` - 프로젝트 발견
-**목적**: 대화형 요구사항 발견 및 프로젝트 계획
-**구문**: `/sc:brainstorm "아이디어"` `[--strategy systematic|creative]`
-
-**사용 사례**:
-- 새 프로젝트 계획: `/sc:brainstorm "전자상거래 플랫폼"`
-- 기능 탐색: `/sc:brainstorm "사용자 인증 시스템"`
-- 문제 해결: `/sc:brainstorm "느린 데이터베이스 쿼리"`
-
-### `/sc:help` - 명령어 참조
-**목적**: 사용 가능한 모든 `/sc` 명령어와 설명 목록 표시
-**구문**: `/sc:help`
-
-**사용 사례**:
-- 사용 가능한 명령어 발견: `/sc:help`
-- 명령어 이름 빠른 확인: `/sc:help`
-
-### `/sc:research` - 심층 연구 명령어
-**목적**: 적응형 계획 및 지능형 검색을 통한 포괄적인 웹 연구
-**구문**: `/sc:research "[쿼리]"` `[--depth quick|standard|deep|exhaustive] [--strategy planning|intent|unified]`
-
-**사용 사례**:
-- 기술 연구: `/sc:research "최신 React 19 기능" --depth deep`
-- 시장 분석: `/sc:research "2024년 AI 코딩 어시스턴트 현황" --strategy unified`
-- 학술 조사: `/sc:research "양자 컴퓨팅 돌파구" --depth exhaustive`
-- 최신 정보: `/sc:research "2024년 최신 AI 개발"`
-
-**핵심 기능**:
-- **6단계 워크플로우**: 이해 → 계획 → TodoWrite → 실행 → 추적 → 검증
-- **적응형 깊이**: Quick(기본 검색), Standard(확장), Deep(포괄적), Exhaustive(최대 깊이)
-- **계획 전략**: Planning(직접), Intent(먼저 명확화), Unified(협업)
-- **병렬 실행**: 기본 병렬 검색 및 추출
-- **증거 관리**: 관련성 점수가 있는 명확한 인용
-- **출력 표준**: 보고서가 `claudedocs/research_[주제]_[타임스탬프].md`에 저장됨
-
-### `/sc:implement` - 기능 개발
-**목적**: 지능형 전문가 라우팅을 통한 풀스택 기능 구현
-**구문**: `/sc:implement "기능 설명"` `[--type frontend|backend|fullstack] [--focus security|performance]`
-
-**사용 사례**:
-- 인증: `/sc:implement "JWT 로그인 시스템"`
-- UI 컴포넌트: `/sc:implement "반응형 대시보드"`
-- API: `/sc:implement "REST 사용자 엔드포인트"`
-- 데이터베이스: `/sc:implement "관계를 가진 사용자 스키마"`
-
-### `/sc:analyze` - 코드 평가
-**목적**: 품질, 보안, 성능에 걸친 포괄적인 코드 분석
-**구문**: `/sc:analyze [경로]` `[--focus quality|security|performance|architecture]`
-
-**사용 사례**:
-- 프로젝트 상태: `/sc:analyze .`
-- 보안 감사: `/sc:analyze --focus security`
-- 성능 검토: `/sc:analyze --focus performance`
-
-### `/sc:business-panel` - 전략적 비즈니스 분석
-**목적**: 9명의 저명한 사상가와 함께하는 다중 전문가 비즈니스 전략 분석
-**구문**: `/sc:business-panel "내용"` `[--mode discussion|debate|socratic] [--experts "name1,name2"]`
-
-**사용 사례**:
-- 전략 평가: `/sc:business-panel "우리의 시장 진출 전략"`
-- 경쟁 분석: `/sc:business-panel @competitor_analysis.pdf --mode debate`
-- 혁신 평가: `/sc:business-panel "AI 제품 아이디어" --experts "christensen,drucker"`
-- 전략적 학습: `/sc:business-panel "경쟁 전략" --mode socratic`
-
-**전문가 패널**: Christensen, Porter, Drucker, Godin, Kim/Mauborgne, Collins, Taleb, Meadows, Doumont
-
-### `/sc:spec-panel` - 전문가 사양 검토
-**목적**: 저명한 사양 및 소프트웨어 엔지니어링 전문가를 사용한 다중 전문가 사양 검토 및 개선
-**구문**: `/sc:spec-panel [내용|@파일]` `[--mode discussion|critique|socratic] [--focus requirements|architecture|testing|compliance]`
-
-**사용 사례**:
-- 사양 검토: `/sc:spec-panel @api_spec.yml --mode critique --focus requirements,architecture`
-- 요구사항 워크숍: `/sc:spec-panel "사용자 스토리 내용" --mode discussion`
-- 아키텍처 검증: `/sc:spec-panel @microservice.spec.yml --mode socratic --focus architecture`
-- 규정 준수 검토: `/sc:spec-panel @security_requirements.yml --focus compliance`
-- 반복적 개선: `/sc:spec-panel @complex_system.spec.yml --iterations 3`
-
-**전문가 패널**: Wiegers, Adzic, Cockburn, Fowler, Nygard, Newman, Hohpe, Crispin, Gregory, Hightower
-
-### `/sc:troubleshoot` - 문제 진단
-**목적**: 근본 원인 분석을 통한 체계적인 문제 진단
-**구문**: `/sc:troubleshoot "문제 설명"` `[--type build|runtime|performance]`
-
-**사용 사례**:
-- 런타임 오류: `/sc:troubleshoot "로그인 시 500 오류"`
-- 빌드 실패: `/sc:troubleshoot --type build`
-- 성능 문제: `/sc:troubleshoot "느린 페이지 로드"`
-
-### `/sc:test` - 품질 보증
-**목적**: 커버리지 분석을 통한 포괄적인 테스팅
-**구문**: `/sc:test` `[--type unit|integration|e2e] [--coverage] [--fix]`
-
-**사용 사례**:
-- 전체 테스트 스위트: `/sc:test --coverage`
-- 단위 테스팅: `/sc:test --type unit --watch`
-- E2E 검증: `/sc:test --type e2e`
-
-### `/sc:improve` - 코드 향상
-**목적**: 체계적인 코드 개선 및 최적화 적용
-**구문**: `/sc:improve [경로]` `[--type performance|quality|security] [--preview]`
-
-**사용 사례**:
-- 일반적인 개선: `/sc:improve src/`
-- 성능 최적화: `/sc:improve --type performance`
-- 보안 강화: `/sc:improve --type security`
-
-### `/sc:document` - 문서 생성
-**목적**: 코드 및 API에 대한 포괄적인 문서 생성
-**구문**: `/sc:document [경로]` `[--type api|user-guide|technical] [--format markdown|html]`
-
-**사용 사례**:
-- API 문서: `/sc:document --type api`
-- 사용자 가이드: `/sc:document --type user-guide`
-- 기술 문서: `/sc:document --type technical`
-
-### `/sc:workflow` - 구현 계획
-**목적**: 요구사항에서 구조화된 구현 계획 생성
-**구문**: `/sc:workflow "기능 설명"` `[--strategy agile|waterfall] [--format markdown]`
-
-**사용 사례**:
-- 기능 계획: `/sc:workflow "사용자 인증"`
-- 스프린트 계획: `/sc:workflow --strategy agile`
-- 아키텍처 계획: `/sc:workflow "마이크로서비스 마이그레이션"`
-
----
-
-## 일반적인 워크플로우
-
-**검증된 명령어 조합:**
-
-### 새 프로젝트 설정
-```bash
-/sc:brainstorm "프로젝트 개념" # 요구사항 정의
-/sc:design "시스템 아키텍처" # 기술 설계 생성
-/sc:workflow "구현 계획" # 개발 로드맵 생성
-```
-
-### 기능 개발
-```bash
-/sc:implement "기능 이름" # 기능 구축
-/sc:test --coverage # 테스트로 검증
-/sc:document --type api # 문서 생성
-```
-
-### 코드 품질 개선
-```bash
-/sc:analyze --focus quality # 현재 상태 평가
-/sc:improve --preview # 개선 사항 미리보기
-/sc:test --coverage # 변경 사항 검증
-```
-
-### 버그 조사
-```bash
-/sc:troubleshoot "문제 설명" # 문제 진단
-/sc:analyze --focus problem-area # 심층 분석
-/sc:improve --fix --safe-mode # 대상 수정 적용
-```
-
-### 사양 개발
-```bash
-/sc:spec-panel @existing_spec.yml --mode critique # 전문가 검토
-/sc:spec-panel @improved_spec.yml --iterations 2 # 반복적 개선
-/sc:document --type technical # 문서 생성
-```
-
-## 전체 명령어 참조
-
-### 개발 명령어
-| 명령어 | 목적 | 최적 사용처 |
-|---------|---------|----------|
-| **workflow** | 구현 계획 | 프로젝트 로드맵, 스프린트 계획 |
-| **implement** | 기능 개발 | 풀스택 기능, API 개발 |
-| **build** | 프로젝트 컴파일 | CI/CD, 프로덕션 빌드 |
-| **design** | 시스템 아키텍처 | API 스펙, 데이터베이스 스키마 |
-
-### 분석 명령어
-| 명령어 | 목적 | 최적 사용처 |
-|---------|---------|----------|
-| **analyze** | 코드 평가 | 품질 감사, 보안 검토 |
-| **research** | 지능형 검색을 통한 웹 연구 | 기술 연구, 최신 정보, 시장 분석 |
-| **business-panel** | 전략적 분석 | 비즈니스 결정, 경쟁 평가 |
-| **spec-panel** | 사양 검토 | 요구사항 검증, 아키텍처 분석 |
-| **troubleshoot** | 문제 진단 | 버그 조사, 성능 문제 |
-| **explain** | 코드 설명 | 학습, 코드 검토 |
-
-### 품질 명령어
-| 명령어 | 목적 | 최적 사용처 |
-|---------|---------|----------|
-| **improve** | 코드 향상 | 성능 최적화, 리팩토링 |
-| **cleanup** | 기술 부채 | 데드 코드 제거, 정리 |
-| **test** | 품질 보증 | 테스트 자동화, 커버리지 분석 |
-| **document** | 문서화 | API 문서, 사용자 가이드 |
-
-### 프로젝트 관리
-| 명령어 | 목적 | 최적 사용처 |
-|---------|---------|----------|
-| **estimate** | 프로젝트 추정 | 타임라인 계획, 리소스 할당 |
-| **task** | 작업 관리 | 복잡한 워크플로우, 작업 추적 |
-| **spawn** | 메타 오케스트레이션 | 대규모 프로젝트, 병렬 실행 |
-
-### 유틸리티 명령어
-| 명령어 | 목적 | 최적 사용처 |
-|---------|---------|----------|
-| **help** | 모든 명령어 나열 | 사용 가능한 명령어 발견 |
-| **git** | 버전 제어 | 커밋 관리, 브랜치 전략 |
-| **index** | 명령어 발견 | 기능 탐색, 명령어 찾기 |
-
-### 세션 명령어
-| 명령어 | 목적 | 최적 사용처 |
-|---------|---------|----------|
-| **load** | 컨텍스트 로딩 | 세션 초기화, 프로젝트 온보딩 |
-| **save** | 세션 지속성 | 체크포인팅, 컨텍스트 보존 |
-| **reflect** | 작업 검증 | 진행 상황 평가, 완료 검증 |
-| **select-tool** | 도구 최적화 | 성능 최적화, 도구 선택 |
-
----
-
-## 명령어 인덱스
-
-**기능별:**
-- **계획**: brainstorm, design, workflow, estimate
-- **개발**: implement, build, git
-- **분석**: analyze, business-panel, spec-panel, troubleshoot, explain
-- **품질**: improve, cleanup, test, document
-- **관리**: task, spawn, load, save, reflect
-- **유틸리티**: help, index, select-tool
-
-**복잡성별:**
-- **초급**: brainstorm, implement, analyze, test, help
-- **중급**: workflow, design, business-panel, spec-panel, improve, document
-- **고급**: spawn, task, select-tool, reflect
-
-## 문제 해결
-
-**명령어 문제:**
-- **명령어를 찾을 수 없음**: 설치 확인: `python3 -m SuperClaude --version`
-- **응답 없음**: Claude Code 세션 재시작
-- **처리 지연**: MCP 서버 없이 테스트하려면 `--no-mcp` 사용
-
-**빠른 수정:**
-- 세션 재설정: `/sc:load`로 다시 초기화
-- 상태 확인: `SuperClaude install --list-components`
-- 도움말 받기: [문제 해결 가이드](../Reference/troubleshooting.md)
-
-## 다음 단계
-
-- [플래그 가이드](flags.md) - 명령어 동작 제어
-- [에이전트 가이드](agents.md) - 전문가 활성화
-- [예제 모음](../Reference/examples-cookbook.md) - 실제 사용 패턴
-
diff --git a/docs/User-Guide-kr/flags.md b/docs/User-Guide-kr/flags.md
deleted file mode 100644
index 5689edd..0000000
--- a/docs/User-Guide-kr/flags.md
+++ /dev/null
@@ -1,271 +0,0 @@
-# SuperClaude 플래그 가이드 🏁
-
-**대부분의 플래그는 자동으로 활성화됩니다** - Claude Code가 요청의 키워드와 패턴을 기반으로 적절한 컨텍스트를 참여시키는 행동 지침을 읽습니다.
-
-## 필수 자동 활성화 플래그 (사용 사례의 90%)
-
-### 핵심 분석 플래그
-| 플래그 | 활성화 시점 | 수행 작업 |
-|------|---------------|--------------|
-| `--think` | 5개 이상 파일 또는 복잡한 분석 | 표준 구조화된 분석 (~4K 토큰) |
-| `--think-hard` | 아키텍처 분석, 시스템 종속성 | 향상된 도구를 사용한 심층 분석 (~10K 토큰) |
-| `--ultrathink` | 중요한 시스템 재설계, 레거시 현대화 | 모든 도구를 사용한 최대 깊이 분석 (~32K 토큰) |
-
-### MCP 서버 플래그
-| 플래그 | 서버 | 목적 | 자동 트리거 |
-|------|---------|---------|---------------|
-| `--c7` / `--context7` | Context7 | 공식 문서, 프레임워크 패턴 | 라이브러리 임포트, 프레임워크 질문 |
-| `--seq` / `--sequential` | Sequential | 다단계 추론, 디버깅 | 복잡한 디버깅, 시스템 설계 |
-| `--magic` | Magic | UI 컴포넌트 생성 | `/ui` 명령어, 프론트엔드 키워드 |
-| `--play` / `--playwright` | Playwright | 브라우저 테스팅, E2E 검증 | 테스팅 요청, 시각적 검증 |
-| `--morph` / `--morphllm` | Morphllm | 대량 변환, 패턴 편집 | 대량 작업, 스타일 강제 |
-| `--serena` | Serena | 프로젝트 메모리, 심볼 작업 | 심볼 작업, 대규모 코드베이스 |
-
-### 행동 모드 플래그
-| 플래그 | 활성화 시점 | 수행 작업 |
-|------|---------------|--------------|
-| `--brainstorm` | 모호한 요청, 탐색 키워드 | 협업 발견 마인드셋 |
-| `--introspect` | 자기 분석, 오류 복구 | 투명성을 갖춘 추론 과정 노출 |
-| `--task-manage` | >3단계, 복잡한 범위 | 위임을 통한 오케스트레이션 |
-| `--orchestrate` | 다중 도구 작업, 성능 필요 | 도구 선택 및 병렬 실행 최적화 |
-| `--token-efficient` / `--uc` | 컨텍스트 >75%, 효율성 필요 | 심볼 강화 커뮤니케이션, 30-50% 감소 |
-
-### 실행 제어 플래그
-| 플래그 | 활성화 시점 | 수행 작업 |
-|------|---------------|--------------|
-| `--loop` | "개선", "다듬기", "정제" 키워드 | 반복적 향상 사이클 |
-| `--safe-mode` | 프로덕션, >85% 리소스 사용 | 최대 검증, 보수적 실행 |
-| `--validate` | 위험 >0.7, 프로덕션 환경 | 실행 전 위험 평가 |
-| `--delegate` | >7개 디렉토리 또는 >50개 파일 | 하위 에이전트 병렬 처리 |
-
-## 명령어별 플래그
-
-### 분석 명령어 플래그 (`/sc:analyze`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--focus` | 특정 도메인 대상 | `security`, `performance`, `quality`, `architecture` |
-| `--depth` | 분석 철저함 | `quick`, `deep` |
-| `--format` | 출력 형식 | `text`, `json`, `report` |
-
-### 빌드 명령어 플래그 (`/sc:build`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--type` | 빌드 구성 | `dev`, `prod`, `test` |
-| `--clean` | 빌드 전 정리 | 불린 |
-| `--optimize` | 최적화 활성화 | 불린 |
-| `--verbose` | 상세 출력 | 불린 |
-
-### 디자인 명령어 플래그 (`/sc:design`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--type` | 디자인 대상 | `architecture`, `api`, `component`, `database` |
-| `--format` | 출력 형식 | `diagram`, `spec`, `code` |
-
-### 설명 명령어 플래그 (`/sc:explain`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--level` | 복잡성 수준 | `basic`, `intermediate`, `advanced` |
-| `--format` | 설명 스타일 | `text`, `examples`, `interactive` |
-| `--context` | 도메인 컨텍스트 | 모든 도메인 (예: `react`, `security`) |
-
-### 개선 명령어 플래그 (`/sc:improve`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--type` | 개선 초점 | `quality`, `performance`, `maintainability`, `style`, `security` |
-| `--safe` | 보수적 접근 | 불린 |
-| `--interactive` | 사용자 안내 | 불린 |
-| `--preview` | 실행 없이 표시 | 불린 |
-
-### 작업 명령어 플래그 (`/sc:task`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--strategy` | 작업 접근법 | `systematic`, `agile`, `enterprise` |
-| `--parallel` | 병렬 실행 | 불린 |
-| `--delegate` | 하위 에이전트 조정 | 불린 |
-
-### 워크플로우 명령어 플래그 (`/sc:workflow`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--strategy` | 워크플로우 접근법 | `systematic`, `agile`, `enterprise` |
-| `--depth` | 분석 깊이 | `shallow`, `normal`, `deep` |
-| `--parallel` | 병렬 조정 | 불린 |
-
-### 문제 해결 명령어 플래그 (`/sc:troubleshoot`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--type` | 문제 카테고리 | `bug`, `build`, `performance`, `deployment` |
-| `--trace` | 추적 분석 포함 | 불린 |
-| `--fix` | 수정 적용 | 불린 |
-
-### 정리 명령어 플래그 (`/sc:cleanup`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--type` | 정리 대상 | `code`, `imports`, `files`, `all` |
-| `--safe` / `--aggressive` | 정리 강도 | 불린 |
-| `--interactive` | 사용자 안내 | 불린 |
-| `--preview` | 실행 없이 표시 | 불린 |
-
-### 추정 명령어 플래그 (`/sc:estimate`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--type` | 추정 초점 | `time`, `effort`, `complexity` |
-| `--unit` | 시간 단위 | `hours`, `days`, `weeks` |
-| `--breakdown` | 상세 분해 | 불린 |
-
-### 인덱스 명령어 플래그 (`/sc:index`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--type` | 인덱스 대상 | `docs`, `api`, `structure`, `readme` |
-| `--format` | 출력 형식 | `md`, `json`, `yaml` |
-
-### 성찰 명령어 플래그 (`/sc:reflect`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--type` | 성찰 범위 | `task`, `session`, `completion` |
-| `--analyze` | 분석 포함 | 불린 |
-| `--validate` | 완전성 검증 | 불린 |
-
-### 스폰 명령어 플래그 (`/sc:spawn`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--strategy` | 조정 접근법 | `sequential`, `parallel`, `adaptive` |
-| `--depth` | 분석 깊이 | `normal`, `deep` |
-
-### Git 명령어 플래그 (`/sc:git`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--smart-commit` | 커밋 메시지 생성 | 불린 |
-| `--interactive` | 안내 작업 | 불린 |
-
-### 도구 선택 명령어 플래그 (`/sc:select-tool`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--analyze` | 도구 분석 | 불린 |
-| `--explain` | 선택 설명 | 불린 |
-
-### 테스트 명령어 플래그 (`/sc:test`)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--coverage` | 커버리지 포함 | 불린 |
-| `--type` | 테스트 유형 | `unit`, `integration`, `e2e` |
-| `--watch` | 감시 모드 | 불린 |
-
-## 고급 제어 플래그
-
-### 범위 및 초점
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--scope` | 분석 경계 | `file`, `module`, `project`, `system` |
-| `--focus` | 도메인 타겟팅 | `performance`, `security`, `quality`, `architecture`, `accessibility`, `testing` |
-
-### 실행 제어
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--concurrency [n]` | 병렬 작업 제어 | 1-15 |
-| `--iterations [n]` | 개선 사이클 | 1-10 |
-| `--all-mcp` | 모든 MCP 서버 활성화 | 불린 |
-| `--no-mcp` | 네이티브 도구만 | 불린 |
-
-### 시스템 플래그 (SuperClaude 설치)
-| 플래그 | 목적 | 값 |
-|------|---------|--------|
-| `--verbose` / `-v` | 상세 로깅 | 불린 |
-| `--quiet` / `-q` | 출력 억제 | 불린 |
-| `--dry-run` | 작업 시뮬레이션 | 불린 |
-| `--force` | 검사 건너뛰기 | 불린 |
-| `--yes` / `-y` | 자동 확인 | 불린 |
-| `--install-dir` | 대상 디렉토리 | 경로 |
-| `--legacy` | 레거시 스크립트 사용 | 불린 |
-| `--version` | 버전 표시 | 불린 |
-| `--help` | 도움말 표시 | 불린 |
-
-## 일반적인 사용 패턴
-
-### 프론트엔드 개발
-```bash
-/sc:implement "반응형 대시보드" --magic --c7
-/sc:design component-library --type component --format code
-/sc:test ui-components/ --magic --play
-/sc:improve legacy-ui/ --magic --morph --validate
-```
-
-### 백엔드 개발
-```bash
-/sc:analyze api/ --focus performance --seq --think
-/sc:design payment-api --type api --format spec
-/sc:troubleshoot "API 타임아웃" --type performance --trace
-/sc:improve auth-service --type security --validate
-```
-
-### 대규모 프로젝트
-```bash
-/sc:analyze . --ultrathink --all-mcp --safe-mode
-/sc:workflow enterprise-system --strategy enterprise --depth deep
-/sc:cleanup . --type all --safe --interactive
-/sc:estimate "마이크로서비스로 마이그레이션" --type complexity --breakdown
-```
-
-### 품질 및 유지보수
-```bash
-/sc:improve src/ --type quality --safe --interactive
-/sc:cleanup imports --type imports --preview
-/sc:reflect --type completion --validate
-/sc:git commit --smart-commit
-```
-
-## 플래그 상호작용
-
-### 호환 가능한 조합
-- `--think` + `--c7`: 문서를 사용한 분석
-- `--magic` + `--play`: 테스팅을 사용한 UI 생성
-- `--serena` + `--morph`: 변환을 사용한 프로젝트 메모리
-- `--safe-mode` + `--validate`: 최대 안전성
-- `--loop` + `--validate`: 검증을 통한 반복적 개선
-
-### 충돌하는 플래그
-- `--all-mcp` vs 개별 MCP 플래그 (하나만 사용)
-- `--no-mcp` vs 모든 MCP 플래그 (--no-mcp 우선)
-- `--safe` vs `--aggressive` (정리 강도)
-- `--quiet` vs `--verbose` (출력 수준)
-
-### 자동 활성화 관계
-- `--safe-mode`는 `--uc` 및 `--validate` 자동 활성화
-- `--ultrathink`는 모든 MCP 서버 자동 활성화
-- `--think-hard`는 `--seq` + `--c7` 자동 활성화
-- `--magic`는 UI 중심 에이전트 트리거
-
-## 플래그 문제 해결
-
-### 일반적인 문제
-- **너무 많은 도구**: 네이티브 도구만 테스트하려면 `--no-mcp` 사용
-- **작업이 너무 느림**: 출력 압축을 위해 `--uc` 추가
-- **검증 차단**: 개발 중에는 `--safe-mode` 대신 `--validate` 사용
-- **컨텍스트 압박**: >75% 사용 시 `--token-efficient` 자동 활성화
-
-### 디버그 플래그
-```bash
-/sc:analyze . --verbose # 결정 로직 및 플래그 활성화 표시
-/sc:select-tool "작업" --explain # 도구 선택 과정 설명
-/sc:reflect --type session --analyze # 현재 세션 결정 검토
-```
-
-### 빠른 수정
-```bash
-/sc:analyze . --help # 명령어에 사용 가능한 플래그 표시
-/sc:analyze . --no-mcp # 네이티브 실행만
-/sc:cleanup . --preview # 정리될 내용 표시
-```
-
-## 플래그 우선순위 규칙
-
-1. **안전 우선**: `--safe-mode` > `--validate` > 최적화 플래그
-2. **명시적 재정의**: 사용자 플래그 > 자동 감지
-3. **깊이 계층**: `--ultrathink` > `--think-hard` > `--think`
-4. **MCP 제어**: `--no-mcp`가 모든 개별 MCP 플래그 재정의
-5. **범위 우선순위**: system > project > module > file
-
-## 관련 리소스
-- [명령어 가이드](commands.md) - 이러한 플래그를 사용하는 명령어
-- [MCP 서버 가이드](mcp-servers.md) - MCP 플래그 활성화 이해
-- [세션 관리](session-management.md) - 영구 세션에서 플래그 사용
-
diff --git a/docs/User-Guide-kr/mcp-servers.md b/docs/User-Guide-kr/mcp-servers.md
deleted file mode 100644
index 0f38de0..0000000
--- a/docs/User-Guide-kr/mcp-servers.md
+++ /dev/null
@@ -1,340 +0,0 @@
-# SuperClaude MCP 서버 가이드 🔌
-
-## 개요
-
-MCP (Model Context Protocol) 서버는 전문 도구를 통해 Claude Code의 기능을 확장합니다. SuperClaude는 8개의 MCP 서버를 통합하고 작업에 따라 언제 활성화할지에 대한 지침을 Claude에 제공합니다.
-
-### 🔍 현실 확인
-- **MCP 서버란**: 추가 도구를 제공하는 외부 Node.js 프로세스
-- **MCP 서버가 아닌 것**: 내장된 SuperClaude 기능
-- **활성화 방식**: Claude가 컨텍스트에 따라 적절한 서버를 사용하도록 지침을 읽음
-- **제공하는 것**: Claude Code의 네이티브 기능을 확장하는 실제 도구
-
-**핵심 서버:**
-- **context7**: 공식 라이브러리 문서 및 패턴
-- **sequential-thinking**: 다단계 추론 및 분석
-- **magic**: 현대적인 UI 컴포넌트 생성
-- **playwright**: 브라우저 자동화 및 E2E 테스팅
-- **morphllm-fast-apply**: 패턴 기반 코드 변환
-- **serena**: 의미론적 코드 이해 및 프로젝트 메모리
-- **tavily**: 웹 검색 및 실시간 정보 검색
-- **chrome-devtools**: 성능 분석 및 디버깅
-
-## 빠른 시작
-
-**설정 확인**: MCP 서버는 자동으로 활성화됩니다. 설치 및 문제 해결은 [설치 가이드](../Getting-Started/installation.md) 및 [문제 해결](../Reference/troubleshooting.md)을 참조하세요.
-
-**자동 활성화 로직:**
-
-| 요청 포함 | 활성화되는 서버 |
-|-----------------|------------------|
-| 라이브러리 임포트, API 이름 | **context7** |
-| `--think`, 디버깅 | **sequential-thinking** |
-| `component`, `UI`, frontend | **magic** |
-| `test`, `e2e`, `browser` | **playwright** |
-| 다중 파일 편집, 리팩토링 | **morphllm-fast-apply** |
-| 대규모 프로젝트, 세션 | **serena** |
-| `/sc:research`, `latest`, `current` | **tavily** |
-| `performance`, `debug`, `LCP` | **chrome-devtools** |
-
-## 서버 세부정보
-
-### context7 📚
-**목적**: 공식 라이브러리 문서 액세스
-**트리거**: Import 문, 프레임워크 키워드, 문서 요청
-**요구사항**: Node.js 16+, API 키 불필요
-
-```bash
-# 자동 활성화
-/sc:implement "React 인증 시스템"
-# → 공식 React 패턴 제공
-
-# 수동 활성화
-/sc:analyze auth-system/ --c7
-```
-
-### sequential-thinking 🧠
-**목적**: 구조화된 다단계 추론 및 체계적 분석
-**트리거**: 복잡한 디버깅, `--think` 플래그, 아키텍처 분석
-**요구사항**: Node.js 16+, API 키 불필요
-
-```bash
-# 자동 활성화
-/sc:troubleshoot "API 성능 문제"
-# → 체계적인 근본 원인 분석 활성화
-
-# 수동 활성화
-/sc:analyze --think-hard architecture/
-```
-
-### magic ✨
-**목적**: 21st.dev 패턴에서 현대적인 UI 컴포넌트 생성
-**트리거**: UI 요청, `/ui` 명령어, 컴포넌트 개발
-**요구사항**: Node.js 16+, TWENTYFIRST_API_KEY ()
-
-```bash
-# 자동 활성화
-/sc:implement "반응형 대시보드 컴포넌트"
-# → 현대적인 패턴으로 접근 가능한 UI 생성
-
-# API 키 설정
-export TWENTYFIRST_API_KEY="your_key_here"
-```
-
-### playwright 🎭
-**목적**: 실제 브라우저 자동화 및 E2E 테스팅
-**트리거**: 브라우저 테스팅, E2E 시나리오, 시각적 검증
-**요구사항**: Node.js 16+, API 키 불필요
-
-```bash
-# 자동 활성화
-/sc:test --type e2e "사용자 로그인 흐름"
-# → 브라우저 자동화 테스팅 활성화
-
-# 수동 활성화
-/sc:validate "접근성 규정 준수" --play
-```
-
-### morphllm-fast-apply 🔄
-**목적**: 효율적인 패턴 기반 코드 변환
-**트리거**: 다중 파일 편집, 리팩토링, 프레임워크 마이그레이션
-**요구사항**: Node.js 16+, MORPH_API_KEY
-
-```bash
-# 자동 활성화
-/sc:improve legacy-codebase/ --focus maintainability
-# → 파일 전반에 일관된 패턴 적용
-
-# API 키 설정
-export MORPH_API_KEY="your_key_here"
-```
-
-### serena 🧭
-**목적**: 프로젝트 메모리를 갖춘 의미론적 코드 이해
-**트리거**: 심볼 작업, 대규모 코드베이스, 세션 관리
-**요구사항**: Python 3.9+, uv 패키지 매니저, API 키 불필요
-
-```bash
-# 자동 활성화
-/sc:load existing-project/
-# → 프로젝트 이해 및 메모리 구축
-
-# 수동 활성화
-/sc:refactor "UserService 추출" --serena
-```
-
-### tavily 🔍
-**목적**: 연구를 위한 웹 검색 및 실시간 정보 검색
-**트리거**: `/sc:research` 명령어, "최신" 정보 요청, 최신 이벤트, 사실 확인
-**요구사항**: Node.js 16+, TAVILY_API_KEY (https://app.tavily.com에서 무료 티어 사용 가능)
-
-```bash
-# 자동 활성화
-/sc:research "2024년 최신 AI 개발"
-# → 지능형 웹 연구 수행
-
-# 수동 활성화
-/sc:analyze "시장 트렌드" --tavily
-
-# API 키 설정 (https://app.tavily.com에서 무료 키 받기)
-export TAVILY_API_KEY="tvly-your_api_key_here"
-```
-
-### chrome-devtools 📊
-**목적**: 성능 분석, 디버깅, 실시간 브라우저 검사
-**트리거**: 성능 감사, 레이아웃 문제 디버깅 (예: CLS), 느린 로딩 시간 (LCP), 콘솔 오류, 네트워크 요청
-**요구사항**: Node.js 16+, API 키 불필요
-
-```bash
-# 자동 활성화
-/sc:debug "페이지 로딩이 느림"
-# → Chrome DevTools로 성능 분석 활성화
-
-# 수동 활성화
-/sc:analyze --performance "홈페이지"
-```
-
-**기능:**
-- **웹 검색**: 랭킹 및 필터링을 통한 포괄적인 검색
-- **뉴스 검색**: 시간 필터링된 최신 이벤트 및 업데이트
-- **콘텐츠 추출**: 검색 결과에서 전체 텍스트 추출
-- **도메인 필터링**: 특정 도메인 포함/제외
-- **다중 홉 연구**: 발견에 기반한 반복적 검색 (최대 5홉)
-
-**연구 깊이 제어:**
-- `--depth quick`: 5-10개 소스, 기본 종합
-- `--depth standard`: 10-20개 소스, 구조화된 보고서 (기본값)
-- `--depth deep`: 20-40개 소스, 포괄적 분석
-- `--depth exhaustive`: 40개 이상 소스, 학술 수준 연구
-
-## 구성
-
-**MCP 구성 파일 (`~/.claude.json`):**
-```json
-{
- "mcpServers": {
- "context7": {
- "command": "npx",
- "args": ["-y", "@upstash/context7-mcp@latest"]
- },
- "sequential-thinking": {
- "command": "npx",
- "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
- },
- "magic": {
- "command": "npx",
- "args": ["@21st-dev/magic"],
- "env": {"TWENTYFIRST_API_KEY": "${TWENTYFIRST_API_KEY}"}
- },
- "playwright": {
- "command": "npx",
- "args": ["@playwright/mcp@latest"]
- },
- "morphllm-fast-apply": {
- "command": "npx",
- "args": ["@morph-llm/morph-fast-apply"],
- "env": {"MORPH_API_KEY": "${MORPH_API_KEY}"}
- },
- "serena": {
- "command": "uvx",
- "args": ["--from", "git+https://github.com/oraios/serena", "serena", "start-mcp-server", "--context", "ide-assistant"]
- },
- "tavily": {
- "command": "npx",
- "args": ["-y", "tavily-mcp@latest"],
- "env": {"TAVILY_API_KEY": "${TAVILY_API_KEY}"}
- },
- "chrome-devtools": {
- "command": "npx",
- "args": ["-y", "chrome-devtools-mcp@latest"]
- }
- }
-}
-```
-
-## 사용 패턴
-
-**서버 제어:**
-```bash
-# 특정 서버 활성화
-/sc:analyze codebase/ --c7 --seq
-
-# 모든 MCP 서버 비활성화
-/sc:implement "간단한 함수" --no-mcp
-
-# 모든 서버 활성화
-/sc:design "복잡한 아키텍처" --all-mcp
-```
-
-**다중 서버 조정:**
-```bash
-# 풀스택 개발
-/sc:implement "전자상거래 체크아웃"
-# → Sequential: 워크플로우 분석
-# → Context7: 결제 패턴
-# → Magic: UI 컴포넌트
-# → Serena: 코드 조직
-# → Playwright: E2E 테스팅
-```
-
-## 문제 해결
-
-**일반적인 문제:**
-- **서버 연결 없음**: Node.js 확인: `node --version` (v16+ 필요)
-- **Context7 실패**: 캐시 정리: `npm cache clean --force`
-- **Magic/Morphllm 오류**: API 키 없이 예상됨 (유료 서비스)
-- **서버 타임아웃**: Claude Code 세션 재시작
-
-**빠른 수정:**
-```bash
-# 연결 재설정
-# Claude Code 세션 재시작
-
-# 종속성 확인
-node --version # v16+ 표시되어야 함
-
-# MCP 없이 테스트
-/sc:command --no-mcp
-
-# 구성 확인
-ls ~/.claude.json
-```
-
-**API 키 구성:**
-```bash
-# Magic 서버용 (UI 생성에 필요)
-export TWENTYFIRST_API_KEY="your_key_here"
-
-# Morphllm 서버용 (대량 변환에 필요)
-export MORPH_API_KEY="your_key_here"
-
-# Tavily 서버용 (웹 검색에 필요 - 무료 티어 사용 가능)
-export TAVILY_API_KEY="tvly-your_key_here"
-
-# 지속성을 위해 셸 프로필에 추가
-echo 'export TWENTYFIRST_API_KEY="your_key"' >> ~/.bashrc
-echo 'export MORPH_API_KEY="your_key"' >> ~/.bashrc
-echo 'export TAVILY_API_KEY="your_key"' >> ~/.bashrc
-```
-
-**환경 변수 사용:**
-- ✅ `TWENTYFIRST_API_KEY` - Magic MCP 서버 기능에 필요
-- ✅ `MORPH_API_KEY` - Morphllm MCP 서버 기능에 필요
-- ✅ `TAVILY_API_KEY` - Tavily MCP 서버 기능에 필요 (무료 티어 사용 가능)
-- ❌ 문서의 다른 환경 변수 - 예제용, 프레임워크에서 사용하지 않음
-- 📝 Magic과 Morphllm은 유료 서비스, Tavily는 무료 티어 있음, 프레임워크는 이들 없이도 작동
-
-## 서버 조합
-
-**API 키 없음 (무료)**:
-- context7 + sequential-thinking + playwright + serena
-
-**API 키 1개**:
-- 전문 UI 개발을 위해 magic 추가
-
-**API 키 2개**:
-- 대규모 리팩토링을 위해 morphllm-fast-apply 추가
-
-**일반적인 워크플로우:**
-- **학습**: context7 + sequential-thinking
-- **웹 개발**: magic + context7 + playwright
-- **엔터프라이즈 리팩토링**: serena + morphllm + sequential-thinking
-- **복잡한 분석**: sequential-thinking + context7 + serena
-- **심층 연구**: tavily + sequential-thinking + serena + playwright
-- **최신 이벤트**: tavily + context7 + sequential-thinking
-- **성능 튜닝**: chrome-devtools + sequential-thinking + playwright
-
-## 통합
-
-**SuperClaude 명령어와 함께:**
-- 분석 명령어는 자동으로 Sequential + Serena 사용
-- 구현 명령어는 Magic + Context7 사용
-- 테스팅 명령어는 Playwright + Sequential 사용
-- 연구 명령어는 Tavily + Sequential + Playwright 사용
-
-**행동 모드와 함께:**
-- 브레인스토밍 모드: 발견을 위한 Sequential
-- 작업 관리: 지속성을 위한 Serena
-- 오케스트레이션 모드: 최적의 서버 선택
-- 심층 연구 모드: Tavily + Sequential + Playwright 조정
-
-**성능 제어:**
-- 시스템 부하에 따른 자동 리소스 관리
-- 동시성 제어: `--concurrency N` (1-15)
-- 제약 조건 하에서 우선순위 기반 서버 선택
-
-## 관련 리소스
-
-**필수 읽기:**
-- [명령어 가이드](commands.md) - MCP 서버를 활성화하는 명령어
-- [빠른 시작 가이드](../Getting-Started/quick-start.md) - MCP 설정 가이드
-
-**고급 사용:**
-- [행동 모드](modes.md) - 모드-MCP 조정
-- [에이전트 가이드](agents.md) - 에이전트-MCP 통합
-- [세션 관리](session-management.md) - Serena 워크플로우
-
-**기술 참조:**
-- [예제 모음](../Reference/examples-cookbook.md) - MCP 워크플로우 패턴
-- [기술 아키텍처](../Developer-Guide/technical-architecture.md) - 통합 세부사항
-
diff --git a/docs/User-Guide-kr/modes.md b/docs/User-Guide-kr/modes.md
deleted file mode 100644
index ddb8750..0000000
--- a/docs/User-Guide-kr/modes.md
+++ /dev/null
@@ -1,658 +0,0 @@
-# SuperClaude 행동 모드 가이드 🧠
-
-## ✅ 빠른 확인
-`/sc:` 명령어를 사용하여 모드를 테스트하세요 - 작업 복잡성에 따라 자동으로 활성화됩니다. 전체 명령어 참조는 [명령어 가이드](commands.md)를 참조하세요.
-
-## 빠른 참조 표
-
-| 모드 | 목적 | 자동 트리거 | 주요 동작 | 최적 사용처 |
-|------|---------|---------------|---------------|---------------|
-| **🧠 브레인스토밍** | 대화형 발견 | "brainstorm", "maybe", 모호한 요청 | 소크라테스식 질문, 요구사항 도출 | 새 프로젝트 계획, 불명확한 요구사항 |
-| **🔍 내성** | 메타인지 분석 | 오류 복구, "추론 분석" | 투명한 사고 마커 (🤔, 🎯, 💡) | 디버깅, 학습, 최적화 |
-| **🔬 심층 연구** | 체계적 조사 마인드셋 | `/sc:research`, 조사 키워드 | 6단계 워크플로우, 증거 기반 추론 | 기술 연구, 최신 이벤트, 시장 분석 |
-| **📋 작업 관리** | 복잡한 조정 | >3단계, >2개 디렉토리 | 단계 분해, 메모리 지속성 | 다단계 작업, 프로젝트 관리 |
-| **🎯 오케스트레이션** | 지능형 도구 선택 | 다중 도구 작업, 높은 리소스 사용 | 최적의 도구 라우팅, 병렬 실행 | 복잡한 분석, 성능 최적화 |
-| **⚡ 토큰 효율성** | 압축 커뮤니케이션 | 높은 컨텍스트 사용, `--uc` 플래그 | 심볼 시스템, 예상 30-50% 토큰 감소 | 리소스 제약, 대규모 작업 |
-
----
-
-## 시작하기 (2분 개요)
-
-**모드는 행동 지침을 통해 활성화됩니다** - Claude Code가 컨텍스트 파일을 읽어 작업 패턴과 복잡성에 따라 채택할 모드 동작을 결정합니다.
-
-**빠른 예제:**
-```bash
-# 자동 활성화 예제
-/sc:brainstorm "모바일 앱" # → 소크라테스식 발견 질문
-/sc:implement "인증 시스템" # → 다단계 조정
-"--uc analyze large-codebase/" # → 압축된 심볼 출력
-```
-
-**수동 플래그를 사용할 때:**
-- 특정 동작 필요: `--brainstorm`, `--introspect`, `--uc`
-- 학습/디버깅을 위한 자동 감지 재정의
-- 특정 제약(메모리, 시간, 명확성)에 최적화
-
----
-
-## 모드 세부정보
-
-### 🧠 브레인스토밍 모드 - 대화형 발견
-
-**목적**: 협업 발견을 통해 모호한 아이디어를 구조화된 요구사항으로 변환합니다.
-
-**자동 활성화 트리거:**
-- 모호한 프로젝트 요청: "만들고 싶어...", "생각하고 있는데..."
-- 탐색 키워드: brainstorm, explore, discuss, figure out, not sure
-- 불확실성 지표: "maybe", "possibly", "could we"
-- 수동 플래그: `--brainstorm`, `--bs`
-
-**행동 변화:**
-- **소크라테스식 질문**: 숨겨진 요구사항을 찾기 위한 탐색 질문
-- **비가정적 접근**: 가정을 피하고 발견 방향을 안내하도록 함
-- **협업 파트너십**: 지시적 컨설팅이 아닌 탐색에서 함께 작업
-- **요구사항 종합**: 통찰력을 구조화된 기술 브리프로 변환
-- **교차 세션 메모리**: 후속 토론을 위한 발견 컨텍스트 유지
-
-**예제 경험:**
-```
-표준 접근법: "JWT 토큰으로 사용자 인증 시스템을 구축하겠습니다..."
-브레인스토밍 접근법:
-"🤔 함께 탐색해봅시다:
- - 인증이 앱에서 해결하는 특정 사용자 문제는 무엇인가요?
- - 사용자는 누구이며 기술적 편안함 수준은 어떤가요?
- - 통합할 기존 시스템이나 소셜 로그인이 있나요?
- - 어떤 보안/규정 준수 요구사항이 있나요?
- 📝 결과: 구현 준비가 된 상세한 인증 요구사항 브리프"
-```
-
-#### 성공 기준
-- [ ] 즉각적인 솔루션 대신 질문으로 응답
-- [ ] 질문이 사용자 요구, 기술 제약, 비즈니스 목표 탐색
-- [ ] 발견 과정 전반에 걸쳐 협업적 어조 유지
-- [ ] 결과로 구조화된 요구사항 또는 기술 브리프 생성
-
-**검증:** `/sc:brainstorm "웹 앱"`은 사용자, 기능, 기술에 대해 질문해야 함
-**테스트:** 모호한 요청은 가정이 아닌 발견 질문을 트리거해야 함
-**확인:** 동일한 대화에서 후속 질문 전반에 걸쳐 모드가 지속되어야 함
-
-**최적의 협업 대상:**
-- **→ 작업 관리**: 요구사항 발견 → 체계적인 구현 계획
-- **→ 오케스트레이션**: 요구사항 명확성 → 구현을 위한 최적의 도구 선택
-- **수동 재정의**: "명확한" 요구사항에도 발견을 강제하려면 `--brainstorm` 사용
-
----
-
-### 🔍 내성 모드 - 메타인지 분석
-
-**목적**: 학습 최적화 및 투명한 의사결정을 위한 추론 과정 노출
-
-**자동 활성화 트리거:**
-- 자기 분석 요청: "내 추론 분석", "결정 성찰"
-- 조사가 필요한 오류 복구 시나리오 및 예상치 못한 결과
-- 여러 가능한 접근법이 있는 복잡한 문제 해결
-- 최적화 기회를 위한 패턴 인식 필요
-- 수동 플래그: `--introspect`
-
-**행동 변화:**
-- **추론 투명성**: 명확한 마커로 사고 과정 노출 (🤔, 🎯, ⚡, 📊, 💡)
-- **결정 분석**: 선택 논리 평가 및 대안 접근법 고려
-- **패턴 인식**: 반복되는 행동 및 개선 기회 식별
-- **메타 학습**: 지속적인 프레임워크 개선을 위한 통찰력 추출
-- **프레임워크 규정 준수**: SuperClaude 원칙 및 품질 게이트에 대한 행동 검증
-
-**예제 경험:**
-```
-표준 접근법: "이 코드 구조를 분석하고 개선 사항을 제안하겠습니다..."
-내성적 접근법:
-"🧠 메타 분석: 왜 기능 흐름보다 구조적 분석을 선택했을까?
- 🎯 결정 논리: 클래스 계층 구조 확인 → OOP 패턴 우세 가정
- 🔄 고려된 대안: 데이터 흐름 분석이 숨겨진 종속성 드러낼 수 있음
- 📊 증거 확인: 파일 임포트가 OOP가 아닌 함수형 구성 시사
- 💡 학습: 분석 전략 선택 전에 임포트 분석 필요
- ⚡ 수정: 함수형 흐름 분석 접근법으로 전환"
-```
-
-**최적의 협업 대상:**
-- **→ 작업 관리**: 복잡한 단계 결정에 대한 투명한 추론 제공
-- **모든 모드**: 다른 모드의 작업에 추론 투명성 레이어 추가
-- **수동 재정의**: 학습 세션 및 디버깅 워크플로우에 `--introspect` 사용
-
----
-
-### 🔬 심층 연구 모드 - 체계적 조사 마인드셋
-
-**목적**: 체계적 조사 및 증거 기반 추론을 위한 연구 마인드셋
-
-**자동 활성화 트리거:**
-- `/sc:research` 명령어 호출
-- 연구 관련 키워드: investigate, explore, discover, analyze
-- 지식 컷오프를 넘어선 최신 정보가 필요한 질문
-- 복잡한 연구 요구사항
-- 수동 플래그: `--research`
-
-**행동 수정:**
-- **사고 스타일**: 캐주얼보다 체계적, 가정보다 증거, 점진적 깊이 탐색
-- **커뮤니케이션**: 신뢰 수준으로 시작, 인라인 인용 제공, 불확실성 인정
-- **우선순위 전환**: 속도보다 완전성, 추측보다 정확성, 가정보다 검증
-- **프로세스 적응**: 항상 조사 계획 생성, 병렬 작업 기본값, 증거 체인 유지
-
-**6단계 연구 워크플로우:**
-- 📋 **이해** (5-10%): 쿼리 복잡성 및 요구사항 평가
-- 📝 **계획** (10-15%): 전략 선택 (planning/intent/unified) 및 병렬화 식별
-- ✅ **TodoWrite** (5%): 복잡성에 따라 적응형 작업 계층 구조 생성 (3-15개 작업)
-- 🔄 **실행** (50-60%): 병렬 우선 검색 및 스마트 추출 라우팅
-- 📊 **추적** (지속적): 진행 상황 모니터링 및 신뢰도 점수 업데이트
-- ✓ **검증** (10-15%): 증거 체인 확인 및 완전성 보장
-
-**예제 경험:**
-```
-표준 모드: "양자 컴퓨팅에 대한 검색 결과입니다..."
-심층 연구 모드:
-"📊 연구 계획: 양자 컴퓨팅 돌파구
- ✓ TodoWrite: 8개 연구 작업 생성
- 🔄 도메인 전반에 걸쳐 병렬 검색 실행
- 📈 신뢰도: 15개 검증된 소스에서 0.82
- 📝 보고서 저장됨: claudedocs/research_quantum_[timestamp].md"
-```
-
-#### 품질 표준
-- [ ] 인라인 인용이 있는 주장당 최소 2개 소스
-- [ ] 모든 발견에 대한 신뢰도 점수 (0.0-1.0)
-- [ ] 독립적인 작업에 대한 병렬 실행 기본값
-- [ ] 적절한 구조로 claudedocs/에 보고서 저장
-- [ ] 명확한 방법론 및 증거 제시
-
-**검증:** `/sc:research "테스트 주제"`는 TodoWrite를 생성하고 체계적으로 실행해야 함
-**테스트:** 모든 연구에 신뢰도 점수 및 인용이 포함되어야 함
-**확인:** 보고서가 자동으로 claudedocs/에 저장되어야 함
-
-**최적의 협업 대상:**
-- **→ 작업 관리**: TodoWrite 통합을 통한 연구 계획
-- **→ 오케스트레이션**: 병렬 Tavily/Playwright 조정
-- **수동 재정의**: 세밀한 제어를 위해 `--depth` 및 `--strategy` 사용
-
----
-
-### 📋 작업 관리 모드 - 복잡한 조정
-
-**목적**: 다단계 작업을 위한 세션 지속성을 갖춘 계층적 작업 조직
-
-**자동 활성화 트리거:**
-- >3개의 조정된 단계가 필요한 작업
-- 다중 파일/디렉토리 범위 (>2개 디렉토리 또는 >3개 파일)
-- 단계 및 체크포인트가 필요한 복잡한 종속성
-- 품질 개선 요청: polish, refine, enhance
-- 수동 플래그: `--task-manage`, `--delegate`
-
-**행동 변화:**
-- **계층적 계획**: 복잡한 작업을 Plan → Phase → Task → Todo 구조로 분해
-- **세션 지속성**: 중단 전반에 걸쳐 프로젝트 컨텍스트 및 진행 상황 유지
-- **메모리 통합**: 상태 보존을 위해 write_memory/read_memory 사용
-- **진행 오케스트레이션**: 추적을 위해 TodoWrite와 메모리 업데이트 조정
-- **품질 게이트**: 단계 간 체계적인 검증 체크포인트 구현
-
-**예제 경험:**
-```
-표준 접근법: "사용자 인증을 구현하겠습니다..." → 직접 구현
-작업 관리 접근법:
-"📋 다단계 구현 계획:
- 🎯 1단계: 보안 요구사항 분석 (세션 1)
- 🎯 2단계: API 설계 및 문서화 (세션 2)
- 🎯 3단계: 구현 및 테스팅 (세션 3-4)
- 🎯 4단계: 통합 및 검증 (세션 5)
- 💾 세션 지속성: 자동으로 컨텍스트 재개
- ✓ 품질 게이트: 각 단계 전환 전 검증"
-```
-
-**최적의 협업 대상:**
-- **브레인스토밍 →**: 요구사항 발견 후 체계적인 구현
-- **+ 오케스트레이션**: 최적의 도구 선택을 통한 작업 조정
-- **+ 내성**: 복잡한 단계 결정에 대한 투명한 추론
-
----
-
-### 🎯 오케스트레이션 모드 - 지능형 도구 선택
-
-**목적**: 지능형 도구 라우팅 및 병렬 조정을 통한 작업 실행 최적화
-
-**자동 활성화 트리거:**
-- 정교한 조정이 필요한 다중 도구 작업
-- 성능 제약 (높은 리소스 사용)
-- 병렬 실행 기회 (>3개 독립적 파일/작업)
-- 여러 유효한 도구 접근법이 있는 복잡한 라우팅 결정
-
-**행동 변화:**
-- **지능형 도구 라우팅**: 각 작업 유형에 최적의 MCP 서버 및 네이티브 도구 선택
-- **리소스 인식**: 시스템 제약 및 가용성에 따라 접근법 조정
-- **병렬 최적화**: 동시 실행을 위한 독립적인 작업 식별
-- **조정 초점**: 조정된 실행을 통한 도구 선택 및 사용 최적화
-- **적응형 폴백**: 선호하는 옵션을 사용할 수 없을 때 도구를 우아하게 전환
-
-**예제 경험:**
-```
-표준 접근법: 순차적 파일별 분석 및 편집
-오케스트레이션 접근법:
-"🎯 다중 도구 조정 전략:
- 🔍 1단계: Serena (의미론적 분석) + Sequential (아키텍처 검토)
- ⚡ 2단계: Morphllm (패턴 편집) + Magic (UI 컴포넌트)
- 🧪 3단계: Playwright (테스팅) + Context7 (문서 패턴)
- 🔄 병렬 실행: 3개 도구 동시 작업"
-```
-
-**최적의 협업 대상:**
-- **작업 관리 →**: 복잡한 다단계 계획을 위한 도구 조정 제공
-- **+ 토큰 효율성**: 압축 커뮤니케이션을 통한 최적의 도구 선택
-- **모든 복잡한 작업**: 실행을 향상시키기 위한 지능형 도구 라우팅 추가
-
----
-
-### ⚡ 토큰 효율성 모드 - 압축 커뮤니케이션
-
-**목적**: 정보 품질을 유지하면서 심볼 시스템을 통해 예상 30-50% 토큰 감소 달성
-
-**자동 활성화 트리거:**
-- 제한에 근접한 높은 컨텍스트 사용
-- 리소스 효율성이 필요한 대규모 작업
-- 사용자 명시적 플래그: `--uc`, `--ultracompressed`
-- 여러 출력이 있는 복잡한 분석 워크플로우
-
-**행동 변화:**
-- **심볼 커뮤니케이션**: 논리 흐름, 상태, 기술 도메인을 위한 시각적 심볼 사용
-- **기술 약어**: 반복되는 기술 용어에 대한 컨텍스트 인식 압축
-- **구조화된 밀도**: 장황한 단락보다 글머리 기호, 표, 간결한 형식
-- **정보 보존**: 압축에도 불구하고 ≥95% 정보 품질 유지
-- **구조화된 형식**: 명확성 및 작업 완료를 위해 조직화
-
-**예제 경험:**
-```
-표준 접근법: "인증 시스템 구현은 즉각적인 주의가 필요한 사용자 검증 함수의 보안 취약점을 보여줍니다..."
-토큰 효율적 접근법:
-"🛡️ 보안 경고:
- auth.js:45 → user val() → 중요한 취약점
- 📊 영향: ❌ 토큰 우회 가능
- ⚡ 조치: 검증 수정 + 감사 ∵ 높은 심각도
- 🔧 예상: 2시간 구현 + 1시간 테스트"
-```
-
-**최적의 협업 대상:**
-- **모든 모드**: 모드별 동작을 유지하면서 압축 레이어 추가
-- **오케스트레이션 →**: 압축된 도구 조정 및 상태 업데이트
-- **수동 재정의**: 컨텍스트 압박 또는 효율성이 우선순위일 때 `--uc` 사용
-
----
-
-### 🎨 표준 모드 - 균형 잡힌 기본값
-
-**목적**: 간단한 개발 작업을 위한 명확하고 전문적인 커뮤니케이션 제공
-
-**자동 활성화 트리거:**
-- 복잡성 지표가 없는 간단하고 잘 정의된 작업
-- 명확한 요구사항이 있는 단일 파일 작업
-- 기본 설명 및 표준 개발 워크플로우
-- 다른 모드 트리거가 감지되지 않음 (기본 폴백)
-
-**행동 변화:**
-- **전문적 커뮤니케이션**: 압축 없이 명확하고 간결한 기술 언어
-- **적당한 세부사항**: 대부분의 개발 작업에 적합한 균형 잡힌 정보 깊이
-- **표준 도구 선택**: 네이티브 Claude 기능 및 기본 도구 사용
-- **품질 초점**: 복잡한 오케스트레이션 오버헤드 없이 코드 품질 유지
-- **반응형 적응**: 복잡성이 증가할 때 전문 모드로 전환할 준비
-
-**예제 경험:**
-```
-표준 접근법: 모든 작업에 대한 일관되고 전문적인 기준선
-"적절한 오류 처리와 함께 로그인 함수를 구현하겠습니다:
-
- 1. 사용자 입력 검증 (이메일 형식, 비밀번호 요구사항)
- 2. 안전한 해싱으로 데이터베이스에 대해 인증
- 3. 적절한 만료를 갖춘 JWT 토큰 생성
- 4. 사용자 데이터와 함께 성공 응답 반환
-
- 구현은 보안 모범 사례를 따르고 포괄적인 오류 처리를 포함할 것입니다."
-```
-
-**최적의 협업 대상:**
-- **→ 모든 모드**: 다른 모드가 향상시키는 기준선 역할
-- **모드 전환**: 필요할 때 자동으로 전문 모드로 확장
-- **명확성 우선순위**: 간단한 커뮤니케이션이 최적화보다 중요할 때
-
----
-
-## 고급 사용
-
-### 모드 조합
-
-**다중 모드 워크플로우:**
-```bash
-# 발견 → 계획 → 구현
-/sc:brainstorm "마이크로서비스 아키텍처" --task-manage
-# → 브레인스토밍: 요구사항 발견
-# → 작업 관리: 다단계 조정
-
-# 투명성 및 효율성을 갖춘 분석
-/sc:analyze legacy-system/ --introspect --uc
-# → 내성: 투명한 추론
-# → 토큰 효율성: 압축된 출력
-```
-
-### 수동 모드 제어
-
-**특정 동작 강제:**
-- `--brainstorm`: 모든 작업에 대한 협업 발견 강제
-- `--introspect`: 모든 모드에 추론 투명성 추가
-- `--task-manage`: 계층적 조정 활성화
-- `--orchestrate`: 도구 선택 및 병렬 실행 최적화
-- `--uc`: 효율성을 위해 커뮤니케이션 압축
-
-**재정의 예제:**
-```bash
-# "명확한" 요구사항에 브레인스토밍 강제
-/sc:implement "사용자 로그인" --brainstorm
-
-# 디버깅에 추론 투명성 추가
-# 투명한 추론으로 인증 문제 디버그
-
-# 간단한 작업에 작업 관리 활성화
-# 체계적인 작업 관리로 styles.css 업데이트
-```
-
-### 모드 경계 및 우선순위
-
-**모드가 활성화되는 시점:**
-1. **복잡성 임계값**: >3개 파일 → 작업 관리
-2. **리소스 압박**: 높은 컨텍스트 사용 → 토큰 효율성
-3. **다중 도구 필요**: 복잡한 분석 → 오케스트레이션
-4. **불확실성**: 모호한 요구사항 → 브레인스토밍
-5. **오류 복구**: 문제 → 내성
-
-**우선순위 규칙:**
-- **안전 우선**: 품질 및 검증이 항상 효율성 재정의
-- **사용자 의도**: 수동 플래그가 자동 감지 재정의
-- **컨텍스트 적응**: 모드가 복잡성에 따라 스택됨
-- **리소스 관리**: 압박 하에서 효율성 모드 활성화
-
----
-
-## 실제 예제
-
-### 완전한 워크플로우 예제
-
-**새 프로젝트 개발:**
-```bash
-# 1단계: 발견 (브레인스토밍 모드 자동 활성화)
-"생산성 앱을 만들고 싶어요"
-→ 🤔 사용자, 기능, 플랫폼 선택에 대한 소크라테스식 질문
-→ 📝 구조화된 요구사항 브리프
-
-# 2단계: 계획 (작업 관리 모드 자동 활성화)
-/sc:implement "핵심 생산성 기능"
-→ 📋 종속성이 있는 다단계 분해
-→ 🎯 품질 게이트를 갖춘 단계 조정
-
-# 3단계: 구현 (오케스트레이션 모드가 도구 조정)
-/sc:implement "프론트엔드 및 백엔드 시스템"
-→ 🎯 Magic (UI) + Context7 (패턴) + Sequential (아키텍처)
-→ ⚡ 병렬 실행 최적화
-```
-
-**복잡한 문제 디버깅:**
-```bash
-# 문제 분석 (내성 모드 자동 활성화)
-"사용자가 간헐적인 인증 실패를 겪고 있어요"
-→ 🤔 잠재적 원인에 대한 투명한 추론
-→ 🎯 가설 형성 및 증거 수집
-→ 💡 유사한 문제 전반의 패턴 인식
-
-# 체계적 해결 (작업 관리가 조정)
-# 인증 시스템 포괄적으로 수정
-→ 📋 1단계: 근본 원인 분석
-→ 📋 2단계: 솔루션 구현
-→ 📋 3단계: 테스팅 및 검증
-```
-
-### 모드 조합 패턴
-
-**높은 복잡성 시나리오:**
-```bash
-# 여러 제약이 있는 대규모 리팩토링
-/sc:improve legacy-system/ --introspect --uc --orchestrate
-→ 🔍 투명한 추론 (내성)
-→ ⚡ 압축 커뮤니케이션 (토큰 효율성)
-→ 🎯 최적의 도구 조정 (오케스트레이션)
-→ 📋 체계적 단계 (작업 관리 자동 활성화)
-```
-
----
-
-## 빠른 참조
-
-### 모드 활성화 패턴
-
-| 트리거 유형 | 예제 입력 | 활성화된 모드 | 주요 동작 |
-|--------------|---------------|----------------|--------------|
-| **모호한 요청** | "앱을 만들고 싶어요" | 🧠 브레인스토밍 | 소크라테스식 발견 질문 |
-| **복잡한 범위** | >3개 파일 또는 >2개 디렉토리 | 📋 작업 관리 | 단계 조정 |
-| **다중 도구 필요** | 분석 + 구현 | 🎯 오케스트레이션 | 도구 최적화 |
-| **오류 복구** | "예상대로 작동하지 않아요" | 🔍 내성 | 투명한 추론 |
-| **리소스 압박** | 높은 컨텍스트 사용 | ⚡ 토큰 효율성 | 심볼 압축 |
-| **간단한 작업** | "이 함수 수정" | 🎨 표준 | 명확하고 직접적인 접근 |
-
-### 수동 재정의 명령어
-
-```bash
-# 특정 모드 동작 강제
-/sc:command --brainstorm # 협업 발견
-/sc:command --introspect # 추론 투명성
-/sc:command --task-manage # 계층적 조정
-/sc:command --orchestrate # 도구 최적화
-/sc:command --uc # 토큰 압축
-
-# 여러 모드 결합
-/sc:command --introspect --uc # 투명 + 효율적
-/sc:command --task-manage --orchestrate # 조정 + 최적화
-```
-
----
-
-## 문제 해결
-
-문제 해결 도움말은 다음을 참조하세요:
-- [일반적인 문제](../Reference/common-issues.md) - 자주 발생하는 문제에 대한 빠른 수정
-- [문제 해결 가이드](../Reference/troubleshooting.md) - 포괄적인 문제 해결
-
-### 일반적인 문제
-- **모드가 활성화되지 않음**: 수동 플래그 사용: `--brainstorm`, `--introspect`, `--uc`
-- **잘못된 모드 활성화**: 요청의 복잡성 트리거 및 키워드 확인
-- **모드가 예기치 않게 전환됨**: 작업 진화에 따른 정상적인 동작
-- **실행 영향**: 모드는 도구 사용 최적화, 실행에 영향을 주지 않아야 함
-- **모드 충돌**: [플래그 가이드](flags.md)의 플래그 우선순위 규칙 확인
-
-### 즉각적인 수정
-- **특정 모드 강제**: `--brainstorm` 또는 `--task-manage`와 같은 명시적 플래그 사용
-- **모드 동작 재설정**: 모드 상태를 재설정하려면 Claude Code 세션 재시작
-- **모드 지표 확인**: 응답에서 🤔, 🎯, 📋 심볼 찾기
-- **복잡성 확인**: 간단한 작업은 표준 모드 사용, 복잡한 작업은 자동 전환
-
-### 모드별 문제 해결
-
-**브레인스토밍 모드 문제:**
-```bash
-# 문제: 모드가 질문 대신 솔루션 제공
-# 빠른 수정: 요청 명확성 확인 및 명시적 플래그 사용
-/sc:brainstorm "웹 앱" --brainstorm # 발견 모드 강제
-"...에 대한 모호한 아이디어가 있어요" # 불확실성 언어 사용
-"...를 구축할 수 있을까요" # 탐색 트리거
-```
-
-**작업 관리 모드 문제:**
-```bash
-# 문제: 간단한 작업이 복잡한 조정을 받음
-# 빠른 수정: 범위 줄이기 또는 더 간단한 명령어 사용
-/sc:implement "함수" --no-task-manage # 조정 비활성화
-/sc:troubleshoot bug.js # 기본 명령어 사용
-# 작업이 정말 복잡한지 확인 (>3개 파일, >2개 디렉토리)
-```
-
-**토큰 효율성 모드 문제:**
-```bash
-# 문제: 출력이 너무 압축되거나 불명확함
-# 빠른 수정: 명확성을 위해 압축 비활성화
-/sc:command --no-uc # 압축 비활성화
-/sc:command --verbose # 상세 출력 강제
-# 명확성이 효율성보다 중요할 때 사용
-```
-
-**내성 모드 문제:**
-```bash
-# 문제: 너무 많은 메타 주석, 충분한 행동 없음
-# 빠른 수정: 직접 작업을 위해 내성 비활성화
-/sc:command --no-introspect # 직접 실행
-# 학습 및 디버깅에만 내성 사용
-```
-
-**오케스트레이션 모드 문제:**
-```bash
-# 문제: 도구 조정이 혼란 야기
-# 빠른 수정: 도구 사용 단순화
-/sc:command --no-mcp # 네이티브 도구만
-/sc:command --simple # 기본 실행
-# 작업 복잡성이 오케스트레이션을 정당화하는지 확인
-```
-
-### 오류 코드 참조
-
-| 모드 오류 | 의미 | 빠른 수정 |
-|------------|---------|-----------|
-| **B001** | 브레인스토밍 활성화 실패 | 명시적 `--brainstorm` 플래그 사용 |
-| **T001** | 작업 관리 오버헤드 | 간단한 작업에 `--no-task-manage` 사용 |
-| **U001** | 토큰 효율성이 너무 공격적 | `--verbose` 또는 `--no-uc` 사용 |
-| **I001** | 내성 모드 정체 | 직접 행동을 위해 `--no-introspect` 사용 |
-| **O001** | 오케스트레이션 조정 실패 | `--no-mcp` 또는 `--simple` 사용 |
-| **M001** | 모드 충돌 감지 | 플래그 우선순위 규칙 확인 |
-| **M002** | 모드 전환 루프 | 상태를 재설정하려면 세션 재시작 |
-| **M003** | 모드를 인식할 수 없음 | SuperClaude 업데이트 또는 철자 확인 |
-
-### 점진적 지원 수준
-
-**수준 1: 빠른 수정 (< 2분)**
-- 자동 모드 선택을 재정의하려면 수동 플래그 사용
-- 작업 복잡성이 예상 모드 동작과 일치하는지 확인
-- Claude Code 세션 재시작 시도
-
-**수준 2: 상세 도움말 (5-15분)**
-```bash
-# 모드별 진단
-/sc:help modes # 사용 가능한 모든 모드 나열
-/sc:reflect --type mode-status # 현재 모드 상태 확인
-# 요청 복잡성 및 트리거 검토
-```
-- 모드 설치 문제는 [일반적인 문제 가이드](../Reference/common-issues.md) 참조
-
-**수준 3: 전문가 지원 (30분 이상)**
-```bash
-# 심층 모드 분석
-SuperClaude install --diagnose
-# 모드 활성화 패턴 확인
-# 행동 트리거 및 임계값 검토
-```
-- 행동 모드 분석은 [진단 참조 가이드](../Reference/diagnostic-reference.md) 참조
-
-**수준 4: 커뮤니티 지원**
-- [GitHub Issues](https://github.com/SuperClaude-Org/SuperClaude_Framework/issues)에서 모드 문제 보고
-- 예상치 못한 모드 동작 예제 포함
-- 원하는 모드 활성화 vs 실제 모드 활성화 설명
-
-### 성공 검증
-
-모드 수정 적용 후 다음으로 테스트:
-- [ ] 간단한 요청은 표준 모드 사용 (명확하고 직접적인 응답)
-- [ ] 복잡한 요청은 적절한 모드 자동 활성화 (조정, 추론)
-- [ ] 수동 플래그가 자동 감지를 올바르게 재정의
-- [ ] 예상될 때 모드 지표 (🤔, 🎯, 📋) 나타남
-- [ ] 다양한 모드 전반에 걸쳐 성능이 양호하게 유지됨
-
-## 빠른 문제 해결 (레거시)
-- **모드가 활성화되지 않음** → 수동 플래그 사용: `--brainstorm`, `--introspect`, `--uc`
-- **잘못된 모드 활성화** → 요청의 복잡성 트리거 및 키워드 확인
-- **모드가 예기치 않게 전환됨** → 작업 진화에 따른 정상적인 동작
-- **실행 영향** → 모드는 도구 사용 최적화, 실행에 영향을 주지 않아야 함
-- **모드 충돌** → [플래그 가이드](flags.md)의 플래그 우선순위 규칙 확인
-
-## 자주 묻는 질문
-
-**Q: 어떤 모드가 활성화되어 있는지 어떻게 알 수 있나요?**
-A: 커뮤니케이션 패턴에서 이러한 지표를 찾으세요:
-- 🤔 발견 질문 → 브레인스토밍
-- 🎯 추론 투명성 → 내성
-- 단계 분해 → 작업 관리
-- 도구 조정 → 오케스트레이션
-- 심볼 압축 → 토큰 효율성
-
-**Q: 특정 모드를 강제할 수 있나요?**
-A: 예, 자동 감지를 재정의하려면 수동 플래그 사용:
-```bash
-/sc:command --brainstorm # 발견 강제
-/sc:command --introspect # 투명성 추가
-/sc:command --task-manage # 조정 활성화
-/sc:command --uc # 출력 압축
-```
-
-**Q: 모드가 실행에 영향을 미치나요?**
-A: 모드는 조정을 통해 도구 사용 최적화:
-- **토큰 효율성**: 30-50% 컨텍스트 감소
-- **오케스트레이션**: 병렬 처리
-- **작업 관리**: 체계적인 계획을 통한 재작업 방지
-
-**Q: 모드가 함께 작동할 수 있나요?**
-A: 예, 모드는 서로를 보완하도록 설계됨:
-- **작업 관리**가 다른 모드 조정
-- **토큰 효율성**이 모든 모드의 출력 압축
-- **내성**이 모든 워크플로우에 투명성 추가
-
----
-
-## 요약
-
-SuperClaude의 5가지 행동 모드는 필요에 따라 자동으로 일치하는 **지능형 적응 시스템**을 만듭니다:
-
-- **🧠 브레인스토밍**: 모호한 아이디어를 명확한 요구사항으로 변환
-- **🔍 내성**: 학습 및 디버깅을 위한 투명한 추론 제공
-- **📋 작업 관리**: 복잡한 다단계 작업 조정
-- **🎯 오케스트레이션**: 도구 선택 및 병렬 실행 최적화
-- **⚡ 토큰 효율성**: 명확성을 유지하면서 커뮤니케이션 압축
-- **🎨 표준**: 간단한 작업을 위한 전문적 기준선 유지
-
-**핵심 인사이트**: 모드에 대해 생각할 필요가 없습니다 - 개발 경험을 향상시키기 위해 투명하게 작동합니다. 달성하고자 하는 것을 설명하면 SuperClaude가 자동으로 필요에 맞게 접근 방식을 조정합니다.
-
----
-
-## 관련 가이드
-
-**학습 진행:**
-
-**🌱 필수 (1주차)**
-- [빠른 시작 가이드](../Getting-Started/quick-start.md) - 모드 활성화 예제
-- [명령어 참조](commands.md) - 명령어가 자동으로 모드 활성화
-- [설치 가이드](../Getting-Started/installation.md) - 행동 모드 설정
-
-**🌿 중급 (2-3주차)**
-- [에이전트 가이드](agents.md) - 모드가 전문가와 조정하는 방법
-- [플래그 가이드](flags.md) - 수동 모드 제어 및 최적화
-- [예제 모음](../Reference/examples-cookbook.md) - 실제 모드 패턴
-
-**🌲 고급 (2개월 이상)**
-- [MCP 서버](mcp-servers.md) - 향상된 기능과의 모드 통합
-- [세션 관리](session-management.md) - 작업 관리 모드 워크플로우
-- [시작하기](../Getting-Started/quick-start.md) - 모드 사용 패턴
-
-**🔧 전문가**
-- [기술 아키텍처](../Developer-Guide/technical-architecture.md) - 모드 구현 세부사항
-- [코드 기여](../Developer-Guide/contributing-code.md) - 모드 기능 확장
-
-**모드별 가이드:**
-- **브레인스토밍**: [요구사항 발견 패턴](../Reference/examples-cookbook.md#requirements)
-- **작업 관리**: [세션 관리 가이드](session-management.md)
-- **오케스트레이션**: [MCP 서버 가이드](mcp-servers.md)
-- **토큰 효율성**: [명령어 기본사항](commands.md#token-efficiency)
-
diff --git a/docs/User-Guide-kr/session-management.md b/docs/User-Guide-kr/session-management.md
deleted file mode 100644
index 6ebdb81..0000000
--- a/docs/User-Guide-kr/session-management.md
+++ /dev/null
@@ -1,311 +0,0 @@
-# 세션 관리 가이드
-
-SuperClaude는 Serena MCP 서버를 통해 영구 세션 관리를 제공하여 Claude Code 대화 전반에 걸쳐 진정한 컨텍스트 보존과 장기 프로젝트 연속성을 가능하게 합니다.
-
-## 영구 메모리를 사용한 핵심 세션 명령어
-
-### `/sc:load` - 영구 메모리를 사용한 컨텍스트 로딩
-**목적**: 이전 세션의 프로젝트 컨텍스트 및 영구 메모리로 세션 초기화
-**MCP 통합**: Serena MCP가 저장된 프로젝트 메모리를 읽도록 트리거
-**구문**: `/sc:load [프로젝트_경로]`
-
-**발생하는 일**:
-- Serena MCP가 이전 세션의 영구 메모리 파일 읽기
-- 저장된 메모리에서 프로젝트 컨텍스트 복원
-- 이전 결정, 패턴, 진행 상황 로드
-- 과거 컨텍스트로 세션 상태 초기화
-
-**사용 사례**:
-```bash
-# 영구 메모리에서 기존 프로젝트 컨텍스트 로드
-/sc:load src/
-
-# 전체 기록과 함께 특정 프로젝트 작업 재개
-/sc:load "authentication-system"
-
-# 코드베이스 분석 및 이전 통찰력으로 초기화
-/sc:load . --analyze
-```
-
-### `/sc:save` - 메모리에 세션 지속성
-**목적**: 현재 세션 상태 및 결정을 영구 메모리에 저장
-**MCP 통합**: Serena MCP가 메모리 파일을 작성하도록 트리거
-**구문**: `/sc:save "세션_설명"`
-
-**발생하는 일**:
-- 현재 컨텍스트 및 결정이 Serena 메모리에 작성됨
-- 프로젝트 상태 및 진행 상황이 대화 전반에 걸쳐 지속됨
-- 주요 통찰력 및 패턴이 향후 세션을 위해 저장됨
-- 검색을 위한 타임스탬프와 함께 세션 요약 생성
-
-**사용 사례**:
-```bash
-# 향후 참조를 위해 완료된 기능 작업 저장
-/sc:save "JWT로 사용자 인증 구현됨"
-
-# 복잡한 작업 중 체크포인트
-/sc:save "API 설계 단계 완료, 구현 준비"
-
-# 아키텍처 결정을 영구적으로 저장
-/sc:save "마이크로서비스 아키텍처 결정, 서비스 경계 정의됨"
-```
-
-### `/sc:reflect` - 메모리 컨텍스트를 사용한 진행 상황 평가
-**목적**: 저장된 메모리에 대한 현재 진행 상황 분석 및 세션 완전성 검증
-**MCP 통합**: Serena MCP를 사용하여 저장된 메모리에 대한 현재 상태 비교
-**구문**: `/sc:reflect [--scope project|session]`
-
-**발생하는 일**:
-- Serena MCP가 이전 메모리 및 현재 컨텍스트 읽기
-- 저장된 목표 및 마일스톤에 대한 진행 상황 평가
-- 과거 컨텍스트를 사용하여 격차 및 다음 단계 식별
-- 프로젝트 메모리에 대한 세션 완전성 검증
-
-**사용 사례**:
-```bash
-# 저장된 마일스톤에 대한 프로젝트 진행 상황 평가
-/sc:reflect --scope project
-
-# 현재 세션 완전성 검증
-/sc:reflect
-
-# 메모리를 기반으로 다음 단계로 이동할 준비가 되었는지 확인
-/sc:reflect --scope session
-```
-
-## 영구 메모리 아키텍처
-
-### Serena MCP가 진정한 지속성을 가능하게 하는 방법
-
-**메모리 저장**:
-- 구조화된 메모리 파일로 저장된 세션 컨텍스트
-- 영구적으로 보존된 프로젝트 결정 및 아키텍처 패턴
-- 대화 전반에 걸쳐 유지되는 코드 분석 결과 및 통찰력
-- 장기적으로 유지되는 진행 상황 추적 및 마일스톤 데이터
-
-**교차 세션 연속성**:
-- 새 대화에서 자동으로 사용 가능한 이전 세션 컨텍스트
-- 대화 전반에 걸쳐 보존되고 액세스 가능한 결정 및 근거
-- 과거 패턴 및 솔루션으로부터의 학습 유지
-- 무기한 유지되는 일관된 프로젝트 이해
-
-**메모리 유형**:
-- **프로젝트 메모리**: 장기 프로젝트 컨텍스트 및 아키텍처
-- **세션 메모리**: 특정 대화 결과 및 결정
-- **패턴 메모리**: 재사용 가능한 솔루션 및 아키텍처 패턴
-- **진행 메모리**: 마일스톤 추적 및 완료 상태
-
-## 지속성을 갖춘 세션 라이프사이클 패턴
-
-### 새 프로젝트 초기화
-```bash
-# 1. 새 프로젝트 시작
-/sc:brainstorm "전자상거래 플랫폼 요구사항"
-
-# 2. 초기 결정을 영구 메모리에 저장
-/sc:save "프로젝트 범위 및 요구사항 정의됨"
-
-# 3. 구현 계획 시작
-/sc:workflow "사용자 인증 시스템"
-
-# 4. 아키텍처 결정을 영구적으로 저장
-/sc:save "인증 아키텍처: JWT + 리프레시 토큰 + 속도 제한"
-```
-
-### 기존 작업 재개 (교차 대화)
-```bash
-# 1. 영구 메모리에서 이전 컨텍스트 로드
-/sc:load "e-commerce-project"
-
-# 2. 저장된 진행 상황에 대한 현재 상태 평가
-/sc:reflect --scope project
-
-# 3. 저장된 컨텍스트를 사용하여 다음 단계 계속
-/sc:implement "결제 처리 통합"
-
-# 4. 진행 상황 체크포인트를 메모리에 저장
-/sc:save "Stripe API와 결제 시스템 통합됨"
-```
-
-### 장기 프로젝트 관리
-```bash
-# 지속성을 갖춘 주간 체크포인트 패턴
-/sc:load project-name
-/sc:reflect --scope project
-# ... 기능 작업 ...
-/sc:save "N주차 진행: 기능 X, Y, Z 완료"
-
-# 메모리를 사용한 단계 완료 패턴
-/sc:reflect --scope project
-/sc:save "1단계 완료: 핵심 인증 및 사용자 관리"
-/sc:workflow "2단계: 결제 및 주문 처리"
-```
-
-## 교차 대화 연속성
-
-### 지속성을 갖춘 새 대화 시작
-
-새 Claude Code 대화를 시작할 때 영구 메모리 시스템이 다음을 허용합니다:
-
-1. **자동 컨텍스트 복원**
- ```bash
- /sc:load project-name
- # 모든 이전 컨텍스트, 결정, 진행 상황을 자동으로 복원
- ```
-
-2. **진행 계속**
- - 이전 세션 결정을 즉시 사용 가능
- - 아키텍처 패턴 및 코드 통찰력 보존
- - 프로젝트 기록 및 근거 유지
-
-3. **지능형 컨텍스트 구축**
- - Serena MCP가 현재 작업에 기반하여 관련 메모리 제공
- - 과거 솔루션 및 패턴이 새 구현 정보 제공
- - 프로젝트 진화 추적 및 이해
-
-### 메모리 최적화
-
-**효과적인 메모리 사용**:
-- 설명적이고 검색 가능한 메모리 이름 사용
-- 프로젝트 단계 및 타임스탬프 컨텍스트 포함
-- 특정 기능 또는 아키텍처 결정 참조
-- 향후 검색을 직관적으로 만들기
-
-**메모리 콘텐츠 전략**:
-- 결과뿐만 아니라 결정 및 근거 저장
-- 고려된 대안 접근법 포함
-- 통합 패턴 및 종속성 문서화
-- 향후 참조를 위한 학습 및 통찰력 보존
-
-**메모리 라이프사이클 관리**:
-- 오래된 메모리의 정기적인 정리
-- 관련 세션 메모리 통합
-- 완료된 프로젝트 단계 아카이빙
-- 쓸모없는 아키텍처 결정 정리
-
-## 영구 세션 모범 사례
-
-### 세션 시작 프로토콜
-1. 기존 프로젝트의 경우 항상 `/sc:load`로 시작
-2. `/sc:reflect`를 사용하여 메모리에서 현재 상태 이해
-3. 영구 컨텍스트 및 저장된 패턴을 기반으로 작업 계획
-4. 이전 결정 및 아키텍처 선택 기반 구축
-
-### 세션 종료 프로토콜
-1. `/sc:reflect`를 사용하여 저장된 목표에 대한 완전성 평가
-2. 향후 세션을 위해 `/sc:save`로 주요 결정 저장
-3. 메모리에 다음 단계 및 미해결 질문 문서화
-4. 원활한 향후 계속을 위한 컨텍스트 보존
-
-### 메모리 품질 유지
-- 쉬운 검색을 위해 명확하고 설명적인 메모리 이름 사용
-- 결정 및 대안 접근법에 대한 컨텍스트 포함
-- 특정 코드 위치 및 패턴 참조
-- 세션 전반에 걸쳐 메모리 구조의 일관성 유지
-
-## 다른 SuperClaude 기능과의 통합
-
-### MCP 서버 조정
-- **Serena MCP**: 영구 메모리 인프라 제공
-- **Sequential MCP**: 향상된 복잡한 분석을 위해 저장된 메모리 사용
-- **Context7 MCP**: 저장된 패턴 및 문서화 접근법 참조
-- **Morphllm MCP**: 저장된 리팩토링 패턴을 일관되게 적용
-
-### 메모리를 사용한 에이전트 협업
-- 에이전트가 향상된 컨텍스트를 위해 영구 메모리 액세스
-- 이전 전문가 결정이 보존되고 참조됨
-- 공유 메모리를 통한 교차 세션 에이전트 조정
-- 프로젝트 기록을 기반으로 한 일관된 전문가 권장사항
-
-### 지속성을 갖춘 명령어 통합
-- 모든 `/sc:` 명령어가 영구 컨텍스트를 참조하고 구축 가능
-- 이전 명령어 출력 및 결정이 세션 전반에 걸쳐 사용 가능
-- 워크플로우 패턴이 저장되고 재사용 가능
-- 구현 기록이 향후 명령어 결정 안내
-
-## 영구 세션 문제 해결
-
-### 일반적인 문제
-
-**메모리 로딩 안 됨**:
-- Serena MCP가 올바르게 구성되고 실행 중인지 확인
-- 메모리 파일 권한 및 접근성 확인
-- 일관된 프로젝트 명명 규칙 보장
-- 메모리 파일 무결성 및 형식 검증
-
-**세션 간 컨텍스트 손실**:
-- 세션을 종료하기 전에 항상 `/sc:save` 사용
-- 쉬운 검색을 위해 설명적인 메모리 이름 사용
-- 메모리 완전성을 검증하기 위한 정기적인 `/sc:reflect`
-- 중요한 메모리 파일을 주기적으로 백업
-
-**메모리 충돌**:
-- 버전 제어를 위해 타임스탬프가 있는 메모리 이름 사용
-- 오래된 메모리의 정기적인 정리
-- 프로젝트 및 세션 메모리 간의 명확한 분리
-- 세션 전반에 걸쳐 일관된 메모리 명명 규칙
-
-### 빠른 수정
-
-**세션 상태 재설정**:
-```bash
-/sc:load --fresh # 이전 컨텍스트 없이 시작
-/sc:reflect # 현재 상태 평가
-```
-
-**메모리 정리**:
-```bash
-/sc:reflect --cleanup # 오래된 메모리 제거
-/sc:save --consolidate # 관련 메모리 병합
-```
-
-**컨텍스트 복구**:
-```bash
-/sc:load --recent # 최근 메모리 로드
-/sc:reflect --repair # 컨텍스트 격차 식별 및 수정
-```
-
-## 고급 영구 세션 패턴
-
-### 다단계 프로젝트
-- 조직을 위한 단계별 메모리 명명 사용
-- 단계 전반에 걸쳐 아키텍처 결정 연속성 유지
-- 영구 메모리를 통한 교차 단계 종속성 추적
-- 과거 컨텍스트를 사용한 점진적 복잡성 관리
-
-### 팀 협업
-- 공유 메모리 규칙 및 명명 표준
-- 팀 컨텍스트를 위한 결정 근거 보존
-- 모든 팀원이 액세스 가능한 통합 패턴 문서
-- 메모리를 통한 일관된 코드 스타일 및 아키텍처 강제
-
-### 장기 유지보수
-- 완료된 프로젝트를 위한 메모리 아카이빙 전략
-- 누적된 메모리를 통한 패턴 라이브러리 개발
-- 시간이 지남에 따라 구축된 재사용 가능한 솔루션 문서
-- 영구 메모리 축적을 통한 지식 베이스 구축
-
-## 영구 세션 관리의 주요 이점
-
-### 프로젝트 연속성
-- 여러 대화에 걸쳐 원활한 작업 계속
-- Claude Code 세션 간 컨텍스트 손실 없음
-- 보존된 아키텍처 결정 및 기술 근거
-- 장기 프로젝트 진화 추적
-
-### 향상된 생산성
-- 프로젝트 컨텍스트를 다시 설명할 필요 감소
-- 계속 작업을 위한 더 빠른 시작 시간
-- 이전 통찰력 및 패턴 기반 구축
-- 누적 프로젝트 지식 성장
-
-### 품질 일관성
-- 세션 전반에 걸쳐 일관된 아키텍처 패턴
-- 보존된 코드 품질 결정 및 표준
-- 재사용 가능한 솔루션 및 모범 사례
-- 유지된 기술 부채 인식
-
----
-
-**핵심 요점**: Serena MCP를 통한 세션 관리는 SuperClaude를 단일 대화 지원에서 영구 프로젝트 파트너십으로 변환하여 모든 개발 단계 및 Claude Code 대화 전반에 걸쳐 컨텍스트, 결정, 학습을 유지합니다.
-
diff --git a/docs/User-Guide-zh/agents.md b/docs/User-Guide-zh/agents.md
deleted file mode 100644
index cdaa908..0000000
--- a/docs/User-Guide-zh/agents.md
+++ /dev/null
@@ -1,819 +0,0 @@
-# SuperClaude 智能体指南 🤖
-
-SuperClaude 提供了 14 个领域专业智能体,Claude Code 可以调用它们获得专业知识。
-
-
-## 🧪 测试智能体激活
-
-使用本指南之前,请验证智能体选择功能是否正常:
-
-```bash
-# 测试手动智能体调用
-@agent-python-expert "explain decorators"
-# 期望行为:Python 专家提供详细解释
-
-# 测试安全智能体自动激活
-/sc:implement "JWT authentication"
-# 期望行为:安全工程师应自动激活
-
-# 测试前端智能体自动激活
-/sc:implement "responsive navigation component"
-# 期望行为:前端架构师 + Magic MCP 应激活
-
-# 测试系统分析
-/sc:troubleshoot "slow API performance"
-# 期望行为:根因分析师 + 性能工程师激活
-
-# 测试手动和自动结合
-/sc:analyze src/
-@agent-refactoring-expert "suggest improvements"
-# 期望行为:分析后跟随重构建议
-```
-
-**如果测试失败**:检查 `~/.claude/agents/` 中是否存在智能体文件,或重启 Claude Code 会话
-
-## 核心概念
-
-### 什么是 SuperClaude 智能体?
-**智能体**是专业的 AI 领域专家,以上下文指令的形式实现,用于修改 Claude Code 的行为。每个智能体都是 `superclaude/Agents/` 目录中精心制作的 `.md` 文件,包含领域特定的专业知识、行为模式和问题解决方法。
-
-**重要提示**:智能体不是独立的 AI 模型或软件 - 它们是 Claude Code 读取的上下文配置,用于采用专门的行为。
-
-### 两种使用智能体的方式
-
-#### 1. 使用 @agent- 前缀手动调用
-```bash
-# 直接调用特定智能体
-@agent-security "review authentication implementation"
-@agent-frontend "design responsive navigation"
-@agent-architect "plan microservices migration"
-```
-
-#### 2. 自动激活Auto-Activation(行为路由)
-"自动激活"意味着 Claude Code 读取行为指令,根据您请求中的关键词和模式来调用相应的上下文。SuperClaude 提供行为指导原则,Claude 遵循这些原则路由到最合适的专业人员。
-
-> **📝 智能体"自动激活"工作原理**:
-> 智能体激活并非自动的系统逻辑——它是上下文文件中的行为指令。
-> 当文档说智能体"自动激活"时,意味着 Claude Code 读取指令,根据您请求中的关键词和模式
-> 调用特定的领域专业知识。这创造了智能路由的体验,同时保持底层机制的透明性。
-
-```bash
-# 这些命令自动激活相关智能体
-/sc:implement "JWT authentication" # → security-engineer 自动激活
-/sc:design "React dashboard" # → frontend-architect 自动激活
-/sc:troubleshoot "memory leak" # → performance-engineer 自动激活
-```
-
-**MCP 服务器** 通过专业工具提供增强功能,如 Context7(文档)、Sequential(分析)、Magic(UI)、Playwright(测试)和 Morphllm(代码转换)。
-
-**领域专家** 专注于狭窄的专业领域,提供比通用方法更深入、更准确的解决方案。
-
-### 智能体选择规则
-
-**优先级层次:**
-1. **手动覆盖** - @agent-[name] 优先于自动激活
-2. **关键词** - 直接的领域术语触发主要智能体
-3. **文件类型** - 扩展名激活语言/框架专家
-4. **复杂度** - 多步骤任务调用协调智能体
-5. **上下文** - 相关概念触发互补智能体
-
-**冲突解决:**
-- 手动调用 → 指定的智能体优先
-- 多个匹配 → 多智能体协调
-- 不明确的上下文 → 需求分析师激活
-- 高复杂度 → 系统架构师监督
-- 质量关注 → 自动包含质量保证智能体
-
-**选择决策树:**
-```
-Task Analysis →
-├─ Manual @agent-? → Use specified agent
-├─ Single Domain? → Activate primary agent
-├─ Multi-Domain? → Coordinate specialist agents
-├─ Complex System? → Add system-architect oversight
-├─ Quality Critical? → Include security + performance + quality agents
-└─ Learning Focus? → Add learning-guide + technical-writer
-```
-
-## 快速开始示例
-
-### 手动调用智能体
-```bash
-# 使用 @agent- 前缀显式调用特定智能体
-@agent-python-expert "optimize this data processing pipeline"
-@agent-quality-engineer "create comprehensive test suite"
-@agent-technical-writer "document this API with examples"
-@agent-socratic-mentor "explain this design pattern"
-```
-
-### 自动智能体协调
-```bash
-# 触发自动激活的命令
-/sc:implement "JWT authentication with rate limiting"
-# → 触发:security-engineer + backend-architect + quality-engineer
-
-/sc:design "accessible React dashboard with documentation"
-# → 触发:frontend-architect + learning-guide + technical-writer
-
-/sc:troubleshoot "slow deployment pipeline with intermittent failures"
-# → 触发:devops-architect + performance-engineer + root-cause-analyst
-
-/sc:audit "payment processing security vulnerabilities"
-# → 触发:security-engineer + quality-engineer + refactoring-expert
-```
-
-### 结合手动和自动方式
-```bash
-# 以命令开始(自动激活)
-/sc:implement "user profile system"
-
-# 然后显式添加专家审查
-@agent-security "review the profile system for OWASP compliance"
-@agent-performance-engineer "optimize database queries"
-```
-
----
-
-## SuperClaude 智能体团队 👥
-
-### 架构和系统设计智能体 🏗️
-
-### system-architect 🏢
-**专业领域:** 大规模分布式系统设计,专注于可扩展性和服务架构
-
-**自动激活:**
-- 关键词:"架构"、"微服务"、"可扩展性"、"系统设计"、"分布式"
-- 上下文:多服务系统、架构决策、技术选择
-- 复杂度:>5 个组件或跨领域集成需求
-
-**能力:**
-- 服务边界定义和微服务分解
-- 技术栈选择和集成策略
-- 可扩展性规划和性能架构
-- 事件驱动架构和消息模式
-- 数据流设计和系统集成
-
-**示例:**
-1. **电子商务平台**:为用户、产品、支付和通知服务设计微服务,采用事件源模式
-2. **实时分析**:高吞吐量数据接入架构,采用流处理和时间序列存储
-3. **多租户 SaaS**:具有租户隔离、共享基础架构和水平扩展策略的系统设计
-
-### 成功标准
-- [ ] 响应中体现系统级思维
-- [ ] 提及服务边界和集成模式
-- [ ] 包含可扩展性和可靠性考虑
-- [ ] 提供技术栈建议
-
-**验证:** `/sc:design "microservices platform"` 应该激活 system-architect
-**测试:** 输出应包含服务分解和集成模式
-**检查:** 应与 devops-architect 协调处理基础架构问题
-
-**最佳搭配:** devops-architect(基础架构)、performance-engineer(优化)、security-engineer(合规)
-
----
-
-### backend-architect ⚙️
-**专业领域**: 强大的服务端系统设计,重点关注 API 可靠性和数据完整性
-
-**自动激活**:
-- 关键词: "API", "backend", "server", "database", "REST", "GraphQL", "endpoint"
-- 文件类型: API 规范、服务器配置、数据库架构
-- 上下文: 服务端逻辑、数据持久化、API 开发
-
-**能力**:
-- RESTful 和 GraphQL API 架构和设计模式
-- 数据库架构设计和查询优化策略
-- 身份验证、授权和安全实现
-- 错误处理、日志记录和监控集成
-- 缓存策略和性能优化
-
-**示例**:
-1. **用户管理 API**: JWT 身份验证与基于角色的访问控制和速率限制
-2. **支付处理**: PCI 合规的交易处理与幂等性和审计跟踪
-3. **内容管理**: 带有缓存、分页和实时通知的 RESTful APIs
-
-**最佳搭配**: security-engineer(身份验证/安全)、performance-engineer(优化)、quality-engineer(测试)
-
----
-
-### frontend-architect 🎨
-**专业领域**: 现代 Web 应用程序架构,重点关注可访问性和用户体验
-
-**自动激活**:
-- 关键词: "UI", "frontend", "React", "Vue", "Angular", "component", "accessibility", "responsive"
-- 文件类型: .jsx, .vue, .ts (前端), .css, .scss
-- 上下文: 用户界面开发、组件设计、客户端架构
-
-**能力**:
-- 组件架构和设计系统实现
-- 状态管理模式(Redux、Zustand、Pinia)
-- 无障碍合规性(WCAG 2.1)和包容性设计
-- 性能优化和包分析
-- 渐进式 Web 应用和移动优先开发
-
-**示例**:
-1. **仪表板界面**: 具有实时更新和响应式网格布局的可访问数据可视化
-2. **表单系统**: 具有验证、错误处理和无障碍功能的复杂多步骤表单
-3. **设计系统**: 具有一致样式和交互模式的可重用组件库
-
-**最佳搭配**: learning-guide(用户指导)、performance-engineer(优化)、quality-engineer(测试)
-
----
-
-### devops-architect 🚀
-**专业领域**: 基础设施自动化和部署管道设计,用于可靠的软件交付
-
-**自动激活**:
-- 关键词: "deploy", "CI/CD", "Docker", "Kubernetes", "infrastructure", "monitoring", "pipeline"
-- 文件类型: Dockerfile、docker-compose.yml、k8s 清单、CI 配置
-- 上下文: 部署流程、基础设施管理、自动化
-
-**能力**:
-- 具有自动化测试和部署的 CI/CD 管道设计
-- 容器编排和 Kubernetes 集群管理
-- 使用 Terraform 和云平台的基础设施即代码
-- 监控、日志记录和可观测性堆栈实现
-- 安全扫描和合规自动化
-
-**示例**:
-1. **微服务部署**: 具有服务网格、自动扩展和蓝绿发布的 Kubernetes 部署
-2. **多环境管道**: 具有自动化测试、安全扫描和分阶段部署的 GitOps 工作流
-3. **监控堆栈**: 具有指标、日志、跟踪和警报系统的综合可观测性
-
-**最佳搭配**: system-architect(基础设施规划)、security-engineer(合规)、performance-engineer(监控)
-
-### 质量与分析智能体 🔍
-
-### security-engineer 🔒
-**专业领域**: 应用安全架构,重点关注威胁建模和漏洞预防
-
-**自动激活**:
-- 关键词: "security", "auth", "authentication", "vulnerability", "encryption", "compliance", "OWASP"
-- 上下文: 安全审查、身份验证流程、数据保护需求
-- 风险指标: 支付处理、用户数据、API 访问、法规合规需求
-
-**能力**:
-- 威胁建模和攻击面分析
-- 安全身份验证和授权设计(OAuth、JWT、SAML)
-- 数据加密策略和密钥管理
-- 漏洞评估和渗透测试指导
-- 安全合规(GDPR、HIPAA、PCI-DSS)实施
-
-**示例**:
-1. **OAuth 实现**: 具有令牌刷新和基于角色访问控制的安全多租户身份验证
-2. **API 安全**: 速率限制、输入验证、SQL 注入防护和安全头
-3. **数据保护**: 静态/传输加密、密钥轮转和隐私设计架构
-
-**最佳搭配**: backend-architect(API 安全)、quality-engineer(安全测试)、root-cause-analyst(事件响应)
-
----
-
-### performance-engineer ⚡
-**专业领域**: 系统性能优化,重点关注可扩展性和资源效率
-
-**自动激活**:
-- 关键词: "performance", "slow", "optimization", "bottleneck", "latency", "memory", "CPU"
-- 上下文: 性能问题、可扩展性担忧、资源约束
-- 指标: 响应时间 >500ms、高内存使用、低吞吐量
-
-**能力**:
-- 性能分析和瓶颈识别
-- 数据库查询优化和索引策略
-- 缓存实现(Redis、CDN、应用级别)
-- 负载测试和容量规划
-- 内存管理和资源优化
-
-**示例**:
-1. **API 优化**: 通过缓存和查询优化将响应时间从 2 秒减少到 200ms
-2. **数据库扩展**: 实现读副本、连接池和查询结果缓存
-3. **前端性能**: 包优化、延迟加载和 CDN 实现,实现 <3 秒加载时间
-
-**最佳搭配**: system-architect(可扩展性)、devops-architect(基础设施)、root-cause-analyst(调试)
-
----
-
-### root-cause-analyst 🔍
-**专业领域**: 使用基于证据的分析和假设测试进行系统化问题调查
-
-**自动激活**:
-- 关键词: "bug", "issue", "problem", "debugging", "investigation", "troubleshoot", "error"
-- 上下文: 系统故障、意外行为、复杂的多组件问题
-- 复杂性: 需要有方法的调查的跨系统问题
-
-**能力**:
-- 系统化调试方法和根本原因分析
-- 跨系统的错误关联和依赖关系映射
-- 日志分析和故障调查的模式识别
-- 复杂问题的假设形成和测试
-- 事件响应和事后分析程序
-
-**示例**:
-1. **数据库连接失败**: 通过连接池、网络超时和资源限制跟踪间歇性故障
-2. **支付处理错误**: 通过 API 日志、数据库状态和外部服务响应调查交易失败
-3. **性能降级**: 通过指标关联、资源使用和代码更改分析逐渐放慢
-
-**最佳搭配**: performance-engineer(性能问题)、security-engineer(安全事件)、quality-engineer(测试失败)
-
----
-
-### quality-engineer ✅
-**专业领域**: 综合测试策略和质量保证,重点关注自动化和覆盖率
-
-**自动激活**:
-- 关键词: "test", "testing", "quality", "QA", "validation", "coverage", "automation"
-- 上下文: 测试规划、质量门禁、验证需求
-- 质量担忧: 代码覆盖率 <80%、缺少测试自动化、质量问题
-
-**能力**:
-- 测试策略设计(单元、集成、端到端、性能测试)
-- 测试自动化框架实现和 CI/CD 集成
-- 质量指标定义和监控(覆盖率、缺陷率)
-- 边缘用例识别和边界测试场景
-- 无障碍测试和合规验证
-
-**示例**:
-1. **电子商务测试**: 涵盖用户流程、支付处理和库存管理的综合测试套件
-2. **API 测试**: REST/GraphQL API 的自动化合约测试、负载测试和安全测试
-3. **无障碍验证**: WCAG 2.1 合规测试,包括自动化和手动无障碍审计
-
-**最佳搭配**: security-engineer(安全测试)、performance-engineer(负载测试)、frontend-architect(UI 测试)
-
----
-
-### refactoring-expert 🔧
-**专业领域**: 通过系统化重构和技术债务管理来改进代码质量
-
-**自动激活**:
-- 关键词: "refactor", "clean code", "technical debt", "SOLID", "maintainability", "code smell"
-- 上下文: 遗留代码改进、架构更新、代码质量问题
-- 质量指标: 高复杂性、重复代码、较低的测试覆盖率
-
-**能力**:
-- SOLID 原则应用和设计模式实现
-- 代码异味识别和系统性消除
-- 遗留代码现代化策略和迁移规划
-- 技术债务评估和优先级框架
-- 代码结构改进和架构重构
-
-**示例**:
-1. **遗留现代化**: 将单体应用转换为具有改进可测试性的模块化架构
-2. **设计模式**: 为支付处理实现策略模式,以减少耦合并提高扩展性
-3. **代码清理**: 移除重复代码、改进命名约定和提取可重用组件
-
-**最佳搭配**: system-architect(架构改进)、quality-engineer(测试策略)、python-expert(语言特定模式)
-
-### 专业化开发智能体 🎯
-
-### python-expert 🐍
-**专业领域**: 生产就绪的 Python 开发,重点关注现代框架和性能
-
-**自动激活**:
-- 关键词: "Python", "Django", "FastAPI", "Flask", "asyncio", "pandas", "pytest"
-- 文件类型: .py、requirements.txt、pyproject.toml、Pipfile
-- 上下文: Python 开发任务、API 开发、数据处理、测试
-
-**能力**:
-- 现代 Python 架构模式和框架选择
-- 使用 asyncio 和并发 futures 的异步编程
-- 通过性能分析和算法改进进行性能优化
-- 使用 pytest、fixture 和测试自动化的测试策略
-- 使用 pip、poetry 和 Docker 的包管理和部署
-
-**示例**:
-1. **FastAPI 微服务**: 具有 Pydantic 验证、依赖注入和 OpenAPI 文档的高性能异步 API
-2. **数据管道**: 基于 Pandas 的 ETL,具有错误处理、日志记录和大数据集的并行处理
-3. **Django 应用**: 具有自定义用户模型、API 端点和综合测试覆盖的全栈 Web 应用
-
-**最佳搭配**: backend-architect(API 设计)、quality-engineer(测试)、performance-engineer(优化)
-
----
-
-### requirements-analyst 📝
-**专业领域**: 通过系统化利益相关者分析进行需求发现和规范开发
-
-**自动激活**:
-- 关键词: "requirements", "specification", "PRD", "user story", "functional", "scope", "stakeholder"
-- 上下文: 项目启动、不明确的需求、范围定义需求
-- 复杂性: 多利益相关者项目、不明确的目标、相互冲突的需求
-
-**能力**:
-- 通过利益相关者访谈和研讨会进行需求引出
-- 具有接受标准和完成定义的用户故事编写
-- 功能和非功能规范文档编制
-- 利益相关者分析和需求优先级框架
-- 范围管理和变更控制流程
-
-**示例**:
-1. **产品需求文档**: 金融科技移动应用的综合 PRD,包括用户画像、功能规范和成功指标
-2. **API 规范**: 支付处理 API 的详细需求,包括错误处理、安全和性能标准
-3. **迁移需求**: 遗留系统现代化需求,包括数据迁移、用户培训和回滚程序
-
-**最佳搭配**: system-architect(技术可行性)、technical-writer(文档)、learning-guide(用户指导)
-
-### 沟通与学习智能体 📚
-
-### technical-writer 📚
-**专业领域**: 技术文档和沟通,重点关注受众分析和清晰性
-
-**自动激活**:
-- 关键词: "documentation", "readme", "API docs", "user guide", "technical writing", "manual"
-- 上下文: 文档请求、API 文档、用户指南、技术解释
-- 文件类型: .md、.rst、API 规范、文档文件
-
-**能力**:
-- 技术文档架构和信息设计
-- 受众分析和面向不同技能水平的内容定位
-- 具有工作示例和集成指导的 API 文档
-- 具有分步程序和故障排除的用户指南创建
-- 无障碍标准应用和包容性语言使用
-
-**示例**:
-1. **API 文档**: 具有身份验证、端点、示例和 SDK 集成指南的综合 REST API 文档
-2. **用户手册**: 具有截图、故障排除和 FAQ 部分的分步安装和配置指南
-3. **技术规范**: 具有图表、数据流和实现细节的系统架构文档
-
-**最佳搭配**: requirements-analyst(规范清晰度)、learning-guide(教育内容)、frontend-architect(UI 文档)
-
----
-
-### learning-guide 🎓
-**专业领域**: 教育内容设计和渐进式学习,重点关注技能开发和指导
-
-**自动激活**:
-- 关键词: "explain", "learn", "tutorial", "beginner", "teaching", "education", "training"
-- 上下文: 教育请求、概念解释、技能开发、学习路径
-- 复杂性: 需要分步骤分解和渐进理解的复杂主题
-
-**能力**:
-- 具有渐进技能开发的学习路径设计
-- 通过类比和示例进行复杂概念解释
-- 具有实践练习的交互式教程创建
-- 技能评估和能力评估框架
-- 指导策略和个性化学习方法
-
-**示例**:
-1. **编程教程**: 具有实践练习、代码示例和渐进复杂性的交互式 React 教程
-2. **概念解释**: 通过实际示例、视觉图表和练习解释数据库规范化
-3. **技能评估**: 具有实际项目和反馈的全栈开发综合评估框架
-
-**最佳搭配**: technical-writer(教育文档)、frontend-architect(交互学习)、requirements-analyst(学习目标)
-
----
-
-## 智能体协调与集成 🤝
-
-### 协调模式
-
-**架构团队**:
-- **全栈开发**: frontend-architect + backend-architect + security-engineer + quality-engineer
-- **系统设计**: system-architect + devops-architect + performance-engineer + security-engineer
-- **遗留现代化**: refactoring-expert + system-architect + quality-engineer + technical-writer
-
-**质量团队**:
-- **安全审计**: security-engineer + quality-engineer + root-cause-analyst + requirements-analyst
-- **性能优化**: performance-engineer + system-architect + devops-architect + root-cause-analyst
-- **测试策略**: quality-engineer + security-engineer + performance-engineer + frontend-architect
-
-**沟通团队**:
-- **文档项目**: technical-writer + requirements-analyst + learning-guide + domain experts
-- **学习平台**: learning-guide + frontend-architect + technical-writer + quality-engineer
-- **API 文档**: backend-architect + technical-writer + security-engineer + quality-engineer
-
-### MCP 服务器集成
-
-**通过 MCP 服务器增强能力**:
-- **Context7**: 为所有架构师和专家提供官方文档模式
-- **Sequential**: 为 root-cause-analyst、system-architect、performance-engineer 提供多步骤分析
-- **Magic**: 为 frontend-architect 提供 UI 生成,为 learning-guide 提供交互内容
-- **Playwright**: 为 quality-engineer 提供浏览器测试,为 frontend-architect 提供无障碍验证
-- **Morphllm**: 为 refactoring-expert 提供代码转换,为 python-expert 提供批量更改
-- **Serena**: 为所有智能体提供项目内存,在会话间保持上下文
-
-### 智能体激活故障排除
-
-## 故障排除
-
-获取故障排除帮助,请参阅:
-- [常见问题](../Reference/common-issues.md) - 常见问题的快速修复
-- [故障排除指南](../Reference/troubleshooting.md) - 综合问题解决
-
-### 常见问题
-- **无智能体激活**: 使用领域关键词:"security"、"performance"、"frontend"
-- **选择了错误的智能体**: 检查智能体文档中的触发关键词
-- **智能体过多**: 将关键词聚焦在主要领域或使用 `/sc:focus [领域]`
-- **智能体不协调**: 增加任务复杂性或使用多领域关键词
-- **智能体专业知识不匹配**: 使用更具体的技术术语
-
-### 即时修复
-- **强制激活智能体**: 在请求中使用明确的领域关键词
-- **重置智能体选择**: 重启 Claude Code 会话以重置智能体状态
-- **检查智能体模式**: 查看智能体文档中的触发关键词
-- **测试基本激活**: 尝试 `/sc:implement "security auth"` 测试 security-engineer
-
-### 特定智能体故障排除
-
-**无安全智能体:**
-```bash
-# 问题:安全问题未触发 security-engineer
-# 快速修复:使用明确的安全关键词
-"实现身份验证" # 通用 - 可能不会触发
-"实现 JWT 身份验证安全" # 明确 - 触发 security-engineer
-"使用加密的安全用户登录" # 安全聚焦 - 触发 security-engineer
-```
-
-**无性能智能体:**
-```bash
-# 问题:性能问题未触发 performance-engineer
-# 快速修复:使用性能相关术语
-"让它更快" # 模糊 - 可能不会触发
-"优化缓慢的数据库查询" # 具体 - 触发 performance-engineer
-"减少 API 延迟和瓶颈" # 性能聚焦 - 触发 performance-engineer
-```
-
-**无架构智能体:**
-```bash
-# 问题:系统设计未触发架构智能体
-# 快速修复:使用架构关键词
-"构建一个应用" # 通用 - 触发基本智能体
-"设计微服务架构" # 具体 - 触发 system-architect
-"可扩展的分布式系统设计" # 架构聚焦 - 触发 system-architect
-```
-
-**错误的智能体组合:**
-```bash
-# 问题:在后端任务中获得前端智能体
-# 快速修复:使用领域特定术语
-"创建用户界面" # 可能触发 frontend-architect
-"创建 REST API 端点" # 具体 - 触发 backend-architect
-"实现服务端身份验证" # 后端聚焦 - 触发 backend-architect
-```
-
-### 支持级别
-
-**快速修复:**
-- 从智能体触发表中使用明确的领域关键词
-- 尝试重启 Claude Code 会话
-- 聚焦在单一领域以避免混淆
-
-**详细帮助:**
-- 查看[常见问题指南](../Reference/common-issues.md)了解智能体安装问题
-- 查看目标智能体的触发关键词
-
-**专家支持:**
-- 使用 `SuperClaude install --diagnose`
-- 查看[诊断参考指南](../Reference/diagnostic-reference.md)进行协调分析
-
-**社区支持:**
-- 在 [GitHub Issues](https://github.com/SuperClaude-Org/SuperClaude_Framework/issues) 报告问题
-- 包括预期与实际智能体激活的示例
-
-### 成功验证
-
-应用智能体修复后,请测试:
-- [ ] 领域特定请求激活正确的智能体(security → security-engineer)
-- [ ] 复杂任务触发多智能体协调(3+ 智能体)
-- [ ] 智能体专业知识匹配任务需求(API → backend-architect)
-- [ ] 质量智能体在适当时自动包含(安全、性能、测试)
-- [ ] 响应显示领域专业知识和专业化知识
-
-## 快速故障排除(遗留)
-- **无智能体激活** → 使用领域关键词:"security"、"performance"、"frontend"
-- **错误的智能体** → 检查智能体文档中的触发关键词
-- **智能体过多** → 将关键词聚焦在主要领域
-- **智能体不协调** → 增加任务复杂性或使用多领域关键词
-
-**智能体未激活?**
-1. **检查关键词**: 使用领域特定术语(例如,对于 security-engineer 使用 "authentication" 而不是 "login")
-2. **添加上下文**: 包含文件类型、框架或特定技术
-3. **增加复杂性**: 多领域问题会触发更多智能体
-4. **使用示例**: 引用与智能体专业知识匹配的具体场景
-
-**智能体过多?**
-- 将关键词聚焦在主要领域需求上
-- 使用 `/sc:focus [领域]` 限制范围
-- 从特定智能体开始,按需扩展
-
-**错误的智能体?**
-- 查看智能体文档中的触发关键词
-- 为目标领域使用更具体的术语
-- 添加明确的需求或约束
-
-## 快速参考 📋
-
-### 智能体触发查找
-
-| 触发类型 | 关键词/模式 | 激活的智能体 |
-|-------------|-------------------|------------------|
-| **安全** | "auth", "security", "vulnerability", "encryption" | security-engineer |
-| **性能** | "slow", "optimization", "bottleneck", "latency" | performance-engineer |
-| **前端** | "UI", "React", "Vue", "component", "responsive" | frontend-architect |
-| **后端** | "API", "server", "database", "REST", "GraphQL" | backend-architect |
-| **测试** | "test", "QA", "validation", "coverage" | quality-engineer |
-| **DevOps** | "deploy", "CI/CD", "Docker", "Kubernetes" | devops-architect |
-| **架构** | "architecture", "microservices", "scalability" | system-architect |
-| **Python** | ".py", "Django", "FastAPI", "asyncio" | python-expert |
-| **问题** | "bug", "issue", "debugging", "troubleshoot" | root-cause-analyst |
-| **代码质量** | "refactor", "clean code", "technical debt" | refactoring-expert |
-| **文档** | "documentation", "readme", "API docs" | technical-writer |
-| **学习** | "explain", "tutorial", "beginner", "teaching" | learning-guide |
-| **需求** | "requirements", "PRD", "specification" | requirements-analyst |
-
-### 命令-智能体映射
-
-| 命令 | 主要智能体 | 支持智能体 |
-|---------|----------------|-------------------|
-| `/sc:implement` | Domain architects (frontend, backend) | security-engineer, quality-engineer |
-| `/sc:analyze` | quality-engineer, security-engineer | performance-engineer, root-cause-analyst |
-| `/sc:troubleshoot` | root-cause-analyst | Domain specialists, performance-engineer |
-| `/sc:improve` | refactoring-expert | quality-engineer, performance-engineer |
-| `/sc:document` | technical-writer | Domain specialists, learning-guide |
-| `/sc:design` | system-architect | Domain architects, requirements-analyst |
-| `/sc:test` | quality-engineer | security-engineer, performance-engineer |
-| `/sc:explain` | learning-guide | technical-writer, domain specialists |
-
-### 有效的智能体组合
-
-**开发工作流**:
-- Web 应用: frontend-architect + backend-architect + security-engineer + quality-engineer + devops-architect
-- API 开发: backend-architect + security-engineer + technical-writer + quality-engineer
-- 数据平台: python-expert + performance-engineer + security-engineer + system-architect
-
-**分析工作流**:
-- 安全审计: security-engineer + quality-engineer + root-cause-analyst + technical-writer
-- 性能调查: performance-engineer + root-cause-analyst + system-architect + devops-architect
-- 遗留评估: refactoring-expert + system-architect + quality-engineer + security-engineer + technical-writer
-
-**沟通工作流**:
-- 技术文档: technical-writer + requirements-analyst + domain experts + learning-guide
-- 教育内容: learning-guide + technical-writer + frontend-architect + quality-engineer
-
-## 最佳实践 💡
-
-### 入门(简单方法)
-
-**自然语言优先:**
-1. **描述目标**: 使用包含领域特定关键词的自然语言
-2. **信任自动激活**: 让系统自动路由到适当的智能体
-3. **从模式中学习**: 观察不同请求类型激活的智能体
-4. **迭代和优化**: 添加具体性以吸引额外的专家智能体
-
-### 优化智能体选择
-
-**有效的关键词使用:**
-- **具体 > 通用**: 对于 security-engineer 使用 "authentication" 而不是 "login"
-- **技术术语**: 包含框架名称、技术和具体挑战
-- **上下文线索**: 提及文件类型、项目范围和复杂性指标
-- **质量关键词**: 添加 "security"、"performance"、"accessibility" 以实现全面覆盖
-
-**请求优化示例:**
-```bash
-# 通用(有限的智能体激活)
-"修复登录功能"
-
-# 优化(多智能体协调)
-"实现具有速率限制和无障碍合规的安全 JWT 身份验证"
-# → 触发: security-engineer + backend-architect + frontend-architect + quality-engineer
-```
-
-### 常见用法模式
-
-**开发工作流:**
-```bash
-# 全栈功能开发
-/sc:implement "具有实时通知的响应式用户仪表板"
-# → frontend-architect + backend-architect + performance-engineer
-
-# 带文档的 API 开发
-/sc:create "带有综合文档的支付处理 REST API"
-# → backend-architect + security-engineer + technical-writer + quality-engineer
-
-# 性能优化调查
-/sc:troubleshoot "影响用户体验的数据库查询缓慢"
-# → performance-engineer + root-cause-analyst + backend-architect
-```
-
-**分析工作流:**
-```bash
-# 安全评估
-/sc:analyze "身份验证系统的 GDPR 合规漏洞"
-# → security-engineer + quality-engineer + requirements-analyst
-
-# 代码质量审查
-/sc:review "遗留代码库的现代化机会"
-# → refactoring-expert + system-architect + quality-engineer + technical-writer
-
-# 学习和解释
-/sc:explain "带实践示例的微服务模式"
-# → system-architect + learning-guide + technical-writer
-```
-
-### 高级智能体协调
-
-**多领域项目:**
-- **从广泛开始**: 从系统级关键词开始以吸引架构智能体
-- **添加具体性**: 包含领域特定需求以激活专家智能体
-- **质量集成**: 自动包含安全、性能和测试视角
-- **文档包含**: 添加学习或文档需求以实现全面覆盖
-
-**智能体选择故障排除:**
-
-**问题:错误的智能体激活**
-- 解决方案:使用更具体的领域术语
-- 示例:"数据库优化" → performance-engineer + backend-architect
-
-**问题:智能体不够**
-- 解决方案:增加复杂性指标和跨领域关键词
-- 示例:向请求添加 "security"、"performance"、"documentation"
-
-**问题:智能体过多**
-- 解决方案:使用具体技术术语聚焦于主要领域
-- 示例:使用 "/sc:focus backend" 来限制范围
-
-### 质量驱动开发
-
-**安全优先方法:**
-始终在开发请求中包含安全考虑,以在领域专家之外自动吸引 security-engineer。
-
-**性能集成:**
-包含性能关键词("fast"、"efficient"、"scalable")以确保从一开始就有 performance-engineer 的协调。
-
-**无障碍合规:**
-使用 "accessible"、"WCAG" 或 "inclusive" 在前端开发中自动包含无障碍验证。
-
-**文档文化:**
-向请求添加 "documented"、"explained" 或 "tutorial" 以自动包含 technical-writer 和知识转移。
-
----
-
-## 理解智能体智能 🧠
-
-### 使智能体高效的因素
-
-**领域专业知识**: 每个智能体都具有专业知识模式、行为方法和针对其领域的问题解决方法。
-
-**上下文激活**: 智能体分析请求上下文,而不仅仅是关键词,以确定相关性和参与程度。
-
-**协作智能**: 多智能体协调产生的协同结果超越了单个智能体的能力。
-
-**自适应学习**: 智能体选择根据请求模式和成功的协调结果不断改进。
-
-### 智能体与传统 AI
-
-**传统方法**: 单个 AI 以不同的专业知识水平处理所有领域
-**智能体方法**: 专业专家以深度领域知识和聚焦问题解决进行协作
-
-**优点**:
-- 在领域特定任务中更高的准确性
-- 更复杂的问题解决方法
-- 通过专家审查实现更好的质量保证
-- 协调的多视角分析
-
-### 信任系统,理解模式
-
-**期望什么**:
-- 自动路由到适当的领域专家
-- 复杂任务的多智能体协调
-- 通过自动包含 QA 智能体实现质量集成
-- 通过教育智能体激活的学习机会
-
-**不用担心什么**:
-- 手动选择或配置智能体
-- 复杂的路由规则或智能体管理
-- 智能体配置或协调
-- 微管理智能体交互
-
----
-
-## 相关资源 📚
-
-### 基本文档
-- **[命令指南](commands.md)** - 掌握触发最优智能体协调的 SuperClaude 命令
-- **[MCP 服务器](mcp-servers.md)** - 通过专业化工具集成增强智能体能力
-- **[会话管理](session-management.md)** - 具有持久智能体上下文的长期工作流
-
-### 高级用法
-- **[行为模式](modes.md)** - 用于增强智能体协调的上下文优化
-- **[入门指南](../Getting-Started/quick-start.md)** - 智能体优化的专家技巧
-- **[示例食谱](../Reference/examples-cookbook.md)** - 实际的智能体协调模式
-
-### 开发资源
-- **[技术架构](../Developer-Guide/technical-architecture.md)** - 理解 SuperClaude 的智能体系统设计
-- **[贡献指南](../Developer-Guide/contributing-code.md)** - 扩展智能体能力和协调模式
-
----
-
-## 您的智能体之旅 🚀
-
-**第 1 周:自然使用**
-从自然语言描述开始。注意哪些智能体会激活以及原因。在不过度思考过程的情况下建立对关键词模式的直觉。
-
-**第 2-3 周:模式识别**
-观察智能体协调模式。理解复杂性和领域关键词如何影响智能体选择。开始优化请求措辞以实现更好的协调。
-
-**第 2 个月+:专家协调**
-掌握触发最优智能体组合的多领域请求。利用故障排除技巧进行有效的智能体选择。使用高级模式处理复杂工作流。
-
-**SuperClaude 优势:**
-体验 14 个专业 AI 专家协调响应的威力,所有这一切都通过简单的自然语言请求实现。无需配置,无需管理,只有随您的需求而扩展的智能协作。
-
-🎯 **准备体验智能智能体协调?从 `/sc:implement` 开始,发现专业 AI 协作的魔力。**
\ No newline at end of file
diff --git a/docs/User-Guide-zh/commands.md b/docs/User-Guide-zh/commands.md
deleted file mode 100644
index b45261b..0000000
--- a/docs/User-Guide-zh/commands.md
+++ /dev/null
@@ -1,305 +0,0 @@
-# SuperClaude 命令指南
-
-SuperClaude 为 Claude Code 提供 21 个命令:用于工作流的 `/sc:*` 命令和用于专家的 `@agent-*`。
-
-## 命令类型
-
-| 类型 | 使用位置 | 格式 | 示例 |
-|------|------------|--------|---------|
-| **斜杠命令** | Claude Code | `/sc:[command]` | `/sc:implement "feature"` |
-| **智能体** | Claude Code | `@agent-[name]` | `@agent-security "review"` |
-| **安装命令** | 终端 | `SuperClaude [command]` | `SuperClaude install` |
-
-## 快速测试
-```bash
-# 终端:验证安装
-python3 -m SuperClaude --version
-# Claude Code CLI 验证:claude --version
-
-# Claude Code:测试命令
-/sc:brainstorm "test project" # 应该询问发现性问题
-/sc:analyze README.md # 应该提供分析
-```
-
-**工作流**:`/sc:brainstorm "idea"` → `/sc:implement "feature"` → `/sc:test`
-
-## 🎯 理解 SuperClaude 命令
-
-## SuperClaude 如何工作
-
-SuperClaude 提供行为上下文文件,Claude Code 通过读取这些文件来采用专门的行为。当您键入 `/sc:implement` 时,Claude Code 读取 `implement.md` 上下文文件并遵循其行为指令。
-
-**SuperClaude 命令不是由软件执行的** - 它们是上下文触发器,通过读取框架中的专门指令文件来修改 Claude Code 的行为。
-
-### 命令类型:
-- **斜杠命令** (`/sc:*`):触发工作流模式和行为模式
-- **智能体调用** (`@agent-*`):手动激活特定领域专家
-- **标志** (`--think`、`--safe-mode`):修改命令行为和深度
-
-### 上下文机制:
-1. **用户输入**:您输入 `/sc:implement "auth system"`
-2. **上下文加载**:Claude Code 读取 `~/.claude/superclaude/Commands/implement.md`
-3. **行为采用**:Claude 运用专业知识进行工具选择和验证
-4. **增强输出**:带有安全考虑和最佳实践的结构化实现
-
-**关键要点**:这通过上下文管理而不是传统的软件执行来创建复杂的开发工作流。
-
-### 安装命令 vs 使用命令
-
-**🖥️ 终端命令** (实际 CLI 软件):
-- `SuperClaude install` - 安装框架组件
-- `SuperClaude update` - 更新现有安装
-- `SuperClaude uninstall` - 卸载框架安装
-- `python3 -m SuperClaude --version` - 检查安装状态
-
-**💬 Claude Code 命令** (上下文触发器):
-- `/sc:brainstorm` - 激活需求发现上下文
-- `/sc:implement` - 激活特性开发上下文
-- `@agent-security` - 激活安全专家上下文
-- 所有命令仅在 Claude Code 聊天界面中工作
-
-
-> **快速开始**:尝试 `/sc:brainstorm "your project idea"` → `/sc:implement "feature name"` → `/sc:test` 体验核心工作流。
-
-## 🧪 Testing Your Setup
-
-### 🖥️ 终端验证(在终端/CMD 中运行)
-```bash
-# 验证 SuperClaude 是否正常工作(主要方法)
-python3 -m SuperClaude --version
-# 示例输出:SuperClaude 4.1.5
-
-# Claude Code CLI 版本检查
-claude --version
-
-# 检查已安装的组件
-python3 -m SuperClaude install --list-components | grep mcp
-# 示例输出:显示已安装的 MCP 组件
-```
-
-### 💬 Claude Code 测试(在 Claude Code 聊天中输入)
-```
-# 测试基本 /sc: 命令
-/sc:brainstorm "test project"
-# 示例行为:开始交互式需求发现
-
-# 测试命令帮助
-/sc:help
-# 示例行为:显示可用命令列表
-```
-
-**如果测试失败**:检查 [安装指南](../Getting-Started/installation.md) 或 [故障排除](#troubleshooting)
-
-### 📝 Command Quick Reference
-
-| Command Type | Where to Run | Format | Purpose | Example |
-|-------------|--------------|--------|---------|----------|
-| **🖥️ 安装** | 终端/CMD | `SuperClaude [command]` | 设置和维护 | `SuperClaude install` |
-| **🔧 配置** | 终端/CMD | `python3 -m SuperClaude [command]` | 高级配置 | `python3 -m SuperClaude --version` |
-| **💬 斜杠命令** | Claude Code | `/sc:[command]` | 工作流自动化 | `/sc:implement "feature"` |
-| **🤖 智能体调用** | Claude Code | `@agent-[name]` | 手动专家激活 | `@agent-security "review"` |
-| **⚡ 增强标志** | Claude Code | `/sc:[command] --flags` | 行为修改 | `/sc:analyze --think-hard` |
-
-> **记住**:所有 `/sc:` 命令和 `@agent-` 调用都在 Claude Code 聊天中工作,而不是在您的终端中。它们触发 Claude Code 从 SuperClaude 框架中读取特定的上下文文件。
-
-## 目录
-
-- [基本命令](#essential-commands) - 从这里开始(8 个核心命令)
-- [常用工作流](#common-workflows) - 有效的命令组合
-- [完整命令参考](#full-command-reference) - 所有 21 个命令按类别组织
-- [故障排除](#troubleshooting) - 常见问题和解决方案
-- [命令索引](#command-index) - 按类别查找命令
-
----
-
-## 基本命令
-
-**立即提高生产力的核心工作流命令:**
-
-### `/sc:brainstorm` - 项目发现
-**目的**:交互式需求发现和项目规划
-**语法**:`/sc:brainstorm "您的想法"` `[--strategy systematic|creative]`
-
-**使用案例**:
-- 新项目规划:`/sc:brainstorm "e-commerce platform"`
-- 特性探索:`/sc:brainstorm "user authentication system"`
-- 问题解决:`/sc:brainstorm "slow database queries"``
-
-### `/sc:implement` - 功能开发
-**目的**: 通过智能专家路由进行全栈功能实现
-**语法**: `/sc:implement "feature description"` `[--type frontend|backend|fullstack] [--focus security|performance]`
-
-**使用场景**:
-- 身份验证: `/sc:implement "JWT login system"`
-- UI 组件: `/sc:implement "responsive dashboard"`
-- APIs: `/sc:implement "REST user endpoints"`
-- 数据库: `/sc:implement "user schema with relationships"`
-
-### `/sc:analyze` - 代码评估
-**目的**: 跨质量、安全性和性能的综合代码分析
-**语法**: `/sc:analyze [path]` `[--focus quality|security|performance|architecture]`
-
-**使用场景**:
-- 项目健康: `/sc:analyze .`
-- 安全审计: `/sc:analyze --focus security`
-- 性能评审: `/sc:analyze --focus performance`
-
-### `/sc:troubleshoot` - 问题诊断
-**目的**: 系统化问题诊断与根本原因分析
-**语法**: `/sc:troubleshoot "问题描述"` `[--type build|runtime|performance]`
-
-**使用场景**:
-- 运行时错误: `/sc:troubleshoot "登录时出现500错误"`
-- 构建失败: `/sc:troubleshoot --type build`
-- 性能问题: `/sc:troubleshoot "页面加载缓慢"`
-
-### `/sc:test` - 质量保证
-**目的**: 全面测试与覆盖率分析
-**语法**: `/sc:test` `[--type unit|integration|e2e] [--coverage] [--fix]`
-
-**使用场景**:
-- 完整测试套件: `/sc:test --coverage`
-- 单元测试: `/sc:test --type unit --watch`
-- 端到端验证: `/sc:test --type e2e`
-
-### `/sc:improve` - 代码增强
-**目的**: 应用系统化的代码改进和优化
-**语法**: `/sc:improve [path]` `[--type performance|quality|security] [--preview]`
-
-**使用场景**:
-- 常规改进: `/sc:improve src/`
-- 性能优化: `/sc:improve --type performance`
-- 安全加固: `/sc:improve --type security`
-
-### `/sc:document` - 文档生成
-**目的**: 为代码和API生成全面的文档
-**语法**: `/sc:document [path]` `[--type api|user-guide|technical] [--format markdown|html]`
-
-**使用场景**:
-- API文档: `/sc:document --type api`
-- 用户指南: `/sc:document --type user-guide`
-- 技术文档: `/sc:document --type technical`
-
-### `/sc:workflow` - 实现规划
-**目的**: 从需求生成结构化的实现计划
-**语法**: `/sc:workflow "功能描述"` `[--strategy agile|waterfall] [--format markdown]`
-
-**使用场景**:
-- 功能规划: `/sc:workflow "用户身份验证"`
-- 冲刺规划: `/sc:workflow --strategy agile`
-- 架构规划: `/sc:workflow "微服务迁移"`
-
----
-
-## 常用工作流
-
-**经过验证的命令组合:**
-
-### 新项目设置
-```bash
-/sc:brainstorm "项目概念" # 定义需求
-/sc:design "系统架构" # 创建技术设计
-/sc:workflow "实现计划" # 制定开发路线图
-```
-
-### 功能开发
-```bash
-/sc:implement "功能名称" # 构建功能
-/sc:test --coverage # 通过测试验证
-/sc:document --type api # 生成文档
-```
-
-### 代码质量改进
-```bash
-/sc:analyze --focus quality # 评估当前状态
-/sc:improve --preview # 预览改进
-/sc:test --coverage # 验证变更
-```
-
-### Bug调查
-```bash
-/sc:troubleshoot "问题描述" # 诊断问题
-/sc:analyze --focus problem-area # 深度分析
-/sc:improve --fix --safe-mode # 应用针对性修复
-```
-
-## 完整命令参考
-
-### 开发命令
-| 命令 | 目的 | 最适用于 |
-|---------|---------|----------|
-| **workflow** | 实现规划 | 项目路线图,冲刺规划 |
-| **implement** | 功能开发 | 全栈功能,API开发 |
-| **build** | 项目编译 | CI/CD,生产构建 |
-| **design** | 系统架构 | API规范,数据库模式 |
-
-### 分析命令
-| 命令 | 目的 | 最适用于 |
-|---------|---------|----------|
-| **analyze** | 代码评估 | 质量审计,安全评审 |
-| **troubleshoot** | 问题诊断 | Bug调查,性能问题 |
-| **explain** | 代码解释 | 学习,代码评审 |
-
-### 质量命令
-| 命令 | 目的 | 最适用于 |
-|---------|---------|----------|
-| **improve** | 代码增强 | 性能优化,重构 |
-| **cleanup** | 技术债务 | 清理无用代码,组织整理 |
-| **test** | 质量保证 | 测试自动化,覆盖率分析 |
-| **document** | 文档生成 | API文档,用户指南 |
-
-### 项目管理
-| 命令 | 目的 | 最适用于 |
-|---------|---------|----------|
-| **estimate** | 项目估算 | 时间线规划,资源分配 |
-| **task** | 任务管理 | 复杂工作流,任务跟踪 |
-| **spawn** | 元编排 | 大型项目,并行执行 |
-
-### 实用工具命令
-| 命令 | 目的 | 最适用于 |
-|---------|---------|----------|
-| **git** | 版本控制 | 提交管理,分支策略 |
-| **index** | 命令发现 | 探索功能,查找命令 |
-
-### 会话命令
-| 命令 | 目的 | 最适用于 |
-|---------|---------|----------|
-| **load** | 上下文加载 | 会话初始化,项目启用 |
-| **save** | 会话持久化 | 检查点,上下文保存 |
-| **reflect** | 任务验证 | 进度评估,完成验证 |
-| **select-tool** | 工具优化 | 性能优化,工具选择 |
-
----
-
-## 命令索引
-
-**按功能分类:**
-- **规划**: brainstorm, design, workflow, estimate
-- **开发**: implement, build, git
-- **分析**: analyze, troubleshoot, explain
-- **质量**: improve, cleanup, test, document
-- **管理**: task, spawn, load, save, reflect
-- **工具**: index, select-tool
-
-**按复杂度分类:**
-- **初学者**: brainstorm, implement, analyze, test
-- **中级**: workflow, design, improve, document
-- **高级**: spawn, task, select-tool, reflect
-
-## 故障排除
-
-**命令问题:**
-- **命令未找到**: 验证安装: `python3 -m SuperClaude --version`
-- **无响应**: 重启 Claude Code 会话
-- **处理延迟**: 使用 `--no-mcp` 测试不使用 MCP 服务器
-
-**快速修复:**
-- 重置会话: `/sc:load` 重新初始化
-- 检查状态: `SuperClaude install --list-components`
-- 获取帮助: [故障排除指南](../Reference/troubleshooting.md)
-
-## 下一步
-
-- [标志指南](flags.md) - 控制命令行为
-- [智能体指南](agents.md) - 专家激活
-- [示例手册](../Reference/examples-cookbook.md) - 真实使用模式
\ No newline at end of file
diff --git a/docs/User-Guide-zh/flags.md b/docs/User-Guide-zh/flags.md
deleted file mode 100644
index 36f5a13..0000000
--- a/docs/User-Guide-zh/flags.md
+++ /dev/null
@@ -1,270 +0,0 @@
-# SuperClaude 标志指南 🏁
-
-**大多数标志会自动激活** - Claude Code 读取行为指令,根据您请求中的关键词和模式来调用适当的上下文。
-
-## 基本自动激活标志(90% 的使用案例)
-
-### 核心分析标志
-| 标志 | 何时激活 | 作用 |
-|------|---------------|--------------|
-| `--think` | 5+ 个文件或复杂分析 | 标准结构化分析(约 4K 令牌)|
-| `--think-hard` | 架构分析、系统依赖关系 | 深度分析(约 10K 令牌)配合增强工具 |
-| `--ultrathink` | 关键系统重设计、遗留系统现代化 | 最大深度分析(约 32K 令牌)配合所有工具 |
-
-### MCP 服务器标志
-| 标志 | 服务器 | 目的 | 自动触发 |
-|------|---------|---------|---------------|
-| `--c7` / `--context7` | Context7 | 官方文档、框架模式 | 库导入、框架问题 |
-| `--seq` / `--sequential` | Sequential | 多步推理、调试 | 复杂调试、系统设计 |
-| `--magic` | Magic | UI 组件生成 | `/ui` 命令、前端关键词 |
-| `--play` / `--playwright` | Playwright | 浏览器测试、E2E 验证 | 测试请求、视觉验证 |
-| `--morph` / `--morphllm` | Morphllm | 批量转换、模式编辑 | 批量操作、样式强制执行 |
-| `--serena` | Serena | 项目内存、符号操作 | 符号操作、大型代码库 |
-
-### 行为模式标志
-| 标志 | 何时激活 | 作用 |
-|------|---------------|--------------|
-| `--brainstorm` | 模糊请求、探索关键词 | 协作发现思维模式 |
-| `--introspect` | 自我分析、错误恢复 | 透明地展现推理过程 |
-| `--task-manage` | >3 步骤、复杂范围 | 通过委托进行协调 |
-| `--orchestrate` | 多工具操作、性能需求 | 优化工具选择和并行执行 |
-| `--token-efficient` / `--uc` | 上下文 >75%、效率需求 | 符号增强通信,减少 30-50% 令牌使用 |
-
-### 执行控制标志
-| 标志 | 何时激活 | 作用 |
-|------|---------------|--------------|
-| `--loop` | "improve"、"polish"、"refine" 关键词 | 迭代增强循环 |
-| `--safe-mode` | 生产环境,>85% 资源使用 | 最大验证,保守执行 |
-| `--validate` | 风险 >0.7,生产环境 | 执行前风险评估 |
-| `--delegate` | >7 个目录或 >50 个文件 | 子智能体并行处理 |
-
-## 特定命令标志
-
-### 分析命令标志 (`/sc:analyze`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--focus` | 针对特定领域 | `security`, `performance`, `quality`, `architecture` |
-| `--depth` | 分析彻底程度 | `quick`, `deep` |
-| `--format` | 输出格式 | `text`, `json`, `report` |
-
-### 构建命令标志 (`/sc:build`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--type` | 构建配置 | `dev`, `prod`, `test` |
-| `--clean` | 构建前清理 | 布尔值 |
-| `--optimize` | 启用优化 | 布尔值 |
-| `--verbose` | 详细输出 | 布尔值 |
-
-### 设计命令标志 (`/sc:design`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--type` | 设计目标 | `architecture`, `api`, `component`, `database` |
-| `--format` | 输出格式 | `diagram`, `spec`, `code` |
-
-### 解释命令标志 (`/sc:explain`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--level` | 复杂度级别 | `basic`, `intermediate`, `advanced` |
-| `--format` | 解释风格 | `text`, `examples`, `interactive` |
-| `--context` | 领域上下文 | 任何领域(如 `react`、`security`)|
-
-### 改进命令标志 (`/sc:improve`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--type` | 改进焦点 | `quality`, `performance`, `maintainability`, `style`, `security` |
-| `--safe` | 保守方法 | 布尔值 |
-| `--interactive` | 用户指导 | 布尔值 |
-| `--preview` | 显示但不执行 | 布尔值 |
-
-### 任务命令标志 (`/sc:task`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--strategy` | 任务方法 | `systematic`, `agile`, `enterprise` |
-| `--parallel` | 并行执行 | 布尔值 |
-| `--delegate` | 子智能体协调 | 布尔值 |
-
-### 工作流命令标志 (`/sc:workflow`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--strategy` | 工作流方法 | `systematic`, `agile`, `enterprise` |
-| `--depth` | 分析深度 | `shallow`, `normal`, `deep` |
-| `--parallel` | 并行协调 | 布尔值 |
-
-### 故障排除命令标志 (`/sc:troubleshoot`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--type` | 问题类别 | `bug`, `build`, `performance`, `deployment` |
-| `--trace` | 包含跟踪分析 | 布尔值 |
-| `--fix` | 执行修复 | 布尔值 |
-
-### 清理命令标志 (`/sc:cleanup`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--type` | 清理目标 | `code`, `imports`, `files`, `all` |
-| `--safe` / `--aggressive` | 清理强度 | 布尔值 |
-| `--interactive` | 用户指导 | 布尔值 |
-| `--preview` | 显示但不执行 | 布尔值 |
-
-### 估算命令标志 (`/sc:estimate`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--type` | 估算焦点 | `time`, `effort`, `complexity` |
-| `--unit` | 时间单位 | `hours`, `days`, `weeks` |
-| `--breakdown` | 详细分解 | 布尔值 |
-
-### 索引命令标志 (`/sc:index`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--type` | 索引目标 | `docs`, `api`, `structure`, `readme` |
-| `--format` | 输出格式 | `md`, `json`, `yaml` |
-
-### 反思命令标志 (`/sc:reflect`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--type` | 反思范围 | `task`, `session`, `completion` |
-| `--analyze` | 包含分析 | 布尔值 |
-| `--validate` | 验证完整性 | 布尔值 |
-
-### 生成命令标志 (`/sc:spawn`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--strategy` | 协调方法 | `sequential`, `parallel`, `adaptive` |
-| `--depth` | 分析深度 | `normal`, `deep` |
-
-### Git 命令标志 (`/sc:git`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--smart-commit` | 生成提交消息 | 布尔值 |
-| `--interactive` | 引导操作 | 布尔值 |
-
-### 工具选择命令标志 (`/sc:select-tool`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--analyze` | 工具分析 | 布尔值 |
-| `--explain` | 解释选择 | 布尔值 |
-
-### 测试命令标志 (`/sc:test`)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--coverage` | 包含覆盖率 | 布尔值 |
-| `--type` | 测试类型 | `unit`, `integration`, `e2e` |
-| `--watch` | 监视模式 | 布尔值 |
-
-## 高级控制标志
-
-### 范围和焦点
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--scope` | 分析边界 | `file`, `module`, `project`, `system` |
-| `--focus` | 领域定向 | `performance`, `security`, `quality`, `architecture`, `accessibility`, `testing` |
-
-### 执行控制
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--concurrency [n]` | 控制并行操作 | 1-15 |
-| `--iterations [n]` | 改进循环 | 1-10 |
-| `--all-mcp` | 启用所有 MCP 服务器 | 布尔值 |
-| `--no-mcp` | 仅使用本地工具 | 布尔值 |
-
-### 系统标志(SuperClaude 安装)
-| 标志 | 目的 | 值 |
-|------|---------|--------|
-| `--verbose` / `-v` | 详细日志 | 布尔值 |
-| `--quiet` / `-q` | 静默输出 | 布尔值 |
-| `--dry-run` | 模拟操作 | 布尔值 |
-| `--force` | 跳过检查 | 布尔值 |
-| `--yes` / `-y` | 自动确认 | 布尔值 |
-| `--install-dir` | 目标目录 | 路径 |
-| `--legacy` | 使用传统脚本 | 布尔值 |
-| `--version` | 显示版本 | 布尔值 |
-| `--help` | 显示帮助 | 布尔值 |
-
-## 常用使用模式
-
-### 前端开发
-```bash
-/sc:implement "responsive dashboard" --magic --c7
-/sc:design component-library --type component --format code
-/sc:test ui-components/ --magic --play
-/sc:improve legacy-ui/ --magic --morph --validate
-```
-
-### 后端开发
-```bash
-/sc:analyze api/ --focus performance --seq --think
-/sc:design payment-api --type api --format spec
-/sc:troubleshoot "API timeout" --type performance --trace
-/sc:improve auth-service --type security --validate
-```
-
-### 大型项目
-```bash
-/sc:analyze . --ultrathink --all-mcp --safe-mode
-/sc:workflow enterprise-system --strategy enterprise --depth deep
-/sc:cleanup . --type all --safe --interactive
-/sc:estimate "migrate to microservices" --type complexity --breakdown
-```
-
-### 质量和维护
-```bash
-/sc:improve src/ --type quality --safe --interactive
-/sc:cleanup imports --type imports --preview
-/sc:reflect --type completion --validate
-/sc:git commit --smart-commit
-```
-
-## 标志交互
-
-### 兼容组合
-- `--think` + `--c7`:带文档的分析
-- `--magic` + `--play`:UI 生成带测试
-- `--serena` + `--morph`:项目内存带转换
-- `--safe-mode` + `--validate`:最大安全性
-- `--loop` + `--validate`:带验证的迭代改进
-
-### 冲突标志
-- `--all-mcp` vs 单独的 MCP 标志(使用其中之一)
-- `--no-mcp` vs 任何 MCP 标志(--no-mcp 获胜)
-- `--safe` vs `--aggressive`(清理强度)
-- `--quiet` vs `--verbose`(输出级别)
-
-### 自动启用关系
-- `--safe-mode` 自动启用 `--uc` 和 `--validate`
-- `--ultrathink` 自动启用所有 MCP 服务器
-- `--think-hard` 自动启用 `--seq` + `--c7`
-- `--magic` 触发以 UI 为中心的智能体
-
-## 标志故障排除
-
-### 常见问题
-- **工具过多**:使用 `--no-mcp` 仅用本地工具测试
-- **操作太慢**:添加 `--uc` 压缩输出
-- **验证阻塞**:在开发中使用 `--validate` 而不是 `--safe-mode`
-- **上下文压力**:在 >75% 使用率时自动激活 `--token-efficient`
-
-### 调试标志
-```bash
-/sc:analyze . --verbose # 显示决策逻辑和标志激活
-/sc:select-tool "操作" --explain # 解释工具选择过程
-/sc:reflect --type session --analyze # 审查当前会话决策
-```
-
-### 快速修复
-```bash
-/sc:analyze . --help # 显示命令的可用标志
-/sc:analyze . --no-mcp # 仅本地执行
-/sc:cleanup . --preview # 显示将被清理的内容
-```
-
-## 标志优先级规则
-
-1. **安全第一**:`--safe-mode` > `--validate` > 优化标志
-2. **显式覆盖**:用户标志 > 自动检测
-3. **深度层次**:`--ultrathink` > `--think-hard` > `--think`
-4. **MCP 控制**:`--no-mcp` 覆盖所有单独的 MCP 标志
-5. **范围优先级**:system > project > module > file
-
-## 相关资源
-- [命令指南](commands.md) - 使用这些标志的命令
-- [MCP 服务器指南](mcp-servers.md) - 理解 MCP 标志激活
-- [会话管理](session-management.md) - 在持久会话中使用标志
\ No newline at end of file
diff --git a/docs/User-Guide-zh/mcp-servers.md b/docs/User-Guide-zh/mcp-servers.md
deleted file mode 100644
index 4f717df..0000000
--- a/docs/User-Guide-zh/mcp-servers.md
+++ /dev/null
@@ -1,272 +0,0 @@
-# SuperClaude MCP 服务器指南 🔌
-
-## 概览
-
-MCP(模型上下文协议)服务器通过专业工具扩展 Claude Code 的能力。SuperClaude 集成了 6 个 MCP 服务器,并为 Claude 提供指令,告诉它何时根据您的任务激活它们。
-
-### 🔍 现实检查
-- **MCP 服务器是什么**:提供附加工具的外部 Node.js 进程
-- **它们不是什么**:内置的 SuperClaude 功能
-- **激活如何工作**:Claude 读取指令,根据上下文使用适当的服务器
-- **它们提供什么**:扩展 Claude Code 本地能力的真实工具
-
-**核心服务器:**
-- **context7**:官方库文档和模式
-- **sequential-thinking**:多步推理和分析
-- **magic**:现代 UI 组件生成
-- **playwright**:浏览器自动化和 E2E 测试
-- **morphllm-fast-apply**:基于模式的代码转换
-- **serena**:语义代码理解和项目内存
-
-## 快速开始
-
-**设置验证**:MCP 服务器会自动激活。有关安装和故障排除,请参阅 [安装指南](../Getting-Started/installation.md) 和 [故障排除](../Reference/troubleshooting.md)。
-
-**自动激活逻辑:**
-
-| 请求包含 | 激活的服务器 |
-|-----------------|------------------|
-| 库导入、API 名称 | **context7** |
-| `--think`、调试 | **sequential-thinking** |
-| `component`、`UI`、前端 | **magic** |
-| `test`、`e2e`、`browser` | **playwright** |
-| 多文件编辑、重构 | **morphllm-fast-apply** |
-| 大型项目、会话 | **serena** |
-
-## 服务器详情
-
-### context7 📚
-**目的**:官方库文档访问
-**触发器**:导入语句、框架关键词、文档请求
-**要求**:Node.js 16+,无需 API 密钥
-
-```bash
-# 自动激活
-/sc:implement "React authentication system"
-# → 提供官方 React 模式
-
-# 手动激活
-/sc:analyze auth-system/ --c7
-```
-
-### sequential-thinking 🧠
-**目的**:结构化多步推理和系统分析
-**触发器**:复杂调试、`--think` 标志、架构分析
-**要求**:Node.js 16+,无需 API 密钥
-
-```bash
-# 自动激活
-/sc:troubleshoot "API performance issues"
-# → 启用系统性根因分析
-
-# 手动激活
-/sc:analyze --think-hard architecture/
-```
-
-### magic ✨
-**目的**:从 21st.dev 模式生成现代 UI 组件
-**触发器**:UI 请求、`/ui` 命令、组件开发
-**要求**:Node.js 16+,TWENTYFIRST_API_KEY
-
-```bash
-# 自动激活
-/sc:implement "responsive dashboard component"
-# → 使用现代模式生成可访问的 UI
-
-# API 密钥设置
-export TWENTYFIRST_API_KEY="your_key_here"
-```
-
-### playwright 🎭
-**目的**:真实浏览器自动化和 E2E 测试
-**触发器**:浏览器测试、E2E 场景、视觉验证
-**要求**:Node.js 16+,无需 API 密钥
-
-```bash
-# 自动激活
-/sc:test --type e2e "user login flow"
-# → 启用浏览器自动化测试
-
-# 手动激活
-/sc:validate "accessibility compliance" --play
-```
-
-### morphllm-fast-apply 🔄
-**目的**:高效的基于模式的代码转换
-**触发器**:多文件编辑、重构、框架迁移
-**要求**:Node.js 16+,MORPH_API_KEY
-
-```bash
-# 自动激活
-/sc:improve legacy-codebase/ --focus maintainability
-# → 在文件中应用一致的模式
-
-# API 密钥设置
-export MORPH_API_KEY="your_key_here"
-```
-
-### serena 🧭
-**目的**:带有项目内存的语义代码理解
-**触发器**:符号操作、大型代码库、会话管理
-**要求**:Python 3.9+、uv 包管理器,无需 API 密钥
-
-```bash
-# 自动激活
-/sc:load existing-project/
-# → 构建项目理解和内存
-
-# 手动激活
-/sc:refactor "extract UserService" --serena
-```
-
-## 配置
-
-**MCP 配置文件 (`~/.claude.json`):**
-```json
-{
- "mcpServers": {
- "context7": {
- "command": "npx",
- "args": ["-y", "@upstash/context7-mcp@latest"]
- },
- "sequential-thinking": {
- "command": "npx",
- "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
- },
- "magic": {
- "command": "npx",
- "args": ["@21st-dev/magic"],
- "env": {"TWENTYFIRST_API_KEY": "${TWENTYFIRST_API_KEY}"}
- },
- "playwright": {
- "command": "npx",
- "args": ["@playwright/mcp@latest"]
- },
- "morphllm-fast-apply": {
- "command": "npx",
- "args": ["@morph-llm/morph-fast-apply"],
- "env": {"MORPH_API_KEY": "${MORPH_API_KEY}"}
- },
- "serena": {
- "command": "uvx",
- "args": ["--from", "git+https://github.com/oraios/serena", "serena", "start-mcp-server", "--context", "ide-assistant"]
- }
- }
-}
-```
-
-## 使用模式
-
-**服务器控制:**
-```bash
-# 启用特定服务器
-/sc:analyze codebase/ --c7 --seq
-
-# 禁用所有 MCP 服务器
-/sc:implement "simple function" --no-mcp
-
-# 启用所有服务器
-/sc:design "complex architecture" --all-mcp
-```
-
-**多服务器协调:**
-```bash
-# 全栈开发
-/sc:implement "e-commerce checkout"
-# → Sequential:工作流分析
-# → Context7:支付模式
-# → Magic:UI 组件
-# → Serena:代码组织
-# → Playwright:E2E 测试
-```
-
-## 故障排除
-
-**常见问题:**
-- **无服务器连接**:检查 Node.js:`node --version`(需要 v16+)
-- **Context7 失败**:清除缓存:`npm cache clean --force`
-- **Magic/Morphllm 错误**:在没有 API 密钥时是预期的(付费服务)
-- **服务器超时**:重启 Claude Code 会话
-
-**快速修复:**
-```bash
-# 重置连接
-# 重启 Claude Code 会话
-
-# 检查依赖
-node --version # 应该显示 v16+
-
-# 不使用 MCP 测试
-/sc:command --no-mcp
-
-# 检查配置
-ls ~/.claude.json
-```
-
-**API 密钥配置:**
-```bash
-# 用于 Magic 服务器(UI 生成所需)
-export TWENTYFIRST_API_KEY="your_key_here"
-
-# 用于 Morphllm 服务器(批量转换所需)
-export MORPH_API_KEY="your_key_here"
-
-# 添加到 shell 配置文件以保持持久
-echo 'export TWENTYFIRST_API_KEY="your_key"' >> ~/.bashrc
-echo 'export MORPH_API_KEY="your_key"' >> ~/.bashrc
-```
-
-**环境变量使用:**
-- ✅ `TWENTYFIRST_API_KEY` - Magic MCP 服务器功能所需
-- ✅ `MORPH_API_KEY` - Morphllm MCP 服务器功能所需
-- ❌ 文档中的其他环境变量 - 仅作示例,框架中不使用
-- 📝 两者都是付费服务 API 密钥,框架在没有它们的情况下也可以工作
-
-## 服务器组合
-
-**无 API 密钥(免费)**:
-- context7 + sequential-thinking + playwright + serena
-
-**1 个 API 密钥**:
-- 添加 magic 用于专业 UI 开发
-
-**2 个 API 密钥**:
-- 添加 morphllm-fast-apply 用于大规模重构
-
-**常见工作流:**
-- **学习**:context7 + sequential-thinking
-- **Web 开发**:magic + context7 + playwright
-- **企业重构**:serena + morphllm + sequential-thinking
-- **复杂分析**:sequential-thinking + context7 + serena
-
-## 集成
-
-**与 SuperClaude 命令:**
-- 分析命令自动使用 Sequential + Serena
-- 实现命令使用 Magic + Context7
-- 测试命令使用 Playwright + Sequential
-
-**与行为模式:**
-- 头脑风暴模式:Sequential 用于发现
-- 任务管理:Serena 用于持久化
-- 编排模式:最佳服务器选择
-
-**性能控制:**
-- 基于系统负载的自动资源管理
-- 并发控制:`--concurrency N` (1-15)
-- 在约束条件下基于优先级的服务器选择
-
-## 相关资源
-
-**必读资料:**
-- [命令指南](commands.md) - 激活 MCP 服务器的命令
-- [快速开始指南](../Getting-Started/quick-start.md) - MCP 设置指南
-
-**高级使用:**
-- [行为模式](modes.md) - 模式-MCP 协调
-- [智能体指南](agents.md) - 智能体-MCP 集成
-- [会话管理](session-management.md) - Serena 工作流
-
-**技术参考:**
-- [示例手册](../Reference/examples-cookbook.md) - MCP 工作流模式
-- [技术架构](../Developer-Guide/technical-architecture.md) - 集成详情
\ No newline at end of file
diff --git a/docs/User-Guide-zh/modes.md b/docs/User-Guide-zh/modes.md
deleted file mode 100644
index 3e915d3..0000000
--- a/docs/User-Guide-zh/modes.md
+++ /dev/null
@@ -1,603 +0,0 @@
-# SuperClaude 行为模式指南 🧠
-
-## ✅ 快速验证
-使用 `/sc:` 命令测试模式 - 它们会根据任务复杂性自动激活。有关完整命令参考,请参阅 [命令指南](commands.md)。
-
-## 快速参考表
-
-| 模式 | 目的 | 自动触发 | 关键行为 | 最适合 |
-|------|---------|---------------|---------------|---------------|
-| **🧠 头脑风暴** | 交互式发现 | "brainstorm"、"maybe"、模糊请求 | 苏格拉底式问题、需求发掘 | 新项目规划、不明确需求 |
-| **🔍 内省** | 元认知分析 | 错误恢复、"分析推理" | 透明思维标记 (🤔, 🎯, 💡) | 调试、学习、优化 |
-| **📋 任务管理** | 复杂协调 | >3 步骤、>2 目录 | 阶段分解、内存持久化 | 多步操作、项目管理 |
-| **🎯 编排** | 智能工具选择 | 多工具操作、高资源使用 | 最优工具路由、并行执行 | 复杂分析、性能优化 |
-| **⚡ 令牌效率** | 压缩通信 | 高上下文使用、`--uc` 标志 | 符号系统,预计减少 30-50% 令牌 | 资源约束、大型操作 |
-
-
----
-
-## 入门指南(2 分钟概览)
-
-**模式通过行为指令激活** - Claude Code 读取上下文文件,根据您的任务模式和复杂性来决定采用哪种模式行为。
-
-**快速示例:**
-```bash
-# 自动激活示例
-/sc:brainstorm "mobile app" # → 苏格拉底式发现问题
-/sc:implement "authentication system" # → 多阶段协调
-"--uc analyze large-codebase/" # → 压缩符号输出
-```
-
-**何时使用手动标志:**
-- 需要特定行为:`--brainstorm`、`--introspect`、`--uc`
-- 为学习/调试而覆盖自动检测
-- 针对特定约束进行优化(内存、时间、清晰度)
-
----
-
-## 模式详情
-
-### 🧠 头脑风暴模式 - 交互式发现
-
-**目的**:通过协作发现将模糊的想法转化为结构化的需求。
-
-**自动激活触发器:**
-- 模糊的项目请求:"我想构建..."、"正在考虑创建..."
-- 探索关键词:brainstorm、explore、discuss、figure out、not sure
-- 不确定指示器:"maybe"、"possibly"、"could we"
-- 手动标志:`--brainstorm`、`--bs`
-
-**行为变化:**
-- **苏格拉底式提问**:提出探性问题以发掘隐藏需求
-- **非预设性方法**:避免假设,让您引导发现方向
-- **协作伙伴关系**:在探索中与您合作,而不是指导性咨询
-- **需求综合**:将见解转化为结构化的技术简报
-- **跨会话内存**:为后续讨论维护发现上下文
-
-**体验示例:**
-```
-Standard Approach: "I'll build a user authentication system with JWT tokens..."
-Brainstorming Approach:
-"🤔 Let's explore this together:
- - What specific user problems does auth solve for your app?
- - Who are your users and what's their technical comfort level?
- - Any existing systems or social logins to integrate with?
- - What security/compliance requirements do you have?
- 📝 Outcome: Detailed auth requirements brief ready for implementation"
-```
-
-#### 成功标准
-- [ ] 用问题而不是直接解决方案来回应
-- [ ] 问题探索用户需求、技术约束和业务目标
-- [ ] 在整个发现过程中保持协作语调
-- [ ] 产生结构化需求或技术简介作为结果
-
-**验证:** `/sc:brainstorm "web app"` 应该询问用户、功能、技术相关问题
-**测试:** 模糊请求应该触发发现性问题,而不是假设
-**检查:** 模式应该在同一会话的后续问题中保持一致
-
-**最佳搭配:**
-- **→ 任务管理**:需求发现 → 系统性实施规划
-- **→ 编排**:需求明确化 → 实施的最优工具选择
-- **手动覆盖**:使用 `--brainstorm` 强制发现,即使对于"明确"的需求
-
----
-
-### 🔍 内省模式 - 元认知分析
-
-**目的**:为学习优化和透明决策制定暴露推理过程。
-
-**自动激活触发器:**
-- 自我分析请求:"分析我的推理"、"反思决策"
-- 错误恢复场景和需要调查的意外结果
-- 具有多种可行方法的复杂问题求解
-- 优化机会的模式识别需求
-- 手动标志:`--introspect`
-
-**行为变化:**
-- **推理透明度**:通过清晰标记暴露思维过程 (🤔, 🎯, ⚡, 📊, 💡)
-- **决策分析**:评估选择逻辑并考虑替代方案
-- **模式识别**:识别重复行为和改进机会
-- **元学习**:提取见解以持续改进框架
-- **框架合规性**:根据 SuperClaude 原则和质量门控验证行为
-
-**体验示例:**
-```
-Standard Approach: "I'll analyze this code structure and suggest improvements..."
-Introspective Approach:
-"🧠 Meta-Analysis: Why did I choose structural analysis over functional flow analysis?
- 🎯 Decision Logic: Saw class hierarchy → assumed OOP patterns dominate
- 🔄 Alternative Considered: Data flow analysis might reveal hidden dependencies
- 📊 Evidence Check: File imports suggest functional composition, not OOP
- 💡 Learning: Need to analyze imports before choosing analysis strategy
- ⚡ Correction: Switching to functional flow analysis approach"
-```
-
-**最佳搭配:**
-- **→ 任务管理**:为复杂阶段决策提供透明推理
-- **任何模式**:为任何其他模式的操作添加推理透明度层
-- **手动覆盖**:在学习会话和调试工作流中使用 `--introspect`
-
----
-
-### 📋 任务管理模式 - 复杂协调
-
-**目的**:具有会话持久性的分层任务组织,用于多步操作。
-
-**自动激活触发器:**
-- 需要超过 3 个协调步骤的操作
-- 多文件/目录范围(>2 目录或 >3 文件)
-- 需要阶段和检查点的复杂依赖关系
-- 质量改进请求:完善、优化、增强
-- 手动标志:`--task-manage`、`--delegate`
-
-**行为变化:**
-- **分层规划**:将复杂工作分解为计划 → 阶段 → 任务 → 待办结构
-- **会话持久性**:在中断期间维护项目上下文和进度
-- **内存集成**:使用 write_memory/read_memory 进行状态保存
-- **进度编排**:协调 TodoWrite 与内存更新以进行跟踪
-- **质量门控**:在阶段之间实施系统验证检查点
-
-**体验示例:**
-```
-Standard Approach: "I'll implement user authentication..." → Direct implementation
-Task Management Approach:
-"📋 Multi-Phase Implementation Plan:
- 🎯 Phase 1: Security requirements analysis (Session 1)
- 🎯 Phase 2: API design & documentation (Session 2)
- 🎯 Phase 3: Implementation & testing (Sessions 3-4)
- 🎯 Phase 4: Integration & validation (Session 5)
- 💾 Session Persistence: Auto-resume context
- ✓ Quality Gates: Validation before each phase transition"
-```
-
-**最佳搭配:**
-- **头脑风暴 →**:需求发现然后系统化实施
-- **+ 编排**:任务协调与最优工具选择
-- **+ 内省**:复杂阶段决策的透明推理
-
----
-
-### 🎯 编排模式 - 智能工具选择
-
-**目的**:通过智能工具路由和并行协调优化任务执行。
-
-**自动激活触发器:**
-- 需要复杂协调的多工具操作
-- 性能约束(高资源使用)
-- 并行执行机会(>3 个独立文件/操作)
-- 具有多种有效工具方法的复杂路由决策
-
-**行为变化:**
-- **智能工具路由**:为每种任务类型选择最优的 MCP 服务器和原生工具
-- **资源感知**:基于系统约束和可用性调整方法
-- **并行优化**:识别独立操作以进行并发执行
-- **协调焦点**:通过协调执行优化工具选择和使用
-- **自适应回退**:当首选选项不可用时优雅地切换工具
-
-**体验示例:**
-```
-Standard Approach: Sequential file-by-file analysis and editing
-Orchestration Approach:
-"🎯 Multi-Tool Coordination Strategy:
- 🔍 Phase 1: Serena (semantic analysis) + Sequential (architecture review)
- ⚡ Phase 2: Morphllm (pattern edits) + Magic (UI components)
- 🧪 Phase 3: Playwright (testing) + Context7 (doc patterns)
- 🔄 Parallel Execution: 3 tools working simultaneously"
-```
-
-**最佳搭配:**
-- **任务管理 →**:为复杂多阶段计划提供工具协调
-- **+ 令牌效率**:带压缩通信的最优工具选择
-- **任何复杂任务**:添加智能工具路由以增强执行
-
----
-
-### ⚡ 令牌效率模式 - 压缩通信
-
-**目的**:通过符号系统实现预计 30-50% 的令牌减少,同时保持信息质量。
-
-**自动激活触发器:**
-- 高上下文使用接近限制
-- 需要资源效率的大规模操作
-- 用户显式标志:`--uc`、`--ultracompressed`
-- 具有多个输出的复杂分析工作流
-
-**行为变化:**
-- **符号通信**:为逻辑流程、状态和技术领域使用视觉符号
-- **技术缩写**:对重复技术术语进行上下文感知压缩
-- **结构化密度**:使用要点、表格和简洁格式,而非冗长段落
-- **信息保留**:尽管压缩,仍保持 ≥95% 的信息质量
-- **结构化格式**:为清晰度和任务完成而组织
-
-**体验示例:**
-```
-Standard Approach: "Authentication system implementation shows security vulnerability in user validation function requiring immediate attention..."
-Token-Efficient Approach:
-"🛡️ Security Alert:
- auth.js:45 → user val() → critical vuln
- 📊 Impact: ❌ possible token bypass
- ⚡ Action: fix validation + audit ∵ high severity
- 🔧 Estimate: 2hr impl + 1hr test"
-```
-
-**最佳搭配:**
-- **任何模式**:在保持特定模式行为的同时添加压缩层
-- **编排 →**:压缩的工具协调和状态更新
-- **手动覆盖**:当上下文压力或效率是优先级时使用 `--uc`
-
----
-
-### 🎨 标准模式 - 均衡默认
-
-**目的**:为直接的开发任务提供清晰、专业的沟通。
-
-**自动激活触发器:**
-- 没有复杂性指标的简单、明确定义的任务
-- 具有明确要求的单文件操作
-- 基本解释和标准开发工作流
-- 未检测到其他模式触发器(默认回退)
-
-**行为变化:**
-- **专业沟通**:清晰、简洁的技术语言,无压缩
-- **适度细节**:适合大多数开发任务的平衡信息深度
-- **标准工具选择**:使用原生 Claude 能力和基本工具
-- **质量焦点**:在无复杂编排开销的情况下保持代码质量
-- **响应式适应**:当复杂性增加时准备切换到专门模式
-
-**体验示例:**
-```
-Standard Approach: Consistent, professional baseline for all tasks
-"I'll implement the login functionality with proper error handling:
-
- 1. Validate user input (email format, password requirements)
- 2. Authenticate against database with secure hashing
- 3. Generate JWT token with appropriate expiration
- 4. Return success response with user data
-
- Implementation will follow security best practices and include comprehensive error handling."
-```
-
-**最佳搭配:**
-- **→ 任何模式**:作为其他模式增强的基线
-- **模式切换**:需要时自动升级到专门模式
-- **清晰优先**:当直接沟通比优化更重要时
-
----
-
-## 高级用法
-
-### 模式组合
-
-**多模式工作流:**
-```bash
-# 发现 → 规划 → 实现
-/sc:brainstorm "microservices architecture" --task-manage
-# → 头脑风暴:需求发现
-# → 任务管理:多阶段协调
-
-# 透明和高效的分析
-/sc:analyze legacy-system/ --introspect --uc
-# → 内省:透明推理
-# → 令牌效率:压缩输出
-```
-
-### 手动模式控制
-
-**强制特定行为:**
-- `--brainstorm`:为任何任务强制协作发现
-- `--introspect`:为任何模式添加推理透明度
-- `--task-manage`:启用分层协调
-- `--orchestrate`:优化工具选择和并行执行
-- `--uc`:为效率压缩通信
-
-**覆盖示例:**
-```bash
-# 对“明确”的需求强制头脑风暴
-/sc:implement "user login" --brainstorm
-
-# 为调试添加推理透明度
-# 使用透明推理调试认证问题
-
-# 为简单操作启用任务管理
-# 系统化任务管理更新样式文件
-```
-
-### 模式边界和优先级
-
-**模式激活时机:**
-1. **复杂度阈值**:>3 文件 → 任务管理
-2. **资源压力**:高上下文使用 → 令牌效率
-3. **多工具需求**:复杂分析 → 编排
-4. **不确定性**:模糊需求 → 头脑风暴
-5. **错误恢复**:问题 → 内省
-
-**优先级规则:**
-- **安全第一**:质量和验证总是覆盖效率
-- **用户意图**:手动标志覆盖自动检测
-- **上下文适应**:基于复杂性堆叠模式
-- **资源管理**:在压力下激活效率模式
-
----
-
-## 现实世界示例
-
-### 完整工作流示例
-
-**新项目开发:**
-```bash
-# 阶段 1:发现(头脑风暴模式自动激活)
-"I want to build a productivity app"
-→ 🤔 关于用户、功能、平台选择的苏格拉底式问题
-→ 📝 结构化需求简报
-
-# 阶段 2:规划(任务管理模式自动激活)
-/sc:implement "core productivity features"
-→ 📋 带依赖关系的多阶段分解
-→ 🎯 带质量门控的阶段协调
-
-# 阶段 3:实现(编排模式协调工具)
-/sc:implement "frontend and backend systems"
-→ 🎯 Magic (UI) + Context7 (模式) + Sequential (架构)
-→ ⚡ 并行执行优化
-```
-
-**调试复杂问题:**
-```bash
-# 问题分析(内省模式自动激活)
-"Users experiencing intermittent authentication failures"
-→ 🤔 关于潜在原因的透明推理
-→ 🎯 假设形成和证据收集
-→ 💡 跨相似问题的模式识别
-
-# 系统性解决(任务管理协调)
-# 全面修复认证系统
-→ 📋 阶段 1:根因分析
-→ 📋 阶段 2:解决方案实现
-→ 📋 阶段 3:测试和验证
-```
-
-### 模式组合模式
-
-**高复杂度场景:**
-```bash
-# 带多重约束的大型重构
-/sc:improve legacy-system/ --introspect --uc --orchestrate
-→ 🔍 透明推理introspect(内省)
-→ ⚡ 压缩通信uc(令牌效率)
-→ 🎯 最优工具协调orchestrate(编排)
-→ 📋 系统化阶段(任务管理自动激活)
-```
-
----
-
-## 快速参考
-
-### 模式激活模式
-
-| 触发类型 | 输入示例 | 激活模式 | 关键行为 |
-|---------|---------|----------|----------|
-| **模糊请求** | "我想构建一个应用" | 🧠 头脑风暴 | 苏格拉底式发现问题 |
-| **复杂范围** | >3 文件或 >2 目录 | 📋 任务管理 | 阶段协调 |
-| **多工具需求** | 分析 + 实施 | 🎯 编排 | 工具优化 |
-| **错误恢复** | "这没有按预期工作" | 🔍 内省 | 透明推理 |
-| **资源压力** | 高上下文使用 | ⚡ 令牌效率 | 符号压缩 |
-| **简单任务** | "修复这个函数" | 🎨 标准 | 清晰、直接的方法 |
-
-### 手动覆盖命令
-
-```bash
-# 强制特定模式行为
-/sc:command --brainstorm # 协作发现
-/sc:command --introspect # 推理透明度
-/sc:command --task-manage # 分层协调
-/sc:command --orchestrate # 工具优化
-/sc:command --uc # 令牌压缩
-
-# 组合多种模式
-/sc:command --introspect --uc # 透明 + 高效
-/sc:command --task-manage --orchestrate # 协调 + 优化
-```
-
----
-
-## 故障排除
-
-有关故障排除帮助,请参阅:
-- [常见问题](../Reference/common-issues.md) - 频繁问题的快速修复
-- [故障排除指南](../Reference/troubleshooting.md) - 全面的问题解决方案
-
-### 常见问题
-- **模式未激活**:使用手动标志:`--brainstorm`、`--introspect`、`--uc`
-- **激活了错误的模式**:检查请求中的复杂性触发器和关键词
-- **模式意外切换**:基于任务演化的正常行为
-- **执行影响**:模式优化工具使用,不应影响执行
-- **模式冲突**:检查[标志指南](flags.md)中的标志优先级规则
-
-### 即时修复
-- **强制特定模式**:使用明确标志如 `--brainstorm` 或 `--task-manage`
-- **重置模式行为**:重启 Claude Code 会话以重置模式状态
-- **检查模式指示器**:在响应中查找 🤔、🎯、📋 符号
-- **验证复杂性**:简单任务使用标准模式,复杂任务自动切换
-
-### 特定模式故障排除
-
-**头脑风暴模式问题:**
-```bash
-# 问题:模式给出解决方案而不是问题
-# 快速修复:检查请求清晰度并使用显式标志
-/sc:brainstorm "web app" --brainstorm # 强制发现模式
-"I have a vague idea about..." # 使用不确定语言
-"Maybe we could build..." # 触发探索
-```
-
-**任务管理模式问题:**
-```bash
-# 问题:简单任务得到复杂协调
-# 快速修复:减少范围或使用更简单的命令
-/sc:implement "function" --no-task-manage # 禁用协调
-/sc:troubleshoot bug.js # 使用基本命令
-# 检查任务是否真正复杂(>3 文件,>2 目录)
-```
-
-**令牌效率模式问题:**
-```bash
-# 问题:输出过于压缩或不清楚
-# 快速修复:禁用压缩以提高清晰度
-/sc:command --no-uc # 禁用压缩
-/sc:command --verbose # 强制详细输出
-# 当清晰度比效率更重要时使用
-```
-
-**内省模式问题:**
-```bash
-# 问题:过多元评论,行动不足
-# 快速修复:为直接工作禁用内省
-/sc:command --no-introspect # 直接执行
-# 仅在学习和调试时使用内省
-```
-
-**编排模式问题:**
-```bash
-# 问题:工具协调造成混乱
-# 快速修复:简化工具使用
-/sc:command --no-mcp # 仅使用原生工具
-/sc:command --simple # 基本执行
-# 检查任务复杂度是否需要编排
-```
-
-### 错误代码参考
-
-| 模式错误 | 含义 | 快速修复 |
-|---------|-----|----------|
-| **B001** | 头脑风暴激活失败 | 使用显式 `--brainstorm` 标志 |
-| **T001** | 任务管理开销 | 对简单任务使用 `--no-task-manage` |
-| **U001** | 令牌效率过于激进 | 使用 `--verbose` 或 `--no-uc` |
-| **I001** | 内省模式卡住 | 对直接行动使用 `--no-introspect` |
-| **O001** | 编排协调失败 | 使用 `--no-mcp` 或 `--simple` |
-| **M001** | 检测到模式冲突 | 检查标志优先级规则 |
-| **M002** | 模式切换循环 | 重启会话以重置状态 |
-| **M003** | 模式无法识别 | 更新 SuperClaude 或检查拼写 |
-
-### 渐进式支持级别
-
-**级别 1:快速修复(< 2 分钟)**
-- 使用手动标志覆盖自动模式选择
-- 检查任务复杂性是否与预期模式行为匹配
-- 尝试重启 Claude Code 会话
-
-**级别 2:详细帮助(5-15 分钟)**
-```bash
-# 特定模式诊断
-/sc:help modes # 列出所有可用模式
-/sc:reflect --type mode-status # 检查当前模式状态
-# 检查请求复杂性和触发器
-```
-- 有关模式安装问题,请参阅[常见问题指南](../Reference/common-issues.md)
-
-**级别 3:专家支持(30+ 分钟)**
-```bash
-# 深度模式分析
-SuperClaude install --diagnose
-# 检查模式激活模式
-# 检查行为触发器和阈值
-```
-- 有关行为模式分析,请参阅[诊断参考指南](../Reference/diagnostic-reference.md)
-
-**级别 4:社区支持**
-- 在 [GitHub Issues](https://github.com/SuperClaude-Org/SuperClaude_Framework/issues) 报告模式问题
-- 包括意外模式行为的示例
-- 描述期望与实际模式激活的差异
-
-### 成功验证
-
-应用模式修复后,进行测试:
-- [ ] 简单请求使用标准模式(清晰、直接的响应)
-- [ ] 复杂请求自动激活适当的模式(协调、推理)
-- [ ] 手动标志正确覆盖自动检测
-- [ ] 模式指示器(🤔、🎯、📋)在预期时出现
-- [ ] 在不同模式下性能保持良好
-
-## 快速故障排除(旧版)
-- **模式未激活** → 使用手动标志:`--brainstorm`、`--introspect`、`--uc`
-- **激活了错误的模式** → 检查请求中的复杂性触发器和关键词
-- **模式意外切换** → 基于任务演化的正常行为
-- **执行影响** → 模式优化工具使用,不应影响执行
-- **模式冲突** → 检查[标志指南](flags.md)中的标志优先级规则
-
-## 常见问题
-
-**问:如何知道哪个模式处于激活状态?**
-答:在通信模式中查找这些指示器:
-- 🤔 发现性问题 → 头脑风暴
-- 🎯 推理透明度 → 内省
-- 阶段分解 → 任务管理
-- 工具协调 → 编排
-- 符号压缩 → 令牌效率
-
-**问:我可以强制特定模式吗?**
-答:是的,使用手动标志覆盖自动检测:
-```bash
-/sc:command --brainstorm # 强制发现模式
-/sc:command --introspect # 增加透明性
-/sc:command --task-manage # 启用协调
-/sc:command --uc # 压缩输出
-```
-
-**问:模式会影响执行吗?**
-答:模式通过协调优化工具使用:
-- **令牌效率**:上下文减少 30-50%
-- **编排**:并行处理
-- **任务管理**:通过系统化规划防止返工
-
-**问:模式可以协同工作吗?**
-答:是的,模式设计为互相补充:
-- **任务管理**协调其他模式
-- **令牌效率**压缩任何模式的输出
-- **内省**为任何工作流添加透明度
-
----
-
-## 总结
-
-SuperClaude 的 5 种行为模式创建了一个**智能适应系统**,自动匹配您的需求:
-
-- **🧠 头脑风暴**:将模糊想法转化为清晰需求
-- **🔍 内省**:为学习和调试提供透明推理
-- **📋 任务管理**:协调复杂的多步操作
-- **🎯 编排**:优化工具选择和并行执行
-- **⚡ 令牌效率**:在保持清晰度的同时压缩通信
-- **🎨 标准**:为直接任务维护专业基线
-
-**关键洞察**:您无需思考模式 - 它们透明地工作以增强您的开发体验。只需描述您想要完成的任务,SuperClaude 会自动调整其方法以匹配您的需求。
-
----
-
-## 相关指南
-
-**学习进展:**
-
-**🌱 基础(第1周)**
-- [快速开始指南](../Getting-Started/quick-start.md) - 模式激活示例
-- [命令参考](commands.md) - 命令自动激活模式
-- [安装指南](../Getting-Started/installation.md) - 设置行为模式
-
-**🌿 中级(第2-3周)**
-- [智能体指南](agents.md) - 模式如何与专家协调
-- [标志指南](flags.md) - 手动模式控制和优化
-- [示例手册](../Reference/examples-cookbook.md) - 实践中的模式模式
-
-**🌲 高级(第2+个月)**
-- [MCP 服务器](mcp-servers.md) - 模式与增强能力的集成
-- [会话管理](session-management.md) - 任务管理模式工作流
-- [入门指南](../Getting-Started/quick-start.md) - 模式使用模式
-
-**🔧 专家级**
-- [技术架构](../Developer-Guide/technical-architecture.md) - 模式实现细节
-- [代码贡献](../Developer-Guide/contributing-code.md) - 扩展模式能力
-
-**特定模式指南:**
-- **头脑风暴**:[需求发现模式](../Reference/examples-cookbook.md#requirements)
-- **任务管理**:[会话管理指南](session-management.md)
-- **编排**:[MCP 服务器指南](mcp-servers.md)
-- **令牌效率**:[命令基础](commands.md#token-efficiency)
\ No newline at end of file
diff --git a/docs/User-Guide-zh/session-management.md b/docs/User-Guide-zh/session-management.md
deleted file mode 100644
index 7a625ca..0000000
--- a/docs/User-Guide-zh/session-management.md
+++ /dev/null
@@ -1,310 +0,0 @@
-# 会话管理指南
-
-SuperClaude 通过 Serena MCP 服务器提供持久会话管理,实现在 Claude Code 对话中真正的上下文保存和长期项目连续性。
-
-## 具有持久内存的核心会话命令
-
-### `/sc:load` - 具有持久内存的上下文加载
-**目的**:使用项目上下文和以前会话的持久内存初始化会话
-**MCP 集成**:触发 Serena MCP 读取存储的项目内存
-**语法**:`/sc:load [project_path]`
-
-**发生什么**:
-- Serena MCP 从以前的会话中读取持久内存文件
-- 从存储的内存中恢复项目上下文
-- 加载以前的决策、模式和进度
-- 使用历史上下文初始化会话状态
-
-**使用案例**:
-```bash
-# 从持久内存加载现有项目上下文
-/sc:load src/
-
-# 恢复特定项目工作及其完整历史
-/sc:load "authentication system"
-
-# 使用代码库分析和先前见解初始化
-/sc:load . --analyze
-```
-
-### `/sc:save` - 会话持久化到内存
-**目的**:将当前会话状态和决策保存到持久内存
-**MCP 集成**:触发 Serena MCP 写入内存文件
-**语法**:`/sc:save "会话描述"`
-
-**发生什么**:
-- 当前上下文和决策被写入 Serena 内存
-- 项目状态和进度在对话中持久保存
-- 关键见解和模式被存储以供未来会话使用
-- 创建带有时间戳的会话摘要以便检索
-
-**使用案例**:
-```bash
-# 保存已完成的特性工作以供未来参考
-/sc:save "user authentication implemented with JWT"
-
-# 复杂工作期间的检查点
-/sc:save "API design phase complete, ready for implementation"
-
-# 永久存储架构决策
-/sc:save "microservices architecture decided, service boundaries defined"
-```
-
-### `/sc:reflect` - 带有内存上下文的进度评估
-**目的**:根据存储的内存分析当前进度并验证会话完整性
-**MCP 集成**:使用 Serena MCP 将当前状态与存储的内存进行比较
-**语法**:`/sc:reflect [--scope project|session]`
-
-**发生什么**:
-- Serena MCP 读取以前的内存和当前上下文
-- 根据存储的目标和里程碑评估进度
-- 使用历史上下文识别差距和下一步
-- 根据项目内存验证会话完整性
-
-**使用案例**:
-```bash
-# 根据存储的里程碑评估项目进度
-/sc:reflect --scope project
-
-# 验证当前会话完整性
-/sc:reflect
-
-# 根据内存检查是否准备进入下一阶段
-/sc:reflect --scope session
-```
-
-## 持久内存架构
-
-### Serena MCP 如何实现真正的持久性
-
-**内存存储**:
-- 会话上下文作为结构化内存文件存储
-- 项目决策和架构模式永久保存
-- 代码分析结果和见解在对话中保持
-- 进度跟踪和里程碑数据长期维护
-
-**跨会话连续性**:
-- 新对话中自动加载以前的会话上下文
-- 决策和理由在对话中保存和可访问
-- 从过去的模式和解决方案中学习并维护
-- 一致的项目理解无限期维护
-
-**内存类型**:
-- **项目内存**:长期项目上下文和架构
-- **会话内存**:特定对话结果和决策
-- **模式内存**:可重用的解决方案和架构模式
-- **进度内存**:里程碑跟踪和完成状态
-
-## 具有持久性的会话生命周期模式
-
-### 新项目初始化
-```bash
-# 1. 开始全新项目
-/sc:brainstorm "e-commerce platform requirements"
-
-# 2. 将初始决策保存到持久内存
-/sc:save "project scope and requirements defined"
-
-# 3. 开始实现规划
-/sc:workflow "user authentication system"
-
-# 4. 永久保存架构决策
-/sc:save "authentication architecture: JWT + refresh tokens + rate limiting"
-```
-
-### 恢复现有工作(跨对话)
-```bash
-# 1. 从持久内存加载以前的上下文
-/sc:load "e-commerce project"
-
-# 2. 根据存储的进度评估当前状态
-/sc:reflect --scope project
-
-# 3. 使用存储的上下文继续下一阶段
-/sc:implement "payment processing integration"
-
-# 4. 将进度检查点保存到内存
-/sc:save "payment system integrated with Stripe API"
-```
-
-### 长期项目管理
-```bash
-# 具有持久性的周检查点模式
-/sc:load project-name
-/sc:reflect --scope project
-# ... 处理特性 ...
-/sc:save "week N progress: features X, Y, Z completed"
-
-# 具有内存的阶段完成模式
-/sc:reflect --scope project
-/sc:save "phase 1 complete: core authentication and user management"
-/sc:workflow "phase 2: payment and order processing"
-```
-
-## 跨对话连续性
-
-### 使用持久性开始新对话
-
-当开始新的 Claude Code 对话时,持久内存系统允许:
-
-1. **自动上下文恢复**
- ```bash
- /sc:load project-name
- # 自动恢复所有以前的上下文、决策和进度
- ```
-
-2. **进度继续**
- - 以前会话的决策立即可用
- - 架构模式和代码见解被保存
- - 项目历史和理由被维护
-
-3. **智能上下文构建**
- - Serena MCP 根据当前工作提供相关内存
- - 过去的解决方案和模式指导新的实现
- - 项目演变被跟踪和理解
-
-### 内存优化
-
-**有效的内存使用**:
-- 使用描述性、可搜索的内存名称
-- 包含项目阶段和时间戳上下文
-- 引用特定功能或架构决策
-- 让未来的检索变得直观
-
-**内存内容策略**:
-- 存储决策和理由,而不仅仅是结果
-- 包含考虑的替代方案
-- 记录集成模式和依赖关系
-- 为未来参考保留学习和洞察
-
-**内存生命周期管理**:
-- 定期清理过时的内存
-- 整合相关的会话内存
-- 归档已完成的项目阶段
-- 修剪过时的架构决策
-
-## 持久会话的最佳实践
-
-### 会话开始协议
-1. 对于现有项目始终以 `/sc:load` 开始
-2. 使用 `/sc:reflect` 从内存中了解当前状态
-3. 根据持久上下文和存储的模式规划工作
-4. 基于以前的决策和架构选择构建
-
-### 会话结束协议
-1. 使用 `/sc:reflect` 根据存储的目标评估完整性
-2. 使用 `/sc:save` 保存关键决策以供未来会话
-3. 在内存中记录下一步和未解决的问题
-4. 为无缝的未来继续保存上下文
-
-### 内存质量维护
-- 使用清晰、描述性的内存名称以便于检索
-- 包含关于决策和替代方法的上下文
-- 引用特定的代码位置和模式
-- 在跨会话中保持内存结构的一致性
-
-## 与其他 SuperClaude 功能的集成
-
-### MCP 服务器协调
-- **Serena MCP**:提供持久内存基础设施
-- **Sequential MCP**:使用存储的内存进行增强的复杂分析
-- **Context7 MCP**:引用存储的模式和文档方法
-- **Morphllm MCP**:一致地应用存储的重构模式
-
-### 智能体与内存的协作
-- 智能体访问持久内存以增强上下文
-- 先前的专家决策被保留和引用
-- 通过共享内存进行跨会话智能体协调
-- 基于项目历史的一致专家建议
-
-### 命令与持久化的集成
-- 所有 `/sc:` 命令都可以引用和构建持久上下文
-- 先前的命令输出和决策在跨会话中可用
-- 工作流程模式被存储和重用
-- 实现历史指导未来的命令决策
-
-## 持久会话故障排除
-
-### 常见问题
-
-**内存未加载**:
-- 验证 Serena MCP 配置正确并正常运行
-- 检查内存文件权限和可访问性
-- 确保一致的项目命名约定
-- 验证内存文件完整性和格式
-
-**会话间上下文丢失**:
-- 在结束会话前始终使用 `/sc:save`
-- 使用描述性内存名称以便于检索
-- 定期使用 `/sc:reflect` 验证内存完整性
-- 定期备份重要的内存文件
-
-**内存冲突**:
-- 使用带时间戳的内存名称进行版本控制
-- 定期清理过时的内存
-- 清楚分离项目和会话内存
-- 在跨会话中保持一致的内存命名约定
-
-### 快速修复
-
-**重置会话状态**:
-```bash
-/sc:load --fresh # 不带先前上下文开始
-/sc:reflect # 评估当前状态
-```
-
-**内存清理**:
-```bash
-/sc:reflect --cleanup # 删除过时的内存
-/sc:save --consolidate # 合并相关内存
-```
-
-**上下文恢复**:
-```bash
-/sc:load --recent # 加载最近的内存
-/sc:reflect --repair # 识别并修复上下文空白
-```
-
-## 高级持久会话模式
-
-### 多阶段项目
-- 使用阶段特定的内存命名进行组织
-- 跨阶段维护架构决策连续性
-- 通过持久内存进行跨阶段依赖跟踪
-- 具有历史上下文的渐进式复杂性管理
-
-### 团队协作
-- 共享的内存约定和命名标准
-- 为团队上下文保留决策理由
-- 所有团队成员都可访问的集成模式文档
-- 通过内存实现一致的代码风格和架构执行
-
-### 长期维护
-- 已完成项目的内存归档策略
-- 通过累积内存开发模式库
-- 随时间建立的可重用解决方案文档
-- 通过持久内存积累建立知识库
-
-## 持久会话管理的关键优势
-
-### 项目连续性
-- 在多次对话中无缝的工作延续
-- Claude Code 会话之间无上下文丢失
-- 保留的架构决策和技术理由
-- 长期项目演进跟踪
-
-### 提升生产力
-- 减少重新解释项目上下文的需要
-- 继续工作的更快启动时间
-- 基于先前的洞察和模式进行构建
-- 累积的项目知识增长
-
-### 质量一致性
-- 跨会话的一致架构模式
-- 保留的代码质量决策和标准
-- 可重用的解决方案和最佳实践
-- 维持的技术债务意识
-
----
-
-**关键要点**:通过 Serena MCP 的会话管理将 SuperClaude 从单次对话帮助转变为持久项目伙伴关系,在所有开发阶段和 Claude Code 对话中维护上下文、决策和学习。
\ No newline at end of file
diff --git a/docs/User-Guide/agents.md b/docs/User-Guide/agents.md
deleted file mode 100644
index ae2d3cc..0000000
--- a/docs/User-Guide/agents.md
+++ /dev/null
@@ -1,936 +0,0 @@
-# SuperClaude Agents Guide 🤖
-
-SuperClaude provides 16 domain specialist agents that Claude Code can invoke for specialized expertise.
-
-
-## 🧪 Testing Agent Activation
-
-Before using this guide, verify agent selection works:
-
-```bash
-# Test manual agent invocation
-@agent-python-expert "explain decorators"
-# Example behavior: Python expert responds with detailed explanation
-
-# Test security agent auto-activation
-/sc:implement "JWT authentication"
-# Example behavior: Security engineer should activate automatically
-
-# Test frontend agent auto-activation
-/sc:implement "responsive navigation component"
-# Example behavior: Frontend architect + Magic MCP should activate
-
-# Test systematic analysis
-/sc:troubleshoot "slow API performance"
-# Example behavior: Root-cause analyst + performance engineer activation
-
-# Test combining manual and auto
-/sc:analyze src/
-@agent-refactoring-expert "suggest improvements"
-# Example behavior: Analysis followed by refactoring suggestions
-```
-
-**If tests fail**: Check agent files exist in `~/.claude/agents/` or restart Claude Code session
-
-## Core Concepts
-
-### What are SuperClaude Agents?
-**Agents** are specialized AI domain experts implemented as context instructions that modify Claude Code's behavior. Each agent is a carefully crafted `.md` file in the `superclaude/Agents/` directory containing domain-specific expertise, behavioral patterns, and problem-solving approaches.
-
-**Important**: Agents are NOT separate AI models or software - they are context configurations that Claude Code reads to adopt specialized behaviors.
-
-### Two Ways to Use Agents
-
-#### 1. Manual Invocation with @agent- Prefix
-```bash
-# Directly invoke a specific agent
-@agent-security "review authentication implementation"
-@agent-frontend "design responsive navigation"
-@agent-architect "plan microservices migration"
-```
-
-#### 2. Auto-Activation (Behavioral Routing)
-"Auto-activation" means Claude Code reads behavioral instructions to engage appropriate contexts based on keywords and patterns in your requests. SuperClaude provides behavioral guidelines that Claude follows to route to the most appropriate specialists.
-
-> **📝 How Agent "Auto-Activation" Works**:
-> Agent activation isn't automatic system logic - it's behavioral instructions in context files.
-> When documentation says agents "auto-activate", it means Claude Code reads instructions to engage
-> specific domain expertise based on keywords and patterns in your request. This creates the
-> experience of intelligent routing while being transparent about the underlying mechanism.
-
-```bash
-# These commands auto-activate relevant agents
-/sc:implement "JWT authentication" # → security-engineer auto-activates
-/sc:design "React dashboard" # → frontend-architect auto-activates
-/sc:troubleshoot "memory leak" # → performance-engineer auto-activates
-```
-
-**MCP Servers** provide enhanced capabilities through specialized tools like Context7 (documentation), Sequential (analysis), Magic (UI), Playwright (testing), and Morphllm (code transformation).
-
-**Domain Specialists** focus on narrow expertise areas to provide deeper, more accurate solutions than generalist approaches.
-
-### Agent Selection Rules
-
-**Priority Hierarchy:**
-1. **Manual Override** - @agent-[name] takes precedence over auto-activation
-2. **Keywords** - Direct domain terminology triggers primary agents
-3. **File Types** - Extensions activate language/framework specialists
-4. **Complexity** - Multi-step tasks engage coordination agents
-5. **Context** - Related concepts trigger complementary agents
-
-**Conflict Resolution:**
-- Manual invocation → Specified agent takes priority
-- Multiple matches → Multi-agent coordination
-- Unclear context → Requirements analyst activation
-- High complexity → System architect oversight
-- Quality concerns → Automatic QA agent inclusion
-
-**Selection Decision Tree:**
-```
-Task Analysis →
-├─ Manual @agent-? → Use specified agent
-├─ Single Domain? → Activate primary agent
-├─ Multi-Domain? → Coordinate specialist agents
-├─ Complex System? → Add system-architect oversight
-├─ Quality Critical? → Include security + performance + quality agents
-└─ Learning Focus? → Add learning-guide + technical-writer
-```
-
-## Quick Start Examples
-
-### Manual Agent Invocation
-```bash
-# Explicitly call specific agents with @agent- prefix
-@agent-python-expert "optimize this data processing pipeline"
-@agent-quality-engineer "create comprehensive test suite"
-@agent-technical-writer "document this API with examples"
-@agent-socratic-mentor "explain this design pattern"
-```
-
-### Automatic Agent Coordination
-```bash
-# Commands that trigger auto-activation
-/sc:implement "JWT authentication with rate limiting"
-# → Triggers: security-engineer + backend-architect + quality-engineer
-
-/sc:design "accessible React dashboard with documentation"
-# → Triggers: frontend-architect + learning-guide + technical-writer
-
-/sc:troubleshoot "slow deployment pipeline with intermittent failures"
-# → Triggers: devops-architect + performance-engineer + root-cause-analyst
-
-/sc:audit "payment processing security vulnerabilities"
-# → Triggers: security-engineer + quality-engineer + refactoring-expert
-```
-
-### Combining Manual and Auto Approaches
-```bash
-# Start with command (auto-activation)
-/sc:implement "user profile system"
-
-# Then explicitly add specialist review
-@agent-security "review the profile system for OWASP compliance"
-@agent-performance-engineer "optimize database queries"
-```
-
----
-
-## The SuperClaude Agent Team 👥
-
-### Meta-Layer Agent 🎯
-
-### pm-agent 📚
-**Expertise**: Self-improvement workflow executor that documents implementations, analyzes mistakes, and maintains knowledge base continuously
-
-**Auto-Activation**:
-- **Post-Implementation**: After any task completion requiring documentation
-- **Mistake Detection**: Immediate analysis when errors or bugs occur
-- **Monthly Maintenance**: Regular documentation health reviews
-- **Knowledge Gap**: When patterns emerge requiring documentation
-- Commands: Automatically activates after `/sc:implement`, `/sc:build`, `/sc:improve` completions
-
-**Capabilities**:
-- **Implementation Documentation**: Record new patterns, architectural decisions, edge cases discovered
-- **Mistake Analysis**: Root cause analysis, prevention checklists, pattern identification
-- **Pattern Recognition**: Extract success patterns, anti-patterns, best practices
-- **Knowledge Maintenance**: Monthly reviews, noise reduction, duplication merging, freshness updates
-- **Self-Improvement Loop**: Transform every experience into reusable knowledge
-
-**How PM Agent Works** (Meta-Layer):
-1. **Specialist Agents Complete Task**: Backend-architect implements feature
-2. **PM Agent Auto-Activates**: After implementation completion
-3. **Documentation**: Records patterns, decisions, edge cases in docs/
-4. **Knowledge Update**: Updates CLAUDE.md if global pattern discovered
-5. **Evidence Collection**: Links test results, screenshots, metrics
-6. **Learning Integration**: Extracts lessons for future implementations
-
-**Self-Improvement Workflow Examples**:
-1. **Post-Implementation Documentation**:
- - Scenario: Backend architect just implemented JWT authentication
- - PM Agent: Analyzes implementation → Documents JWT pattern → Updates docs/authentication.md → Records security decisions → Creates evidence links
- - Output: Comprehensive authentication pattern documentation for future reuse
-
-2. **Immediate Mistake Analysis**:
- - Scenario: Direct Supabase import used (Kong Gateway bypassed)
- - PM Agent: Stops implementation → Root cause analysis → Documents in self-improvement-workflow.md → Creates prevention checklist → Updates CLAUDE.md
- - Output: Mistake recorded with prevention strategy, won't repeat error
-
-3. **Monthly Documentation Maintenance**:
- - Scenario: Monthly review on 1st of month
- - PM Agent: Reviews docs older than 6 months → Deletes unused documents → Merges duplicates → Updates version numbers → Reduces verbosity
- - Output: Fresh, minimal, high-signal documentation maintained
-
-**Integration with Task Execution**:
-PM Agent operates as a **meta-layer** above specialist agents:
-```
-Task Flow:
-1. User Request → Auto-activation selects specialist agent
-2. Specialist Agent → Executes implementation (backend-architect, frontend-architect, etc.)
-3. PM Agent (Auto-triggered) → Documents learnings
-4. Knowledge Base → Updated with patterns, mistakes, improvements
-```
-
-**Works Best With**: All agents (documents their work, not replaces them)
-
-**Quality Standards**:
-- **Latest**: Last Verified dates on all documents
-- **Minimal**: Necessary information only, no verbosity
-- **Clear**: Concrete examples and copy-paste ready code
-- **Practical**: Immediately applicable to real work
-
-**Self-Improvement Loop Phases**:
-- **AFTER Phase**: Primary responsibility - document implementations, update docs/, create evidence
-- **MISTAKE RECOVERY**: Immediate stop, root cause analysis, documentation update
-- **MAINTENANCE**: Monthly pruning, merging, freshness updates, noise reduction
-
-**Verify**: Activates automatically after task completions requiring documentation
-**Test**: Should document patterns after backend-architect implements features
-**Check**: Should create prevention checklists when mistakes detected
-
----
-
-### Architecture & System Design Agents 🏗️
-
-### system-architect 🏢
-**Expertise**: Large-scale distributed system design with focus on scalability and service architecture
-
-**Auto-Activation**:
-- Keywords: "architecture", "microservices", "scalability", "system design", "distributed"
-- Context: Multi-service systems, architectural decisions, technology selection
-- Complexity: >5 components or cross-domain integration requirements
-
-**Capabilities**:
-- Service boundary definition and microservices decomposition
-- Technology stack selection and integration strategy
-- Scalability planning and performance architecture
-- Event-driven architecture and messaging patterns
-- Data flow design and system integration
-
-**Examples**:
-1. **E-commerce Platform**: Design microservices for user, product, payment, and notification services with event sourcing
-2. **Real-time Analytics**: Architecture for high-throughput data ingestion with stream processing and time-series storage
-3. **Multi-tenant SaaS**: System design with tenant isolation, shared infrastructure, and horizontal scaling strategies
-
-### Success Criteria
-- [ ] System-level thinking evident in responses
-- [ ] Mentions service boundaries and integration patterns
-- [ ] Includes scalability and reliability considerations
-- [ ] Provides technology stack recommendations
-
-**Verify:** `/sc:design "microservices platform"` should activate system-architect
-**Test:** Output should include service decomposition and integration patterns
-**Check:** Should coordinate with devops-architect for infrastructure concerns
-
-**Works Best With**: devops-architect (infrastructure), performance-engineer (optimization), security-engineer (compliance)
-
----
-
-### backend-architect ⚙️
-**Expertise**: Robust server-side system design with emphasis on API reliability and data integrity
-
-**Auto-Activation**:
-- Keywords: "API", "backend", "server", "database", "REST", "GraphQL", "endpoint"
-- File Types: API specs, server configs, database schemas
-- Context: Server-side logic, data persistence, API development
-
-**Capabilities**:
-- RESTful and GraphQL API architecture and design patterns
-- Database schema design and query optimization strategies
-- Authentication, authorization, and security implementation
-- Error handling, logging, and monitoring integration
-- Caching strategies and performance optimization
-
-**Examples**:
-1. **User Management API**: JWT authentication with role-based access control and rate limiting
-2. **Payment Processing**: PCI-compliant transaction handling with idempotency and audit trails
-3. **Content Management**: RESTful APIs with caching, pagination, and real-time notifications
-
-**Works Best With**: security-engineer (auth/security), performance-engineer (optimization), quality-engineer (testing)
-
----
-
-### frontend-architect 🎨
-**Expertise**: Modern web application architecture with focus on accessibility and user experience
-
-**Auto-Activation**:
-- Keywords: "UI", "frontend", "React", "Vue", "Angular", "component", "accessibility", "responsive"
-- File Types: .jsx, .vue, .ts (frontend), .css, .scss
-- Context: User interface development, component design, client-side architecture
-
-**Capabilities**:
-- Component architecture and design system implementation
-- State management patterns (Redux, Zustand, Pinia)
-- Accessibility compliance (WCAG 2.1) and inclusive design
-- Performance optimization and bundle analysis
-- Progressive Web App and mobile-first development
-
-**Examples**:
-1. **Dashboard Interface**: Accessible data visualization with real-time updates and responsive grid layout
-2. **Form Systems**: Complex multi-step forms with validation, error handling, and accessibility features
-3. **Design System**: Reusable component library with consistent styling and interaction patterns
-
-**Works Best With**: learning-guide (user guidance), performance-engineer (optimization), quality-engineer (testing)
-
----
-
-### devops-architect 🚀
-**Expertise**: Infrastructure automation and deployment pipeline design for reliable software delivery
-
-**Auto-Activation**:
-- Keywords: "deploy", "CI/CD", "Docker", "Kubernetes", "infrastructure", "monitoring", "pipeline"
-- File Types: Dockerfile, docker-compose.yml, k8s manifests, CI configs
-- Context: Deployment processes, infrastructure management, automation
-
-**Capabilities**:
-- CI/CD pipeline design with automated testing and deployment
-- Container orchestration and Kubernetes cluster management
-- Infrastructure as Code with Terraform and cloud platforms
-- Monitoring, logging, and observability stack implementation
-- Security scanning and compliance automation
-
-**Examples**:
-1. **Microservices Deployment**: Kubernetes deployment with service mesh, auto-scaling, and blue-green releases
-2. **Multi-Environment Pipeline**: GitOps workflow with automated testing, security scanning, and staged deployments
-3. **Monitoring Stack**: Comprehensive observability with metrics, logs, traces, and alerting systems
-
-**Works Best With**: system-architect (infrastructure planning), security-engineer (compliance), performance-engineer (monitoring)
-
----
-
-### deep-research-agent 🔬
-**Expertise**: Comprehensive research with adaptive strategies and multi-hop reasoning
-
-**Auto-Activation**:
-- Keywords: "research", "investigate", "discover", "explore", "find out", "search for", "latest", "current"
-- Commands: `/sc:research` automatically activates this agent
-- Context: Complex queries requiring thorough research, current information needs, fact-checking
-- Complexity: Questions spanning multiple domains or requiring iterative exploration
-
-**Capabilities**:
-- **Adaptive Planning Strategies**: Planning (direct), Intent (clarify first), Unified (collaborative)
-- **Multi-Hop Reasoning**: Up to 5 levels - entity expansion, temporal progression, conceptual deepening, causal chains
-- **Self-Reflective Mechanisms**: Progress assessment after each major step with replanning triggers
-- **Evidence Management**: Clear citations, relevance scoring, uncertainty acknowledgment
-- **Tool Orchestration**: Parallel-first execution with Tavily (search), Playwright (JavaScript content), Sequential (reasoning)
-- **Learning Integration**: Pattern recognition and strategy reuse via Serena memory
-
-**Research Depth Levels**:
-- **Quick**: Basic search, 1 hop, summary output
-- **Standard**: Extended search, 2-3 hops, structured report (default)
-- **Deep**: Comprehensive search, 3-4 hops, detailed analysis
-- **Exhaustive**: Maximum depth, 5 hops, complete investigation
-
-**Examples**:
-1. **Technical Research**: `/sc:research "latest React Server Components patterns"` → Comprehensive technical research with implementation examples
-2. **Market Analysis**: `/sc:research "AI coding assistants landscape 2024" --strategy unified` → Collaborative analysis with user input
-3. **Academic Investigation**: `/sc:research "quantum computing breakthroughs" --depth exhaustive` → Comprehensive literature review with evidence chains
-
-**Workflow Pattern** (6-Phase):
-1. **Understand** (5-10%): Assess query complexity
-2. **Plan** (10-15%): Select strategy and identify parallel opportunities
-3. **TodoWrite** (5%): Create adaptive task hierarchy (3-15 tasks)
-4. **Execute** (50-60%): Parallel searches and extractions
-5. **Track** (Continuous): Monitor progress and confidence
-6. **Validate** (10-15%): Verify evidence chains
-
-**Output**: Reports saved to `claudedocs/research_[topic]_[timestamp].md`
-
-**Works Best With**: system-architect (technical research), learning-guide (educational research), requirements-analyst (market research)
-
-### Quality & Analysis Agents 🔍
-
-### security-engineer 🔒
-**Expertise**: Application security architecture with focus on threat modeling and vulnerability prevention
-
-**Auto-Activation**:
-- Keywords: "security", "auth", "authentication", "vulnerability", "encryption", "compliance", "OWASP"
-- Context: Security reviews, authentication flows, data protection requirements
-- Risk Indicators: Payment processing, user data, API access, regulatory compliance needs
-
-**Capabilities**:
-- Threat modeling and attack surface analysis
-- Secure authentication and authorization design (OAuth, JWT, SAML)
-- Data encryption strategies and key management
-- Vulnerability assessment and penetration testing guidance
-- Security compliance (GDPR, HIPAA, PCI-DSS) implementation
-
-**Examples**:
-1. **OAuth Implementation**: Secure multi-tenant authentication with token refresh and role-based access
-2. **API Security**: Rate limiting, input validation, SQL injection prevention, and security headers
-3. **Data Protection**: Encryption at rest/transit, key rotation, and privacy-by-design architecture
-
-**Works Best With**: backend-architect (API security), quality-engineer (security testing), root-cause-analyst (incident response)
-
----
-
-### performance-engineer ⚡
-**Expertise**: System performance optimization with focus on scalability and resource efficiency
-
-**Auto-Activation**:
-- Keywords: "performance", "slow", "optimization", "bottleneck", "latency", "memory", "CPU"
-- Context: Performance issues, scalability concerns, resource constraints
-- Metrics: Response times >500ms, high memory usage, poor throughput
-
-**Capabilities**:
-- Performance profiling and bottleneck identification
-- Database query optimization and indexing strategies
-- Caching implementation (Redis, CDN, application-level)
-- Load testing and capacity planning
-- Memory management and resource optimization
-
-**Examples**:
-1. **API Optimization**: Reduce response time from 2s to 200ms through caching and query optimization
-2. **Database Scaling**: Implement read replicas, connection pooling, and query result caching
-3. **Frontend Performance**: Bundle optimization, lazy loading, and CDN implementation for <3s load times
-
-**Works Best With**: system-architect (scalability), devops-architect (infrastructure), root-cause-analyst (debugging)
-
----
-
-### root-cause-analyst 🔍
-**Expertise**: Systematic problem investigation using evidence-based analysis and hypothesis testing
-
-**Auto-Activation**:
-- Keywords: "bug", "issue", "problem", "debugging", "investigation", "troubleshoot", "error"
-- Context: System failures, unexpected behavior, complex multi-component issues
-- Complexity: Cross-system problems requiring methodical investigation
-
-**Capabilities**:
-- Systematic debugging methodology and root cause analysis
-- Error correlation and dependency mapping across systems
-- Log analysis and pattern recognition for failure investigation
-- Hypothesis formation and testing for complex problems
-- Incident response and post-mortem analysis procedures
-
-**Examples**:
-1. **Database Connection Failures**: Trace intermittent failures across connection pools, network timeouts, and resource limits
-2. **Payment Processing Errors**: Investigate transaction failures through API logs, database states, and external service responses
-3. **Performance Degradation**: Analyze gradual slowdown through metrics correlation, resource usage, and code changes
-
-**Works Best With**: performance-engineer (performance issues), security-engineer (security incidents), quality-engineer (testing failures)
-
----
-
-### quality-engineer ✅
-**Expertise**: Comprehensive testing strategy and quality assurance with focus on automation and coverage
-
-**Auto-Activation**:
-- Keywords: "test", "testing", "quality", "QA", "validation", "coverage", "automation"
-- Context: Test planning, quality gates, validation requirements
-- Quality Concerns: Code coverage <80%, missing test automation, quality issues
-
-**Capabilities**:
-- Test strategy design (unit, integration, e2e, performance testing)
-- Test automation framework implementation and CI/CD integration
-- Quality metrics definition and monitoring (coverage, defect rates)
-- Edge case identification and boundary testing scenarios
-- Accessibility testing and compliance validation
-
-**Examples**:
-1. **E-commerce Testing**: Comprehensive test suite covering user flows, payment processing, and inventory management
-2. **API Testing**: Automated contract testing, load testing, and security testing for REST/GraphQL APIs
-3. **Accessibility Validation**: WCAG 2.1 compliance testing with automated and manual accessibility audits
-
-**Works Best With**: security-engineer (security testing), performance-engineer (load testing), frontend-architect (UI testing)
-
----
-
-### refactoring-expert 🔧
-**Expertise**: Code quality improvement through systematic refactoring and technical debt management
-
-**Auto-Activation**:
-- Keywords: "refactor", "clean code", "technical debt", "SOLID", "maintainability", "code smell"
-- Context: Legacy code improvements, architecture updates, code quality issues
-- Quality Indicators: High complexity, duplicated code, poor test coverage
-
-**Capabilities**:
-- SOLID principles application and design pattern implementation
-- Code smell identification and systematic elimination
-- Legacy code modernization strategies and migration planning
-- Technical debt assessment and prioritization frameworks
-- Code structure improvement and architecture refactoring
-
-**Examples**:
-1. **Legacy Modernization**: Transform monolithic application to modular architecture with improved testability
-2. **Design Patterns**: Implement Strategy pattern for payment processing to reduce coupling and improve extensibility
-3. **Code Cleanup**: Remove duplicated code, improve naming conventions, and extract reusable components
-
-**Works Best With**: system-architect (architecture improvements), quality-engineer (testing strategy), python-expert (language-specific patterns)
-
-### Specialized Development Agents 🎯
-
-### python-expert 🐍
-**Expertise**: Production-ready Python development with emphasis on modern frameworks and performance
-
-**Auto-Activation**:
-- Keywords: "Python", "Django", "FastAPI", "Flask", "asyncio", "pandas", "pytest"
-- File Types: .py, requirements.txt, pyproject.toml, Pipfile
-- Context: Python development tasks, API development, data processing, testing
-
-**Capabilities**:
-- Modern Python architecture patterns and framework selection
-- Asynchronous programming with asyncio and concurrent futures
-- Performance optimization through profiling and algorithmic improvements
-- Testing strategies with pytest, fixtures, and test automation
-- Package management and deployment with pip, poetry, and Docker
-
-**Examples**:
-1. **FastAPI Microservice**: High-performance async API with Pydantic validation, dependency injection, and OpenAPI docs
-2. **Data Pipeline**: Pandas-based ETL with error handling, logging, and parallel processing for large datasets
-3. **Django Application**: Full-stack web app with custom user models, API endpoints, and comprehensive test coverage
-
-**Works Best With**: backend-architect (API design), quality-engineer (testing), performance-engineer (optimization)
-
----
-
-### requirements-analyst 📝
-**Expertise**: Requirements discovery and specification development through systematic stakeholder analysis
-
-**Auto-Activation**:
-- Keywords: "requirements", "specification", "PRD", "user story", "functional", "scope", "stakeholder"
-- Context: Project initiation, unclear requirements, scope definition needs
-- Complexity: Multi-stakeholder projects, unclear objectives, conflicting requirements
-
-**Capabilities**:
-- Requirements elicitation through stakeholder interviews and workshops
-- User story writing with acceptance criteria and definition of done
-- Functional and non-functional specification documentation
-- Stakeholder analysis and requirement prioritization frameworks
-- Scope management and change control processes
-
-**Examples**:
-1. **Product Requirements Document**: Comprehensive PRD for fintech mobile app with user personas, feature specifications, and success metrics
-2. **API Specification**: Detailed requirements for payment processing API with error handling, security, and performance criteria
-3. **Migration Requirements**: Legacy system modernization requirements with data migration, user training, and rollback procedures
-
-**Works Best With**: system-architect (technical feasibility), technical-writer (documentation), learning-guide (user guidance)
-
-### Communication & Learning Agents 📚
-
-### technical-writer 📚
-**Expertise**: Technical documentation and communication with focus on audience analysis and clarity
-
-**Auto-Activation**:
-- Keywords: "documentation", "readme", "API docs", "user guide", "technical writing", "manual"
-- Context: Documentation requests, API documentation, user guides, technical explanations
-- File Types: .md, .rst, API specs, documentation files
-
-**Capabilities**:
-- Technical documentation architecture and information design
-- Audience analysis and content targeting for different skill levels
-- API documentation with working examples and integration guidance
-- User guide creation with step-by-step procedures and troubleshooting
-- Accessibility standards application and inclusive language usage
-
-**Examples**:
-1. **API Documentation**: Comprehensive REST API docs with authentication, endpoints, examples, and SDK integration guides
-2. **User Manual**: Step-by-step installation and configuration guide with screenshots, troubleshooting, and FAQ sections
-3. **Technical Specification**: System architecture documentation with diagrams, data flows, and implementation details
-
-**Works Best With**: requirements-analyst (specification clarity), learning-guide (educational content), frontend-architect (UI documentation)
-
----
-
-### learning-guide 🎓
-**Expertise**: Educational content design and progressive learning with focus on skill development and mentorship
-
-**Auto-Activation**:
-- Keywords: "explain", "learn", "tutorial", "beginner", "teaching", "education", "training"
-- Context: Educational requests, concept explanations, skill development, learning paths
-- Complexity: Complex topics requiring step-by-step breakdown and progressive understanding
-
-**Capabilities**:
-- Learning path design with progressive skill development
-- Complex concept explanation through analogies and examples
-- Interactive tutorial creation with hands-on exercises
-- Skill assessment and competency evaluation frameworks
-- Mentorship strategies and personalized learning approaches
-
-**Examples**:
-1. **Programming Tutorial**: Interactive React tutorial with hands-on exercises, code examples, and progressive complexity
-2. **Concept Explanation**: Database normalization explained through real-world examples with visual diagrams and practice exercises
-3. **Skill Assessment**: Comprehensive evaluation framework for full-stack development with practical projects and feedback
-
-**Works Best With**: technical-writer (educational documentation), frontend-architect (interactive learning), requirements-analyst (learning objectives)
-
----
-
-## Agent Coordination & Integration 🤝
-
-### Coordination Patterns
-
-**Architecture Teams**:
-- **Full-Stack Development**: frontend-architect + backend-architect + security-engineer + quality-engineer
-- **System Design**: system-architect + devops-architect + performance-engineer + security-engineer
-- **Legacy Modernization**: refactoring-expert + system-architect + quality-engineer + technical-writer
-
-**Quality Teams**:
-- **Security Audit**: security-engineer + quality-engineer + root-cause-analyst + requirements-analyst
-- **Performance Optimization**: performance-engineer + system-architect + devops-architect + root-cause-analyst
-- **Testing Strategy**: quality-engineer + security-engineer + performance-engineer + frontend-architect
-
-**Communication Teams**:
-- **Documentation Project**: technical-writer + requirements-analyst + learning-guide + domain experts
-- **Learning Platform**: learning-guide + frontend-architect + technical-writer + quality-engineer
-- **API Documentation**: backend-architect + technical-writer + security-engineer + quality-engineer
-
-### MCP Server Integration
-
-**Enhanced Capabilities through MCP Servers**:
-- **Context7**: Official documentation patterns for all architects and specialists
-- **Sequential**: Multi-step analysis for root-cause-analyst, system-architect, performance-engineer
-- **Magic**: UI generation for frontend-architect, learning-guide interactive content
-- **Playwright**: Browser testing for quality-engineer, accessibility validation for frontend-architect
-- **Morphllm**: Code transformation for refactoring-expert, bulk changes for python-expert
-- **Serena**: Project memory for all agents, context preservation across sessions
-
-### Troubleshooting Agent Activation
-
-## Troubleshooting
-
-For troubleshooting help, see:
-- [Common Issues](../Reference/common-issues.md) - Quick fixes for frequent problems
-- [Troubleshooting Guide](../Reference/troubleshooting.md) - Comprehensive problem resolution
-
-### Common Issues
-- **No agent activation**: Use domain keywords: "security", "performance", "frontend"
-- **Wrong agents selected**: Check trigger keywords in agent documentation
-- **Too many agents**: Focus keywords on primary domain or use `/sc:focus [domain]`
-- **Agents not coordinating**: Increase task complexity or use multi-domain keywords
-- **Agent expertise mismatch**: Use more specific technical terminology
-
-### Immediate Fixes
-- **Force agent activation**: Use explicit domain keywords in requests
-- **Reset agent selection**: Restart Claude Code session to reset agent state
-- **Check agent patterns**: Review trigger keywords in agent documentation
-- **Test basic activation**: Try `/sc:implement "security auth"` to test security-engineer
-
-### Agent-Specific Troubleshooting
-
-**No Security Agent:**
-```bash
-# Problem: Security concerns not triggering security-engineer
-# Quick Fix: Use explicit security keywords
-"implement authentication" # Generic - may not trigger
-"implement JWT authentication security" # Explicit - triggers security-engineer
-"secure user login with encryption" # Security focus - triggers security-engineer
-```
-
-**No Performance Agent:**
-```bash
-# Problem: Performance issues not triggering performance-engineer
-# Quick Fix: Use performance-specific terminology
-"make it faster" # Vague - may not trigger
-"optimize slow database queries" # Specific - triggers performance-engineer
-"reduce API latency and bottlenecks" # Performance focus - triggers performance-engineer
-```
-
-**No Architecture Agent:**
-```bash
-# Problem: System design not triggering architecture agents
-# Quick Fix: Use architectural keywords
-"build an app" # Generic - triggers basic agents
-"design microservices architecture" # Specific - triggers system-architect
-"scalable distributed system design" # Architecture focus - triggers system-architect
-```
-
-**Wrong Agent Combination:**
-```bash
-# Problem: Getting frontend agent for backend tasks
-# Quick Fix: Use domain-specific terminology
-"create user interface" # May trigger frontend-architect
-"create REST API endpoints" # Specific - triggers backend-architect
-"implement server-side authentication" # Backend focus - triggers backend-architect
-```
-
-### Support Levels
-
-**Quick Fix:**
-- Use explicit domain keywords from agent trigger table
-- Try restarting Claude Code session
-- Focus on single domain to avoid confusion
-
-**Detailed Help:**
-- See [Common Issues Guide](../Reference/common-issues.md) for agent installation problems
-- Review trigger keywords for target agents
-
-**Expert Support:**
-- Use `SuperClaude install --diagnose`
-- See [Diagnostic Reference Guide](../Reference/diagnostic-reference.md) for coordination analysis
-
-**Community Support:**
-- Report issues at [GitHub Issues](https://github.com/SuperClaude-Org/SuperClaude_Framework/issues)
-- Include examples of expected vs actual agent activation
-
-### Success Validation
-
-After applying agent fixes, test with:
-- [ ] Domain-specific requests activate correct agents (security → security-engineer)
-- [ ] Complex tasks trigger multi-agent coordination (3+ agents)
-- [ ] Agent expertise matches task requirements (API → backend-architect)
-- [ ] Quality agents auto-include when appropriate (security, performance, testing)
-- [ ] Responses show domain expertise and specialized knowledge
-
-## Quick Troubleshooting (Legacy)
-- **No agent activation** → Use domain keywords: "security", "performance", "frontend"
-- **Wrong agents** → Check trigger keywords in agent documentation
-- **Too many agents** → Focus keywords on primary domain
-- **Agents not coordinating** → Increase task complexity or use multi-domain keywords
-
-**Agent Not Activating?**
-1. **Check Keywords**: Use domain-specific terminology (e.g., "authentication" not "login" for security-engineer)
-2. **Add Context**: Include file types, frameworks, or specific technologies
-3. **Increase Complexity**: Multi-domain problems trigger more agents
-4. **Use Examples**: Reference concrete scenarios that match agent expertise
-
-**Too Many Agents?**
-- Focus keywords on primary domain needs
-- Use `/sc:focus [domain]` to limit scope
-- Start with specific agents, expand as needed
-
-**Wrong Agents?**
-- Review trigger keywords in agent documentation
-- Use more specific terminology for target domain
-- Add explicit requirements or constraints
-
-## Quick Reference 📋
-
-### Agent Trigger Lookup
-
-| Trigger Type | Keywords/Patterns | Activated Agents |
-|-------------|-------------------|------------------|
-| **Security** | "auth", "security", "vulnerability", "encryption" | security-engineer |
-| **Performance** | "slow", "optimization", "bottleneck", "latency" | performance-engineer |
-| **Frontend** | "UI", "React", "Vue", "component", "responsive" | frontend-architect |
-| **Backend** | "API", "server", "database", "REST", "GraphQL" | backend-architect |
-| **Testing** | "test", "QA", "validation", "coverage" | quality-engineer |
-| **DevOps** | "deploy", "CI/CD", "Docker", "Kubernetes" | devops-architect |
-| **Architecture** | "architecture", "microservices", "scalability" | system-architect |
-| **Python** | ".py", "Django", "FastAPI", "asyncio" | python-expert |
-| **Problems** | "bug", "issue", "debugging", "troubleshoot" | root-cause-analyst |
-| **Code Quality** | "refactor", "clean code", "technical debt" | refactoring-expert |
-| **Documentation** | "documentation", "readme", "API docs" | technical-writer |
-| **Learning** | "explain", "tutorial", "beginner", "teaching" | learning-guide |
-| **Requirements** | "requirements", "PRD", "specification" | requirements-analyst |
-| **Research** | "research", "investigate", "latest", "current" | deep-research-agent |
-
-### Command-Agent Mapping
-
-| Command | Primary Agents | Supporting Agents |
-|---------|----------------|-------------------|
-| `/sc:implement` | Domain architects (frontend, backend) | security-engineer, quality-engineer |
-| `/sc:analyze` | quality-engineer, security-engineer | performance-engineer, root-cause-analyst |
-| `/sc:troubleshoot` | root-cause-analyst | Domain specialists, performance-engineer |
-| `/sc:improve` | refactoring-expert | quality-engineer, performance-engineer |
-| `/sc:document` | technical-writer | Domain specialists, learning-guide |
-| `/sc:design` | system-architect | Domain architects, requirements-analyst |
-| `/sc:test` | quality-engineer | security-engineer, performance-engineer |
-| `/sc:explain` | learning-guide | technical-writer, domain specialists |
-| `/sc:research` | deep-research-agent | Technical specialists, learning-guide |
-
-### Effective Agent Combinations
-
-**Development Workflows**:
-- Web application: frontend-architect + backend-architect + security-engineer + quality-engineer + devops-architect
-- API development: backend-architect + security-engineer + technical-writer + quality-engineer
-- Data platform: python-expert + performance-engineer + security-engineer + system-architect
-
-**Analysis Workflows**:
-- Security audit: security-engineer + quality-engineer + root-cause-analyst + technical-writer
-- Performance investigation: performance-engineer + root-cause-analyst + system-architect + devops-architect
-- Legacy assessment: refactoring-expert + system-architect + quality-engineer + security-engineer + technical-writer
-
-**Communication Workflows**:
-- Technical documentation: technical-writer + requirements-analyst + domain experts + learning-guide
-- Educational content: learning-guide + technical-writer + frontend-architect + quality-engineer
-
-## Best Practices 💡
-
-### Getting Started (Simple Approach)
-
-**Natural Language First:**
-1. **Describe Your Goal**: Use natural language with domain-specific keywords
-2. **Trust Auto-Activation**: Let the system route to appropriate agents automatically
-3. **Learn from Patterns**: Observe which agents activate for different request types
-4. **Iterate and Refine**: Add specificity to engage additional specialist agents
-
-### Optimizing Agent Selection
-
-**Effective Keyword Usage:**
-- **Specific > Generic**: Use "authentication" instead of "login" for security-engineer
-- **Technical Terms**: Include framework names, technologies, and specific challenges
-- **Context Clues**: Mention file types, project scope, and complexity indicators
-- **Quality Keywords**: Add "security", "performance", "accessibility" for comprehensive coverage
-
-**Request Optimization Examples:**
-```bash
-# Generic (limited agent activation)
-"Fix the login feature"
-
-# Optimized (multi-agent coordination)
-"Implement secure JWT authentication with rate limiting and accessibility compliance"
-# → Triggers: security-engineer + backend-architect + frontend-architect + quality-engineer
-```
-
-### Common Usage Patterns
-
-**Development Workflows:**
-```bash
-# Full-stack feature development
-/sc:implement "responsive user dashboard with real-time notifications"
-# → frontend-architect + backend-architect + performance-engineer
-
-# API development with documentation
-/sc:create "REST API for payment processing with comprehensive docs"
-# → backend-architect + security-engineer + technical-writer + quality-engineer
-
-# Performance optimization investigation
-/sc:troubleshoot "slow database queries affecting user experience"
-# → performance-engineer + root-cause-analyst + backend-architect
-```
-
-**Analysis Workflows:**
-```bash
-# Security assessment
-/sc:analyze "authentication system for GDPR compliance vulnerabilities"
-# → security-engineer + quality-engineer + requirements-analyst
-
-# Code quality review
-/sc:review "legacy codebase for modernization opportunities"
-# → refactoring-expert + system-architect + quality-engineer + technical-writer
-
-# Learning and explanation
-/sc:explain "microservices patterns with hands-on examples"
-# → system-architect + learning-guide + technical-writer
-```
-
-### Advanced Agent Coordination
-
-**Multi-Domain Projects:**
-- **Start Broad**: Begin with system-level keywords to engage architecture agents
-- **Add Specificity**: Include domain-specific needs to activate specialist agents
-- **Quality Integration**: Automatically include security, performance, and testing perspectives
-- **Documentation Inclusion**: Add learning or documentation needs for comprehensive coverage
-
-**Troubleshooting Agent Selection:**
-
-**Problem: Wrong agents activating**
-- Solution: Use more specific domain terminology
-- Example: "database optimization" → performance-engineer + backend-architect
-
-**Problem: Not enough agents**
-- Solution: Increase complexity indicators and cross-domain keywords
-- Example: Add "security", "performance", "documentation" to requests
-
-**Problem: Too many agents**
-- Solution: Focus on primary domain with specific technical terms
-- Example: Use "/sc:focus backend" to limit scope
-
-### Quality-Driven Development
-
-**Security-First Approach:**
-Always include security considerations in development requests to automatically engage security-engineer alongside domain specialists.
-
-**Performance Integration:**
-Include performance keywords ("fast", "efficient", "scalable") to ensure performance-engineer coordination from the start.
-
-**Accessibility Compliance:**
-Use "accessible", "WCAG", or "inclusive" to automatically include accessibility validation in frontend development.
-
-**Documentation Culture:**
-Add "documented", "explained", or "tutorial" to requests for automatic technical-writer inclusion and knowledge transfer.
-
----
-
-## Understanding Agent Intelligence 🧠
-
-### What Makes Agents Effective
-
-**Domain Expertise**: Each agent has specialized knowledge patterns, behavioral approaches, and problem-solving methodologies specific to their domain.
-
-**Contextual Activation**: Agents analyze request context, not just keywords, to determine relevance and engagement level.
-
-**Collaborative Intelligence**: Multi-agent coordination produces synergistic results that exceed individual agent capabilities.
-
-**Adaptive Learning**: Agent selection improves based on request patterns and successful coordination outcomes.
-
-### Agent vs. Traditional AI
-
-**Traditional Approach**: Single AI handles all domains with varying levels of expertise
-**Agent Approach**: Specialized experts collaborate with deep domain knowledge and focused problem-solving
-
-**Benefits**:
-- Higher accuracy in domain-specific tasks
-- More sophisticated problem-solving methodologies
-- Better quality assurance through specialist review
-- Coordinated multi-perspective analysis
-
-### Trust the System, Understand the Patterns
-
-**What to Expect**:
-- Automatic routing to appropriate domain experts
-- Multi-agent coordination for complex tasks
-- Quality integration through automatic QA agent inclusion
-- Learning opportunities through educational agent activation
-
-**What Not to Worry About**:
-- Manual agent selection or configuration
-- Complex routing rules or agent management
-- Agent configuration or coordination
-- Micromanaging agent interactions
-
----
-
-## Related Resources 📚
-
-### Essential Documentation
-- **[Commands Guide](commands.md)** - Master SuperClaude commands that trigger optimal agent coordination
-- **[MCP Servers](mcp-servers.md)** - Enhanced agent capabilities through specialized tool integration
-- **[Session Management](session-management.md)** - Long-term workflows with persistent agent context
-
-### Advanced Usage
-- **[Behavioral Modes](modes.md)** - Context optimization for enhanced agent coordination
-- **[Getting Started](../Getting-Started/quick-start.md)** - Expert techniques for agent optimization
-- **[Examples Cookbook](../Reference/examples-cookbook.md)** - Real-world agent coordination patterns
-
-### Development Resources
-- **[Technical Architecture](../Developer-Guide/technical-architecture.md)** - Understanding SuperClaude's agent system design
-- **[Contributing](../Developer-Guide/contributing-code.md)** - Extending agent capabilities and coordination patterns
-
----
-
-## Your Agent Journey 🚀
-
-**Week 1: Natural Usage**
-Start with natural language descriptions. Notice which agents activate and why. Build intuition for keyword patterns without overthinking the process.
-
-**Week 2-3: Pattern Recognition**
-Observe agent coordination patterns. Understand how complexity and domain keywords influence agent selection. Begin optimizing request phrasing for better coordination.
-
-**Month 2+: Expert Coordination**
-Master multi-domain requests that trigger optimal agent combinations. Leverage troubleshooting techniques for effective agent selection. Use advanced patterns for complex workflows.
-
-**The SuperClaude Advantage:**
-Experience the power of 14 specialized AI experts working in coordinated response, all through simple, natural language requests. No configuration, no management, just intelligent collaboration that scales with your needs.
-
-🎯 **Ready to experience intelligent agent coordination? Start with `/sc:implement` and discover the magic of specialized AI collaboration.**
\ No newline at end of file
diff --git a/docs/User-Guide/commands.md b/docs/User-Guide/commands.md
deleted file mode 100644
index c30cb25..0000000
--- a/docs/User-Guide/commands.md
+++ /dev/null
@@ -1,367 +0,0 @@
-# SuperClaude Commands Guide
-
-SuperClaude provides 25 commands for Claude Code: `/sc:*` commands for workflows and `@agent-*` for specialists.
-
-## Command Types
-
-| Type | Where Used | Format | Example |
-|------|------------|--------|---------|
-| **Slash Commands** | Claude Code | `/sc:[command]` | `/sc:implement "feature"` |
-| **Agents** | Claude Code | `@agent-[name]` | `@agent-security "review"` |
-| **Installation** | Terminal | `SuperClaude [command]` | `SuperClaude install` |
-
-## Quick Test
-```bash
-# Terminal: Verify installation
-python3 -m SuperClaude --version
-# Claude Code CLI verification: claude --version
-
-# Claude Code: Test commands
-/sc:brainstorm "test project" # Should ask discovery questions
-/sc:analyze README.md # Should provide analysis
-```
-
-**Workflow**: `/sc:brainstorm "idea"` → `/sc:implement "feature"` → `/sc:test`
-
-## 🎯 Understanding SuperClaude Commands
-
-## How SuperClaude Works
-
-SuperClaude provides behavioral context files that Claude Code reads to adopt specialized behaviors. When you type `/sc:implement`, Claude Code reads the `implement.md` context file and follows its behavioral instructions.
-
-**SuperClaude commands are NOT executed by software** - they are context triggers that modify Claude Code's behavior through reading specialized instruction files from the framework.
-
-### Command Types:
-- **Slash Commands** (`/sc:*`): Trigger workflow patterns and behavioral modes
-- **Agent Invocations** (`@agent-*`): Manually activate specific domain specialists
-- **Flags** (`--think`, `--safe-mode`): Modify command behavior and depth
-
-### The Context Mechanism:
-1. **User Input**: You type `/sc:implement "auth system"`
-2. **Context Loading**: Claude Code reads `~/.claude/superclaude/Commands/implement.md`
-3. **Behavior Adoption**: Claude applies domain expertise, tool selection, and validation patterns
-4. **Enhanced Output**: Structured implementation with security considerations and best practices
-
-**Key Point**: This creates sophisticated development workflows through context management rather than traditional software execution.
-
-### Installation vs Usage Commands
-
-**🖥️ Terminal Commands** (Actual CLI software):
-- `SuperClaude install` - Installs the framework components
-- `SuperClaude update` - Updates existing installation
-- `SuperClaude uninstall` - Removes framework installation
-- `python3 -m SuperClaude --version` - Check installation status
-
-**💬 Claude Code Commands** (Context triggers):
-- `/sc:brainstorm` - Activates requirements discovery context
-- `/sc:implement` - Activates feature development context
-- `@agent-security` - Activates security specialist context
-- All commands work inside Claude Code chat interface only
-
-
-> **Quick Start**: Try `/sc:brainstorm "your project idea"` → `/sc:implement "feature name"` → `/sc:test` to experience the core workflow.
-
-## 🧪 Testing Your Setup
-
-### 🖥️ Terminal Verification (Run in Terminal/CMD)
-```bash
-# Verify SuperClaude is working (primary method)
-python3 -m SuperClaude --version
-# Example output: SuperClaude 4.1.5
-
-# Claude Code CLI version check
-claude --version
-
-# Check installed components
-python3 -m SuperClaude install --list-components | grep mcp
-# Example output: Shows installed MCP components
-```
-
-### 💬 Claude Code Testing (Type in Claude Code Chat)
-```
-# Test basic /sc: command
-/sc:brainstorm "test project"
-# Example behavior: Interactive requirements discovery starts
-
-# Test command help
-/sc:help
-# Example behavior: List of available commands
-```
-
-**If tests fail**: Check [Installation Guide](../Getting-Started/installation.md) or [Troubleshooting](#troubleshooting)
-
-### 📝 Command Quick Reference
-
-| Command Type | Where to Run | Format | Purpose | Example |
-|-------------|--------------|--------|---------|----------|
-| **🖥️ Installation** | Terminal/CMD | `SuperClaude [command]` | Setup and maintenance | `SuperClaude install` |
-| **🔧 Configuration** | Terminal/CMD | `python3 -m SuperClaude [command]` | Advanced configuration | `python3 -m SuperClaude --version` |
-| **💬 Slash Commands** | Claude Code | `/sc:[command]` | Workflow automation | `/sc:implement "feature"` |
-| **🤖 Agent Invocation** | Claude Code | `@agent-[name]` | Manual specialist activation | `@agent-security "review"` |
-| **⚡ Enhanced Flags** | Claude Code | `/sc:[command] --flags` | Behavior modification | `/sc:analyze --think-hard` |
-
-> **Remember**: All `/sc:` commands and `@agent-` invocations work inside Claude Code chat, not your terminal. They trigger Claude Code to read specific context files from the SuperClaude framework.
-
-## Table of Contents
-
-- [Essential Commands](#essential-commands) - Start here (8 core commands)
-- [Common Workflows](#common-workflows) - Command combinations that work
-- [Full Command Reference](#full-command-reference) - All 25 commands organized by category
-- [Troubleshooting](#troubleshooting) - Common issues and solutions
-- [Command Index](#command-index) - Find commands by category
-
----
-
-## Essential Commands
-
-**Core workflow commands for immediate productivity:**
-
-### `/sc:brainstorm` - Project Discovery
-**Purpose**: Interactive requirements discovery and project planning
-**Syntax**: `/sc:brainstorm "your idea"` `[--strategy systematic|creative]`
-
-**Use Cases**:
-- New project planning: `/sc:brainstorm "e-commerce platform"`
-- Feature exploration: `/sc:brainstorm "user authentication system"`
-- Problem solving: `/sc:brainstorm "slow database queries"`
-
-### `/sc:help` - Command Reference
-**Purpose**: Displays a list of all available `/sc` commands and their descriptions.
-**Syntax**: `/sc:help`
-
-**Use Cases**:
-- Discovering available commands: `/sc:help`
-- Getting a quick reminder of command names: `/sc:help`
-
-### `/sc:research` - Deep Research Command
-**Purpose**: Comprehensive web research with adaptive planning and intelligent search
-**Syntax**: `/sc:research "[query]"` `[--depth quick|standard|deep|exhaustive] [--strategy planning|intent|unified]`
-
-**Use Cases**:
-- Technical research: `/sc:research "latest React 19 features" --depth deep`
-- Market analysis: `/sc:research "AI coding assistant landscape 2024" --strategy unified`
-- Academic investigation: `/sc:research "quantum computing breakthroughs" --depth exhaustive`
-- Current events: `/sc:research "latest AI developments 2024"`
-
-**Key Capabilities**:
-- **6-Phase Workflow**: Understand → Plan → TodoWrite → Execute → Track → Validate
-- **Adaptive Depth**: Quick (basic search), Standard (extended), Deep (comprehensive), Exhaustive (maximum depth)
-- **Planning Strategies**: Planning (direct), Intent (clarify first), Unified (collaborative)
-- **Parallel Execution**: Default parallel searches and extractions
-- **Evidence Management**: Clear citations with relevance scoring
-- **Output Standards**: Reports saved to `claudedocs/research_[topic]_[timestamp].md`
-
-### `/sc:implement` - Feature Development
-**Purpose**: Full-stack feature implementation with intelligent specialist routing
-**Syntax**: `/sc:implement "feature description"` `[--type frontend|backend|fullstack] [--focus security|performance]`
-
-**Use Cases**:
-- Authentication: `/sc:implement "JWT login system"`
-- UI components: `/sc:implement "responsive dashboard"`
-- APIs: `/sc:implement "REST user endpoints"`
-- Database: `/sc:implement "user schema with relationships"`
-
-### `/sc:analyze` - Code Assessment
-**Purpose**: Comprehensive code analysis across quality, security, and performance
-**Syntax**: `/sc:analyze [path]` `[--focus quality|security|performance|architecture]`
-
-**Use Cases**:
-- Project health: `/sc:analyze .`
-- Security audit: `/sc:analyze --focus security`
-- Performance review: `/sc:analyze --focus performance`
-
-### `/sc:business-panel` - Strategic Business Analysis
-**Purpose**: Multi-expert business strategy analysis with 9 renowned thought leaders
-**Syntax**: `/sc:business-panel "content"` `[--mode discussion|debate|socratic] [--experts "name1,name2"]`
-
-**Use Cases**:
-- Strategy evaluation: `/sc:business-panel "our go-to-market strategy"`
-- Competitive analysis: `/sc:business-panel @competitor_analysis.pdf --mode debate`
-- Innovation assessment: `/sc:business-panel "AI product idea" --experts "christensen,drucker"`
-- Strategic learning: `/sc:business-panel "competitive strategy" --mode socratic`
-
-**Expert Panel**: Christensen, Porter, Drucker, Godin, Kim/Mauborgne, Collins, Taleb, Meadows, Doumont
-
-### `/sc:spec-panel` - Expert Specification Review
-**Purpose**: Multi-expert specification review and improvement using renowned specification and software engineering experts
-**Syntax**: `/sc:spec-panel [content|@file]` `[--mode discussion|critique|socratic] [--focus requirements|architecture|testing|compliance]`
-
-**Use Cases**:
-- Specification review: `/sc:spec-panel @api_spec.yml --mode critique --focus requirements,architecture`
-- Requirements workshop: `/sc:spec-panel "user story content" --mode discussion`
-- Architecture validation: `/sc:spec-panel @microservice.spec.yml --mode socratic --focus architecture`
-- Compliance review: `/sc:spec-panel @security_requirements.yml --focus compliance`
-- Iterative improvement: `/sc:spec-panel @complex_system.spec.yml --iterations 3`
-
-**Expert Panel**: Wiegers, Adzic, Cockburn, Fowler, Nygard, Newman, Hohpe, Crispin, Gregory, Hightower
-
-### `/sc:troubleshoot` - Problem Diagnosis
-**Purpose**: Systematic issue diagnosis with root cause analysis
-**Syntax**: `/sc:troubleshoot "issue description"` `[--type build|runtime|performance]`
-
-**Use Cases**:
-- Runtime errors: `/sc:troubleshoot "500 error on login"`
-- Build failures: `/sc:troubleshoot --type build`
-- Performance problems: `/sc:troubleshoot "slow page load"`
-
-### `/sc:test` - Quality Assurance
-**Purpose**: Comprehensive testing with coverage analysis
-**Syntax**: `/sc:test` `[--type unit|integration|e2e] [--coverage] [--fix]`
-
-**Use Cases**:
-- Full test suite: `/sc:test --coverage`
-- Unit testing: `/sc:test --type unit --watch`
-- E2E validation: `/sc:test --type e2e`
-
-### `/sc:improve` - Code Enhancement
-**Purpose**: Apply systematic code improvements and optimizations
-**Syntax**: `/sc:improve [path]` `[--type performance|quality|security] [--preview]`
-
-**Use Cases**:
-- General improvements: `/sc:improve src/`
-- Performance optimization: `/sc:improve --type performance`
-- Security hardening: `/sc:improve --type security`
-
-### `/sc:document` - Documentation Generation
-**Purpose**: Generate comprehensive documentation for code and APIs
-**Syntax**: `/sc:document [path]` `[--type api|user-guide|technical] [--format markdown|html]`
-
-**Use Cases**:
-- API docs: `/sc:document --type api`
-- User guides: `/sc:document --type user-guide`
-- Technical docs: `/sc:document --type technical`
-
-### `/sc:workflow` - Implementation Planning
-**Purpose**: Generate structured implementation plans from requirements
-**Syntax**: `/sc:workflow "feature description"` `[--strategy agile|waterfall] [--format markdown]`
-
-**Use Cases**:
-- Feature planning: `/sc:workflow "user authentication"`
-- Sprint planning: `/sc:workflow --strategy agile`
-- Architecture planning: `/sc:workflow "microservices migration"`
-
----
-
-## Common Workflows
-
-**Proven command combinations:**
-
-### New Project Setup
-```bash
-/sc:brainstorm "project concept" # Define requirements
-/sc:design "system architecture" # Create technical design
-/sc:workflow "implementation plan" # Generate development roadmap
-```
-
-### Feature Development
-```bash
-/sc:implement "feature name" # Build the feature
-/sc:test --coverage # Validate with tests
-/sc:document --type api # Generate documentation
-```
-
-### Code Quality Improvement
-```bash
-/sc:analyze --focus quality # Assess current state
-/sc:improve --preview # Preview improvements
-/sc:test --coverage # Validate changes
-```
-
-### Bug Investigation
-```bash
-/sc:troubleshoot "issue description" # Diagnose the problem
-/sc:analyze --focus problem-area # Deep analysis
-/sc:improve --fix --safe-mode # Apply targeted fixes
-```
-
-### Specification Development
-```bash
-/sc:spec-panel @existing_spec.yml --mode critique # Expert review
-/sc:spec-panel @improved_spec.yml --iterations 2 # Iterative refinement
-/sc:document --type technical # Generate documentation
-```
-
-## Full Command Reference
-
-### Development Commands
-| Command | Purpose | Best For |
-|---------|---------|----------|
-| **workflow** | Implementation planning | Project roadmaps, sprint planning |
-| **implement** | Feature development | Full-stack features, API development |
-| **build** | Project compilation | CI/CD, production builds |
-| **design** | System architecture | API specs, database schemas |
-
-### Analysis Commands
-| Command | Purpose | Best For |
-|---------|---------|----------|
-| **analyze** | Code assessment | Quality audits, security reviews |
-| **research** | Web research with intelligent search | Technical research, current events, market analysis |
-| **business-panel** | Strategic analysis | Business decisions, competitive assessment |
-| **spec-panel** | Specification review | Requirements validation, architecture analysis |
-| **troubleshoot** | Problem diagnosis | Bug investigation, performance issues |
-| **explain** | Code explanation | Learning, code reviews |
-
-### Quality Commands
-| Command | Purpose | Best For |
-|---------|---------|----------|
-| **improve** | Code enhancement | Performance optimization, refactoring |
-| **cleanup** | Technical debt | Dead code removal, organization |
-| **test** | Quality assurance | Test automation, coverage analysis |
-| **document** | Documentation | API docs, user guides |
-
-### Project Management
-| Command | Purpose | Best For |
-|---------|---------|----------|
-| **estimate** | Project estimation | Timeline planning, resource allocation |
-| **task** | Task management | Complex workflows, task tracking |
-| **spawn** | Meta-orchestration | Large-scale projects, parallel execution |
-
-### Utility Commands
-| Command | Purpose | Best For |
-|---------|---------|----------|
-| **help** | List all commands | Discovering available commands |
-| **git** | Version control | Commit management, branch strategies |
-| **index** | Command discovery | Exploring capabilities, finding commands |
-
-### Session Commands
-| Command | Purpose | Best For |
-|---------|---------|----------|
-| **load** | Context loading | Session initialization, project onboarding |
-| **save** | Session persistence | Checkpointing, context preservation |
-| **reflect** | Task validation | Progress assessment, completion validation |
-| **select-tool** | Tool optimization | Performance optimization, tool selection |
-
----
-
-## Command Index
-
-**By Function:**
-- **Planning**: brainstorm, design, workflow, estimate
-- **Development**: implement, build, git
-- **Analysis**: analyze, business-panel, spec-panel, troubleshoot, explain
-- **Quality**: improve, cleanup, test, document
-- **Management**: task, spawn, load, save, reflect
-- **Utility**: help, index, select-tool
-
-**By Complexity:**
-- **Beginner**: brainstorm, implement, analyze, test, help
-- **Intermediate**: workflow, design, business-panel, spec-panel, improve, document
-- **Advanced**: spawn, task, select-tool, reflect
-
-## Troubleshooting
-
-**Command Issues:**
-- **Command not found**: Verify installation: `python3 -m SuperClaude --version`
-- **No response**: Restart Claude Code session
-- **Processing delays**: Use `--no-mcp` to test without MCP servers
-
-**Quick Fixes:**
-- Reset session: `/sc:load` to reinitialize
-- Check status: `SuperClaude install --list-components`
-- Get help: [Troubleshooting Guide](../Reference/troubleshooting.md)
-
-## Next Steps
-
-- [Flags Guide](flags.md) - Control command behavior
-- [Agents Guide](agents.md) - Specialist activation
-- [Examples Cookbook](../Reference/examples-cookbook.md) - Real usage patterns
\ No newline at end of file
diff --git a/docs/User-Guide/flags.md b/docs/User-Guide/flags.md
deleted file mode 100644
index 639e15e..0000000
--- a/docs/User-Guide/flags.md
+++ /dev/null
@@ -1,273 +0,0 @@
-# SuperClaude Flags Guide 🏁
-
-**Most flags activate automatically** - Claude Code reads behavioral instructions to engage appropriate contexts based on keywords and patterns in your requests.
-
-## Essential Auto-Activation Flags (90% of Use Cases)
-
-### Core Analysis Flags
-| Flag | When Activated | What It Does |
-|------|---------------|--------------|
-| `--think` | 5+ files OR complex analysis | Standard structured analysis (~4K tokens) |
-| `--think-hard` | Architectural analysis, system dependencies | Deep analysis (~10K tokens) with enhanced tools |
-| `--ultrathink` | Critical system redesign, legacy modernization | Maximum depth analysis (~32K tokens) with all tools |
-
-### MCP Server Flags
-| Flag | Server | Purpose | Auto-Triggers |
-|------|---------|---------|---------------|
-| `--c7` / `--context7` | Context7 | Official docs, framework patterns | Library imports, framework questions |
-| `--seq` / `--sequential` | Sequential | Multi-step reasoning, debugging | Complex debugging, system design |
-| `--magic` | Magic | UI component generation | `/ui` commands, frontend keywords |
-| `--play` / `--playwright` | Playwright | Browser testing, E2E validation | Testing requests, visual validation |
-| `--chrome` / `--devtools` | Chrome DevTools | Performance analysis, debugging | Performance auditing, debugging, layout issues |
-| `--tavily` | Tavily | Web search, real-time info | Web search requests, research queries |
-| `--morph` / `--morphllm` | Morphllm | Bulk transformations, pattern edits | Bulk operations, style enforcement |
-| `--serena` | Serena | Project memory, symbol operations | Symbol operations, large codebases |
-
-### Behavioral Mode Flags
-| Flag | When Activated | What It Does |
-|------|---------------|--------------|
-| `--brainstorm` | Vague requests, exploration keywords | Collaborative discovery mindset |
-| `--introspect` | Self-analysis, error recovery | Expose reasoning process with transparency |
-| `--task-manage` | >3 steps, complex scope | Orchestrate through delegation |
-| `--orchestrate` | Multi-tool operations, performance needs | Optimize tool selection and parallel execution |
-| `--token-efficient` / `--uc` | Context >75%, efficiency needs | Symbol-enhanced communication, 30-50% reduction |
-
-### Execution Control Flags
-| Flag | When Activated | What It Does |
-|------|---------------|--------------|
-| `--loop` | "improve", "polish", "refine" keywords | Iterative enhancement cycles |
-| `--safe-mode` | Production, >85% resource usage | Maximum validation, conservative execution |
-| `--validate` | Risk >0.7, production environment | Pre-execution risk assessment |
-| `--delegate` | >7 directories OR >50 files | Sub-agent parallel processing |
-
-## Command-Specific Flags
-
-### Analysis Command Flags (`/sc:analyze`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--focus` | Target specific domain | `security`, `performance`, `quality`, `architecture` |
-| `--depth` | Analysis thoroughness | `quick`, `deep` |
-| `--format` | Output format | `text`, `json`, `report` |
-
-### Build Command Flags (`/sc:build`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--type` | Build configuration | `dev`, `prod`, `test` |
-| `--clean` | Clean before build | Boolean |
-| `--optimize` | Enable optimizations | Boolean |
-| `--verbose` | Detailed output | Boolean |
-
-### Design Command Flags (`/sc:design`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--type` | Design target | `architecture`, `api`, `component`, `database` |
-| `--format` | Output format | `diagram`, `spec`, `code` |
-
-### Explain Command Flags (`/sc:explain`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--level` | Complexity level | `basic`, `intermediate`, `advanced` |
-| `--format` | Explanation style | `text`, `examples`, `interactive` |
-| `--context` | Domain context | Any domain (e.g., `react`, `security`) |
-
-### Improve Command Flags (`/sc:improve`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--type` | Improvement focus | `quality`, `performance`, `maintainability`, `style`, `security` |
-| `--safe` | Conservative approach | Boolean |
-| `--interactive` | User guidance | Boolean |
-| `--preview` | Show without executing | Boolean |
-
-### Task Command Flags (`/sc:task`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--strategy` | Task approach | `systematic`, `agile`, `enterprise` |
-| `--parallel` | Parallel execution | Boolean |
-| `--delegate` | Sub-agent coordination | Boolean |
-
-### Workflow Command Flags (`/sc:workflow`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--strategy` | Workflow approach | `systematic`, `agile`, `enterprise` |
-| `--depth` | Analysis depth | `shallow`, `normal`, `deep` |
-| `--parallel` | Parallel coordination | Boolean |
-
-### Troubleshoot Command Flags (`/sc:troubleshoot`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--type` | Issue category | `bug`, `build`, `performance`, `deployment` |
-| `--trace` | Include trace analysis | Boolean |
-| `--fix` | Apply fixes | Boolean |
-
-### Cleanup Command Flags (`/sc:cleanup`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--type` | Cleanup target | `code`, `imports`, `files`, `all` |
-| `--safe` / `--aggressive` | Cleanup intensity | Boolean |
-| `--interactive` | User guidance | Boolean |
-| `--preview` | Show without executing | Boolean |
-
-### Estimate Command Flags (`/sc:estimate`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--type` | Estimate focus | `time`, `effort`, `complexity` |
-| `--unit` | Time unit | `hours`, `days`, `weeks` |
-| `--breakdown` | Detailed breakdown | Boolean |
-
-### Index Command Flags (`/sc:index`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--type` | Index target | `docs`, `api`, `structure`, `readme` |
-| `--format` | Output format | `md`, `json`, `yaml` |
-
-### Reflect Command Flags (`/sc:reflect`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--type` | Reflection scope | `task`, `session`, `completion` |
-| `--analyze` | Include analysis | Boolean |
-| `--validate` | Validate completeness | Boolean |
-
-### Spawn Command Flags (`/sc:spawn`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--strategy` | Coordination approach | `sequential`, `parallel`, `adaptive` |
-| `--depth` | Analysis depth | `normal`, `deep` |
-
-### Git Command Flags (`/sc:git`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--smart-commit` | Generate commit message | Boolean |
-| `--interactive` | Guided operations | Boolean |
-
-### Select-Tool Command Flags (`/sc:select-tool`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--analyze` | Tool analysis | Boolean |
-| `--explain` | Explain selection | Boolean |
-
-### Test Command Flags (`/sc:test`)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--coverage` | Include coverage | Boolean |
-| `--type` | Test type | `unit`, `integration`, `e2e` |
-| `--watch` | Watch mode | Boolean |
-
-## Advanced Control Flags
-
-### Scope and Focus
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--scope` | Analysis boundary | `file`, `module`, `project`, `system` |
-| `--focus` | Domain targeting | `performance`, `security`, `quality`, `architecture`, `accessibility`, `testing` |
-
-### Execution Control
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--concurrency [n]` | Control parallel ops | 1-15 |
-| `--iterations [n]` | Improvement cycles | 1-10 |
-| `--all-mcp` | Enable all MCP servers | Boolean |
-| `--no-mcp` | Native tools only | Boolean |
-| `--frontend-verify` | UI testing, frontend debugging, layout validation | Enable Playwright + Chrome DevTools + Serena |
-
-### System Flags (SuperClaude Installation)
-| Flag | Purpose | Values |
-|------|---------|--------|
-| `--verbose` / `-v` | Verbose logging | Boolean |
-| `--quiet` / `-q` | Suppress output | Boolean |
-| `--dry-run` | Simulate operation | Boolean |
-| `--force` | Skip checks | Boolean |
-| `--yes` / `-y` | Auto-confirm | Boolean |
-| `--install-dir` | Target directory | Path |
-| `--legacy` | Use legacy script | Boolean |
-| `--version` | Show version | Boolean |
-| `--help` | Show help | Boolean |
-
-## Common Usage Patterns
-
-### Frontend Development
-```bash
-/sc:implement "responsive dashboard" --magic --c7
-/sc:design component-library --type component --format code
-/sc:test ui-components/ --magic --play
-/sc:improve legacy-ui/ --magic --morph --validate
-```
-
-### Backend Development
-```bash
-/sc:analyze api/ --focus performance --seq --think
-/sc:design payment-api --type api --format spec
-/sc:troubleshoot "API timeout" --type performance --trace
-/sc:improve auth-service --type security --validate
-```
-
-### Large Projects
-```bash
-/sc:analyze . --ultrathink --all-mcp --safe-mode
-/sc:workflow enterprise-system --strategy enterprise --depth deep
-/sc:cleanup . --type all --safe --interactive
-/sc:estimate "migrate to microservices" --type complexity --breakdown
-```
-
-### Quality & Maintenance
-```bash
-/sc:improve src/ --type quality --safe --interactive
-/sc:cleanup imports --type imports --preview
-/sc:reflect --type completion --validate
-/sc:git commit --smart-commit
-```
-
-## Flag Interactions
-
-### Compatible Combinations
-- `--think` + `--c7`: Analysis with documentation
-- `--magic` + `--play`: UI generation with testing
-- `--serena` + `--morph`: Project memory with transformations
-- `--safe-mode` + `--validate`: Maximum safety
-- `--loop` + `--validate`: Iterative improvement with validation
-
-### Conflicting Flags
-- `--all-mcp` vs individual MCP flags (use one or the other)
-- `--no-mcp` vs any MCP flags (--no-mcp wins)
-- `--safe` vs `--aggressive` (cleanup intensity)
-- `--quiet` vs `--verbose` (output level)
-
-### Auto-Enabling Relationships
-- `--safe-mode` auto-enables `--uc` and `--validate`
-- `--ultrathink` auto-enables all MCP servers
-- `--think-hard` auto-enables `--seq` + `--c7`
-- `--magic` triggers UI-focused agents
-
-## Troubleshooting Flags
-
-### Common Issues
-- **Too many tools**: Use `--no-mcp` to test with native tools only
-- **Operation too slow**: Add `--uc` to compress output
-- **Validation blocking**: Use `--validate` instead of `--safe-mode` in development
-- **Context pressure**: Auto-activates `--token-efficient` at >75% usage
-
-### Debug Flags
-```bash
-/sc:analyze . --verbose # Shows decision logic and flag activation
-/sc:select-tool "operation" --explain # Explains tool selection process
-/sc:reflect --type session --analyze # Reviews current session decisions
-```
-
-### Quick Fixes
-```bash
-/sc:analyze . --help # Shows available flags for command
-/sc:analyze . --no-mcp # Native execution only
-/sc:cleanup . --preview # Shows what would be cleaned
-```
-
-## Flag Priority Rules
-
-1. **Safety First**: `--safe-mode` > `--validate` > optimization flags
-2. **Explicit Override**: User flags > auto-detection
-3. **Depth Hierarchy**: `--ultrathink` > `--think-hard` > `--think`
-4. **MCP Control**: `--no-mcp` overrides all individual MCP flags
-5. **Scope Precedence**: system > project > module > file
-
-## Related Resources
-- [Commands Guide](commands.md) - Commands that use these flags
-- [MCP Servers Guide](mcp-servers.md) - Understanding MCP flag activation
-- [Session Management](session-management.md) - Using flags with persistent sessions
\ No newline at end of file
diff --git a/docs/User-Guide/mcp-servers.md b/docs/User-Guide/mcp-servers.md
deleted file mode 100644
index 256295e..0000000
--- a/docs/User-Guide/mcp-servers.md
+++ /dev/null
@@ -1,339 +0,0 @@
-# SuperClaude MCP Servers Guide 🔌
-
-## Overview
-
-MCP (Model Context Protocol) servers extend Claude Code's capabilities through specialized tools. SuperClaude integrates 8 MCP servers and provides Claude with instructions on when to activate them based on your tasks.
-
-### 🔍 Reality Check
-- **What MCP servers are**: External Node.js processes that provide additional tools
-- **What they aren't**: Built-in SuperClaude functionality
-- **How activation works**: Claude reads instructions to use appropriate servers based on context
-- **What they provide**: Real tools that extend Claude Code's native capabilities
-
-**Core Servers:**
-- **context7**: Official library documentation and patterns
-- **sequential-thinking**: Multi-step reasoning and analysis
-- **magic**: Modern UI component generation
-- **playwright**: Browser automation and E2E testing
-- **morphllm-fast-apply**: Pattern-based code transformations
-- **serena**: Semantic code understanding and project memory
-- **tavily**: Web search and real-time information retrieval
-- **chrome-devtools**: Performance analysis and debugging
-
-## Quick Start
-
-**Setup Verification**: MCP servers activate automatically. For installation and troubleshooting, see [Installation Guide](../Getting-Started/installation.md) and [Troubleshooting](../Reference/troubleshooting.md).
-
-**Auto-Activation Logic:**
-
-| Request Contains | Servers Activated |
-|-----------------|------------------|
-| Library imports, API names | **context7** |
-| `--think`, debugging | **sequential-thinking** |
-| `component`, `UI`, frontend | **magic** |
-| `test`, `e2e`, `browser` | **playwright** |
-| Multi-file edits, refactoring | **morphllm-fast-apply** |
-| Large projects, sessions | **serena** |
-| `/sc:research`, `latest`, `current` | **tavily** |
-| `performance`, `debug`, `LCP` | **chrome-devtools** |
-
-## Server Details
-
-### context7 📚
-**Purpose**: Official library documentation access
-**Triggers**: Import statements, framework keywords, documentation requests
-**Requirements**: Node.js 16+, no API key
-
-```bash
-# Automatic activation
-/sc:implement "React authentication system"
-# → Provides official React patterns
-
-# Manual activation
-/sc:analyze auth-system/ --c7
-```
-
-### sequential-thinking 🧠
-**Purpose**: Structured multi-step reasoning and systematic analysis
-**Triggers**: Complex debugging, `--think` flags, architectural analysis
-**Requirements**: Node.js 16+, no API key
-
-```bash
-# Automatic activation
-/sc:troubleshoot "API performance issues"
-# → Enables systematic root cause analysis
-
-# Manual activation
-/sc:analyze --think-hard architecture/
-```
-
-### magic ✨
-**Purpose**: Modern UI component generation from 21st.dev patterns
-**Triggers**: UI requests, `/ui` commands, component development
-**Requirements**: Node.js 16+, TWENTYFIRST_API_KEY ()
-
-```bash
-# Automatic activation
-/sc:implement "responsive dashboard component"
-# → Generates accessible UI with modern patterns
-
-# API key setup
-export TWENTYFIRST_API_KEY="your_key_here"
-```
-
-### playwright 🎭
-**Purpose**: Real browser automation and E2E testing
-**Triggers**: Browser testing, E2E scenarios, visual validation
-**Requirements**: Node.js 16+, no API key
-
-```bash
-# Automatic activation
-/sc:test --type e2e "user login flow"
-# → Enables browser automation testing
-
-# Manual activation
-/sc:validate "accessibility compliance" --play
-```
-
-### morphllm-fast-apply 🔄
-**Purpose**: Efficient pattern-based code transformations
-**Triggers**: Multi-file edits, refactoring, framework migrations
-**Requirements**: Node.js 16+, MORPH_API_KEY
-
-```bash
-# Automatic activation
-/sc:improve legacy-codebase/ --focus maintainability
-# → Applies consistent patterns across files
-
-# API key setup
-export MORPH_API_KEY="your_key_here"
-```
-
-### serena 🧭
-**Purpose**: Semantic code understanding with project memory
-**Triggers**: Symbol operations, large codebases, session management
-**Requirements**: Python 3.9+, uv package manager, no API key
-
-```bash
-# Automatic activation
-/sc:load existing-project/
-# → Builds project understanding and memory
-
-# Manual activation
-/sc:refactor "extract UserService" --serena
-```
-
-### tavily 🔍
-**Purpose**: Web search and real-time information retrieval for research
-**Triggers**: `/sc:research` commands, "latest" information requests, current events, fact-checking
-**Requirements**: Node.js 16+, TAVILY_API_KEY (free tier available at https://app.tavily.com)
-
-```bash
-# Automatic activation
-/sc:research "latest AI developments 2024"
-# → Performs intelligent web research
-
-# Manual activation
-/sc:analyze "market trends" --tavily
-
-# API key setup (get free key at https://app.tavily.com)
-export TAVILY_API_KEY="tvly-your_api_key_here"
-```
-
-### chrome-devtools 📊
-**Purpose**: Performance analysis, debugging, and real-time browser inspection
-**Triggers**: Performance auditing, debugging layout issues (e.g., CLS), slow loading times (LCP), console errors, network requests
-**Requirements**: Node.js 16+, no API key
-
-```bash
-# Automatic activation
-/sc:debug "page is loading slowly"
-# → Enables performance analysis with Chrome DevTools
-
-# Manual activation
-/sc:analyze --performance "homepage"
-```
-
-**Capabilities:**
-- **Web Search**: Comprehensive searches with ranking and filtering
-- **News Search**: Time-filtered current events and updates
-- **Content Extraction**: Full-text extraction from search results
-- **Domain Filtering**: Include/exclude specific domains
-- **Multi-Hop Research**: Iterative searches based on findings (up to 5 hops)
-
-**Research Depth Control:**
-- `--depth quick`: 5-10 sources, basic synthesis
-- `--depth standard`: 10-20 sources, structured report (default)
-- `--depth deep`: 20-40 sources, comprehensive analysis
-- `--depth exhaustive`: 40+ sources, academic-level research
-
-## Configuration
-
-**MCP Configuration File (`~/.claude.json`):**
-```json
-{
- "mcpServers": {
- "context7": {
- "command": "npx",
- "args": ["-y", "@upstash/context7-mcp@latest"]
- },
- "sequential-thinking": {
- "command": "npx",
- "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
- },
- "magic": {
- "command": "npx",
- "args": ["@21st-dev/magic"],
- "env": {"TWENTYFIRST_API_KEY": "${TWENTYFIRST_API_KEY}"}
- },
- "playwright": {
- "command": "npx",
- "args": ["@playwright/mcp@latest"]
- },
- "morphllm-fast-apply": {
- "command": "npx",
- "args": ["@morph-llm/morph-fast-apply"],
- "env": {"MORPH_API_KEY": "${MORPH_API_KEY}"}
- },
- "serena": {
- "command": "uvx",
- "args": ["--from", "git+https://github.com/oraios/serena", "serena", "start-mcp-server", "--context", "ide-assistant"]
- },
- "tavily": {
- "command": "npx",
- "args": ["-y", "tavily-mcp@latest"],
- "env": {"TAVILY_API_KEY": "${TAVILY_API_KEY}"}
- },
- "chrome-devtools": {
- "command": "npx",
- "args": ["-y", "chrome-devtools-mcp@latest"]
- }
- }
-}
-```
-
-## Usage Patterns
-
-**Server Control:**
-```bash
-# Enable specific servers
-/sc:analyze codebase/ --c7 --seq
-
-# Disable all MCP servers
-/sc:implement "simple function" --no-mcp
-
-# Enable all servers
-/sc:design "complex architecture" --all-mcp
-```
-
-**Multi-Server Coordination:**
-```bash
-# Full-stack development
-/sc:implement "e-commerce checkout"
-# → Sequential: workflow analysis
-# → Context7: payment patterns
-# → Magic: UI components
-# → Serena: code organization
-# → Playwright: E2E testing
-```
-
-## Troubleshooting
-
-**Common Issues:**
-- **No servers connected**: Check Node.js: `node --version` (need v16+)
-- **Context7 fails**: Clear cache: `npm cache clean --force`
-- **Magic/Morphllm errors**: Expected without API keys (paid services)
-- **Server timeouts**: Restart Claude Code session
-
-**Quick Fixes:**
-```bash
-# Reset connections
-# Restart Claude Code session
-
-# Check dependencies
-node --version # Should show v16+
-
-# Test without MCP
-/sc:command --no-mcp
-
-# Check configuration
-ls ~/.claude.json
-```
-
-**API Key Configuration:**
-```bash
-# For Magic server (required for UI generation)
-export TWENTYFIRST_API_KEY="your_key_here"
-
-# For Morphllm server (required for bulk transformations)
-export MORPH_API_KEY="your_key_here"
-
-# For Tavily server (required for web search - free tier available)
-export TAVILY_API_KEY="tvly-your_key_here"
-
-# Add to shell profile for persistence
-echo 'export TWENTYFIRST_API_KEY="your_key"' >> ~/.bashrc
-echo 'export MORPH_API_KEY="your_key"' >> ~/.bashrc
-echo 'export TAVILY_API_KEY="your_key"' >> ~/.bashrc
-```
-
-**Environment Variable Usage:**
-- ✅ `TWENTYFIRST_API_KEY` - Required for Magic MCP server functionality
-- ✅ `MORPH_API_KEY` - Required for Morphllm MCP server functionality
-- ✅ `TAVILY_API_KEY` - Required for Tavily MCP server functionality (free tier available)
-- ❌ Other env vars in docs - Examples only, not used by framework
-- 📝 Magic and Morphllm are paid services, Tavily has free tier, framework works without them
-
-## Server Combinations
-
-**No API Keys (Free)**:
-- context7 + sequential-thinking + playwright + serena
-
-**1 API Key**:
-- Add magic for professional UI development
-
-**2 API Keys**:
-- Add morphllm-fast-apply for large-scale refactoring
-
-**Common Workflows:**
-- **Learning**: context7 + sequential-thinking
-- **Web Development**: magic + context7 + playwright
-- **Enterprise Refactoring**: serena + morphllm + sequential-thinking
-- **Complex Analysis**: sequential-thinking + context7 + serena
-- **Deep Research**: tavily + sequential-thinking + serena + playwright
-- **Current Events**: tavily + context7 + sequential-thinking
-- **Performance Tuning**: chrome-devtools + sequential-thinking + playwright
-
-## Integration
-
-**With SuperClaude Commands:**
-- Analysis commands automatically use Sequential + Serena
-- Implementation commands use Magic + Context7
-- Testing commands use Playwright + Sequential
-- Research commands use Tavily + Sequential + Playwright
-
-**With Behavioral Modes:**
-- Brainstorming Mode: Sequential for discovery
-- Task Management: Serena for persistence
-- Orchestration Mode: Optimal server selection
-- Deep Research Mode: Tavily + Sequential + Playwright coordination
-
-**Performance Control:**
-- Automatic resource management based on system load
-- Concurrency control: `--concurrency N` (1-15)
-- Priority-based server selection under constraints
-
-## Related Resources
-
-**Essential Reading:**
-- [Commands Guide](commands.md) - Commands that activate MCP servers
-- [Quick Start Guide](../Getting-Started/quick-start.md) - MCP setup guide
-
-**Advanced Usage:**
-- [Behavioral Modes](modes.md) - Mode-MCP coordination
-- [Agents Guide](agents.md) - Agent-MCP integration
-- [Session Management](session-management.md) - Serena workflows
-
-**Technical References:**
-- [Examples Cookbook](../Reference/examples-cookbook.md) - MCP workflow patterns
-- [Technical Architecture](../Developer-Guide/technical-architecture.md) - Integration details
\ No newline at end of file
diff --git a/docs/User-Guide/modes.md b/docs/User-Guide/modes.md
deleted file mode 100644
index b1ef9db..0000000
--- a/docs/User-Guide/modes.md
+++ /dev/null
@@ -1,659 +0,0 @@
-# SuperClaude Behavioral Modes Guide 🧠
-
-## ✅ Quick Verification
-Test modes by using `/sc:` commands - they activate automatically based on task complexity. For full command reference, see [Commands Guide](commands.md).
-
-## Quick Reference Table
-
-| Mode | Purpose | Auto-Triggers | Key Behaviors | Best Used For |
-|------|---------|---------------|---------------|---------------|
-| **🧠 Brainstorming** | Interactive discovery | "brainstorm", "maybe", vague requests | Socratic questions, requirement elicitation | New project planning, unclear requirements |
-| **🔍 Introspection** | Meta-cognitive analysis | Error recovery, "analyze reasoning" | Transparent thinking markers (🤔, 🎯, 💡) | Debugging, learning, optimization |
-| **🔬 Deep Research** | Systematic investigation mindset | `/sc:research`, investigation keywords | 6-phase workflow, evidence-based reasoning | Technical research, current events, market analysis |
-| **📋 Task Management** | Complex coordination | >3 steps, >2 directories | Phase breakdown, memory persistence | Multi-step operations, project management |
-| **🎯 Orchestration** | Intelligent tool selection | Multi-tool ops, high resource usage | Optimal tool routing, parallel execution | Complex analysis, performance optimization |
-| **⚡ Token Efficiency** | Compressed communication | High context usage, `--uc` flag | Symbol systems, estimated 30-50% token reduction | Resource constraints, large operations |
-
-
----
-
-## Getting Started (2-Minute Overview)
-
-**Modes activate through behavioral instructions** - Claude Code reads context files to determine which mode behaviors to adopt based on your task patterns and complexity.
-
-**Quick Examples:**
-```bash
-# Automatic activation examples
-/sc:brainstorm "mobile app" # → Socratic discovery questions
-/sc:implement "auth system" # → Multi-phase coordination
-"--uc analyze large-codebase/" # → Compressed symbol output
-```
-
-**When to use manual flags:**
-- Need specific behavior: `--brainstorm`, `--introspect`, `--uc`
-- Override automatic detection for learning/debugging
-- Optimize for specific constraints (memory, time, clarity)
-
----
-
-## Mode Details
-
-### 🧠 Brainstorming Mode - Interactive Discovery
-
-**Purpose**: Transform vague ideas into structured requirements through collaborative discovery.
-
-**Auto-Activation Triggers:**
-- Vague project requests: "I want to build...", "Thinking about creating..."
-- Exploration keywords: brainstorm, explore, discuss, figure out, not sure
-- Uncertainty indicators: "maybe", "possibly", "could we"
-- Manual flags: `--brainstorm`, `--bs`
-
-**Behavioral Changes:**
-- **Socratic Questioning**: Asks probing questions to uncover hidden requirements
-- **Non-Presumptive Approach**: Avoids assumptions, lets you guide discovery direction
-- **Collaborative Partnership**: Works with you in exploration rather than directive consultation
-- **Requirement Synthesis**: Converts insights into structured technical briefs
-- **Cross-Session Memory**: Maintains discovery context for follow-up discussions
-
-**Example Experience:**
-```
-Standard Approach: "I'll build a user authentication system with JWT tokens..."
-Brainstorming Approach:
-"🤔 Let's explore this together:
- - What specific user problems does auth solve for your app?
- - Who are your users and what's their technical comfort level?
- - Any existing systems or social logins to integrate with?
- - What security/compliance requirements do you have?
- 📝 Outcome: Detailed auth requirements brief ready for implementation"
-```
-
-#### Success Criteria
-- [ ] Responds with questions instead of immediate solutions
-- [ ] Questions explore user needs, technical constraints, and business goals
-- [ ] Maintains collaborative tone throughout discovery process
-- [ ] Produces structured requirements or technical brief as outcome
-
-**Verify:** `/sc:brainstorm "web app"` should ask about users, features, technology
-**Test:** Vague requests should trigger discovery questions, not assumptions
-**Check:** Mode should persist across follow-up questions in same conversation
-
-**Works Best With:**
-- **→ Task Management**: Requirements discovery → systematic implementation planning
-- **→ Orchestration**: Requirements clarity → optimal tool selection for implementation
-- **Manual Override**: Use `--brainstorm` to force discovery even for "clear" requirements
-
----
-
-### 🔍 Introspection Mode - Meta-Cognitive Analysis
-
-**Purpose**: Expose reasoning process for learning optimization and transparent decision-making.
-
-**Auto-Activation Triggers:**
-- Self-analysis requests: "analyze my reasoning", "reflect on decision"
-- Error recovery scenarios and unexpected results requiring investigation
-- Complex problem solving with multiple viable approaches
-- Pattern recognition needs for optimization opportunities
-- Manual flag: `--introspect`
-
-**Behavioral Changes:**
-- **Reasoning Transparency**: Exposes thinking process with clear markers (🤔, 🎯, ⚡, 📊, 💡)
-- **Decision Analysis**: Evaluates choice logic and considers alternative approaches
-- **Pattern Recognition**: Identifies recurring behaviors and improvement opportunities
-- **Meta-Learning**: Extracts insights for continuous framework improvement
-- **Framework Compliance**: Validates actions against SuperClaude principles and quality gates
-
-**Example Experience:**
-```
-Standard Approach: "I'll analyze this code structure and suggest improvements..."
-Introspective Approach:
-"🧠 Meta-Analysis: Why did I choose structural analysis over functional flow?
- 🎯 Decision Logic: Saw class hierarchy → assumed OOP pattern dominance
- 🔄 Alternative Considered: Data flow analysis might reveal hidden dependencies
- 📊 Evidence Check: File imports suggest functional composition, not OOP
- 💡 Learning: Need to analyze imports before choosing analysis strategy
- ⚡ Correction: Switching to functional flow analysis approach"
-```
-
-**Works Best With:**
-- **→ Task Management**: Provides transparent reasoning for complex phase decisions
-- **Any Mode**: Adds reasoning transparency layer to any other mode's operation
-- **Manual Override**: Use `--introspect` for learning sessions and debugging workflows
-
----
-
-### 🔬 Deep Research Mode - Systematic Investigation Mindset
-
-**Purpose**: Research mindset for systematic investigation and evidence-based reasoning.
-
-**Auto-Activation Triggers:**
-- `/sc:research` command invocation
-- Research-related keywords: investigate, explore, discover, analyze
-- Questions requiring current information beyond knowledge cutoff
-- Complex research requirements
-- Manual flag: `--research`
-
-**Behavioral Modifications:**
-- **Thinking Style**: Systematic over casual, evidence over assumption, progressive depth exploration
-- **Communication**: Lead with confidence levels, provide inline citations, acknowledge uncertainties
-- **Priority Shifts**: Completeness over speed, accuracy over speculation, verification over assumption
-- **Process Adaptations**: Always create investigation plans, default to parallel operations, maintain evidence chains
-
-**6-Phase Research Workflow:**
-- 📋 **Understand** (5-10%): Assess query complexity and requirements
-- 📝 **Plan** (10-15%): Select strategy (planning/intent/unified) and identify parallelization
-- ✅ **TodoWrite** (5%): Create adaptive task hierarchy (3-15 tasks based on complexity)
-- 🔄 **Execute** (50-60%): Parallel-first searches and smart extraction routing
-- 📊 **Track** (Continuous): Monitor progress and update confidence scores
-- ✓ **Validate** (10-15%): Verify evidence chains and ensure completeness
-
-**Example Experience:**
-```
-Standard Mode: "Here are some search results about quantum computing..."
-Deep Research Mode:
-"📊 Research Plan: Quantum computing breakthroughs
- ✓ TodoWrite: Created 8 research tasks
- 🔄 Executing parallel searches across domains
- 📈 Confidence: 0.82 across 15 verified sources
- 📝 Report saved: claudedocs/research_quantum_[timestamp].md"
-```
-
-#### Quality Standards
-- [ ] Minimum 2 sources per claim with inline citations
-- [ ] Confidence scoring (0.0-1.0) for all findings
-- [ ] Parallel execution by default for independent operations
-- [ ] Reports saved to claudedocs/ with proper structure
-- [ ] Clear methodology and evidence presentation
-
-**Verify:** `/sc:research "test topic"` should create TodoWrite and execute systematically
-**Test:** All research should include confidence scores and citations
-**Check:** Reports should be saved to claudedocs/ automatically
-
-**Works Best With:**
-- **→ Task Management**: Research planning with TodoWrite integration
-- **→ Orchestration**: Parallel Tavily/Playwright coordination
-- **Manual Override**: Use `--depth` and `--strategy` for fine control
-
----
-
-### 📋 Task Management Mode - Complex Coordination
-
-**Purpose**: Hierarchical task organization with session persistence for multi-step operations.
-
-**Auto-Activation Triggers:**
-- Operations requiring >3 coordinated steps
-- Multiple file/directory scope (>2 directories OR >3 files)
-- Complex dependencies requiring phases and checkpoints
-- Quality improvement requests: polish, refine, enhance
-- Manual flags: `--task-manage`, `--delegate`
-
-**Behavioral Changes:**
-- **Hierarchical Planning**: Breaks complex work into Plan → Phase → Task → Todo structure
-- **Session Persistence**: Maintains project context and progress across interruptions
-- **Memory Integration**: Uses write_memory/read_memory for state preservation
-- **Progress Orchestration**: Coordinates TodoWrite with memory updates for tracking
-- **Quality Gates**: Implements systematic validation checkpoints between phases
-
-**Example Experience:**
-```
-Standard Approach: "I'll implement user authentication..." → Direct implementation
-Task Management Approach:
-"📋 Multi-Phase Implementation Plan:
- 🎯 Phase 1: Security Requirements Analysis (Session 1)
- 🎯 Phase 2: API Design & Documentation (Session 2)
- 🎯 Phase 3: Implementation & Testing (Session 3-4)
- 🎯 Phase 4: Integration & Validation (Session 5)
- 💾 Session persistence: Resume context automatically
- ✓ Quality gates: Validation before each phase transition"
-```
-
-**Works Best With:**
-- **Brainstorming →**: Requirements discovery then systematic implementation
-- **+ Orchestration**: Task coordination with optimal tool selection
-- **+ Introspection**: Transparent reasoning for complex phase decisions
-
----
-
-### 🎯 Orchestration Mode - Intelligent Tool Selection
-
-**Purpose**: Optimize task execution through intelligent tool routing and parallel coordination.
-
-**Auto-Activation Triggers:**
-- Multi-tool operations requiring sophisticated coordination
-- Performance constraints (high resource usage)
-- Parallel execution opportunities (>3 independent files/operations)
-- Complex routing decisions with multiple valid tool approaches
-
-**Behavioral Changes:**
-- **Intelligent Tool Routing**: Selects optimal MCP servers and native tools for each task type
-- **Resource Awareness**: Adapts approach based on system constraints and availability
-- **Parallel Optimization**: Identifies independent operations for concurrent execution
-- **Coordination Focus**: Optimizes tool selection and usage through coordinated execution
-- **Adaptive Fallback**: Switches tools gracefully when preferred options are unavailable
-
-**Example Experience:**
-```
-Standard Approach: Sequential file-by-file analysis and editing
-Orchestration Approach:
-"🎯 Multi-Tool Coordination Strategy:
- 🔍 Phase 1: Serena (semantic analysis) + Sequential (architecture review)
- ⚡ Phase 2: Morphllm (pattern edits) + Magic (UI components)
- 🧪 Phase 3: Playwright (testing) + Context7 (documentation patterns)
- 🔄 Parallel execution: 3 tools working simultaneously
-\"
-```
-
-**Works Best With:**
-- **Task Management →**: Provides tool coordination for complex multi-phase plans
-- **+ Token Efficiency**: Optimal tool selection with compressed communication
-- **Any Complex Task**: Adds intelligent tool routing to enhance execution
-
----
-
-### ⚡ Token Efficiency Mode - Compressed Communication
-
-**Purpose**: Achieve estimated 30-50% token reduction through symbol systems while preserving information quality.
-
-**Auto-Activation Triggers:**
-- High context usage approaching limits
-- Large-scale operations requiring resource efficiency
-- User explicit flags: `--uc`, `--ultracompressed`
-- Complex analysis workflows with multiple outputs
-
-**Behavioral Changes:**
-- **Symbol Communication**: Uses visual symbols for logic flows, status, and technical domains
-- **Technical Abbreviation**: Context-aware compression for repeated technical terms
-- **Structured Density**: Bullet points, tables, and concise formatting over verbose paragraphs
-- **Information Preservation**: Maintains ≥95% information quality despite compression
-- **Structured Format**: Organized for clarity and task completion
-
-**Example Experience:**
-```
-Standard Approach: "The authentication system implementation shows a security vulnerability in the user validation function that needs immediate attention..."
-Token Efficient Approach:
-"🛡️ Security Alert:
- auth.js:45 → user val() → critical vuln
- 📊 Impact: ❌ token bypass possible
- ⚡ Action: fix validation + audit ∵ high sev
- 🔧 Est: 2h impl + 1h test"
-```
-
-**Works Best With:**
-- **Any Mode**: Adds compression layer while preserving mode-specific behaviors
-- **Orchestration →**: Compressed tool coordination and status updates
-- **Manual Override**: Use `--uc` when context pressure or efficiency is priority
-
----
-
-### 🎨 Standard Mode - Balanced Default
-
-**Purpose**: Provide clear, professional communication for straightforward development tasks.
-
-**Auto-Activation Triggers:**
-- Simple, well-defined tasks without complexity indicators
-- Single-file operations with clear requirements
-- Basic explanations and standard development workflows
-- No other mode triggers detected (default fallback)
-
-**Behavioral Changes:**
-- **Professional Communication**: Clear, concise technical language without compression
-- **Moderate Detail**: Balanced information depth suitable for most development tasks
-- **Standard Tool Selection**: Uses native Claude capabilities and basic tools
-- **Quality Focus**: Maintains code quality without complex orchestration overhead
-- **Responsive Adaptation**: Ready to switch to specialized modes when complexity increases
-
-**Example Experience:**
-```
-Standard Approach: Consistent, professional baseline for all tasks
-"I'll implement the login function with proper error handling:
-
- 1. Validate user input (email format, password requirements)
- 2. Authenticate against database with secure hashing
- 3. Generate JWT token with appropriate expiration
- 4. Return success response with user data
-
- The implementation will follow security best practices and include comprehensive error handling."
-```
-
-**Works Best With:**
-- **→ Any Mode**: Serves as baseline that other modes enhance
-- **Mode Switching**: Automatically escalates to specialized modes when needed
-- **Clarity Priority**: When straightforward communication is more important than optimization
-
----
-
-## Advanced Usage
-
-### Mode Combinations
-
-**Multi-Mode Workflows:**
-```bash
-# Discovery → Planning → Implementation
-/sc:brainstorm "microservices architecture" --task-manage
-# → Brainstorming: requirement discovery
-# → Task Management: multi-phase coordination
-
-# Analysis with transparency and efficiency
-/sc:analyze legacy-system/ --introspect --uc
-# → Introspection: transparent reasoning
-# → Token Efficiency: compressed output
-```
-
-### Manual Mode Control
-
-**Force Specific Behaviors:**
-- `--brainstorm`: Force collaborative discovery for any task
-- `--introspect`: Add reasoning transparency to any mode
-- `--task-manage`: Enable hierarchical coordination
-- `--orchestrate`: Optimize tool selection and parallel execution
-- `--uc`: Compress communication for efficiency
-
-**Override Examples:**
-```bash
-# Force brainstorming on "clear" requirements
-/sc:implement "user login" --brainstorm
-
-# Add reasoning transparency to debugging
-# Debug authentication issue with transparent reasoning
-
-# Enable task management for simple operations
-# Update styles.css with systematic task management
-```
-
-### Mode Boundaries and Priority
-
-**When Modes Activate:**
-1. **Complexity Threshold**: >3 files → Task Management
-2. **Resource Pressure**: High context usage → Token Efficiency
-3. **Multi-Tool Need**: Complex analysis → Orchestration
-4. **Uncertainty**: Vague requirements → Brainstorming
-5. **Error Recovery**: Problems → Introspection
-
-**Priority Rules:**
-- **Safety First**: Quality and validation always override efficiency
-- **User Intent**: Manual flags override automatic detection
-- **Context Adaptation**: Modes stack based on complexity
-- **Resource Management**: Efficiency modes activate under pressure
-
----
-
-## Real-World Examples
-
-### Complete Workflow Examples
-
-**New Project Development:**
-```bash
-# Phase 1: Discovery (Brainstorming Mode auto-activates)
-"I want to build a productivity app"
-→ 🤔 Socratic questions about users, features, platform choice
-→ 📝 Structured requirements brief
-
-# Phase 2: Planning (Task Management Mode auto-activates)
-/sc:implement "core productivity features"
-→ 📋 Multi-phase breakdown with dependencies
-→ 🎯 Phase coordination with quality gates
-
-# Phase 3: Implementation (Orchestration Mode coordinates tools)
-/sc:implement "frontend and backend systems"
-→ 🎯 Magic (UI) + Context7 (patterns) + Sequential (architecture)
-→ ⚡ Parallel execution optimization
-```
-
-**Debugging Complex Issues:**
-```bash
-# Problem analysis (Introspection Mode auto-activates)
-"Users getting intermittent auth failures"
-→ 🤔 Transparent reasoning about potential causes
-→ 🎯 Hypothesis formation and evidence gathering
-→ 💡 Pattern recognition across similar issues
-
-# Systematic resolution (Task Management coordinates)
-# Fix authentication system comprehensively
-→ 📋 Phase 1: Root cause analysis
-→ 📋 Phase 2: Solution implementation
-→ 📋 Phase 3: Testing and validation
-```
-
-### Mode Combination Patterns
-
-**High-Complexity Scenarios:**
-```bash
-# Large refactoring with multiple constraints
-/sc:improve legacy-system/ --introspect --uc --orchestrate
-→ 🔍 Transparent reasoning (Introspection)
-→ ⚡ Compressed communication (Token Efficiency)
-→ 🎯 Optimal tool coordination (Orchestration)
-→ 📋 Systematic phases (Task Management auto-activates)
-```
-
----
-
-## Quick Reference
-
-### Mode Activation Patterns
-
-| Trigger Type | Example Input | Mode Activated | Key Behavior |
-|--------------|---------------|----------------|--------------|
-| **Vague Request** | "I want to build an app" | 🧠 Brainstorming | Socratic discovery questions |
-| **Complex Scope** | >3 files or >2 directories | 📋 Task Management | Phase coordination |
-| **Multi-Tool Need** | Analysis + Implementation | 🎯 Orchestration | Tool optimization |
-| **Error Recovery** | "This isn't working as expected" | 🔍 Introspection | Transparent reasoning |
-| **Resource Pressure** | High context usage | ⚡ Token Efficiency | Symbol compression |
-| **Simple Task** | "Fix this function" | 🎨 Standard | Clear, direct approach |
-
-### Manual Override Commands
-
-```bash
-# Force specific mode behaviors
-/sc:command --brainstorm # Collaborative discovery
-/sc:command --introspect # Reasoning transparency
-/sc:command --task-manage # Hierarchical coordination
-/sc:command --orchestrate # Tool optimization
-/sc:command --uc # Token compression
-
-# Combine multiple modes
-/sc:command --introspect --uc # Transparent + efficient
-/sc:command --task-manage --orchestrate # Coordinated + optimized
-```
-
----
-
-## Troubleshooting
-
-For troubleshooting help, see:
-- [Common Issues](../Reference/common-issues.md) - Quick fixes for frequent problems
-- [Troubleshooting Guide](../Reference/troubleshooting.md) - Comprehensive problem resolution
-
-### Common Issues
-- **Mode not activating**: Use manual flags: `--brainstorm`, `--introspect`, `--uc`
-- **Wrong mode active**: Check complexity triggers and keywords in request
-- **Mode switching unexpectedly**: Normal behavior based on task evolution
-- **Execution impact**: Modes optimize tool usage, shouldn't affect execution
-- **Mode conflicts**: Check flag priority rules in [Flags Guide](flags.md)
-
-### Immediate Fixes
-- **Force specific mode**: Use explicit flags like `--brainstorm` or `--task-manage`
-- **Reset mode behavior**: Restart Claude Code session to reset mode state
-- **Check mode indicators**: Look for 🤔, 🎯, 📋 symbols in responses
-- **Verify complexity**: Simple tasks use Standard mode, complex tasks auto-switch
-
-### Mode-Specific Troubleshooting
-
-**Brainstorming Mode Issues:**
-```bash
-# Problem: Mode gives solutions instead of asking questions
-# Quick Fix: Check request clarity and use explicit flag
-/sc:brainstorm "web app" --brainstorm # Force discovery mode
-"I have a vague idea about..." # Use uncertainty language
-"Maybe we could build..." # Trigger exploration
-```
-
-**Task Management Mode Issues:**
-```bash
-# Problem: Simple tasks getting complex coordination
-# Quick Fix: Reduce scope or use simpler commands
-/sc:implement "function" --no-task-manage # Disable coordination
-/sc:troubleshoot bug.js # Use basic commands
-# Check if task really is complex (>3 files, >2 directories)
-```
-
-**Token Efficiency Mode Issues:**
-```bash
-# Problem: Output too compressed or unclear
-# Quick Fix: Disable compression for clarity
-/sc:command --no-uc # Disable compression
-/sc:command --verbose # Force detailed output
-# Use when clarity is more important than efficiency
-```
-
-**Introspection Mode Issues:**
-```bash
-# Problem: Too much meta-commentary, not enough action
-# Quick Fix: Disable introspection for direct work
-/sc:command --no-introspect # Direct execution
-# Use introspection only for learning and debugging
-```
-
-**Orchestration Mode Issues:**
-```bash
-# Problem: Tool coordination causing confusion
-# Quick Fix: Simplify tool usage
-/sc:command --no-mcp # Native tools only
-/sc:command --simple # Basic execution
-# Check if task complexity justifies orchestration
-```
-
-### Error Code Reference
-
-| Mode Error | Meaning | Quick Fix |
-|------------|---------|-----------|
-| **B001** | Brainstorming failed to activate | Use explicit `--brainstorm` flag |
-| **T001** | Task management overhead | Use `--no-task-manage` for simple tasks |
-| **U001** | Token efficiency too aggressive | Use `--verbose` or `--no-uc` |
-| **I001** | Introspection mode stuck | Use `--no-introspect` for direct action |
-| **O001** | Orchestration coordination failed | Use `--no-mcp` or `--simple` |
-| **M001** | Mode conflict detected | Check flag priority rules |
-| **M002** | Mode switching loop | Restart session to reset state |
-| **M003** | Mode not recognized | Update SuperClaude or check spelling |
-
-### Progressive Support Levels
-
-**Level 1: Quick Fix (< 2 min)**
-- Use manual flags to override automatic mode selection
-- Check if task complexity matches expected mode behavior
-- Try restarting Claude Code session
-
-**Level 2: Detailed Help (5-15 min)**
-```bash
-# Mode-specific diagnostics
-/sc:help modes # List all available modes
-/sc:reflect --type mode-status # Check current mode state
-# Review request complexity and triggers
-```
-- See [Common Issues Guide](../Reference/common-issues.md) for mode installation problems
-
-**Level 3: Expert Support (30+ min)**
-```bash
-# Deep mode analysis
-SuperClaude install --diagnose
-# Check mode activation patterns
-# Review behavioral triggers and thresholds
-```
-- See [Diagnostic Reference Guide](../Reference/diagnostic-reference.md) for behavioral mode analysis
-
-**Level 4: Community Support**
-- Report mode issues at [GitHub Issues](https://github.com/SuperClaude-Org/SuperClaude_Framework/issues)
-- Include examples of unexpected mode behavior
-- Describe desired vs actual mode activation
-
-### Success Validation
-
-After applying mode fixes, test with:
-- [ ] Simple requests use Standard mode (clear, direct responses)
-- [ ] Complex requests auto-activate appropriate modes (coordination, reasoning)
-- [ ] Manual flags override automatic detection correctly
-- [ ] Mode indicators (🤔, 🎯, 📋) appear when expected
-- [ ] Performance remains good across different modes
-
-## Quick Troubleshooting (Legacy)
-- **Mode not activating** → Use manual flags: `--brainstorm`, `--introspect`, `--uc`
-- **Wrong mode active** → Check complexity triggers and keywords in request
-- **Mode switching unexpectedly** → Normal behavior based on task evolution
-- **Execution impact** → Modes optimize tool usage, shouldn't affect execution
-- **Mode conflicts** → Check flag priority rules in [Flags Guide](flags.md)
-
-## Frequently Asked Questions
-
-**Q: How do I know which mode is active?**
-A: Look for these indicators in communication patterns:
-- 🤔 Discovery questions → Brainstorming
-- 🎯 Reasoning transparency → Introspection
-- Phase breakdowns → Task Management
-- Tool coordination → Orchestration
-- Symbol compression → Token Efficiency
-
-**Q: Can I force specific modes?**
-A: Yes, use manual flags to override automatic detection:
-```bash
-/sc:command --brainstorm # Force discovery
-/sc:command --introspect # Add transparency
-/sc:command --task-manage # Enable coordination
-/sc:command --uc # Compress output
-```
-
-**Q: Do modes affect execution?**
-A: Modes optimize tool usage through coordination:
-- **Token Efficiency**: 30-50% context reduction
-- **Orchestration**: Parallel processing
-- **Task Management**: Prevents rework through systematic planning
-
-**Q: Can modes work together?**
-A: Yes, modes are designed to complement each other:
-- **Task Management** coordinates other modes
-- **Token Efficiency** compresses any mode's output
-- **Introspection** adds transparency to any workflow
-
----
-
-## Summary
-
-SuperClaude's 5 behavioral modes create an **intelligent adaptation system** that matches your needs automatically:
-
-- **🧠 Brainstorming**: Transforms vague ideas into clear requirements
-- **🔍 Introspection**: Provides transparent reasoning for learning and debugging
-- **📋 Task Management**: Coordinates complex multi-step operations
-- **🎯 Orchestration**: Optimizes tool selection and parallel execution
-- **⚡ Token Efficiency**: Compresses communication while preserving clarity
-- **🎨 Standard**: Maintains professional baseline for straightforward tasks
-
-**The key insight**: You don't need to think about modes - they work transparently to enhance your development experience. Simply describe what you want to accomplish, and SuperClaude automatically adapts its approach to match your needs.
-
----
-
-## Related Guides
-
-**Learning Progression:**
-
-**🌱 Essential (Week 1)**
-- [Quick Start Guide](../Getting-Started/quick-start.md) - Mode activation examples
-- [Commands Reference](commands.md) - Commands automatically activate modes
-- [Installation Guide](../Getting-Started/installation.md) - Set up behavioral modes
-
-**🌿 Intermediate (Week 2-3)**
-- [Agents Guide](agents.md) - How modes coordinate with specialists
-- [Flags Guide](flags.md) - Manual mode control and optimization
-- [Examples Cookbook](../Reference/examples-cookbook.md) - Mode patterns in practice
-
-**🌲 Advanced (Month 2+)**
-- [MCP Servers](mcp-servers.md) - Mode integration with enhanced capabilities
-- [Session Management](session-management.md) - Task Management mode workflows
-- [Getting Started](../Getting-Started/quick-start.md) - Mode usage patterns
-
-**🔧 Expert**
-- [Technical Architecture](../Developer-Guide/technical-architecture.md) - Mode implementation details
-- [Contributing Code](../Developer-Guide/contributing-code.md) - Extend mode capabilities
-
-**Mode-Specific Guides:**
-- **Brainstorming**: [Requirements Discovery Patterns](../Reference/examples-cookbook.md#requirements)
-- **Task Management**: [Session Management Guide](session-management.md)
-- **Orchestration**: [MCP Servers Guide](mcp-servers.md)
-- **Token Efficiency**: [Command Fundamentals](commands.md#token-efficiency)
\ No newline at end of file
diff --git a/docs/User-Guide/session-management.md b/docs/User-Guide/session-management.md
deleted file mode 100644
index 2364923..0000000
--- a/docs/User-Guide/session-management.md
+++ /dev/null
@@ -1,310 +0,0 @@
-# Session Management Guide
-
-SuperClaude provides persistent session management through the Serena MCP server, enabling true context preservation across Claude Code conversations and long-term project continuity.
-
-## Core Session Commands with Persistent Memory
-
-### `/sc:load` - Context Loading with Persistent Memory
-**Purpose**: Initialize session with project context and persistent memory from previous sessions
-**MCP Integration**: Triggers Serena MCP to read stored project memories
-**Syntax**: `/sc:load [project_path]`
-
-**What Happens**:
-- Serena MCP reads persistent memory files from previous sessions
-- Project context is restored from stored memories
-- Previous decisions, patterns, and progress are loaded
-- Session state is initialized with historical context
-
-**Use Cases**:
-```bash
-# Load existing project context from persistent memory
-/sc:load src/
-
-# Resume specific project work with full history
-/sc:load "authentication-system"
-
-# Initialize with codebase analysis and previous insights
-/sc:load . --analyze
-```
-
-### `/sc:save` - Session Persistence to Memory
-**Purpose**: Save current session state and decisions to persistent memory
-**MCP Integration**: Triggers Serena MCP to write memory files
-**Syntax**: `/sc:save "session_description"`
-
-**What Happens**:
-- Current context and decisions are written to Serena memory
-- Project state and progress are persisted across conversations
-- Key insights and patterns are stored for future sessions
-- Session summary is created with timestamp for retrieval
-
-**Use Cases**:
-```bash
-# Save completed feature work for future reference
-/sc:save "user authentication implemented with JWT"
-
-# Checkpoint during complex work
-/sc:save "API design phase complete, ready for implementation"
-
-# Store architectural decisions permanently
-/sc:save "microservices architecture decided, service boundaries defined"
-```
-
-### `/sc:reflect` - Progress Assessment with Memory Context
-**Purpose**: Analyze current progress against stored memories and validate session completeness
-**MCP Integration**: Uses Serena MCP to compare current state against stored memories
-**Syntax**: `/sc:reflect [--scope project|session]`
-
-**What Happens**:
-- Serena MCP reads previous memories and current context
-- Progress is assessed against stored goals and milestones
-- Gaps and next steps are identified using historical context
-- Session completeness is validated against project memory
-
-**Use Cases**:
-```bash
-# Assess project progress against stored milestones
-/sc:reflect --scope project
-
-# Validate current session completeness
-/sc:reflect
-
-# Check if ready to move to next phase based on memory
-/sc:reflect --scope session
-```
-
-## Persistent Memory Architecture
-
-### How Serena MCP Enables True Persistence
-
-**Memory Storage**:
-- Session contexts stored as structured memory files
-- Project decisions and architectural patterns preserved permanently
-- Code analysis results and insights retained across conversations
-- Progress tracking and milestone data maintained long-term
-
-**Cross-Session Continuity**:
-- Previous session context automatically available in new conversations
-- Decisions and rationale preserved and accessible across conversations
-- Learning from past patterns and solutions maintained
-- Consistent project understanding maintained indefinitely
-
-**Memory Types**:
-- **Project Memories**: Long-term project context and architecture
-- **Session Memories**: Specific conversation outcomes and decisions
-- **Pattern Memories**: Reusable solutions and architectural patterns
-- **Progress Memories**: Milestone tracking and completion status
-
-## Session Lifecycle Patterns with Persistence
-
-### New Project Initialization
-```bash
-# 1. Start fresh project
-/sc:brainstorm "e-commerce platform requirements"
-
-# 2. Save initial decisions to persistent memory
-/sc:save "project scope and requirements defined"
-
-# 3. Begin implementation planning
-/sc:workflow "user authentication system"
-
-# 4. Save architectural decisions permanently
-/sc:save "auth architecture: JWT + refresh tokens + rate limiting"
-```
-
-### Resuming Existing Work (Cross-Conversation)
-```bash
-# 1. Load previous context from persistent memory
-/sc:load "e-commerce-project"
-
-# 2. Assess current state against stored progress
-/sc:reflect --scope project
-
-# 3. Continue with next phase using stored context
-/sc:implement "payment processing integration"
-
-# 4. Save progress checkpoint to memory
-/sc:save "payment system integrated with Stripe API"
-```
-
-### Long-Term Project Management
-```bash
-# Weekly checkpoint pattern with persistence
-/sc:load project-name
-/sc:reflect --scope project
-# ... work on features ...
-/sc:save "week N progress: features X, Y, Z completed"
-
-# Phase completion pattern with memory
-/sc:reflect --scope project
-/sc:save "Phase 1 complete: core authentication and user management"
-/sc:workflow "Phase 2: payment and order processing"
-```
-
-## Cross-Conversation Continuity
-
-### Starting New Conversations with Persistence
-
-When starting a new Claude Code conversation, the persistent memory system allows:
-
-1. **Automatic Context Restoration**
- ```bash
- /sc:load project-name
- # Automatically restores all previous context, decisions, and progress
- ```
-
-2. **Progress Continuation**
- - Previous session decisions are immediately available
- - Architectural patterns and code insights are preserved
- - Project history and rationale are maintained
-
-3. **Intelligent Context Building**
- - Serena MCP provides relevant memories based on current work
- - Past solutions and patterns inform new implementations
- - Project evolution is tracked and understood
-
-### Memory Optimization
-
-**Effective Memory Usage**:
-- Use descriptive, searchable memory names
-- Include project phase and timestamp context
-- Reference specific features or architectural decisions
-- Make future retrieval intuitive
-
-**Memory Content Strategy**:
-- Store decisions and rationale, not just outcomes
-- Include alternative approaches considered
-- Document integration patterns and dependencies
-- Preserve learning and insights for future reference
-
-**Memory Lifecycle Management**:
-- Regular cleanup of outdated memories
-- Consolidation of related session memories
-- Archiving of completed project phases
-- Pruning of obsolete architectural decisions
-
-## Best Practices for Persistent Sessions
-
-### Session Start Protocol
-1. Always begin with `/sc:load` for existing projects
-2. Use `/sc:reflect` to understand current state from memory
-3. Plan work based on persistent context and stored patterns
-4. Build on previous decisions and architectural choices
-
-### Session End Protocol
-1. Use `/sc:reflect` to assess completeness against stored goals
-2. Save key decisions with `/sc:save` for future sessions
-3. Document next steps and open questions in memory
-4. Preserve context for seamless future continuation
-
-### Memory Quality Maintenance
-- Use clear, descriptive memory names for easy retrieval
-- Include context about decisions and alternative approaches
-- Reference specific code locations and patterns
-- Maintain consistency in memory structure across sessions
-
-## Integration with Other SuperClaude Features
-
-### MCP Server Coordination
-- **Serena MCP**: Provides the persistent memory infrastructure
-- **Sequential MCP**: Uses stored memories for enhanced complex analysis
-- **Context7 MCP**: References stored patterns and documentation approaches
-- **Morphllm MCP**: Applies stored refactoring patterns consistently
-
-### Agent Collaboration with Memory
-- Agents access persistent memories for enhanced context
-- Previous specialist decisions are preserved and referenced
-- Cross-session agent coordination through shared memory
-- Consistent specialist recommendations based on project history
-
-### Command Integration with Persistence
-- All `/sc:` commands can reference and build on persistent context
-- Previous command outputs and decisions are available across sessions
-- Workflow patterns are stored and reusable
-- Implementation history guides future command decisions
-
-## Troubleshooting Persistent Sessions
-
-### Common Issues
-
-**Memory Not Loading**:
-- Verify Serena MCP is configured and running properly
-- Check memory file permissions and accessibility
-- Ensure consistent project naming conventions
-- Validate memory file integrity and format
-
-**Context Loss Between Sessions**:
-- Always use `/sc:save` before ending sessions
-- Use descriptive memory names for easy retrieval
-- Regular `/sc:reflect` to validate memory completeness
-- Backup important memory files periodically
-
-**Memory Conflicts**:
-- Use timestamped memory names for version control
-- Regular cleanup of obsolete memories
-- Clear separation between project and session memories
-- Consistent memory naming conventions across sessions
-
-### Quick Fixes
-
-**Reset Session State**:
-```bash
-/sc:load --fresh # Start without previous context
-/sc:reflect # Assess current state
-```
-
-**Memory Cleanup**:
-```bash
-/sc:reflect --cleanup # Remove obsolete memories
-/sc:save --consolidate # Merge related memories
-```
-
-**Context Recovery**:
-```bash
-/sc:load --recent # Load most recent memories
-/sc:reflect --repair # Identify and fix context gaps
-```
-
-## Advanced Persistent Session Patterns
-
-### Multi-Phase Projects
-- Use phase-specific memory naming for organization
-- Maintain architectural decision continuity across phases
-- Cross-phase dependency tracking through persistent memory
-- Progressive complexity management with historical context
-
-### Team Collaboration
-- Shared memory conventions and naming standards
-- Decision rationale preservation for team context
-- Integration pattern documentation accessible to all team members
-- Consistent code style and architecture enforcement through memory
-
-### Long-Term Maintenance
-- Memory archiving strategies for completed projects
-- Pattern library development through accumulated memories
-- Reusable solution documentation built over time
-- Knowledge base building through persistent memory accumulation
-
-## Key Benefits of Persistent Session Management
-
-### Project Continuity
-- Seamless work continuation across multiple conversations
-- No context loss between Claude Code sessions
-- Preserved architectural decisions and technical rationale
-- Long-term project evolution tracking
-
-### Enhanced Productivity
-- Reduced need to re-explain project context
-- Faster startup time for continued work
-- Building on previous insights and patterns
-- Cumulative project knowledge growth
-
-### Quality Consistency
-- Consistent architectural patterns across sessions
-- Preserved code quality decisions and standards
-- Reusable solutions and best practices
-- Maintained technical debt awareness
-
----
-
-**Key Takeaway**: Session management through Serena MCP transforms SuperClaude from single-conversation assistance to persistent project partnership, maintaining context, decisions, and learning across all development phases and Claude Code conversations.
\ No newline at end of file
diff --git a/docs/User-Guide/mcp-installation.md b/docs/user-guide/mcp-installation.md
similarity index 100%
rename from docs/User-Guide/mcp-installation.md
rename to docs/user-guide/mcp-installation.md