Files
SuperClaude/.claude/commands/shared/compression-performance-patterns.yml
kevinpauer 65915024a1 feat: Add comprehensive review command with quality analysis (#24)
* feat: Add comprehensive review command with quality analysis

- Add new /review command with --files, --commit, --pr flags
- Implement evidence-based quality assessment patterns
- Create comprehensive review patterns YAML resource
- Update command index to reflect 19 total commands
- Integrate with existing analysis workflow

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
Signed-off-by: Kevin Pauer <kevinpauer@users.noreply.github.com>

* fix: remove new custom .yml and reuse existing ones; adjust compression-performance-patterns

* feat: add command documentation

---------

Signed-off-by: Kevin Pauer <kevinpauer@users.noreply.github.com>
Co-authored-by: Kevin Pauer <kevinpauer@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
2025-06-26 15:31:35 +02:00

266 lines
9.3 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# Compression & Performance Patterns - Consolidated Optimization
# UltraCompressed mode, token optimization, and performance monitoring
## Legend
@include universal-constants.yml#Universal_Legend
## UltraCompressed Mode Configuration
```yaml
Activation_Triggers:
Explicit_Flags: ["--ultracompressed", "--uc"]
Natural_Language: ["compress", "concise", "brief", "minimal", "telegram style"]
Automatic_Triggers:
High_Context_Usage: "Context usage >75% → Auto-activate"
Token_Budget_Pressure: "Approaching token limits → Auto-activate"
Large_Codebases: "Project >10k files → Recommend --uc"
Long_Sessions: "Session >2 hours → Suggest --uc"
Task_Operations: "Always for task files"
Core_Compression_Rules:
Remove_Words:
Articles: ["the", "a", "an"]
Conjunctions: ["and", "or", "but", "however", "therefore"]
Prepositions: ["of", "in", "on", "at", "to", "for", "with", "from"]
Fillers: ["that", "which", "who", "very", "really", "quite"]
Verbose_Phrases:
"in order to": "to"
"make sure": "ensure"
"as well as": "&"
"due to the fact that": "∵"
Symbol_Substitutions:
Logical: "→(leads to) &(and) |(or) ∵(because) ∴(therefore) ≡(equivalent)"
Mathematical: "∀(all) ∃(exists) ∈(member) ⊂(subset) (union) ∩(intersection)"
Process: "▶(start) ⏸(pause) ⏹(stop) ⚡(fast) 🔄(cycle) ✅(success) ❌(failure)"
Technical: "cfg(config) impl(implementation) perf(performance) val(validation)"
```
## Token Optimization Patterns
```yaml
Structure_Optimization:
Priority_Order:
1_YAML: "Most compact structured data"
2_Tables: "Comparison & reference data"
3_Lists: "Enumeration & sequences"
4_Prose: "Only when absolutely necessary"
Compression_Techniques:
Headers: "60-80% reduction via symbol substitution"
Paragraphs: "70-75% reduction via word removal"
Lists: "50-60% reduction via abbreviations"
Overall_Target: "~70% average token reduction"
Content_Compression:
Technical_Abbreviations:
analyze→anlz | build→bld | deploy→dply | test→tst
database→db | interface→api | environment→env | dependency→dep
configuration→cfg | implementation→impl | performance→perf
Communication_Patterns:
Telegram_Style: "Direct, no fluff, action-oriented"
Bullet_Lists: "• Key point | • Action item | • Result"
Symbol_Heavy: "Use established symbols consistently"
Context_Aware: "Abbreviate only when meaning clear"
UltraCompressed_Templates:
Command_Output:
Status: "✅ Done | ❌ Failed | ⚠ Warning | Info"
Progress: "3/5 complete (60%)"
Files: "Modified: 3 | Added: 1 | Deleted: 0"
Task_Format:
Header: "T: {TITLE} | S: {STATUS} | P: {PRIORITY}"
Progress: "{COMPLETED}/{TOTAL} ({%})"
Focus: "→ {CURRENT_ACTION}"
```
## Performance Monitoring System
```yaml
Command_Performance_Metrics:
Timing_Analysis:
Start_Time: "Record command initiation timestamp"
End_Time: "Record command completion timestamp"
Duration: "end_time - start_time"
Phase_Breakdown: "Analysis, execution, reporting phases"
Token_Economics:
Input_Tokens: "User command + context"
Output_Tokens: "Response + tool calls"
MCP_Tokens: "MCP server consumption"
Efficiency_Ratio: "output_value / total_tokens"
Context_Growth: "Track context size throughout operation"
Operation_Analytics:
Tools_Used: "Read, Edit, Bash, MCP calls"
Files_Accessed: "Number read/written/analyzed"
MCP_Usage: "Server calls + frequency"
Error_Count: "Errors encountered + recovery success"
Success_Indicators:
Task_Completion: "Goals achieved vs. attempted"
Quality_Metrics: "Code quality, test coverage, security"
User_Satisfaction: "Explicit feedback + usage patterns"
Performance_Baselines:
Command_Benchmarks:
Simple_Commands: "<5 seconds (read, analyze single file)"
Medium_Commands: "5-30 seconds (build, test, multi-file)"
Complex_Commands: "30-300 seconds (deploy, migrate, analysis)"
Token_Budgets:
Light_Operations: "<1K tokens"
Standard_Operations: "1K-5K tokens"
Heavy_Operations: "5K-20K tokens"
Critical_Operations: "20K+ tokens (with justification)"
Resource_Thresholds:
Memory_Usage: "Monitor for memory leaks"
CPU_Utilization: "Track intensive operations"
Network_Usage: "MCP server communication overhead"
Disk_I_O: "File operations efficiency"
Review_Scope_Limits:
Single_File: "Files >1000 lines flagged for review scope"
Directory: "Directories >50 files require batch processing"
Repository: "Repos >10K files get incremental analysis"
Large_File_Warning: "Files >5MB may require streaming analysis"
```
## MCP Performance Integration
```yaml
MCP_Server_Performance:
Response_Time_Targets:
Context7: "Fast response (network dependent)"
Sequential: "Moderate duration (complexity dependent)"
Magic: "Fast to moderate (component complexity)"
Puppeteer: "Fast to moderate (page load dependent)"
Resource_Usage_Profiles:
Context7: "Low CPU, Medium Network"
Sequential: "High CPU, Low Network"
Magic: "Medium CPU, High Network"
Puppeteer: "Medium CPU, Low Network"
Reliability_Scoring:
Context7: "Very high (library availability dependent)"
Sequential: "Very high (internal processing)"
Magic: "High (external service dependency)"
Puppeteer: "Very high (browser dependency)"
MCP_Optimization_Strategies:
Caching_Patterns:
Context7_Cache: "Library docs + examples (session-persistent)"
Sequential_Cache: "Analysis patterns + solutions (cross-session)"
Magic_Cache: "Component templates + variations (persistent)"
Fallback_Performance:
MCP_Timeout: "5-10 second timeout → fallback to native"
Network_Issues: "Auto-fallback → cached data → manual guidance"
Service_Degradation: "Progressive degradation → reduced functionality"
```
## Compression Algorithm Implementation
```yaml
Text_Compression_Pipeline:
Phase_1_Structure:
Convert_To_YAML: "Transform prose → structured data"
Table_Optimization: "Multi-column data → compact tables"
List_Compression: "Paragraph lists → bullet points"
Phase_2_Language:
Remove_Articles: "Systematic article removal where clear"
Compress_Conjunctions: "and→& | with→w/ | to→→"
Symbol_Substitution: "Replace common phrases w/ symbols"
Phase_3_Technical:
Abbreviate_Terms: "Use established technical abbreviations"
Compress_Patterns: "Repeated patterns → @include references"
Context_Awareness: "Maintain meaning despite compression"
Quality_Preservation:
Information_Density: "Higher info per token ratio"
Clarity_Maintenance: "Compressed but still clear"
Context_Preservation: "Critical information retained"
Reversibility: "Can expand for detailed explanation"
Compression_Validation:
Meaning_Preservation: "Core information intact"
Actionability: "Instructions still executable"
Clarity_Check: "Understandable by target audience"
Token_Reduction: "Measurable reduction achieved"
```
## Performance Optimization Strategies
```yaml
Command_Optimization:
Parallel_Processing:
Tool_Calls: "Concurrent file operations where possible"
MCP_Requests: "Parallel MCP server calls"
Background_Tasks: "Non-blocking operations"
Caching_Strategies:
Result_Caching: "Cache command outputs for reuse"
Context_Caching: "Preserve analysis results"
Pattern_Caching: "Store successful workflow patterns"
Resource_Management:
Memory_Efficiency: "Stream large files, cleanup temp data"
CPU_Optimization: "Efficient algorithms, avoid redundant work"
Network_Optimization: "Batch requests, compress transfers"
System_Performance:
Startup_Optimization:
Lazy_Loading: "Load components on demand"
Cache_Warmup: "Pre-load frequently used data"
Configuration_Caching: "Cache parsed config files"
Runtime_Optimization:
Context_Compression: "Compress long-running context"
Garbage_Collection: "Clean unused references"
Resource_Pooling: "Reuse expensive resources"
Shutdown_Optimization:
Graceful_Cleanup: "Properly close resources"
State_Persistence: "Save valuable session data"
Cache_Cleanup: "Remove temporary caches"
```
## Monitoring & Analytics
```yaml
Performance_Dashboard:
Real_Time_Metrics:
Current_Command: "Active operation status"
Token_Usage: "Current session consumption"
Resource_Utilization: "CPU, memory, network usage"
Historical_Analysis:
Command_Trends: "Performance over time"
Token_Efficiency: "Cost-benefit analysis"
Error_Patterns: "Failure trend analysis"
Optimization_Recommendations:
Performance_Bottlenecks: "Identify slow operations"
Token_Waste: "Highlight inefficient patterns"
Caching_Opportunities: "Suggest result caching"
Alerting_System:
Performance_Alerts:
Slow_Commands: "Operations exceeding baseline"
High_Token_Usage: "Approaching budget limits"
Resource_Exhaustion: "Memory/CPU threshold warnings"
Quality_Alerts:
Error_Rate_Increase: "Rising failure patterns"
User_Satisfaction_Drop: "Decreased effectiveness"
System_Degradation: "Overall performance decline"
```
---
*Compression & Performance Patterns v3 - Consolidated UltraCompressed mode, token optimization, and performance monitoring*