2025-11-01 19:37:20 -05:00
# PRD Workflow - Intent-Driven Product Planning
2025-10-14 19:58:44 -05:00
2025-10-15 21:17:09 -05:00
<critical>The workflow execution engine is governed by: {project-root}/bmad/core/tasks/workflow.xml</critical>
2025-10-14 19:58:44 -05:00
<critical>You MUST have already loaded and processed: {installed_path}/workflow.yaml</critical>
2025-11-01 19:37:20 -05:00
<critical>This workflow uses INTENT-DRIVEN PLANNING - adapt organically to product type and context</critical>
<critical>Communicate all responses in {communication_language} and adapt deeply to {user_skill_level}</critical>
2025-10-17 19:46:25 -05:00
<critical>Generate all documents in {document_output_language}</critical>
2025-11-01 19:37:20 -05:00
<critical>LIVING DOCUMENT: Write to PRD.md continuously as you discover - never wait until the end</critical>
<critical>GUIDING PRINCIPLE: Find and weave the product's magic throughout - what makes it special should inspire every section</critical>
refactor: comprehensive workflow modernization and standardization
## Major Improvements
### 1. Elicitation System Modernization
- Removed legacy `<elicit-required />` tag from workflow.xml
- Replaced with direct `<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>` pattern
- More explicit, self-documenting, and eliminates indirection layer
- Added strategic elicitation points across all planning workflows:
- PRD: After success criteria, scope, functional requirements, and final review
- Create-Epics-And-Stories: After epic proposals and each epic's stories
- Architecture: After decisions, structure, patterns, implementation patterns, and final doc
- Updated audit-workflow tag scanner to remove obsolete elicit-required reference
### 2. Input Document Discovery Streamlined
- Replaced verbose 19-line "Input Document Discovery" sections with single critical tag
- New format: `<critical>Input documents specified in workflow.yaml input_file_patterns...</critical>`
- Eliminates duplication - workflow.yaml already defines patterns
- Updated across 6 workflows (PRD, create-epics-and-stories, architecture, tech-spec, UX, gate-check)
- Saved ~114 lines of repeated bloat
### 3. Scale System Migration (Levels 0-4 → 3 Tracks)
- Updated PRD workflow from "Level 0-4" to "Quick Flow / BMad Method / Enterprise Method"
- Changed `project_level` variable to `project_track`
- Removed `target_scale` variable (no longer needed)
- Updated workflow.yaml descriptions to reference tracks not levels
- Updated checklist from "Level 2" and "Level 3-4" to "BMad Method" and "Enterprise Method"
- Aligns with new scale-adaptive-system.md (3-track methodology)
### 4. Epic/Story Template Standardization
- Replaced hardcoded 8-epic template with clean repeating pattern using N/M variables
- Added BDD-style acceptance criteria (Given/When/Then/And)
- Removed instructional bloat from templates (moved to instructions.md where it belongs)
- Template shows OUTPUT structure, instructions show PROCESS
- Applied to both create-epics-and-stories and tech-spec workflows
- Templates now use HTML comments to indicate repeating sections
### 5. Workflow.yaml Pattern Consistency
- Standardized input_file_patterns across all workflows
- Separated `recommended_inputs` (semantic WHAT) from `input_file_patterns` (file discovery WHERE)
- Removed duplication between recommended_inputs file paths and input_file_patterns
- Create-epics-and-stories now uses proper whole/sharded pattern like architecture workflow
- Solutioning-gate-check cleaned up to use semantic descriptions not file paths
## Files Changed (18)
- Core: workflow.xml (removed elicit-required tag and references)
- Audit workflow: Updated tag pattern scanner
- PRD workflow: Elicitation points, track migration, input discovery
- Create-epics-and-stories: Template rebuild, BDD format, elicitation, input patterns
- Tech-spec: Template rebuild, BDD format, input discovery
- UX Design: Input discovery streamlined
- Architecture: Elicitation at 5 key decision points, input discovery
- Gate-check: Input pattern cleanup, input discovery
## Impact
- More consistent elicitation across workflows
- Cleaner, more maintainable templates
- Better separation of concerns (templates vs instructions)
- Aligned with v6 3-track scale system
- Reduced bloat and duplication significantly
2025-11-04 00:09:19 -06:00
<critical>Input documents specified in workflow.yaml input_file_patterns - workflow engine handles fuzzy matching, whole vs sharded document discovery automatically</critical>
feat: add universal document sharding support with dual-strategy loading
Implement comprehensive document sharding system across all BMM workflows enabling 90%+ token savings for large multi-epic projects through selective loading optimization.
## Document Sharding System
### Core Features
- **Universal Support**: All 12 BMM workflows (Phase 1-4) handle both whole and sharded documents
- **Dual Loading Strategy**: Full Load (Phase 1-3) vs Selective Load (Phase 4)
- **Automatic Discovery**: Workflows detect format transparently (whole → sharded priority)
- **Efficiency Optimization**: 90%+ token reduction for 10+ epic projects in Phase 4
### Implementation Details
**Phase 1-3 Workflows (7 workflows) - Full Load Strategy:**
- product-brief, prd, gdd, create-ux-design, tech-spec, architecture, solutioning-gate-check
- Load entire sharded documents when present
- Transparent to user experience
- Better organization for large projects
**Phase 4 Workflows (5 workflows) - Selective Load Strategy:**
- sprint-planning (Full Load exception - needs all epics)
- epic-tech-context, create-story, story-context, code-review (Selective Load)
- Load ONLY the specific epic needed (e.g., epic-3.md for Epic 3 stories)
- Massive efficiency: Skip loading 9 other epics in 10-epic project
### Workflow Enhancements
**Added to all workflows:**
- `input_file_patterns` in workflow.yaml with wildcard discovery
- Document Discovery section in instructions.md
- Support for sharded index + section files
- Brownfield `docs/index.md` support
**Pattern standardization:**
```yaml
input_file_patterns:
document:
whole: "{output_folder}/*doc*.md"
sharded: "{output_folder}/*doc*/index.md"
sharded_single: "{output_folder}/*doc*/section-{{id}}.md" # Selective load
```
### Retrospective Workflow Major Overhaul
Transformed retrospective into immersive, interactive team experience:
**Epic Discovery Priority (Fixed):**
- Priority 1: Check sprint-status.yaml for last completed epic
- Priority 2: Ask user directly
- Priority 3: Scan stories folder (last resort)
**New Capabilities:**
- Deep story analysis: Extract dev notes, mistakes, review feedback, lessons learned
- Previous retro integration: Track action items, verify lessons applied
- Significant change detection: Alert when discoveries require epic updates
- Intent-based facilitation: Natural conversation vs scripted phrases
- Party mode protocol: Clear speaker identification (Name (Role): dialogue)
- Team dynamics: Drama, disagreements, diverse perspectives, authentic conflict
**Structure:**
- 12 whole-number steps (no decimals)
- Highly interactive with constant user engagement
- Cross-references previous retro for accountability
- Synthesizes patterns across all stories
- Detects architectural assumption changes
## Documentation
**Created:**
- `docs/document-sharding-guide.md` - Comprehensive 300+ line guide
- What is sharding, when to use it (token thresholds)
- How sharding works (discovery system, loading strategies)
- Using shard-doc tool
- Full Load vs Selective Load patterns
- Complete examples and troubleshooting
- Custom workflow integration patterns
**Updated:**
- `README.md` - Added Document Sharding feature section
- `docs/index.md` - Added under Advanced Topics → Optimization
- `src/modules/bmm/workflows/README.md` - Added sharding section with usage
- `src/modules/bmb/workflows/create-workflow/workflow-creation-guide.md` - Added complete implementation patterns for workflow builders
**Documentation levels:**
1. Overview (README.md) - Quick feature highlight
2. User guide (BMM workflows README) - Practical usage
3. Reference (document-sharding-guide.md) - Complete details
4. Builder guide (workflow-creation-guide.md) - Implementation patterns
## Efficiency Gains
**Example: 10-Epic Project**
Before sharding:
- epic-tech-context for Epic 3: Load all 10 epics (~50k tokens)
- create-story for Epic 3: Load all 10 epics (~50k tokens)
- story-context for Epic 3: Load all 10 epics (~50k tokens)
After sharding with selective load:
- epic-tech-context for Epic 3: Load Epic 3 only (~5k tokens) = 90% reduction
- create-story for Epic 3: Load Epic 3 only (~5k tokens) = 90% reduction
- story-context for Epic 3: Load Epic 3 only (~5k tokens) = 90% reduction
## Breaking Changes
None - fully backward compatible. Workflows work with existing whole documents.
## Files Changed
**Workflows Updated (25 files):**
- 7 Phase 1-3 workflows: Added full load sharding support
- 5 Phase 4 workflows: Added selective load sharding support
- 1 retrospective workflow: Complete overhaul with sharding support
**Documentation (5 files):**
- Created: document-sharding-guide.md
- Updated: README.md, docs/index.md, BMM workflows README, BMB workflow-creation-guide
- Removed: Old conversion report (obsolete)
## Future Extensibility
- BMB workflows now aware of sharding patterns
- Custom modules can easily implement sharding support
- Standard patterns documented for consistency
- No need to explain concept in future development
2025-11-02 00:13:33 -05:00
2025-10-15 21:17:09 -05:00
<workflow>
2025-10-14 19:58:44 -05:00
2025-10-30 08:13:18 -05:00
<step n="0" goal="Validate workflow readiness" tag="workflow-status">
2025-11-01 19:37:20 -05:00
<action>Check if {status_file} exists</action>
<action if="status file not found">Set standalone_mode = true</action>
2025-10-15 23:10:33 -05:00
2025-10-30 08:13:18 -05:00
<check if="status file found">
2025-11-01 19:37:20 -05:00
<action>Load the FULL file: {status_file}</action>
2025-10-30 08:13:18 -05:00
<action>Parse workflow_status section</action>
<action>Check status of "prd" workflow</action>
refactor: comprehensive workflow modernization and standardization
## Major Improvements
### 1. Elicitation System Modernization
- Removed legacy `<elicit-required />` tag from workflow.xml
- Replaced with direct `<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>` pattern
- More explicit, self-documenting, and eliminates indirection layer
- Added strategic elicitation points across all planning workflows:
- PRD: After success criteria, scope, functional requirements, and final review
- Create-Epics-And-Stories: After epic proposals and each epic's stories
- Architecture: After decisions, structure, patterns, implementation patterns, and final doc
- Updated audit-workflow tag scanner to remove obsolete elicit-required reference
### 2. Input Document Discovery Streamlined
- Replaced verbose 19-line "Input Document Discovery" sections with single critical tag
- New format: `<critical>Input documents specified in workflow.yaml input_file_patterns...</critical>`
- Eliminates duplication - workflow.yaml already defines patterns
- Updated across 6 workflows (PRD, create-epics-and-stories, architecture, tech-spec, UX, gate-check)
- Saved ~114 lines of repeated bloat
### 3. Scale System Migration (Levels 0-4 → 3 Tracks)
- Updated PRD workflow from "Level 0-4" to "Quick Flow / BMad Method / Enterprise Method"
- Changed `project_level` variable to `project_track`
- Removed `target_scale` variable (no longer needed)
- Updated workflow.yaml descriptions to reference tracks not levels
- Updated checklist from "Level 2" and "Level 3-4" to "BMad Method" and "Enterprise Method"
- Aligns with new scale-adaptive-system.md (3-track methodology)
### 4. Epic/Story Template Standardization
- Replaced hardcoded 8-epic template with clean repeating pattern using N/M variables
- Added BDD-style acceptance criteria (Given/When/Then/And)
- Removed instructional bloat from templates (moved to instructions.md where it belongs)
- Template shows OUTPUT structure, instructions show PROCESS
- Applied to both create-epics-and-stories and tech-spec workflows
- Templates now use HTML comments to indicate repeating sections
### 5. Workflow.yaml Pattern Consistency
- Standardized input_file_patterns across all workflows
- Separated `recommended_inputs` (semantic WHAT) from `input_file_patterns` (file discovery WHERE)
- Removed duplication between recommended_inputs file paths and input_file_patterns
- Create-epics-and-stories now uses proper whole/sharded pattern like architecture workflow
- Solutioning-gate-check cleaned up to use semantic descriptions not file paths
## Files Changed (18)
- Core: workflow.xml (removed elicit-required tag and references)
- Audit workflow: Updated tag pattern scanner
- PRD workflow: Elicitation points, track migration, input discovery
- Create-epics-and-stories: Template rebuild, BDD format, elicitation, input patterns
- Tech-spec: Template rebuild, BDD format, input discovery
- UX Design: Input discovery streamlined
- Architecture: Elicitation at 5 key decision points, input discovery
- Gate-check: Input pattern cleanup, input discovery
## Impact
- More consistent elicitation across workflows
- Cleaner, more maintainable templates
- Better separation of concerns (templates vs instructions)
- Aligned with v6 3-track scale system
- Reduced bloat and duplication significantly
2025-11-04 00:09:19 -06:00
<action>Get project_track from YAML metadata</action>
2025-10-30 08:13:18 -05:00
<action>Find first non-completed workflow (next expected workflow)</action>
2025-10-15 23:10:33 -05:00
refactor: comprehensive workflow modernization and standardization
## Major Improvements
### 1. Elicitation System Modernization
- Removed legacy `<elicit-required />` tag from workflow.xml
- Replaced with direct `<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>` pattern
- More explicit, self-documenting, and eliminates indirection layer
- Added strategic elicitation points across all planning workflows:
- PRD: After success criteria, scope, functional requirements, and final review
- Create-Epics-And-Stories: After epic proposals and each epic's stories
- Architecture: After decisions, structure, patterns, implementation patterns, and final doc
- Updated audit-workflow tag scanner to remove obsolete elicit-required reference
### 2. Input Document Discovery Streamlined
- Replaced verbose 19-line "Input Document Discovery" sections with single critical tag
- New format: `<critical>Input documents specified in workflow.yaml input_file_patterns...</critical>`
- Eliminates duplication - workflow.yaml already defines patterns
- Updated across 6 workflows (PRD, create-epics-and-stories, architecture, tech-spec, UX, gate-check)
- Saved ~114 lines of repeated bloat
### 3. Scale System Migration (Levels 0-4 → 3 Tracks)
- Updated PRD workflow from "Level 0-4" to "Quick Flow / BMad Method / Enterprise Method"
- Changed `project_level` variable to `project_track`
- Removed `target_scale` variable (no longer needed)
- Updated workflow.yaml descriptions to reference tracks not levels
- Updated checklist from "Level 2" and "Level 3-4" to "BMad Method" and "Enterprise Method"
- Aligns with new scale-adaptive-system.md (3-track methodology)
### 4. Epic/Story Template Standardization
- Replaced hardcoded 8-epic template with clean repeating pattern using N/M variables
- Added BDD-style acceptance criteria (Given/When/Then/And)
- Removed instructional bloat from templates (moved to instructions.md where it belongs)
- Template shows OUTPUT structure, instructions show PROCESS
- Applied to both create-epics-and-stories and tech-spec workflows
- Templates now use HTML comments to indicate repeating sections
### 5. Workflow.yaml Pattern Consistency
- Standardized input_file_patterns across all workflows
- Separated `recommended_inputs` (semantic WHAT) from `input_file_patterns` (file discovery WHERE)
- Removed duplication between recommended_inputs file paths and input_file_patterns
- Create-epics-and-stories now uses proper whole/sharded pattern like architecture workflow
- Solutioning-gate-check cleaned up to use semantic descriptions not file paths
## Files Changed (18)
- Core: workflow.xml (removed elicit-required tag and references)
- Audit workflow: Updated tag pattern scanner
- PRD workflow: Elicitation points, track migration, input discovery
- Create-epics-and-stories: Template rebuild, BDD format, elicitation, input patterns
- Tech-spec: Template rebuild, BDD format, input discovery
- UX Design: Input discovery streamlined
- Architecture: Elicitation at 5 key decision points, input discovery
- Gate-check: Input pattern cleanup, input discovery
## Impact
- More consistent elicitation across workflows
- Cleaner, more maintainable templates
- Better separation of concerns (templates vs instructions)
- Aligned with v6 3-track scale system
- Reduced bloat and duplication significantly
2025-11-04 00:09:19 -06:00
<check if="project_track is Quick Flow">
<output>**Quick Flow Track - Redirecting**
2025-10-14 19:58:44 -05:00
refactor: comprehensive workflow modernization and standardization
## Major Improvements
### 1. Elicitation System Modernization
- Removed legacy `<elicit-required />` tag from workflow.xml
- Replaced with direct `<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>` pattern
- More explicit, self-documenting, and eliminates indirection layer
- Added strategic elicitation points across all planning workflows:
- PRD: After success criteria, scope, functional requirements, and final review
- Create-Epics-And-Stories: After epic proposals and each epic's stories
- Architecture: After decisions, structure, patterns, implementation patterns, and final doc
- Updated audit-workflow tag scanner to remove obsolete elicit-required reference
### 2. Input Document Discovery Streamlined
- Replaced verbose 19-line "Input Document Discovery" sections with single critical tag
- New format: `<critical>Input documents specified in workflow.yaml input_file_patterns...</critical>`
- Eliminates duplication - workflow.yaml already defines patterns
- Updated across 6 workflows (PRD, create-epics-and-stories, architecture, tech-spec, UX, gate-check)
- Saved ~114 lines of repeated bloat
### 3. Scale System Migration (Levels 0-4 → 3 Tracks)
- Updated PRD workflow from "Level 0-4" to "Quick Flow / BMad Method / Enterprise Method"
- Changed `project_level` variable to `project_track`
- Removed `target_scale` variable (no longer needed)
- Updated workflow.yaml descriptions to reference tracks not levels
- Updated checklist from "Level 2" and "Level 3-4" to "BMad Method" and "Enterprise Method"
- Aligns with new scale-adaptive-system.md (3-track methodology)
### 4. Epic/Story Template Standardization
- Replaced hardcoded 8-epic template with clean repeating pattern using N/M variables
- Added BDD-style acceptance criteria (Given/When/Then/And)
- Removed instructional bloat from templates (moved to instructions.md where it belongs)
- Template shows OUTPUT structure, instructions show PROCESS
- Applied to both create-epics-and-stories and tech-spec workflows
- Templates now use HTML comments to indicate repeating sections
### 5. Workflow.yaml Pattern Consistency
- Standardized input_file_patterns across all workflows
- Separated `recommended_inputs` (semantic WHAT) from `input_file_patterns` (file discovery WHERE)
- Removed duplication between recommended_inputs file paths and input_file_patterns
- Create-epics-and-stories now uses proper whole/sharded pattern like architecture workflow
- Solutioning-gate-check cleaned up to use semantic descriptions not file paths
## Files Changed (18)
- Core: workflow.xml (removed elicit-required tag and references)
- Audit workflow: Updated tag pattern scanner
- PRD workflow: Elicitation points, track migration, input discovery
- Create-epics-and-stories: Template rebuild, BDD format, elicitation, input patterns
- Tech-spec: Template rebuild, BDD format, input discovery
- UX Design: Input discovery streamlined
- Architecture: Elicitation at 5 key decision points, input discovery
- Gate-check: Input pattern cleanup, input discovery
## Impact
- More consistent elicitation across workflows
- Cleaner, more maintainable templates
- Better separation of concerns (templates vs instructions)
- Aligned with v6 3-track scale system
- Reduced bloat and duplication significantly
2025-11-04 00:09:19 -06:00
Quick Flow projects use tech-spec workflow for implementation-focused planning.
PRD is for BMad Method and Enterprise Method tracks that need comprehensive requirements.</output>
2025-11-01 19:37:20 -05:00
<action>Exit and suggest tech-spec workflow</action>
2025-10-17 16:44:06 -05:00
</check>
2025-10-15 23:10:33 -05:00
2025-10-30 08:13:18 -05:00
<check if="prd status is file path (already completed)">
<output>⚠️ PRD already completed: {{prd status}}</output>
<ask>Re-running will overwrite the existing PRD. Continue? (y/n)</ask>
<check if="n">
<output>Exiting. Use workflow-status to see your next step.</output>
<action>Exit workflow</action>
</check>
</check>
2025-10-15 23:10:33 -05:00
2025-10-30 08:13:18 -05:00
<action>Set standalone_mode = false</action>
2025-10-14 19:58:44 -05:00
</check>
2025-10-17 16:44:06 -05:00
</step>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<step n="1" goal="Discovery - Project, Domain, and Vision">
<action>Welcome {user_name} and begin comprehensive discovery, and then start to GATHER ALL CONTEXT:
1. Check workflow-status.yaml for project_context (if exists)
2. Look for existing documents (Product Brief, Domain Brief, research)
3. Detect project type AND domain complexity
Load references:
{installed_path}/project-types.csv
{installed_path}/domain-complexity.csv
Through natural conversation:
"Tell me about what you want to build - what problem does it solve and for whom?"
DUAL DETECTION:
Project type signals: API, mobile, web, CLI, SDK, SaaS
Domain complexity signals: medical, finance, government, education, aerospace
SPECIAL ROUTING:
If game detected → Suggest game-brief and GDD workflows
If complex domain detected → Offer domain research options:
A) Run domain-research workflow (thorough)
B) Quick web search (basic)
C) User provides context
D) Continue with general knowledge
CAPTURE THE MAGIC EARLY with a few questions such as for example: "What excites you most about this product?", "What would make users love this?", "What's the moment that will make people go 'wow'?"
This excitement becomes the thread woven throughout the PRD.</action>
<template-output>vision_alignment</template-output>
<template-output>project_classification</template-output>
<template-output>project_type</template-output>
<template-output>domain_type</template-output>
<template-output>complexity_level</template-output>
<check if="complex domain">
<template-output>domain_context_summary</template-output>
2025-10-15 21:17:09 -05:00
</check>
2025-11-01 19:37:20 -05:00
<template-output>product_magic_essence</template-output>
<template-output>product_brief_path</template-output>
<template-output>domain_brief_path</template-output>
<template-output>research_documents</template-output>
2025-10-14 19:58:44 -05:00
</step>
2025-11-01 19:37:20 -05:00
<step n="2" goal="Success Definition">
<action>Define what winning looks like for THIS specific product
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
INTENT: Meaningful success criteria, not generic metrics
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Adapt to context:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- Consumer: User love, engagement, retention
- B2B: ROI, efficiency, adoption
- Developer tools: Developer experience, community
- Regulated: Compliance, safety, validation
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Make it specific:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- NOT: "10,000 users"
- BUT: "100 power users who rely on it daily"
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- NOT: "99.9% uptime"
- BUT: "Zero data loss during critical operations"
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Weave in the magic:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- "Success means users experience [that special moment] and [desired outcome]"</action>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<template-output>success_criteria</template-output>
<check if="business focus">
<template-output>business_metrics</template-output>
2025-10-14 19:58:44 -05:00
</check>
refactor: comprehensive workflow modernization and standardization
## Major Improvements
### 1. Elicitation System Modernization
- Removed legacy `<elicit-required />` tag from workflow.xml
- Replaced with direct `<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>` pattern
- More explicit, self-documenting, and eliminates indirection layer
- Added strategic elicitation points across all planning workflows:
- PRD: After success criteria, scope, functional requirements, and final review
- Create-Epics-And-Stories: After epic proposals and each epic's stories
- Architecture: After decisions, structure, patterns, implementation patterns, and final doc
- Updated audit-workflow tag scanner to remove obsolete elicit-required reference
### 2. Input Document Discovery Streamlined
- Replaced verbose 19-line "Input Document Discovery" sections with single critical tag
- New format: `<critical>Input documents specified in workflow.yaml input_file_patterns...</critical>`
- Eliminates duplication - workflow.yaml already defines patterns
- Updated across 6 workflows (PRD, create-epics-and-stories, architecture, tech-spec, UX, gate-check)
- Saved ~114 lines of repeated bloat
### 3. Scale System Migration (Levels 0-4 → 3 Tracks)
- Updated PRD workflow from "Level 0-4" to "Quick Flow / BMad Method / Enterprise Method"
- Changed `project_level` variable to `project_track`
- Removed `target_scale` variable (no longer needed)
- Updated workflow.yaml descriptions to reference tracks not levels
- Updated checklist from "Level 2" and "Level 3-4" to "BMad Method" and "Enterprise Method"
- Aligns with new scale-adaptive-system.md (3-track methodology)
### 4. Epic/Story Template Standardization
- Replaced hardcoded 8-epic template with clean repeating pattern using N/M variables
- Added BDD-style acceptance criteria (Given/When/Then/And)
- Removed instructional bloat from templates (moved to instructions.md where it belongs)
- Template shows OUTPUT structure, instructions show PROCESS
- Applied to both create-epics-and-stories and tech-spec workflows
- Templates now use HTML comments to indicate repeating sections
### 5. Workflow.yaml Pattern Consistency
- Standardized input_file_patterns across all workflows
- Separated `recommended_inputs` (semantic WHAT) from `input_file_patterns` (file discovery WHERE)
- Removed duplication between recommended_inputs file paths and input_file_patterns
- Create-epics-and-stories now uses proper whole/sharded pattern like architecture workflow
- Solutioning-gate-check cleaned up to use semantic descriptions not file paths
## Files Changed (18)
- Core: workflow.xml (removed elicit-required tag and references)
- Audit workflow: Updated tag pattern scanner
- PRD workflow: Elicitation points, track migration, input discovery
- Create-epics-and-stories: Template rebuild, BDD format, elicitation, input patterns
- Tech-spec: Template rebuild, BDD format, input discovery
- UX Design: Input discovery streamlined
- Architecture: Elicitation at 5 key decision points, input discovery
- Gate-check: Input pattern cleanup, input discovery
## Impact
- More consistent elicitation across workflows
- Cleaner, more maintainable templates
- Better separation of concerns (templates vs instructions)
- Aligned with v6 3-track scale system
- Reduced bloat and duplication significantly
2025-11-04 00:09:19 -06:00
<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>
2025-10-14 19:58:44 -05:00
</step>
2025-11-01 19:37:20 -05:00
<step n="3" goal="Scope Definition">
<action>Smart scope negotiation - find the sweet spot
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
The Scoping Game:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
1. "What must work for this to be useful?" → MVP
2. "What makes it competitive?" → Growth
3. "What's the dream version?" → Vision
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Challenge scope creep conversationally:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- "Could that wait until after launch?"
- "Is that essential for proving the concept?"
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
For complex domains:
2025-10-15 21:17:09 -05:00
2025-11-01 19:37:20 -05:00
- Include compliance minimums in MVP
- Note regulatory gates between phases</action>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<template-output>mvp_scope</template-output>
<template-output>growth_features</template-output>
<template-output>vision_features</template-output>
refactor: comprehensive workflow modernization and standardization
## Major Improvements
### 1. Elicitation System Modernization
- Removed legacy `<elicit-required />` tag from workflow.xml
- Replaced with direct `<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>` pattern
- More explicit, self-documenting, and eliminates indirection layer
- Added strategic elicitation points across all planning workflows:
- PRD: After success criteria, scope, functional requirements, and final review
- Create-Epics-And-Stories: After epic proposals and each epic's stories
- Architecture: After decisions, structure, patterns, implementation patterns, and final doc
- Updated audit-workflow tag scanner to remove obsolete elicit-required reference
### 2. Input Document Discovery Streamlined
- Replaced verbose 19-line "Input Document Discovery" sections with single critical tag
- New format: `<critical>Input documents specified in workflow.yaml input_file_patterns...</critical>`
- Eliminates duplication - workflow.yaml already defines patterns
- Updated across 6 workflows (PRD, create-epics-and-stories, architecture, tech-spec, UX, gate-check)
- Saved ~114 lines of repeated bloat
### 3. Scale System Migration (Levels 0-4 → 3 Tracks)
- Updated PRD workflow from "Level 0-4" to "Quick Flow / BMad Method / Enterprise Method"
- Changed `project_level` variable to `project_track`
- Removed `target_scale` variable (no longer needed)
- Updated workflow.yaml descriptions to reference tracks not levels
- Updated checklist from "Level 2" and "Level 3-4" to "BMad Method" and "Enterprise Method"
- Aligns with new scale-adaptive-system.md (3-track methodology)
### 4. Epic/Story Template Standardization
- Replaced hardcoded 8-epic template with clean repeating pattern using N/M variables
- Added BDD-style acceptance criteria (Given/When/Then/And)
- Removed instructional bloat from templates (moved to instructions.md where it belongs)
- Template shows OUTPUT structure, instructions show PROCESS
- Applied to both create-epics-and-stories and tech-spec workflows
- Templates now use HTML comments to indicate repeating sections
### 5. Workflow.yaml Pattern Consistency
- Standardized input_file_patterns across all workflows
- Separated `recommended_inputs` (semantic WHAT) from `input_file_patterns` (file discovery WHERE)
- Removed duplication between recommended_inputs file paths and input_file_patterns
- Create-epics-and-stories now uses proper whole/sharded pattern like architecture workflow
- Solutioning-gate-check cleaned up to use semantic descriptions not file paths
## Files Changed (18)
- Core: workflow.xml (removed elicit-required tag and references)
- Audit workflow: Updated tag pattern scanner
- PRD workflow: Elicitation points, track migration, input discovery
- Create-epics-and-stories: Template rebuild, BDD format, elicitation, input patterns
- Tech-spec: Template rebuild, BDD format, input discovery
- UX Design: Input discovery streamlined
- Architecture: Elicitation at 5 key decision points, input discovery
- Gate-check: Input pattern cleanup, input discovery
## Impact
- More consistent elicitation across workflows
- Cleaner, more maintainable templates
- Better separation of concerns (templates vs instructions)
- Aligned with v6 3-track scale system
- Reduced bloat and duplication significantly
2025-11-04 00:09:19 -06:00
<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>
2025-10-14 19:58:44 -05:00
</step>
2025-11-01 19:37:20 -05:00
<step n="4" goal="Domain-Specific Exploration" optional="true">
<action>Only if complex domain detected or domain-brief exists
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Synthesize domain requirements that will shape everything:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- Regulatory requirements
- Compliance needs
- Industry standards
- Safety/risk factors
- Required validations
- Special expertise needed
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
These inform:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- What features are mandatory
- What NFRs are critical
- How to sequence development
- What validation is required</action>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<check if="complex domain">
<template-output>domain_considerations</template-output>
2025-10-14 19:58:44 -05:00
</check>
</step>
2025-11-01 19:37:20 -05:00
<step n="5" goal="Innovation Discovery" optional="true">
<action>Identify truly novel patterns if applicable
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Listen for innovation signals:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- "Nothing like this exists"
- "We're rethinking how [X] works"
- "Combining [A] with [B] for the first time"
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Explore deeply:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- What makes it unique?
- What assumption are you challenging?
- How do we validate it?
- What's the fallback?
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<WebSearch if="novel">{concept} innovations {date}</WebSearch></action>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<check if="innovation detected">
<template-output>innovation_patterns</template-output>
<template-output>validation_approach</template-output>
</check>
2025-10-14 19:58:44 -05:00
</step>
2025-11-01 19:37:20 -05:00
<step n="6" goal="Project-Specific Deep Dive">
<action>Based on detected project type, dive deep into specific needs
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Load project type requirements from CSV and expand naturally.
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
FOR API/BACKEND:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- Map out endpoints, methods, parameters
- Define authentication and authorization
- Specify error codes and rate limits
- Document data schemas
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
FOR MOBILE:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- Platform requirements (iOS/Android/both)
- Device features needed
- Offline capabilities
- Store compliance
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
FOR SAAS B2B:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- Multi-tenant architecture
- Permission models
- Subscription tiers
- Critical integrations
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
[Continue for other types...]
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Always relate back to the product magic:
"How does [requirement] enhance [the special thing]?"</action>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<template-output>project_type_requirements</template-output>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<!-- Dynamic sections based on project type -->
<check if="API/Backend project">
<template-output>endpoint_specification</template-output>
<template-output>authentication_model</template-output>
</check>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<check if="Mobile project">
<template-output>platform_requirements</template-output>
<template-output>device_features</template-output>
</check>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<check if="SaaS B2B project">
<template-output>tenant_model</template-output>
<template-output>permission_matrix</template-output>
</check>
2025-10-14 19:58:44 -05:00
</step>
refactor: comprehensive workflow modernization and standardization
## Major Improvements
### 1. Elicitation System Modernization
- Removed legacy `<elicit-required />` tag from workflow.xml
- Replaced with direct `<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>` pattern
- More explicit, self-documenting, and eliminates indirection layer
- Added strategic elicitation points across all planning workflows:
- PRD: After success criteria, scope, functional requirements, and final review
- Create-Epics-And-Stories: After epic proposals and each epic's stories
- Architecture: After decisions, structure, patterns, implementation patterns, and final doc
- Updated audit-workflow tag scanner to remove obsolete elicit-required reference
### 2. Input Document Discovery Streamlined
- Replaced verbose 19-line "Input Document Discovery" sections with single critical tag
- New format: `<critical>Input documents specified in workflow.yaml input_file_patterns...</critical>`
- Eliminates duplication - workflow.yaml already defines patterns
- Updated across 6 workflows (PRD, create-epics-and-stories, architecture, tech-spec, UX, gate-check)
- Saved ~114 lines of repeated bloat
### 3. Scale System Migration (Levels 0-4 → 3 Tracks)
- Updated PRD workflow from "Level 0-4" to "Quick Flow / BMad Method / Enterprise Method"
- Changed `project_level` variable to `project_track`
- Removed `target_scale` variable (no longer needed)
- Updated workflow.yaml descriptions to reference tracks not levels
- Updated checklist from "Level 2" and "Level 3-4" to "BMad Method" and "Enterprise Method"
- Aligns with new scale-adaptive-system.md (3-track methodology)
### 4. Epic/Story Template Standardization
- Replaced hardcoded 8-epic template with clean repeating pattern using N/M variables
- Added BDD-style acceptance criteria (Given/When/Then/And)
- Removed instructional bloat from templates (moved to instructions.md where it belongs)
- Template shows OUTPUT structure, instructions show PROCESS
- Applied to both create-epics-and-stories and tech-spec workflows
- Templates now use HTML comments to indicate repeating sections
### 5. Workflow.yaml Pattern Consistency
- Standardized input_file_patterns across all workflows
- Separated `recommended_inputs` (semantic WHAT) from `input_file_patterns` (file discovery WHERE)
- Removed duplication between recommended_inputs file paths and input_file_patterns
- Create-epics-and-stories now uses proper whole/sharded pattern like architecture workflow
- Solutioning-gate-check cleaned up to use semantic descriptions not file paths
## Files Changed (18)
- Core: workflow.xml (removed elicit-required tag and references)
- Audit workflow: Updated tag pattern scanner
- PRD workflow: Elicitation points, track migration, input discovery
- Create-epics-and-stories: Template rebuild, BDD format, elicitation, input patterns
- Tech-spec: Template rebuild, BDD format, input discovery
- UX Design: Input discovery streamlined
- Architecture: Elicitation at 5 key decision points, input discovery
- Gate-check: Input pattern cleanup, input discovery
## Impact
- More consistent elicitation across workflows
- Cleaner, more maintainable templates
- Better separation of concerns (templates vs instructions)
- Aligned with v6 3-track scale system
- Reduced bloat and duplication significantly
2025-11-04 00:09:19 -06:00
<step n="7" goal="UX Principles" if="project has UI or UX">
<action>Only if product has a UI
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Light touch on UX - not full design:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- Visual personality
- Key interaction patterns
- Critical user flows
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
"How should this feel to use?"
"What's the vibe - professional, playful, minimal?"
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Connect to the magic:
"The UI should reinforce [the special moment] through [design approach]"</action>
2025-10-14 19:58:44 -05:00
refactor: comprehensive workflow modernization and standardization
## Major Improvements
### 1. Elicitation System Modernization
- Removed legacy `<elicit-required />` tag from workflow.xml
- Replaced with direct `<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>` pattern
- More explicit, self-documenting, and eliminates indirection layer
- Added strategic elicitation points across all planning workflows:
- PRD: After success criteria, scope, functional requirements, and final review
- Create-Epics-And-Stories: After epic proposals and each epic's stories
- Architecture: After decisions, structure, patterns, implementation patterns, and final doc
- Updated audit-workflow tag scanner to remove obsolete elicit-required reference
### 2. Input Document Discovery Streamlined
- Replaced verbose 19-line "Input Document Discovery" sections with single critical tag
- New format: `<critical>Input documents specified in workflow.yaml input_file_patterns...</critical>`
- Eliminates duplication - workflow.yaml already defines patterns
- Updated across 6 workflows (PRD, create-epics-and-stories, architecture, tech-spec, UX, gate-check)
- Saved ~114 lines of repeated bloat
### 3. Scale System Migration (Levels 0-4 → 3 Tracks)
- Updated PRD workflow from "Level 0-4" to "Quick Flow / BMad Method / Enterprise Method"
- Changed `project_level` variable to `project_track`
- Removed `target_scale` variable (no longer needed)
- Updated workflow.yaml descriptions to reference tracks not levels
- Updated checklist from "Level 2" and "Level 3-4" to "BMad Method" and "Enterprise Method"
- Aligns with new scale-adaptive-system.md (3-track methodology)
### 4. Epic/Story Template Standardization
- Replaced hardcoded 8-epic template with clean repeating pattern using N/M variables
- Added BDD-style acceptance criteria (Given/When/Then/And)
- Removed instructional bloat from templates (moved to instructions.md where it belongs)
- Template shows OUTPUT structure, instructions show PROCESS
- Applied to both create-epics-and-stories and tech-spec workflows
- Templates now use HTML comments to indicate repeating sections
### 5. Workflow.yaml Pattern Consistency
- Standardized input_file_patterns across all workflows
- Separated `recommended_inputs` (semantic WHAT) from `input_file_patterns` (file discovery WHERE)
- Removed duplication between recommended_inputs file paths and input_file_patterns
- Create-epics-and-stories now uses proper whole/sharded pattern like architecture workflow
- Solutioning-gate-check cleaned up to use semantic descriptions not file paths
## Files Changed (18)
- Core: workflow.xml (removed elicit-required tag and references)
- Audit workflow: Updated tag pattern scanner
- PRD workflow: Elicitation points, track migration, input discovery
- Create-epics-and-stories: Template rebuild, BDD format, elicitation, input patterns
- Tech-spec: Template rebuild, BDD format, input discovery
- UX Design: Input discovery streamlined
- Architecture: Elicitation at 5 key decision points, input discovery
- Gate-check: Input pattern cleanup, input discovery
## Impact
- More consistent elicitation across workflows
- Cleaner, more maintainable templates
- Better separation of concerns (templates vs instructions)
- Aligned with v6 3-track scale system
- Reduced bloat and duplication significantly
2025-11-04 00:09:19 -06:00
<check if="has UI">
<template-output>ux_principles</template-output>
<template-output>key_interactions</template-output>
</check>
2025-10-14 19:58:44 -05:00
</step>
2025-11-01 19:37:20 -05:00
<step n="8" goal="Functional Requirements Synthesis">
<action>Transform everything discovered into clear functional requirements
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Pull together:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- Core features from scope
- Domain-mandated features
- Project-type specific needs
- Innovation requirements
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Organize by capability, not technology:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- User Management (not "auth system")
- Content Discovery (not "search algorithm")
- Team Collaboration (not "websockets")
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Each requirement should:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- Be specific and measurable
- Connect to user value
- Include acceptance criteria
- Note domain constraints
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
The magic thread:
Highlight which requirements deliver the special experience</action>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<template-output>functional_requirements_complete</template-output>
refactor: comprehensive workflow modernization and standardization
## Major Improvements
### 1. Elicitation System Modernization
- Removed legacy `<elicit-required />` tag from workflow.xml
- Replaced with direct `<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>` pattern
- More explicit, self-documenting, and eliminates indirection layer
- Added strategic elicitation points across all planning workflows:
- PRD: After success criteria, scope, functional requirements, and final review
- Create-Epics-And-Stories: After epic proposals and each epic's stories
- Architecture: After decisions, structure, patterns, implementation patterns, and final doc
- Updated audit-workflow tag scanner to remove obsolete elicit-required reference
### 2. Input Document Discovery Streamlined
- Replaced verbose 19-line "Input Document Discovery" sections with single critical tag
- New format: `<critical>Input documents specified in workflow.yaml input_file_patterns...</critical>`
- Eliminates duplication - workflow.yaml already defines patterns
- Updated across 6 workflows (PRD, create-epics-and-stories, architecture, tech-spec, UX, gate-check)
- Saved ~114 lines of repeated bloat
### 3. Scale System Migration (Levels 0-4 → 3 Tracks)
- Updated PRD workflow from "Level 0-4" to "Quick Flow / BMad Method / Enterprise Method"
- Changed `project_level` variable to `project_track`
- Removed `target_scale` variable (no longer needed)
- Updated workflow.yaml descriptions to reference tracks not levels
- Updated checklist from "Level 2" and "Level 3-4" to "BMad Method" and "Enterprise Method"
- Aligns with new scale-adaptive-system.md (3-track methodology)
### 4. Epic/Story Template Standardization
- Replaced hardcoded 8-epic template with clean repeating pattern using N/M variables
- Added BDD-style acceptance criteria (Given/When/Then/And)
- Removed instructional bloat from templates (moved to instructions.md where it belongs)
- Template shows OUTPUT structure, instructions show PROCESS
- Applied to both create-epics-and-stories and tech-spec workflows
- Templates now use HTML comments to indicate repeating sections
### 5. Workflow.yaml Pattern Consistency
- Standardized input_file_patterns across all workflows
- Separated `recommended_inputs` (semantic WHAT) from `input_file_patterns` (file discovery WHERE)
- Removed duplication between recommended_inputs file paths and input_file_patterns
- Create-epics-and-stories now uses proper whole/sharded pattern like architecture workflow
- Solutioning-gate-check cleaned up to use semantic descriptions not file paths
## Files Changed (18)
- Core: workflow.xml (removed elicit-required tag and references)
- Audit workflow: Updated tag pattern scanner
- PRD workflow: Elicitation points, track migration, input discovery
- Create-epics-and-stories: Template rebuild, BDD format, elicitation, input patterns
- Tech-spec: Template rebuild, BDD format, input discovery
- UX Design: Input discovery streamlined
- Architecture: Elicitation at 5 key decision points, input discovery
- Gate-check: Input pattern cleanup, input discovery
## Impact
- More consistent elicitation across workflows
- Cleaner, more maintainable templates
- Better separation of concerns (templates vs instructions)
- Aligned with v6 3-track scale system
- Reduced bloat and duplication significantly
2025-11-04 00:09:19 -06:00
<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>
2025-11-01 19:37:20 -05:00
</step>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<step n="9" goal="Non-Functional Requirements Discovery">
<action>Only document NFRs that matter for THIS product
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Performance: Only if user-facing impact
Security: Only if handling sensitive data
Scale: Only if growth expected
Accessibility: Only if broad audience
Integration: Only if connecting systems
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
For each NFR:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- Why it matters for THIS product
- Specific measurable criteria
- Domain-driven requirements
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Skip categories that don't apply!</action>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<!-- Only output sections that were discussed -->
<check if="performance matters">
<template-output>performance_requirements</template-output>
</check>
<check if="security matters">
<template-output>security_requirements</template-output>
</check>
<check if="scale matters">
<template-output>scalability_requirements</template-output>
</check>
<check if="accessibility matters">
<template-output>accessibility_requirements</template-output>
</check>
<check if="integration matters">
<template-output>integration_requirements</template-output>
</check>
</step>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<step n="10" goal="Review PRD and transition to epics">
<action>Review the PRD we've built together
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
"Let's review what we've captured:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- Vision: [summary]
- Success: [key metrics]
- Scope: [MVP highlights]
- Requirements: [count] functional, [count] non-functional
- Special considerations: [domain/innovation]
2025-10-14 19:58:44 -05:00
refactor: comprehensive workflow modernization and standardization
## Major Improvements
### 1. Elicitation System Modernization
- Removed legacy `<elicit-required />` tag from workflow.xml
- Replaced with direct `<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>` pattern
- More explicit, self-documenting, and eliminates indirection layer
- Added strategic elicitation points across all planning workflows:
- PRD: After success criteria, scope, functional requirements, and final review
- Create-Epics-And-Stories: After epic proposals and each epic's stories
- Architecture: After decisions, structure, patterns, implementation patterns, and final doc
- Updated audit-workflow tag scanner to remove obsolete elicit-required reference
### 2. Input Document Discovery Streamlined
- Replaced verbose 19-line "Input Document Discovery" sections with single critical tag
- New format: `<critical>Input documents specified in workflow.yaml input_file_patterns...</critical>`
- Eliminates duplication - workflow.yaml already defines patterns
- Updated across 6 workflows (PRD, create-epics-and-stories, architecture, tech-spec, UX, gate-check)
- Saved ~114 lines of repeated bloat
### 3. Scale System Migration (Levels 0-4 → 3 Tracks)
- Updated PRD workflow from "Level 0-4" to "Quick Flow / BMad Method / Enterprise Method"
- Changed `project_level` variable to `project_track`
- Removed `target_scale` variable (no longer needed)
- Updated workflow.yaml descriptions to reference tracks not levels
- Updated checklist from "Level 2" and "Level 3-4" to "BMad Method" and "Enterprise Method"
- Aligns with new scale-adaptive-system.md (3-track methodology)
### 4. Epic/Story Template Standardization
- Replaced hardcoded 8-epic template with clean repeating pattern using N/M variables
- Added BDD-style acceptance criteria (Given/When/Then/And)
- Removed instructional bloat from templates (moved to instructions.md where it belongs)
- Template shows OUTPUT structure, instructions show PROCESS
- Applied to both create-epics-and-stories and tech-spec workflows
- Templates now use HTML comments to indicate repeating sections
### 5. Workflow.yaml Pattern Consistency
- Standardized input_file_patterns across all workflows
- Separated `recommended_inputs` (semantic WHAT) from `input_file_patterns` (file discovery WHERE)
- Removed duplication between recommended_inputs file paths and input_file_patterns
- Create-epics-and-stories now uses proper whole/sharded pattern like architecture workflow
- Solutioning-gate-check cleaned up to use semantic descriptions not file paths
## Files Changed (18)
- Core: workflow.xml (removed elicit-required tag and references)
- Audit workflow: Updated tag pattern scanner
- PRD workflow: Elicitation points, track migration, input discovery
- Create-epics-and-stories: Template rebuild, BDD format, elicitation, input patterns
- Tech-spec: Template rebuild, BDD format, input discovery
- UX Design: Input discovery streamlined
- Architecture: Elicitation at 5 key decision points, input discovery
- Gate-check: Input pattern cleanup, input discovery
## Impact
- More consistent elicitation across workflows
- Cleaner, more maintainable templates
- Better separation of concerns (templates vs instructions)
- Aligned with v6 3-track scale system
- Reduced bloat and duplication significantly
2025-11-04 00:09:19 -06:00
Does this capture your product vision?"</action>
<template-output>prd_summary</template-output>
<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>
<action>After PRD review and refinement complete:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
"Excellent! Now we need to break these requirements into implementable epics and stories.
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
For the epic breakdown, you have two options:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
1. Start a new session focused on epics (recommended for complex projects)
2. Continue here (I'll transform requirements into epics now)
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Which would you prefer?"
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
If new session:
"To start epic planning in a new session:
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
1. Save your work here
2. Start fresh and run: workflow epics-stories
3. It will load your PRD and create the epic breakdown
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
This keeps each session focused and manageable."
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
If continue:
"Let's continue with epic breakdown here..."
[Proceed with epics-stories subworkflow]
refactor: comprehensive workflow modernization and standardization
## Major Improvements
### 1. Elicitation System Modernization
- Removed legacy `<elicit-required />` tag from workflow.xml
- Replaced with direct `<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>` pattern
- More explicit, self-documenting, and eliminates indirection layer
- Added strategic elicitation points across all planning workflows:
- PRD: After success criteria, scope, functional requirements, and final review
- Create-Epics-And-Stories: After epic proposals and each epic's stories
- Architecture: After decisions, structure, patterns, implementation patterns, and final doc
- Updated audit-workflow tag scanner to remove obsolete elicit-required reference
### 2. Input Document Discovery Streamlined
- Replaced verbose 19-line "Input Document Discovery" sections with single critical tag
- New format: `<critical>Input documents specified in workflow.yaml input_file_patterns...</critical>`
- Eliminates duplication - workflow.yaml already defines patterns
- Updated across 6 workflows (PRD, create-epics-and-stories, architecture, tech-spec, UX, gate-check)
- Saved ~114 lines of repeated bloat
### 3. Scale System Migration (Levels 0-4 → 3 Tracks)
- Updated PRD workflow from "Level 0-4" to "Quick Flow / BMad Method / Enterprise Method"
- Changed `project_level` variable to `project_track`
- Removed `target_scale` variable (no longer needed)
- Updated workflow.yaml descriptions to reference tracks not levels
- Updated checklist from "Level 2" and "Level 3-4" to "BMad Method" and "Enterprise Method"
- Aligns with new scale-adaptive-system.md (3-track methodology)
### 4. Epic/Story Template Standardization
- Replaced hardcoded 8-epic template with clean repeating pattern using N/M variables
- Added BDD-style acceptance criteria (Given/When/Then/And)
- Removed instructional bloat from templates (moved to instructions.md where it belongs)
- Template shows OUTPUT structure, instructions show PROCESS
- Applied to both create-epics-and-stories and tech-spec workflows
- Templates now use HTML comments to indicate repeating sections
### 5. Workflow.yaml Pattern Consistency
- Standardized input_file_patterns across all workflows
- Separated `recommended_inputs` (semantic WHAT) from `input_file_patterns` (file discovery WHERE)
- Removed duplication between recommended_inputs file paths and input_file_patterns
- Create-epics-and-stories now uses proper whole/sharded pattern like architecture workflow
- Solutioning-gate-check cleaned up to use semantic descriptions not file paths
## Files Changed (18)
- Core: workflow.xml (removed elicit-required tag and references)
- Audit workflow: Updated tag pattern scanner
- PRD workflow: Elicitation points, track migration, input discovery
- Create-epics-and-stories: Template rebuild, BDD format, elicitation, input patterns
- Tech-spec: Template rebuild, BDD format, input discovery
- UX Design: Input discovery streamlined
- Architecture: Elicitation at 5 key decision points, input discovery
- Gate-check: Input pattern cleanup, input discovery
## Impact
- More consistent elicitation across workflows
- Cleaner, more maintainable templates
- Better separation of concerns (templates vs instructions)
- Aligned with v6 3-track scale system
- Reduced bloat and duplication significantly
2025-11-04 00:09:19 -06:00
Set project_track based on workflow status (BMad Method or Enterprise Method)
2025-11-01 19:37:20 -05:00
Generate epic_details for the epics breakdown document</action>
2025-10-14 19:58:44 -05:00
refactor: comprehensive workflow modernization and standardization
## Major Improvements
### 1. Elicitation System Modernization
- Removed legacy `<elicit-required />` tag from workflow.xml
- Replaced with direct `<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>` pattern
- More explicit, self-documenting, and eliminates indirection layer
- Added strategic elicitation points across all planning workflows:
- PRD: After success criteria, scope, functional requirements, and final review
- Create-Epics-And-Stories: After epic proposals and each epic's stories
- Architecture: After decisions, structure, patterns, implementation patterns, and final doc
- Updated audit-workflow tag scanner to remove obsolete elicit-required reference
### 2. Input Document Discovery Streamlined
- Replaced verbose 19-line "Input Document Discovery" sections with single critical tag
- New format: `<critical>Input documents specified in workflow.yaml input_file_patterns...</critical>`
- Eliminates duplication - workflow.yaml already defines patterns
- Updated across 6 workflows (PRD, create-epics-and-stories, architecture, tech-spec, UX, gate-check)
- Saved ~114 lines of repeated bloat
### 3. Scale System Migration (Levels 0-4 → 3 Tracks)
- Updated PRD workflow from "Level 0-4" to "Quick Flow / BMad Method / Enterprise Method"
- Changed `project_level` variable to `project_track`
- Removed `target_scale` variable (no longer needed)
- Updated workflow.yaml descriptions to reference tracks not levels
- Updated checklist from "Level 2" and "Level 3-4" to "BMad Method" and "Enterprise Method"
- Aligns with new scale-adaptive-system.md (3-track methodology)
### 4. Epic/Story Template Standardization
- Replaced hardcoded 8-epic template with clean repeating pattern using N/M variables
- Added BDD-style acceptance criteria (Given/When/Then/And)
- Removed instructional bloat from templates (moved to instructions.md where it belongs)
- Template shows OUTPUT structure, instructions show PROCESS
- Applied to both create-epics-and-stories and tech-spec workflows
- Templates now use HTML comments to indicate repeating sections
### 5. Workflow.yaml Pattern Consistency
- Standardized input_file_patterns across all workflows
- Separated `recommended_inputs` (semantic WHAT) from `input_file_patterns` (file discovery WHERE)
- Removed duplication between recommended_inputs file paths and input_file_patterns
- Create-epics-and-stories now uses proper whole/sharded pattern like architecture workflow
- Solutioning-gate-check cleaned up to use semantic descriptions not file paths
## Files Changed (18)
- Core: workflow.xml (removed elicit-required tag and references)
- Audit workflow: Updated tag pattern scanner
- PRD workflow: Elicitation points, track migration, input discovery
- Create-epics-and-stories: Template rebuild, BDD format, elicitation, input patterns
- Tech-spec: Template rebuild, BDD format, input discovery
- UX Design: Input discovery streamlined
- Architecture: Elicitation at 5 key decision points, input discovery
- Gate-check: Input pattern cleanup, input discovery
## Impact
- More consistent elicitation across workflows
- Cleaner, more maintainable templates
- Better separation of concerns (templates vs instructions)
- Aligned with v6 3-track scale system
- Reduced bloat and duplication significantly
2025-11-04 00:09:19 -06:00
<template-output>project_track</template-output>
2025-11-01 19:37:20 -05:00
<template-output>epic_details</template-output>
2025-10-15 21:17:09 -05:00
</step>
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
<step n="11" goal="Complete PRD and suggest next steps">
<template-output>product_magic_summary</template-output>
2025-10-17 16:44:06 -05:00
2025-10-30 08:13:18 -05:00
<check if="standalone_mode != true">
2025-11-01 19:37:20 -05:00
<action>Load the FULL file: {status_file}</action>
2025-10-30 08:13:18 -05:00
<action>Update workflow_status["prd"] = "{default_output_file}"</action>
2025-11-01 19:37:20 -05:00
<action>Save file, preserving ALL comments and structure</action>
2025-10-17 23:44:43 -05:00
</check>
2025-10-17 16:44:06 -05:00
2025-11-01 19:37:20 -05:00
<output>**✅ PRD Complete, {user_name}!**
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
Your product requirements are documented and ready for implementation.
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
**Created:**
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
- **PRD.md** - Complete requirements adapted to {project_type} and {domain}
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
**Next Steps:**
2025-10-15 23:10:33 -05:00
2025-11-01 19:37:20 -05:00
1. **Epic Breakdown ** (Required)
Run: `workflow create-epics-and-stories` to decompose requirements into implementable stories
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
2. **UX Design ** (If UI exists)
Run: `workflow ux-design` for detailed user experience design
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
3. **Architecture ** (Recommended)
Run: `workflow create-architecture` for technical architecture decisions
2025-10-14 19:58:44 -05:00
2025-11-01 19:37:20 -05:00
The magic of your product - {product_magic_summary} - is woven throughout the PRD and will guide all subsequent work.
</output>
2025-10-14 19:58:44 -05:00
</step>
</workflow>