pig/pig-farm-controller
1
0
Fork 0
Code Issues 11 Pull Requests Actions Packages Projects Releases Wiki Activity

bmad初始化

Browse Source
This commit is contained in:
huang
2025-11-01 19:22:39 +08:00
parent 5b21dc0bd5
commit 426ae41f54
447 changed files with 80633 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

146
bmad/bmm/workflows/4-implementation/create-story/README.md Normal file
View File

@@ -0,0 +1,146 @@
# Create Story Workflow
Just-in-time story generation creating one story at a time based on epic backlog state. Run by Scrum Master (SM) agent to ensure planned stories align with approved epics.
## Table of Contents
- [Usage](#usage)
- [Key Features](#key-features)
- [Inputs & Outputs](#inputs--outputs)
- [Workflow Behavior](#workflow-behavior)
- [Integration](#integration)
## Usage
```bash
# SM initiates next story creation
bmad sm *create-story
```
**When to run:**
- Sprint has capacity for new work
- Previous story is Done/Approved
- Team ready for next planned story
## Key Features
### Strict Planning Enforcement
- **Only creates stories enumerated in epics.md**
- Halts if story not found in epic plan
- Prevents scope creep through validation
### Intelligent Document Discovery
- Auto-finds tech spec: `tech-spec-epic-{N}-*.md`
- Discovers architecture docs across directories
- Builds prioritized requirement sources
### Source Document Grounding
- Every requirement traced to source
- No invention of domain facts
- Citations included in output
### Non-Interactive Mode
- Default "#yolo" mode minimizes prompts
- Smooth automated story preparation
- Only prompts when critical
## Inputs & Outputs
### Required Files
| File | Purpose | Priority |
| ------------------------ | ----------------------------- | -------- |
| epics.md | Story enumeration (MANDATORY) | Critical |
| tech-spec-epic-{N}-\*.md | Epic technical spec | High |
| PRD.md | Product requirements | Medium |
| Architecture docs | Technical constraints | Low |
### Auto-Discovered Docs
- `tech-stack.md`, `unified-project-structure.md`
- `testing-strategy.md`, `backend/frontend-architecture.md`
- `data-models.md`, `database-schema.md`, `api-specs.md`
### Output
**Story Document:** `{story_dir}/story-{epic}.{story}.md`
- User story statement (role, action, benefit)
- Acceptance criteria from tech spec/epics
- Tasks mapped to ACs
- Testing requirements
- Dev notes with sources
- Status: "Draft"
## Workflow Behavior
### Story Number Management
- Auto-detects next story number
- No duplicates or skipped numbers
- Maintains epic.story convention
### Update vs Create
- **If current story not Done:** Updates existing
- **If current story Done:** Creates next (if planned)
### Validation Safeguards
**No Story Found:**
```
"No planned next story found in epics.md for epic {N}.
Run *correct-course to add/modify epic stories."
```
**Missing Config:**
Ensure `dev_story_location` set in config.yaml
## Integration
### v6 Implementation Cycle
1. **create-story** ← Current step (defines "what")
2. story-context (adds technical "how")
3. dev-story (implementation)
4. code-review (validation)
5. correct-course (if needed)
6. retrospective (after epic)
### Document Priority
1. **tech_spec_file** - Epic-specific spec
2. **epics_file** - Story breakdown
3. **prd_file** - Business requirements
4. **architecture_docs** - Technical guidance
## Configuration
```yaml
# bmad/bmm/config.yaml
dev_story_location: ./stories
output_folder: ./output
# workflow.yaml defaults
non_interactive: true
auto_run_context: true
```
## Troubleshooting
| Issue | Solution |
| ----------------------- | ------------------------------------------ |
| "No planned next story" | Run `*correct-course` to add story to epic |
| Missing story_dir | Set `dev_story_location` in config |
| Tech spec not found | Use naming: `tech-spec-epic-{N}-*.md` |
| No architecture docs | Add docs to docs/ or output/ folder |
---
For workflow details, see [instructions.md](./instructions.md) and [checklist.md](./checklist.md).

240
bmad/bmm/workflows/4-implementation/create-story/checklist.md Normal file
View File

@@ -0,0 +1,240 @@
# Create Story Quality Validation Checklist
```xml
<critical>This validation runs in a FRESH CONTEXT by an independent validator agent</critical>
<critical>The validator audits story quality and offers to improve if issues are found</critical>
<critical>Load only the story file and necessary source documents - do NOT load workflow instructions</critical>
<validation-checklist>
<expectations>
**What create-story workflow should have accomplished:**
1. **Previous Story Continuity:** If a previous story exists (status: done/review/in-progress), current story should have "Learnings from Previous Story" subsection in Dev Notes that references: new files created, completion notes, architectural decisions, unresolved review items
2. **Source Document Coverage:** Story should cite tech spec (if exists), epics, PRD, and relevant architecture docs (architecture.md, testing-strategy.md, coding-standards.md, unified-project-structure.md)
3. **Requirements Traceability:** ACs sourced from tech spec (preferred) or epics, not invented
4. **Dev Notes Quality:** Specific guidance with citations, not generic advice
5. **Task-AC Mapping:** Every AC has tasks, every task references AC, testing subtasks present
6. **Structure:** Status="drafted", proper story statement, Dev Agent Record sections initialized
</expectations>
## Validation Steps
### 1. Load Story and Extract Metadata
- [ ] Load story file: {{story_file_path}}
- [ ] Parse sections: Status, Story, ACs, Tasks, Dev Notes, Dev Agent Record, Change Log
- [ ] Extract: epic_num, story_num, story_key, story_title
- [ ] Initialize issue tracker (Critical/Major/Minor)
### 2. Previous Story Continuity Check
**Find previous story:**
- [ ] Load {output_folder}/sprint-status.yaml
- [ ] Find current {{story_key}} in development_status
- [ ] Identify story entry immediately above (previous story)
- [ ] Check previous story status
**If previous story status is done/review/in-progress:**
- [ ] Load previous story file: {story_dir}/{{previous_story_key}}.md
- [ ] Extract: Dev Agent Record (Completion Notes, File List with NEW/MODIFIED)
- [ ] Extract: Senior Developer Review section if present
- [ ] Count unchecked [ ] items in Review Action Items
- [ ] Count unchecked [ ] items in Review Follow-ups (AI)
**Validate current story captured continuity:**
- [ ] Check: "Learnings from Previous Story" subsection exists in Dev Notes
- If MISSING and previous story has content → **CRITICAL ISSUE**
- [ ] If subsection exists, verify it includes:
- [ ] References to NEW files from previous story → If missing → **MAJOR ISSUE**
- [ ] Mentions completion notes/warnings → If missing → **MAJOR ISSUE**
- [ ] Calls out unresolved review items (if any exist) → If missing → **CRITICAL ISSUE**
- [ ] Cites previous story: [Source: stories/{{previous_story_key}}.md]
**If previous story status is backlog/drafted:**
- [ ] No continuity expected (note this)
**If no previous story exists:**
- [ ] First story in epic, no continuity expected
### 3. Source Document Coverage Check
**Build available docs list:**
- [ ] Check exists: tech-spec-epic-{{epic_num}}*.md in {tech_spec_search_dir}
- [ ] Check exists: {output_folder}/epics.md
- [ ] Check exists: {output_folder}/PRD.md
- [ ] Check exists in {output_folder}/ or {project-root}/docs/:
- architecture.md, testing-strategy.md, coding-standards.md
- unified-project-structure.md, tech-stack.md
- backend-architecture.md, frontend-architecture.md, data-models.md
**Validate story references available docs:**
- [ ] Extract all [Source: ...] citations from story Dev Notes
- [ ] Tech spec exists but not cited → **CRITICAL ISSUE**
- [ ] Epics exists but not cited → **CRITICAL ISSUE**
- [ ] Architecture.md exists → Read for relevance → If relevant but not cited → **MAJOR ISSUE**
- [ ] Testing-strategy.md exists → Check Dev Notes mentions testing standards → If not → **MAJOR ISSUE**
- [ ] Testing-strategy.md exists → Check Tasks have testing subtasks → If not → **MAJOR ISSUE**
- [ ] Coding-standards.md exists → Check Dev Notes references standards → If not → **MAJOR ISSUE**
- [ ] Unified-project-structure.md exists → Check Dev Notes has "Project Structure Notes" subsection → If not → **MAJOR ISSUE**
**Validate citation quality:**
- [ ] Verify cited file paths are correct and files exist → Bad citations → **MAJOR ISSUE**
- [ ] Check citations include section names, not just file paths → Vague citations → **MINOR ISSUE**
### 4. Acceptance Criteria Quality Check
- [ ] Extract Acceptance Criteria from story
- [ ] Count ACs: {{ac_count}} (if 0 → **CRITICAL ISSUE** and halt)
- [ ] Check story indicates AC source (tech spec, epics, PRD)
**If tech spec exists:**
- [ ] Load tech spec
- [ ] Search for this story number
- [ ] Extract tech spec ACs for this story
- [ ] Compare story ACs vs tech spec ACs → If mismatch → **MAJOR ISSUE**
**If no tech spec but epics.md exists:**
- [ ] Load epics.md
- [ ] Search for Epic {{epic_num}}, Story {{story_num}}
- [ ] Story not found in epics → **CRITICAL ISSUE** (should have halted)
- [ ] Extract epics ACs
- [ ] Compare story ACs vs epics ACs → If mismatch without justification → **MAJOR ISSUE**
**Validate AC quality:**
- [ ] Each AC is testable (measurable outcome)
- [ ] Each AC is specific (not vague)
- [ ] Each AC is atomic (single concern)
- [ ] Vague ACs found → **MINOR ISSUE**
### 5. Task-AC Mapping Check
- [ ] Extract Tasks/Subtasks from story
- [ ] For each AC: Search tasks for "(AC: #{{ac_num}})" reference
- [ ] AC has no tasks → **MAJOR ISSUE**
- [ ] For each task: Check if references an AC number
- [ ] Tasks without AC refs (and not testing/setup) → **MINOR ISSUE**
- [ ] Count tasks with testing subtasks
- [ ] Testing subtasks < ac_count → **MAJOR ISSUE**
### 6. Dev Notes Quality Check
**Check required subsections exist:**
- [ ] Architecture patterns and constraints
- [ ] References (with citations)
- [ ] Project Structure Notes (if unified-project-structure.md exists)
- [ ] Learnings from Previous Story (if previous story has content)
- [ ] Missing required subsections → **MAJOR ISSUE**
**Validate content quality:**
- [ ] Architecture guidance is specific (not generic "follow architecture docs") → If generic → **MAJOR ISSUE**
- [ ] Count citations in References subsection
- [ ] No citations → **MAJOR ISSUE**
- [ ] < 3 citations and multiple arch docs exist → **MINOR ISSUE**
- [ ] Scan for suspicious specifics without citations:
- API endpoints, schema details, business rules, tech choices
- [ ] Likely invented details found → **MAJOR ISSUE**
### 7. Story Structure Check
- [ ] Status = "drafted" → If not → **MAJOR ISSUE**
- [ ] Story section has "As a / I want / so that" format → If malformed → **MAJOR ISSUE**
- [ ] Dev Agent Record has required sections:
- Context Reference, Agent Model Used, Debug Log References, Completion Notes List, File List
- [ ] Missing sections → **MAJOR ISSUE**
- [ ] Change Log initialized → If missing → **MINOR ISSUE**
- [ ] File in correct location: {story_dir}/{{story_key}}.md → If not → **MAJOR ISSUE**
### 8. Unresolved Review Items Alert
**CRITICAL CHECK for incomplete review items from previous story:**
- [ ] If previous story has "Senior Developer Review (AI)" section:
- [ ] Count unchecked [ ] items in "Action Items"
- [ ] Count unchecked [ ] items in "Review Follow-ups (AI)"
- [ ] If unchecked items > 0:
- [ ] Check current story "Learnings from Previous Story" mentions these
- [ ] If NOT mentioned → **CRITICAL ISSUE** with details:
- List all unchecked items with severity
- Note: "These may represent epic-wide concerns"
- Required: Add to Learnings section with note about pending items
## Validation Report Generation
**Calculate severity counts:**
- Critical: {{critical_count}}
- Major: {{major_count}}
- Minor: {{minor_count}}
**Determine outcome:**
- Critical > 0 OR Major > 3 → **FAIL**
- Major ≤ 3 and Critical = 0 → **PASS with issues**
- All = 0 → **PASS**
**Generate report:**
```
# Story Quality Validation Report
Story: {{story_key}} - {{story_title}}
Outcome: {{outcome}} (Critical: {{critical_count}}, Major: {{major_count}}, Minor: {{minor_count}})
## Critical Issues (Blockers)
{{list_each_with_description_and_evidence}}
## Major Issues (Should Fix)
{{list_each_with_description_and_evidence}}
## Minor Issues (Nice to Have)
{{list_each_with_description}}
## Successes
{{list_what_was_done_well}}
```
## User Alert and Remediation
**If FAIL:**
- Show issues summary and top 3 issues
- Offer options: (1) Auto-improve story, (2) Show detailed findings, (3) Fix manually, (4) Accept as-is
- If option 1: Re-load source docs, regenerate affected sections, re-run validation
**If PASS with issues:**
- Show issues list
- Ask: "Improve story? (y/n)"
- If yes: Enhance story with missing items
**If PASS:**
- Confirm: All quality standards met
- List successes
- Ready for story-context generation
</validation-checklist>
```
## Quick Reference
**Validation runs in fresh context and checks:**
1. ✅ Previous story continuity captured (files, notes, **unresolved review items**)
2. ✅ All relevant source docs discovered and cited
3. ✅ ACs match tech spec/epics exactly
4. ✅ Tasks cover all ACs with testing
5. ✅ Dev Notes have specific guidance with citations (not generic)
6. ✅ Structure and metadata complete
**Severity Levels:**
- **CRITICAL** = Missing previous story reference, missing tech spec cite, unresolved review items not called out, story not in epics
- **MAJOR** = Missing arch docs, missing files from previous story, vague Dev Notes, ACs don't match source, no testing subtasks
- **MINOR** = Vague citations, orphan tasks, missing Change Log
**Outcome Triggers:**
- **FAIL** = Any critical OR >3 major issues
- **PASS with issues** = ≤3 major issues, no critical
- **PASS** = All checks passed

254
bmad/bmm/workflows/4-implementation/create-story/instructions.md Normal file
View File

@@ -0,0 +1,254 @@
# Create Story - Workflow Instructions (Spec-compliant, non-interactive by default)
````xml
<critical>The workflow execution engine is governed by: {project_root}/bmad/core/tasks/workflow.xml</critical>
<critical>You MUST have already loaded and processed: {installed_path}/workflow.yaml</critical>
<critical>Generate all documents in {document_output_language}</critical>
<critical>This workflow creates or updates the next user story from epics/PRD and architecture context, saving to the configured stories directory and optionally invoking Story Context.</critical>
<critical>DOCUMENT OUTPUT: Concise, technical, actionable story specifications. Use tables/lists for acceptance criteria and tasks.</critical>
<workflow>
<step n="1" goal="Load config and initialize">
<action>Resolve variables from config_source: story_dir (dev_story_location), output_folder, user_name, communication_language. If story_dir missing and {{non_interactive}} == false → ASK user to provide a stories directory and update variable. If {{non_interactive}} == true and missing, HALT with a clear message.</action>
<action>Create {{story_dir}} if it does not exist</action>
<action>Resolve installed component paths from workflow.yaml: template, instructions, validation</action>
<action>Resolve recommended inputs if present: epics_file, prd_file, architecture_file</action>
</step>
<step n="2" goal="Discover and load source documents">
<critical>PREVIOUS STORY CONTINUITY: Essential for maintaining context and learning from prior development</critical>
<action>Find the previous completed story to extract dev agent learnings and review findings:
1. Load {{output_folder}}/sprint-status.yaml COMPLETELY
2. Find current {{story_key}} in development_status section
3. Identify the story entry IMMEDIATELY ABOVE current story (previous row in file order)
4. If previous story exists:
- Extract {{previous_story_key}}
- Check previous story status (done, in-progress, review, etc.)
- If status is "done", "review", or "in-progress" (has some completion):
* Construct path: {{story_dir}}/{{previous_story_key}}.md
* Load the COMPLETE previous story file
* Parse ALL sections comprehensively:
A) Dev Agent Record → Completion Notes List:
- New patterns/services created (to reuse, not recreate)
- Architectural deviations or decisions made
- Technical debt deferred to future stories
- Warnings or recommendations for next story
- Interfaces/methods created for reuse
B) Dev Agent Record → Debug Log References:
- Issues encountered and solutions
- Gotchas or unexpected challenges
- Workarounds applied
C) Dev Agent Record → File List:
- Files created (NEW) - understand new capabilities
- Files modified (MODIFIED) - track evolving components
- Files deleted (DELETED) - removed functionality
D) Dev Notes:
- Any "future story" notes or TODOs
- Patterns established
- Constraints discovered
E) Senior Developer Review (AI) section (if present):
- Review outcome (Approve/Changes Requested/Blocked)
- Unresolved action items (unchecked [ ] items)
- Key findings that might affect this story
- Architectural concerns raised
F) Senior Developer Review → Action Items (if present):
- Check for unchecked [ ] items still pending
- Note any systemic issues that apply to multiple stories
G) Review Follow-ups (AI) tasks (if present):
- Check for unchecked [ ] review tasks still pending
- Determine if they're epic-wide concerns
H) Story Status:
- If "review" or "in-progress" - incomplete, note what's pending
- If "done" - confirmed complete
* Store ALL findings as {{previous_story_learnings}} with structure:
- new_files: [list]
- modified_files: [list]
- new_services: [list with descriptions]
- architectural_decisions: [list]
- technical_debt: [list]
- warnings_for_next: [list]
- review_findings: [list if review exists]
- pending_items: [list of unchecked action items]
- If status is "backlog" or "drafted":
* Set {{previous_story_learnings}} = "Previous story not yet implemented"
5. If no previous story exists (first story in epic):
- Set {{previous_story_learnings}} = "First story in epic - no predecessor context"
</action>
<action>If {{tech_spec_file}} empty: derive from {{tech_spec_glob_template}} with {{epic_num}} and search {{tech_spec_search_dir}} recursively. If multiple, pick most recent by modified time.</action>
<action>Build a prioritized document set for this epic:
1) tech_spec_file (epic-scoped)
2) epics_file (acceptance criteria and breakdown)
3) prd_file (business requirements and constraints)
4) architecture_file (architecture constraints)
5) Architecture docs under docs/ and output_folder/: tech-stack.md, unified-project-structure.md, coding-standards.md, testing-strategy.md, backend-architecture.md, frontend-architecture.md, data-models.md, database-schema.md, rest-api-spec.md, external-apis.md (include if present)
</action>
<action>READ COMPLETE FILES for all items found in the prioritized set. Store content and paths for citation.</action>
</step>
<step n="3" goal="Find next backlog story to draft" tag="sprint-status">
<critical>MUST read COMPLETE sprint-status.yaml file from start to end to preserve order</critical>
<action>Load the FULL file: {{output_folder}}/sprint-status.yaml</action>
<action>Read ALL lines from beginning to end - do not skip any content</action>
<action>Parse the development_status section completely to understand story order</action>
<action>Find the FIRST story (by reading in order from top to bottom) where:
- Key matches pattern: number-number-name (e.g., "1-2-user-auth")
- NOT an epic key (epic-X) or retrospective (epic-X-retrospective)
- Status value equals "backlog"
</action>
<check if="no backlog story found">
<output>📋 No backlog stories found in sprint-status.yaml
All stories are either already drafted or completed.
**Options:**
1. Run sprint-planning to refresh story tracking
2. Load PM agent and run correct-course to add more stories
3. Check if current sprint is complete
</output>
<action>HALT</action>
</check>
<action>Extract from found story key (e.g., "1-2-user-authentication"):
- epic_num: first number before dash (e.g., "1")
- story_num: second number after first dash (e.g., "2")
- story_title: remainder after second dash (e.g., "user-authentication")
</action>
<action>Set {{story_id}} = "{{epic_num}}.{{story_num}}"</action>
<action>Store story_key for later use (e.g., "1-2-user-authentication")</action>
<action>Verify story is enumerated in {{epics_file}}. If not found, HALT with message:</action>
<action>"Story {{story_key}} not found in epics.md. Please load PM agent and run correct-course to sync epics, then rerun create-story."</action>
<action>Check if story file already exists at expected path in {{story_dir}}</action>
<check if="story file exists">
<output>ℹ️ Story file already exists: {{story_file_path}}
Will update existing story file rather than creating new one.
</output>
<action>Set update_mode = true</action>
</check>
</step>
<step n="4" goal="Extract requirements and derive story statement">
<action>From tech_spec_file (preferred) or epics_file: extract epic {{epic_num}} title/summary, acceptance criteria for the next story, and any component references. If not present, fall back to PRD sections mapping to this epic/story.</action>
<action>From architecture and architecture docs: extract constraints, patterns, component boundaries, and testing guidance relevant to the extracted ACs. ONLY capture information that directly informs implementation of this story.</action>
<action>Derive a clear user story statement (role, action, benefit) grounded strictly in the above sources. If ambiguous and {{non_interactive}} == false → ASK user to clarify. If {{non_interactive}} == true → generate the best grounded statement WITHOUT inventing domain facts.</action>
<template-output file="{default_output_file}">requirements_context_summary</template-output>
</step>
<step n="5" goal="Project structure alignment and lessons learned">
<action>Review {{previous_story_learnings}} and extract actionable intelligence:
- New patterns/services created → Note for reuse (DO NOT recreate)
- Architectural deviations → Understand and maintain consistency
- Technical debt items → Assess if this story should address them
- Files modified → Understand current state of evolving components
- Warnings/recommendations → Apply to this story's approach
- Review findings → Learn from issues found in previous story
- Pending action items → Determine if epic-wide concerns affect this story
</action>
<action>If unified-project-structure.md present: align expected file paths, module names, and component locations; note any potential conflicts.</action>
<action>Cross-reference {{previous_story_learnings}}.new_files with project structure to understand where new capabilities are located.</action>
<template-output file="{default_output_file}">structure_alignment_summary</template-output>
</step>
<step n="6" goal="Assemble acceptance criteria and tasks">
<action>Assemble acceptance criteria list from tech_spec or epics. If gaps exist, derive minimal, testable criteria from PRD verbatim phrasing (NO invention).</action>
<action>Create tasks/subtasks directly mapped to ACs. Include explicit testing subtasks per testing-strategy and existing tests framework. Cite architecture/source documents for any technical mandates.</action>
<template-output file="{default_output_file}">acceptance_criteria</template-output>
<template-output file="{default_output_file}">tasks_subtasks</template-output>
</step>
<step n="7" goal="Create or update story document">
<action>Resolve output path: {default_output_file} using current {{epic_num}} and {{story_num}}. If targeting an existing story for update, use its path.</action>
<action>Initialize from template.md if creating a new file; otherwise load existing file for edit.</action>
<action>Compute a concise story_title from epic/story context; if missing, synthesize from PRD feature name and epic number.</action>
<template-output file="{default_output_file}">story_header</template-output>
<template-output file="{default_output_file}">story_body</template-output>
<template-output file="{default_output_file}">dev_notes_with_citations</template-output>
<action>If {{previous_story_learnings}} contains actionable items (not "First story" or "not yet implemented"):
- Add "Learnings from Previous Story" subsection to Dev Notes
- Include relevant completion notes, new files/patterns, deviations
- Cite previous story file as reference [Source: stories/{{previous_story_key}}.md]
- Highlight interfaces/services to REUSE (not recreate)
- Note any technical debt to address in this story
- List pending review items that affect this story (if any)
- Reference specific files created: "Use {{file_path}} for {{purpose}}"
- Format example:
```
### Learnings from Previous Story
**From Story {{previous_story_key}} (Status: {{previous_status}})**
- **New Service Created**: `AuthService` base class available at `src/services/AuthService.js` - use `AuthService.register()` method
- **Architectural Change**: Switched from session-based to JWT authentication
- **Schema Changes**: User model now includes `passwordHash` field, migration applied
- **Technical Debt**: Email verification skipped, should be included in this or subsequent story
- **Testing Setup**: Auth test suite initialized at `tests/integration/auth.test.js` - follow patterns established there
- **Pending Review Items**: Rate limiting mentioned in review - consider for this story
[Source: stories/{{previous_story_key}}.md#Dev-Agent-Record]
```
</action>
<template-output file="{default_output_file}">change_log</template-output>
</step>
<step n="8" goal="Validate, save, and mark story drafted" tag="sprint-status">
<invoke-task>Validate against checklist at {installed_path}/checklist.md using bmad/core/tasks/validate-workflow.xml</invoke-task>
<action>Save document unconditionally (non-interactive default). In interactive mode, allow user confirmation.</action>
<!-- Mark story as drafted in sprint status -->
<action>Update {{output_folder}}/sprint-status.yaml</action>
<action>Load the FULL file and read all development_status entries</action>
<action>Find development_status key matching {{story_key}}</action>
<action>Verify current status is "backlog" (expected previous state)</action>
<action>Update development_status[{{story_key}}] = "drafted"</action>
<action>Save file, preserving ALL comments and structure including STATUS DEFINITIONS</action>
<check if="story key not found in file">
<output>⚠️ Could not update story status: {{story_key}} not found in sprint-status.yaml
Story file was created successfully, but sprint-status.yaml was not updated.
You may need to run sprint-planning to refresh tracking, or manually set the story row status to `drafted`.
</output>
</check>
<action>Report created/updated story path</action>
<output>**✅ Story Created Successfully, {user_name}!**
**Story Details:**
- Story ID: {{story_id}}
- Story Key: {{story_key}}
- File: {{story_file}}
- Status: drafted (was backlog)
**⚠️ Important:** The following workflows are context-intensive. It's recommended to clear context and restart the SM agent before running the next command.
**Next Steps:**
1. Review the drafted story in {{story_file}}
2. **[RECOMMENDED]** Run `story-context` to generate technical context XML and mark story ready for development (combines context + ready in one step)
3. Or run `story-ready` to manually mark the story ready without generating technical context
</output>
</step>
</workflow>
````

51
bmad/bmm/workflows/4-implementation/create-story/template.md Normal file
View File

@@ -0,0 +1,51 @@
# Story {{epic_num}}.{{story_num}}: {{story_title}}
Status: drafted
## Story
As a {{role}},
I want {{action}},
so that {{benefit}}.
## Acceptance Criteria
1. [Add acceptance criteria from epics/PRD]
## Tasks / Subtasks
- [ ] Task 1 (AC: #)
- [ ] Subtask 1.1
- [ ] Task 2 (AC: #)
- [ ] Subtask 2.1
## Dev Notes
- Relevant architecture patterns and constraints
- Source tree components to touch
- Testing standards summary
### Project Structure Notes
- Alignment with unified project structure (paths, modules, naming)
- Detected conflicts or variances (with rationale)
### References
- Cite all technical details with source paths and sections, e.g. [Source: docs/<file>.md#Section]
## Dev Agent Record
### Context Reference
<!-- Path(s) to story context XML will be added here by context workflow -->
### Agent Model Used
{{agent_model_name_version}}
### Debug Log References
### Completion Notes List
### File List

47
bmad/bmm/workflows/4-implementation/create-story/workflow.yaml Normal file
View File

@@ -0,0 +1,47 @@
name: create-story
description: "Create the next user story markdown from epics/PRD and architecture, using a standard template and saving to the stories folder"
author: "BMad"
# Critical variables from config
config_source: "{project-root}/bmad/bmm/config.yaml"
output_folder: "{config_source}:output_folder"
user_name: "{config_source}:user_name"
communication_language: "{config_source}:communication_language"
date: system-generated
# Workflow components
installed_path: "{project-root}/bmad/bmm/workflows/4-implementation/create-story"
template: "{installed_path}/template.md"
instructions: "{installed_path}/instructions.md"
validation: "{installed_path}/checklist.md"
# Variables and inputs
variables:
story_dir: "{config_source}:dev_story_location" # Directory where stories are stored
epics_file: "{output_folder}/epics.md" # Preferred source for epic/story breakdown
prd_file: "{output_folder}/PRD.md" # Fallback for requirements
architecture_file: "{output_folder}/architecture.md" # Optional architecture context
tech_spec_file: "" # Will be auto-discovered from docs as tech-spec-epic-{{epic_num}}-*.md
tech_spec_search_dir: "{project-root}/docs"
tech_spec_glob_template: "tech-spec-epic-{{epic_num}}*.md"
arch_docs_search_dirs: |
- "{project-root}/docs"
- "{output_folder}"
arch_docs_file_names: |
- architecture.md
- infrastructure-architecture.md
story_title: "" # Will be elicited if not derivable
epic_num: 1
story_num: 1
non_interactive: true # Generate without elicitation; avoid interactive prompts
# Output configuration
# Uses story_key from sprint-status.yaml (e.g., "1-2-user-authentication")
default_output_file: "{story_dir}/{{story_key}}.md"
recommended_inputs:
- epics: "Epic breakdown (epics.md)"
- prd: "PRD document"
- architecture: "Architecture (optional)"
standalone: true