ros/BMAD-METHOD
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: WIP create-docv2

Browse Source
This commit is contained in:
Brian Madison
2025-07-06 00:10:00 -05:00
parent be9453f234
commit c107af0598
16 changed files with 4064 additions and 1916 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
bmad-core/agents/bmad-master.md
View File

@@ -38,6 +38,7 @@ commands:
- task {task}: Execute task, if not found or none specified, ONLY list available dependencies/tasks listed below
- list {task|template|util|checklist|workflow}: List resources by type ONLY from the corresponding dependencies sub item below
- create-doc {template}: execute task create-doc (no template = ONLY show available templates listed under dependencies/templates below)
- create-prd: Execute task create-doc2 with prd-tmpl2 template (new front matter-driven PRD creation)
- execute-checklist {checklist}: Run task execute-checklist (no checklist = ONLY show available checklists listed under dependencies/checklist below)
- shard-doc {document} {destination}: run the task shard-doc against the optionally provided document to the specified destination
- plan: Execute the task Create workflow plan
@@ -65,6 +66,7 @@ dependencies:
- correct-course
- create-deep-research-prompt
- create-doc
- create-doc2
- create-workflow-plan
- document-project
- create-next-story
@@ -83,6 +85,7 @@ dependencies:
- fullstack-architecture-tmpl
- market-research-tmpl
- prd-tmpl
- prd-tmpl2
- project-brief-tmpl
- story-tmpl
data:

85
bmad-core/data/bmad-kb.md
View File

@@ -33,13 +33,15 @@ BMad transforms you into a "Vibe CEO" - directing a team of specialized AI agent
### The Two-Phase Approach
**Phase 1: Planning (Web UI - Cost Effective)**
#### Phase 1: Planning (Web UI - Cost Effective)
- Use large context windows (Gemini's 1M tokens)
- Generate comprehensive documents (PRD, Architecture)
- Leverage multiple agents for brainstorming
- Create once, use throughout development
**Phase 2: Development (IDE - Implementation)**
#### Phase 2: Development (IDE - Implementation)
- Shard documents into manageable pieces
- Execute focused SM → Dev cycles
- One story at a time, sequential progress
@@ -69,6 +71,7 @@ BMad transforms you into a "Vibe CEO" - directing a team of specialized AI agent
### Quick Start Options
#### Option 1: Web UI
**Best for**: ChatGPT, Claude, Gemini users who want to start immediately
1. Navigate to `dist/teams/`
@@ -78,6 +81,7 @@ BMad transforms you into a "Vibe CEO" - directing a team of specialized AI agent
5. Type `/help` to see available commands
#### Option 2: IDE Integration
**Best for**: Cursor, Claude Code, Windsurf, Trae, Cline, Roo Code, Github Copilot users
```bash
@@ -86,6 +90,7 @@ npx bmad-method install
```
**Installation Steps**:
- Choose "Complete installation"
- Select your IDE from supported options:
- **Cursor**: Native AI integration
@@ -99,6 +104,7 @@ npx bmad-method install
**Note for VS Code Users**: BMad-Method assumes when you mention "VS Code" that you're using it with an AI-powered extension like GitHub Copilot, Cline, or Roo. Standard VS Code without AI capabilities cannot run BMad agents. The installer includes built-in support for Cline and Roo.
**Verify Installation**:
- `.bmad-core/` folder created with all agents
- IDE-specific integration files created
- All agent commands/rules/modes available
@@ -108,12 +114,14 @@ npx bmad-method install
### Environment Selection Guide
**Use Web UI for**:
- Initial planning and documentation (PRD, architecture)
- Cost-effective document creation (especially with Gemini)
- Brainstorming and analysis phases
- Multi-agent consultation and planning
**Use IDE for**:
- Active development and coding
- File operations and project integration
- Document sharding and story management
@@ -126,35 +134,41 @@ npx bmad-method install
**Can you do everything in IDE?** Yes, but understand the tradeoffs:
**Pros of IDE-Only**:
- Single environment workflow
- Direct file operations from start
- No copy/paste between environments
- Immediate project integration
**Cons of IDE-Only**:
- Higher token costs for large document creation
- Smaller context windows (varies by IDE/model)
- May hit limits during planning phases
- Less cost-effective for brainstorming
**Using Web Agents in IDE**:
- **NOT RECOMMENDED**: Web agents (PM, Architect) have rich dependencies designed for large contexts
- **Why it matters**: Dev agents are kept lean to maximize coding context
- **The principle**: "Dev agents code, planning agents plan" - mixing breaks this optimization
**About bmad-master and bmad-orchestrator**:
- **bmad-master**: CAN do any task without switching agents, BUT...
- **Still use specialized agents for planning**: PM, Architect, and UX Expert have tuned personas that produce better results
- **Why specialization matters**: Each agent's personality and focus creates higher quality outputs
- **If using bmad-master/orchestrator**: Fine for planning phases, but...
**CRITICAL RULE for Development**:
- **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator
- **ALWAYS use Dev agent for implementation** - Never use bmad-master/orchestrator
- **Why this matters**: SM and Dev agents are specifically optimized for the development workflow
- **No exceptions**: Even if using bmad-master for everything else, switch to SM → Dev for implementation
**Best Practice for IDE-Only**:
1. Use PM/Architect/UX agents for planning (better than bmad-master)
2. Create documents directly in project
3. Shard immediately after creation
@@ -178,17 +192,20 @@ This configuration file acts as a map for BMad agents, telling them exactly wher
### Key Configuration Areas
#### PRD Configuration
- **prdVersion**: Tells agents if PRD follows v3 or v4 conventions
- **prdSharded**: Whether epics are embedded (false) or in separate files (true)
- **prdShardedLocation**: Where to find sharded epic files
- **epicFilePattern**: Pattern for epic filenames (e.g., `epic-{n}*.md`)
#### Architecture Configuration
- **architectureVersion**: v3 (monolithic) or v4 (sharded)
- **architectureSharded**: Whether architecture is split into components
- **architectureShardedLocation**: Where sharded architecture files live
#### Developer Files
- **devLoadAlwaysFiles**: List of files the dev agent loads for every task
- **devDebugLog**: Where dev agent logs repeated failures
- **agentCoreDump**: Export location for chat conversations
@@ -203,6 +220,7 @@ This configuration file acts as a map for BMad agents, telling them exactly wher
### Common Configurations
**Legacy V3 Project**:
```yaml
prdVersion: v3
prdSharded: false
@@ -211,6 +229,7 @@ architectureSharded: false
```
**V4 Optimized Project**:
```yaml
prdVersion: v4
prdSharded: true
@@ -276,6 +295,7 @@ You are the "Vibe CEO" - thinking like a CEO with unlimited resources and a sing
#### IDE-Specific Syntax
**Agent Loading by IDE**:
- **Claude Code**: `/agent-name` (e.g., `/bmad-master`)
- **Cursor**: `@agent-name` (e.g., `@bmad-master`)
- **Windsurf**: `@agent-name` (e.g., `@bmad-master`)
@@ -284,10 +304,12 @@ You are the "Vibe CEO" - thinking like a CEO with unlimited resources and a sing
- **Github Copilot**: Open the Chat view (`⌃⌘I` on Mac, `Ctrl+Alt+I` on Windows/Linux) and select **Agent** from the chat mode selector.
**Chat Management Guidelines**:
- **Claude Code, Cursor, Windsurf, Trae**: Start new chats when switching agents
- **Roo Code**: Switch modes within the same conversation
**Common Task Commands**:
- `*help` - Show available commands
- `*status` - Show current context/progress
- `*exit` - Exit the agent mode
@@ -296,6 +318,7 @@ You are the "Vibe CEO" - thinking like a CEO with unlimited resources and a sing
- `*create` - Run create-next-story task (SM agent)
**In Web UI**:
```text
/pm create-doc prd
/architect review system design
@@ -309,16 +332,19 @@ You are the "Vibe CEO" - thinking like a CEO with unlimited resources and a sing
### Pre-Built Teams
#### Team All
- **Includes**: All 10 agents + orchestrator
- **Use Case**: Complete projects requiring all roles
- **Bundle**: `team-all.txt`
#### Team Fullstack
- **Includes**: PM, Architect, Developer, QA, UX Expert
- **Use Case**: End-to-end web/mobile development
- **Bundle**: `team-fullstack.txt`
#### Team No-UI
- **Includes**: PM, Architect, Developer, QA (no UX Expert)
- **Use Case**: Backend services, APIs, system development
- **Bundle**: `team-no-ui.txt`
@@ -332,22 +358,26 @@ The BMad-Method is built around a modular architecture centered on the `bmad-cor
### Key Architectural Components
#### 1. Agents (`bmad-core/agents/`)
- **Purpose**: Each markdown file defines a specialized AI agent for a specific Agile role (PM, Dev, Architect, etc.)
- **Structure**: Contains YAML headers specifying the agent's persona, capabilities, and dependencies
- **Dependencies**: Lists of tasks, templates, checklists, and data files the agent can use
- **Startup Instructions**: Can load project-specific documentation for immediate context
#### 2. Agent Teams (`bmad-core/agent-teams/`)
- **Purpose**: Define collections of agents bundled together for specific purposes
- **Examples**: `team-all.yaml` (comprehensive bundle), `team-fullstack.yaml` (full-stack development)
- **Usage**: Creates pre-packaged contexts for web UI environments
#### 3. Workflows (`bmad-core/workflows/`)
- **Purpose**: YAML files defining prescribed sequences of steps for specific project types
- **Types**: Greenfield (new projects) and Brownfield (existing projects) for UI, service, and fullstack development
- **Structure**: Defines agent interactions, artifacts created, and transition conditions
#### 4. Reusable Resources
- **Templates** (`bmad-core/templates/`): Markdown templates for PRDs, architecture specs, user stories
- **Tasks** (`bmad-core/tasks/`): Instructions for specific repeatable actions like "shard-doc" or "create-next-story"
- **Checklists** (`bmad-core/checklists/`): Quality assurance checklists for validation and review
@@ -387,6 +417,7 @@ BMad employs a sophisticated template system with three key components:
### Technical Preferences Integration
The `technical-preferences.md` file serves as a persistent technical profile that:
- Ensures consistency across all agents and projects
- Eliminates repetitive technology specification
- Provides personalized recommendations aligned with user preferences
@@ -395,6 +426,7 @@ The `technical-preferences.md` file serves as a persistent technical profile tha
### Build and Delivery Process
The `web-builder.js` tool creates web-ready bundles by:
1. Reading agent or team definition files
2. Recursively resolving all dependencies
3. Concatenating content into single text files with clear separators
@@ -409,11 +441,13 @@ This architecture enables seamless operation across environments while maintaini
**Ideal for cost efficiency with Gemini's massive context:**
**For Brownfield Projects - Start Here!**:
1. **Upload entire project to Gemini Web** (GitHub URL, files, or zip)
2. **Document existing system**: `/analyst` → `*document-project`
3. **Creates comprehensive docs** from entire codebase analysis
**For All Projects**:
1. **Optional Analysis**: `/analyst` - Market research, competitive analysis
2. **Project Brief**: Create foundation document (Analyst or user)
3. **PRD Creation**: `/pm create-doc prd` - Comprehensive product requirements
@@ -424,12 +458,14 @@ This architecture enables seamless operation across environments while maintaini
#### Example Planning Prompts
**For PRD Creation**:
```text
"I want to build a [type] application that [core purpose].
Help me brainstorm features and create a comprehensive PRD."
```
**For Architecture Design**:
```text
"Based on this PRD, design a scalable technical architecture
that can handle [specific requirements]."
@@ -447,7 +483,7 @@ that can handle [specific requirements]."
**Prerequisites**: Planning documents must exist in `docs/` folder
1. **Document Sharding** (CRITICAL STEP):
1. **Document Sharding** (CRITICAL STEP):
- Documents created by PM/Architect (in Web or IDE) MUST be sharded for development
- Two methods to shard:
a) **Manual**: Drag `shard-doc` task + document file into chat
@@ -461,32 +497,33 @@ that can handle [specific requirements]."
- Source tree document and coding standards for dev agent reference
- Sharded docs for SM agent story creation
**Resulting Folder Structure**:
Resulting Folder Structure:
- `docs/prd/` - Broken down PRD sections
- `docs/architecture/` - Broken down architecture sections
- `docs/stories/` - Generated user stories
3. **Development Cycle** (Sequential, one story at a time):
1. **Development Cycle** (Sequential, one story at a time):
**CRITICAL CONTEXT MANAGEMENT**:
- **Context windows matter!** Always use fresh, clean context windows
- **Model selection matters!** Use most powerful thinking model for SM story creation
- **ALWAYS start new chat between SM, Dev, and QA work**
**Step 1 - Story Creation**:
**Step 1 - Story Creation**:
- **NEW CLEAN CHAT** → Select powerful model → `@sm` → `*create`
- SM executes create-next-story task
- Review generated story in `docs/stories/`
- Update status from "Draft" to "Approved"
**Step 2 - Story Implementation**:
**Step 2 - Story Implementation**:
- **NEW CLEAN CHAT** → `@dev`
- Agent asks which story to implement
- Include story file content to save dev agent lookup time
- Dev follows tasks/subtasks, marking completion
- Dev maintains File List of all changes
- Dev marks story as "Review" when complete with all tests passing
**Step 3 - Senior QA Review**:
- **NEW CLEAN CHAT** → `@qa` → execute review-story task
- QA performs senior developer code review
@@ -494,7 +531,7 @@ that can handle [specific requirements]."
- QA appends results to story's QA Results section
- If approved: Status → "Done"
- If changes needed: Status stays "Review" with unchecked items for dev
**Step 4 - Repeat**: Continue SM → Dev → QA cycle until all epic stories complete
**Important**: Only 1 story in progress at a time, worked sequentially until all epic stories complete.
@@ -502,6 +539,7 @@ that can handle [specific requirements]."
### Status Tracking Workflow
Stories progress through defined statuses:
- **Draft** → **Approved** → **InProgress** → **Done**
Each status change requires user verification and approval before proceeding.
@@ -509,6 +547,7 @@ Each status change requires user verification and approval before proceeding.
### Workflow Types
#### Greenfield Development
- Business analysis and market research
- Product requirements and feature definition
- System architecture and design
@@ -522,6 +561,7 @@ Each status change requires user verification and approval before proceeding.
**Complete Brownfield Workflow Options**:
**Option 1: PRD-First (Recommended for Large Codebases/Monorepos)**:
1. **Upload project to Gemini Web** (GitHub URL, files, or zip)
2. **Create PRD first**: `@pm` → `*create-doc brownfield-prd`
3. **Focused documentation**: `@analyst` → `*document-project`
@@ -532,18 +572,19 @@ Each status change requires user verification and approval before proceeding.
- Avoids bloating docs with unused code
**Option 2: Document-First (Good for Smaller Projects)**:
1. **Upload project to Gemini Web**
2. **Document everything**: `@analyst` → `*document-project`
3. **Then create PRD**: `@pm` → `*create-doc brownfield-prd`
- More thorough but can create excessive documentation
2. **Requirements Gathering**:
4. **Requirements Gathering**:
- **Brownfield PRD**: Use PM agent with `brownfield-prd-tmpl`
- **Analyzes**: Existing system, constraints, integration points
- **Defines**: Enhancement scope, compatibility requirements, risk assessment
- **Creates**: Epic and story structure for changes
3. **Architecture Planning**:
5. **Architecture Planning**:
- **Brownfield Architecture**: Use Architect agent with `brownfield-architecture-tmpl`
- **Integration Strategy**: How new features integrate with existing system
- **Migration Planning**: Gradual rollout and backwards compatibility
@@ -552,10 +593,12 @@ Each status change requires user verification and approval before proceeding.
**Brownfield-Specific Resources**:
**Templates**:
- `brownfield-prd-tmpl.md`: Comprehensive enhancement planning with existing system analysis
- `brownfield-architecture-tmpl.md`: Integration-focused architecture for existing systems
**Tasks**:
- `document-project`: Generates comprehensive documentation from existing codebase
- `brownfield-create-epic`: Creates single epic for focused enhancements (when full PRD is overkill)
- `brownfield-create-story`: Creates individual story for small, isolated changes
@@ -563,18 +606,21 @@ Each status change requires user verification and approval before proceeding.
**When to Use Each Approach**:
**Full Brownfield Workflow** (Recommended for):
- Major feature additions
- System modernization
- Complex integrations
- Multiple related changes
**Quick Epic/Story Creation** (Use when):
- Single, focused enhancement
- Isolated bug fixes
- Small feature additions
- Well-documented existing system
**Critical Success Factors**:
1. **Documentation First**: Always run `document-project` if docs are outdated/missing
2. **Context Matters**: Provide agents access to relevant code sections
3. **Integration Focus**: Emphasize compatibility and non-breaking changes
@@ -590,6 +636,7 @@ Each status change requires user verification and approval before proceeding.
- `docs/architecture.md` - System Architecture Document
**Why These Names Matter**:
- Agents automatically reference these files during development
- Sharding tasks expect these specific filenames
- Workflow automation depends on standard naming
@@ -608,6 +655,7 @@ Each status change requires user verification and approval before proceeding.
Templates with Level 2 headings (`##`) can be automatically sharded:
**Original PRD**:
```markdown
## Goals and Background Context
## Requirements
@@ -616,6 +664,7 @@ Templates with Level 2 headings (`##`) can be automatically sharded:
```
**After Sharding**:
- `docs/prd/goals-and-background-context.md`
- `docs/prd/requirements.md`
- `docs/prd/user-interface-design-goals.md`
@@ -628,12 +677,14 @@ Use the `shard-doc` task or `@kayvan/markdown-tree-parser` tool for automatic sh
### Environment-Specific Usage
**Web UI Best For**:
- Initial planning and documentation phases
- Cost-effective large document creation
- Agent consultation and brainstorming
- Multi-agent workflows with orchestrator
**IDE Best For**:
- Active development and implementation
- File operations and project integration
- Story management and development cycles
@@ -668,6 +719,7 @@ Use the `shard-doc` task or `@kayvan/markdown-tree-parser` tool for automatic sh
For full details, see `CONTRIBUTING.md`. Key points:
**Fork Workflow**:
1. Fork the repository
2. Create feature branches
3. Submit PRs to `next` branch (default) or `main` for critical fixes only
@@ -675,12 +727,14 @@ For full details, see `CONTRIBUTING.md`. Key points:
5. One feature/fix per PR
**PR Requirements**:
- Clear descriptions (max 200 words) with What/Why/How/Testing
- Use conventional commits (feat:, fix:, docs:)
- Atomic commits - one logical change per commit
- Must align with guiding principles
**Core Principles** (from GUIDING-PRINCIPLES.md):
- **Dev Agents Must Be Lean**: Minimize dependencies, save context for code
- **Natural Language First**: Everything in markdown, no code in core
- **Core vs Expansion Packs**: Core for universal needs, packs for specialized domains
@@ -702,12 +756,14 @@ Expansion packs extend BMad-Method beyond traditional software development into
### Available Expansion Packs
**Technical Packs**:
- **Infrastructure/DevOps**: Cloud architects, SRE experts, security specialists
- **Game Development**: Game designers, level designers, narrative writers
- **Mobile Development**: iOS/Android specialists, mobile UX experts
- **Data Science**: ML engineers, data scientists, visualization experts
**Non-Technical Packs**:
- **Business Strategy**: Consultants, financial analysts, marketing strategists
- **Creative Writing**: Plot architects, character developers, world builders
- **Health & Wellness**: Fitness trainers, nutritionists, habit engineers
@@ -715,6 +771,7 @@ Expansion packs extend BMad-Method beyond traditional software development into
- **Legal Support**: Contract analysts, compliance checkers
**Specialty Packs**:
- **Expansion Creator**: Tools to build your own expansion packs
- **RPG Game Master**: Tabletop gaming assistance
- **Life Event Planning**: Wedding planners, event coordinators
@@ -724,11 +781,13 @@ Expansion packs extend BMad-Method beyond traditional software development into
1. **Browse Available Packs**: Check `expansion-packs/` directory
2. **Get Inspiration**: See `docs/expansion-packs.md` for detailed examples and ideas
3. **Install via CLI**:
3. **Install via CLI**:
```bash
npx bmad-method install
# Select "Install expansion pack" option
```
4. **Use in Your Workflow**: Installed packs integrate seamlessly with existing agents
### Creating Custom Expansion Packs

202
bmad-core/templates/prd-tmpl2.yaml Normal file
View File

@@ -0,0 +1,202 @@
template:
id: prd-template-v2
name: Product Requirements Document
version: 2.0
output:
format: markdown
filename: docs/prd.md
title: "{{project_name}} Product Requirements Document (PRD)"
workflow:
mode: interactive
elicitation: advanced-elicitation
sections:
- id: goals-context
title: Goals and Background Context
instruction: |
Ask if Project Brief document is available. If NO Project Brief exists, STRONGLY recommend creating one first using project-brief-tmpl (it provides essential foundation: problem statement, target users, success metrics, MVP scope, constraints). If user insists on PRD without brief, gather this information during Goals section. If Project Brief exists, review and use it to populate Goals (bullet list of desired outcomes) and Background Context (1-2 paragraphs on what this solves and why) so we can determine what is and is not in scope for PRD mvp. Either way this is critical to determine the requirements. Include Change Log table.
sections:
- id: goals
title: Goals
type: bullet-list
instruction: Bullet list of 1 line desired outcomes the PRD will deliver if successful - user and project desires
- id: background
title: Background Context
type: paragraphs
instruction: 1-2 short paragraphs summarizing the background context, such as what we learned in the brief without being redundant with the goals, what and why this solves a problem, what the current landscape or need is
- id: changelog
title: Change Log
type: table
columns: [Date, Version, Description, Author]
instruction: Track document versions and changes
- id: requirements
title: Requirements
instruction: Draft the list of functional and non functional requirements under the two child sections
elicit: true
sections:
- id: functional
title: Functional
type: numbered-list
prefix: FR
instruction: Each Requirement will be a bullet markdown and an identifier sequence starting with FR
examples:
- "FR6: The Todo List uses AI to detect and warn against potentially duplicate todo items that are worded differently."
- id: non-functional
title: Non Functional
type: numbered-list
prefix: NFR
instruction: Each Requirement will be a bullet markdown and an identifier sequence starting with NFR
examples:
- "NFR1: AWS service usage must aim to stay within free-tier limits where feasible."
- id: ui-goals
title: User Interface Design Goals
condition: PRD has UX/UI requirements
instruction: |
Capture high-level UI/UX vision to guide Design Architect and to inform story creation. Steps:
1. Pre-fill all subsections with educated guesses based on project context
2. Present the complete rendered section to user
3. Clearly let the user know where assumptions were made
4. Ask targeted questions for unclear/missing elements or areas needing more specification
5. This is NOT detailed UI spec - focus on product vision and user goals
elicit: true
choices:
accessibility: [None, WCAG AA, WCAG AAA]
platforms: [Web Responsive, Mobile Only, Desktop Only, Cross-Platform]
sections:
- id: ux-vision
title: Overall UX Vision
- id: interaction-paradigms
title: Key Interaction Paradigms
- id: core-screens
title: Core Screens and Views
instruction: From a product perspective, what are the most critical screens or views necessary to deliver the the PRD values and goals? This is meant to be Conceptual High Level to Drive Rough Epic or User Stories
examples:
- "Login Screen"
- "Main Dashboard"
- "Item Detail Page"
- "Settings Page"
- id: accessibility
title: "Accessibility: {None|WCAG AA|WCAG AAA|Custom Requirements}"
- id: branding
title: Branding
instruction: Any known branding elements or style guides that must be incorporated?
examples:
- "Replicate the look and feel of early 1900s black and white cinema, including animated effects replicating film damage or projector glitches during page or state transitions."
- "Attached is the full color pallet and tokens for our corporate branding."
- id: target-platforms
title: "Target Device and Platforms: {Web Responsive|Mobile Only|Desktop Only|Cross-Platform}"
examples:
- "Web Responsive, and all mobile platforms"
- "iPhone Only"
- "ASCII Windows Desktop"
- id: technical-assumptions
title: Technical Assumptions
instruction: |
Gather technical decisions that will guide the Architect. Steps:
1. Check if data#technical-preferences or an attached technical-preferences file exists - use it to pre-populate choices
2. Ask user about: languages, frameworks, starter templates, libraries, APIs, deployment targets
3. For unknowns, offer guidance based on project goals and MVP scope
4. Document ALL technical choices with rationale (why this choice fits the project)
5. These become constraints for the Architect - be specific and complete
elicit: true
choices:
repository: [Monorepo, Polyrepo]
architecture: [Monolith, Microservices, Serverless]
testing: [Unit Only, Unit + Integration, Full Testing Pyramid]
sections:
- id: repository-structure
title: "Repository Structure: {Monorepo|Polyrepo|Multi-repo}"
- id: service-architecture
title: Service Architecture
instruction: "CRITICAL DECISION - Document the high-level service architecture (e.g., Monolith, Microservices, Serverless functions within a Monorepo)."
- id: testing-requirements
title: Testing Requirements
instruction: "CRITICAL DECISION - Document the testing requirements, unit only, integration, e2e, manual, need for manual testing convenience methods)."
- id: additional-assumptions
title: Additional Technical Assumptions and Requests
instruction: Throughout the entire process of drafting this document, if any other technical assumptions are raised or discovered appropriate for the architect, add them here as additional bulleted items
- id: epic-list
title: Epic List
instruction: |
Present a high-level list of all epics for user approval. Each epic should have a title and a short (1 sentence) goal statement. This allows the user to review the overall structure before diving into details.
CRITICAL: Epics MUST be logically sequential following agile best practices:
- Each epic should deliver a significant, end-to-end, fully deployable increment of testable functionality
- Epic 1 must establish foundational project infrastructure (app setup, Git, CI/CD, core services) unless we are adding new functionality to an existing app, while also delivering an initial piece of functionality, even as simple as a health-check route or display of a simple canary page - remember this when we produce the stories for the first epic!
- Each subsequent epic builds upon previous epics' functionality delivering major blocks of functionality that provide tangible value to users or business when deployed
- Not every project needs multiple epics, an epic needs to deliver value. For example, an API completed can deliver value even if a UI is not complete and planned for a separate epic.
- Err on the side of less epics, but let the user know your rationale and offer options for splitting them if it seems some are too large or focused on disparate things.
- Cross Cutting Concerns should flow through epics and stories and not be final stories. For example, adding a logging framework as a last story of an epic, or at the end of a project as a final epic or story would be terrible as we would not have logging from the beginning.
elicit: true
examples:
- "Epic 1: Foundation & Core Infrastructure: Establish project setup, authentication, and basic user management"
- "Epic 2: Core Business Entities: Create and manage primary domain objects with CRUD operations"
- "Epic 3: User Workflows & Interactions: Enable key user journeys and business processes"
- "Epic 4: Reporting & Analytics: Provide insights and data visualization for users"
- id: epic-details
title: Epic {{epic_number}} {{epic_title}}
repeatable: true
instruction: |
After the epic list is approved, present each epic with all its stories and acceptance criteria as a complete review unit.
For each epic provide expanded goal (2-3 sentences describing the objective and value all the stories will achieve).
CRITICAL STORY SEQUENCING REQUIREMENTS:
- Stories within each epic MUST be logically sequential
- Each story should be a "vertical slice" delivering complete functionality aside from early enabler stories for project foundation
- No story should depend on work from a later story or epic
- Identify and note any direct prerequisite stories
- Focus on "what" and "why" not "how" (leave technical implementation to Architect) yet be precise enough to support a logical sequential order of operations from story to story.
- Ensure each story delivers clear user or business value, try to avoid enablers and build them into stories that deliver value.
- Size stories for AI agent execution: Each story must be completable by a single AI agent in one focused session without context overflow
- Think "junior developer working for 2-4 hours" - stories must be small, focused, and self-contained
- If a story seems complex, break it down further as long as it can deliver a vertical slice
elicit: true
template: "{{epic_goal}}"
sections:
- id: story
title: Story {{epic_number}}.{{story_number}} {{story_title}}
repeatable: true
template: |
As a {{user_type}},
I want {{action}},
so that {{benefit}}.
sections:
- id: acceptance-criteria
title: Acceptance Criteria
type: numbered-list
item_template: "{{criterion_number}}: {{criteria}}"
repeatable: true
instruction: |
Define clear, comprehensive, and testable acceptance criteria that:
- Precisely define what "done" means from a functional perspective
- Are unambiguous and serve as basis for verification
- Include any critical non-functional requirements from the PRD
- Consider local testability for backend/data components
- Specify UI/UX requirements and framework adherence where applicable
- Avoid cross-cutting concerns that should be in other stories or PRD sections
- id: checklist-results
title: Checklist Results Report
instruction: Before running the checklist and drafting the prompts, offer to output the full updated PRD. If outputting it, confirm with the user that you will be proceeding to run the checklist and produce the report. Once the user confirms, execute the pm-checklist and populate the results in this section.
- id: next-steps
title: Next Steps
sections:
- id: design-architect-prompt
title: Design Architect Prompt
instruction: This section will contain the prompt for the Design Architect, keep it short and to the point to initiate create architecture mode using this document as input.
- id: architect-prompt
title: Architect Prompt
instruction: This section will contain the prompt for the Architect, keep it short and to the point to initiate create architecture mode using this document as input.

22
bmad-core/utils/plan-management.md
View File

@@ -8,14 +8,10 @@ Provides utilities for agents and tasks to interact with workflow plans, check p
### 1. Check Plan Existence
[[LLM: When any agent starts or task begins, check if a workflow plan exists]]
```
Check for workflow plan:
1. Look for docs/workflow-plan.md (default location)
2. Check core-config.yaml for custom plan location
3. Return plan status (exists/not exists)
```
2. Return plan status to user (exists/not exists) - if not exists then HALT.
### 2. Parse Plan Status
@@ -56,7 +52,7 @@ Check for workflow plan:
**Warning Templates:**
```
```text
SEQUENCE WARNING:
The workflow plan shows you should complete "{expected_step}" next.
You're attempting to: "{requested_action}"
@@ -90,7 +86,7 @@ In flexible mode: Allow with confirmation
**For Agents (startup sequence)**:
```
```text
1. Check if plan exists using this utility
2. If exists:
- Parse current status
@@ -101,7 +97,7 @@ In flexible mode: Allow with confirmation
**For Tasks (pre-execution)**:
```
```text
1. Check if plan exists
2. If exists:
- Verify this task aligns with plan
@@ -117,7 +113,7 @@ In flexible mode: Allow with confirmation
[[LLM: Standard format for showing plan status]]
```
```text
📋 Workflow Plan Status
━━━━━━━━━━━━━━━━━━━━
Workflow: {workflow_name}
@@ -170,7 +166,7 @@ If user wants to abandon plan:
### Example 1: Agent Startup Check
```
```text
BMad Master starting...
[Check for plan]
@@ -184,7 +180,7 @@ Use *agent pm to switch, or *plan-status to see full progress.
### Example 2: Task Sequence Warning
```
```text
User: *task create-next-story
[Plan check triggered]
@@ -200,7 +196,7 @@ Would you like to:
### Example 3: Automatic Plan Update
```
```text
[After completing create-doc task for PRD]
✅ Plan Updated: Marked "Create PRD" as complete