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

1
.vscode/settings.json vendored
View File

@@ -32,6 +32,7 @@
"playtesting", "playtesting",
"pointerdown", "pointerdown",
"pointerup", "pointerup",
"Polyrepo",
"replayability", "replayability",
"roguelike", "roguelike",
"roomodes", "roomodes",

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 - 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 - 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-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) - 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 - 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 - plan: Execute the task Create workflow plan
@@ -65,6 +66,7 @@ dependencies:
- correct-course - correct-course
- create-deep-research-prompt - create-deep-research-prompt
- create-doc - create-doc
- create-doc2
- create-workflow-plan - create-workflow-plan
- document-project - document-project
- create-next-story - create-next-story
@@ -83,6 +85,7 @@ dependencies:
- fullstack-architecture-tmpl - fullstack-architecture-tmpl
- market-research-tmpl - market-research-tmpl
- prd-tmpl - prd-tmpl
- prd-tmpl2
- project-brief-tmpl - project-brief-tmpl
- story-tmpl - story-tmpl
data: 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 ### 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) - Use large context windows (Gemini's 1M tokens)
- Generate comprehensive documents (PRD, Architecture) - Generate comprehensive documents (PRD, Architecture)
- Leverage multiple agents for brainstorming - Leverage multiple agents for brainstorming
- Create once, use throughout development - Create once, use throughout development
**Phase 2: Development (IDE - Implementation)** #### Phase 2: Development (IDE - Implementation)
- Shard documents into manageable pieces - Shard documents into manageable pieces
- Execute focused SM → Dev cycles - Execute focused SM → Dev cycles
- One story at a time, sequential progress - 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 ### Quick Start Options
#### Option 1: Web UI #### Option 1: Web UI
**Best for**: ChatGPT, Claude, Gemini users who want to start immediately **Best for**: ChatGPT, Claude, Gemini users who want to start immediately
1. Navigate to `dist/teams/` 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 5. Type `/help` to see available commands
#### Option 2: IDE Integration #### Option 2: IDE Integration
**Best for**: Cursor, Claude Code, Windsurf, Trae, Cline, Roo Code, Github Copilot users **Best for**: Cursor, Claude Code, Windsurf, Trae, Cline, Roo Code, Github Copilot users
```bash ```bash
@@ -86,6 +90,7 @@ npx bmad-method install
``` ```
**Installation Steps**: **Installation Steps**:
- Choose "Complete installation" - Choose "Complete installation"
- Select your IDE from supported options: - Select your IDE from supported options:
- **Cursor**: Native AI integration - **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. **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**: **Verify Installation**:
- `.bmad-core/` folder created with all agents - `.bmad-core/` folder created with all agents
- IDE-specific integration files created - IDE-specific integration files created
- All agent commands/rules/modes available - All agent commands/rules/modes available
@@ -108,12 +114,14 @@ npx bmad-method install
### Environment Selection Guide ### Environment Selection Guide
**Use Web UI for**: **Use Web UI for**:
- Initial planning and documentation (PRD, architecture) - Initial planning and documentation (PRD, architecture)
- Cost-effective document creation (especially with Gemini) - Cost-effective document creation (especially with Gemini)
- Brainstorming and analysis phases - Brainstorming and analysis phases
- Multi-agent consultation and planning - Multi-agent consultation and planning
**Use IDE for**: **Use IDE for**:
- Active development and coding - Active development and coding
- File operations and project integration - File operations and project integration
- Document sharding and story management - Document sharding and story management
@@ -126,35 +134,41 @@ npx bmad-method install
**Can you do everything in IDE?** Yes, but understand the tradeoffs: **Can you do everything in IDE?** Yes, but understand the tradeoffs:
**Pros of IDE-Only**: **Pros of IDE-Only**:
- Single environment workflow - Single environment workflow
- Direct file operations from start - Direct file operations from start
- No copy/paste between environments - No copy/paste between environments
- Immediate project integration - Immediate project integration
**Cons of IDE-Only**: **Cons of IDE-Only**:
- Higher token costs for large document creation - Higher token costs for large document creation
- Smaller context windows (varies by IDE/model) - Smaller context windows (varies by IDE/model)
- May hit limits during planning phases - May hit limits during planning phases
- Less cost-effective for brainstorming - Less cost-effective for brainstorming
**Using Web Agents in IDE**: **Using Web Agents in IDE**:
- **NOT RECOMMENDED**: Web agents (PM, Architect) have rich dependencies designed for large contexts - **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 - **Why it matters**: Dev agents are kept lean to maximize coding context
- **The principle**: "Dev agents code, planning agents plan" - mixing breaks this optimization - **The principle**: "Dev agents code, planning agents plan" - mixing breaks this optimization
**About bmad-master and bmad-orchestrator**: **About bmad-master and bmad-orchestrator**:
- **bmad-master**: CAN do any task without switching agents, BUT... - **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 - **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 - **Why specialization matters**: Each agent's personality and focus creates higher quality outputs
- **If using bmad-master/orchestrator**: Fine for planning phases, but... - **If using bmad-master/orchestrator**: Fine for planning phases, but...
**CRITICAL RULE for Development**: **CRITICAL RULE for Development**:
- **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator - **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator
- **ALWAYS use Dev agent for implementation** - 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 - **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 - **No exceptions**: Even if using bmad-master for everything else, switch to SM → Dev for implementation
**Best Practice for IDE-Only**: **Best Practice for IDE-Only**:
1. Use PM/Architect/UX agents for planning (better than bmad-master) 1. Use PM/Architect/UX agents for planning (better than bmad-master)
2. Create documents directly in project 2. Create documents directly in project
3. Shard immediately after creation 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 ### Key Configuration Areas
#### PRD Configuration #### PRD Configuration
- **prdVersion**: Tells agents if PRD follows v3 or v4 conventions - **prdVersion**: Tells agents if PRD follows v3 or v4 conventions
- **prdSharded**: Whether epics are embedded (false) or in separate files (true) - **prdSharded**: Whether epics are embedded (false) or in separate files (true)
- **prdShardedLocation**: Where to find sharded epic files - **prdShardedLocation**: Where to find sharded epic files
- **epicFilePattern**: Pattern for epic filenames (e.g., `epic-{n}*.md`) - **epicFilePattern**: Pattern for epic filenames (e.g., `epic-{n}*.md`)
#### Architecture Configuration #### Architecture Configuration
- **architectureVersion**: v3 (monolithic) or v4 (sharded) - **architectureVersion**: v3 (monolithic) or v4 (sharded)
- **architectureSharded**: Whether architecture is split into components - **architectureSharded**: Whether architecture is split into components
- **architectureShardedLocation**: Where sharded architecture files live - **architectureShardedLocation**: Where sharded architecture files live
#### Developer Files #### Developer Files
- **devLoadAlwaysFiles**: List of files the dev agent loads for every task - **devLoadAlwaysFiles**: List of files the dev agent loads for every task
- **devDebugLog**: Where dev agent logs repeated failures - **devDebugLog**: Where dev agent logs repeated failures
- **agentCoreDump**: Export location for chat conversations - **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 ### Common Configurations
**Legacy V3 Project**: **Legacy V3 Project**:
```yaml ```yaml
prdVersion: v3 prdVersion: v3
prdSharded: false prdSharded: false
@@ -211,6 +229,7 @@ architectureSharded: false
``` ```
**V4 Optimized Project**: **V4 Optimized Project**:
```yaml ```yaml
prdVersion: v4 prdVersion: v4
prdSharded: true prdSharded: true
@@ -276,6 +295,7 @@ You are the "Vibe CEO" - thinking like a CEO with unlimited resources and a sing
#### IDE-Specific Syntax #### IDE-Specific Syntax
**Agent Loading by IDE**: **Agent Loading by IDE**:
- **Claude Code**: `/agent-name` (e.g., `/bmad-master`) - **Claude Code**: `/agent-name` (e.g., `/bmad-master`)
- **Cursor**: `@agent-name` (e.g., `@bmad-master`) - **Cursor**: `@agent-name` (e.g., `@bmad-master`)
- **Windsurf**: `@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. - **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**: **Chat Management Guidelines**:
- **Claude Code, Cursor, Windsurf, Trae**: Start new chats when switching agents - **Claude Code, Cursor, Windsurf, Trae**: Start new chats when switching agents
- **Roo Code**: Switch modes within the same conversation - **Roo Code**: Switch modes within the same conversation
**Common Task Commands**: **Common Task Commands**:
- `*help` - Show available commands - `*help` - Show available commands
- `*status` - Show current context/progress - `*status` - Show current context/progress
- `*exit` - Exit the agent mode - `*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) - `*create` - Run create-next-story task (SM agent)
**In Web UI**: **In Web UI**:
```text ```text
/pm create-doc prd /pm create-doc prd
/architect review system design /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 ### Pre-Built Teams
#### Team All #### Team All
- **Includes**: All 10 agents + orchestrator - **Includes**: All 10 agents + orchestrator
- **Use Case**: Complete projects requiring all roles - **Use Case**: Complete projects requiring all roles
- **Bundle**: `team-all.txt` - **Bundle**: `team-all.txt`
#### Team Fullstack #### Team Fullstack
- **Includes**: PM, Architect, Developer, QA, UX Expert - **Includes**: PM, Architect, Developer, QA, UX Expert
- **Use Case**: End-to-end web/mobile development - **Use Case**: End-to-end web/mobile development
- **Bundle**: `team-fullstack.txt` - **Bundle**: `team-fullstack.txt`
#### Team No-UI #### Team No-UI
- **Includes**: PM, Architect, Developer, QA (no UX Expert) - **Includes**: PM, Architect, Developer, QA (no UX Expert)
- **Use Case**: Backend services, APIs, system development - **Use Case**: Backend services, APIs, system development
- **Bundle**: `team-no-ui.txt` - **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 ### Key Architectural Components
#### 1. Agents (`bmad-core/agents/`) #### 1. Agents (`bmad-core/agents/`)
- **Purpose**: Each markdown file defines a specialized AI agent for a specific Agile role (PM, Dev, Architect, etc.) - **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 - **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 - **Dependencies**: Lists of tasks, templates, checklists, and data files the agent can use
- **Startup Instructions**: Can load project-specific documentation for immediate context - **Startup Instructions**: Can load project-specific documentation for immediate context
#### 2. Agent Teams (`bmad-core/agent-teams/`) #### 2. Agent Teams (`bmad-core/agent-teams/`)
- **Purpose**: Define collections of agents bundled together for specific purposes - **Purpose**: Define collections of agents bundled together for specific purposes
- **Examples**: `team-all.yaml` (comprehensive bundle), `team-fullstack.yaml` (full-stack development) - **Examples**: `team-all.yaml` (comprehensive bundle), `team-fullstack.yaml` (full-stack development)
- **Usage**: Creates pre-packaged contexts for web UI environments - **Usage**: Creates pre-packaged contexts for web UI environments
#### 3. Workflows (`bmad-core/workflows/`) #### 3. Workflows (`bmad-core/workflows/`)
- **Purpose**: YAML files defining prescribed sequences of steps for specific project types - **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 - **Types**: Greenfield (new projects) and Brownfield (existing projects) for UI, service, and fullstack development
- **Structure**: Defines agent interactions, artifacts created, and transition conditions - **Structure**: Defines agent interactions, artifacts created, and transition conditions
#### 4. Reusable Resources #### 4. Reusable Resources
- **Templates** (`bmad-core/templates/`): Markdown templates for PRDs, architecture specs, user stories - **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" - **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 - **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 ### Technical Preferences Integration
The `technical-preferences.md` file serves as a persistent technical profile that: The `technical-preferences.md` file serves as a persistent technical profile that:
- Ensures consistency across all agents and projects - Ensures consistency across all agents and projects
- Eliminates repetitive technology specification - Eliminates repetitive technology specification
- Provides personalized recommendations aligned with user preferences - 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 ### Build and Delivery Process
The `web-builder.js` tool creates web-ready bundles by: The `web-builder.js` tool creates web-ready bundles by:
1. Reading agent or team definition files 1. Reading agent or team definition files
2. Recursively resolving all dependencies 2. Recursively resolving all dependencies
3. Concatenating content into single text files with clear separators 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:** **Ideal for cost efficiency with Gemini's massive context:**
**For Brownfield Projects - Start Here!**: **For Brownfield Projects - Start Here!**:
1. **Upload entire project to Gemini Web** (GitHub URL, files, or zip) 1. **Upload entire project to Gemini Web** (GitHub URL, files, or zip)
2. **Document existing system**: `/analyst` → `*document-project` 2. **Document existing system**: `/analyst` → `*document-project`
3. **Creates comprehensive docs** from entire codebase analysis 3. **Creates comprehensive docs** from entire codebase analysis
**For All Projects**: **For All Projects**:
1. **Optional Analysis**: `/analyst` - Market research, competitive analysis 1. **Optional Analysis**: `/analyst` - Market research, competitive analysis
2. **Project Brief**: Create foundation document (Analyst or user) 2. **Project Brief**: Create foundation document (Analyst or user)
3. **PRD Creation**: `/pm create-doc prd` - Comprehensive product requirements 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 #### Example Planning Prompts
**For PRD Creation**: **For PRD Creation**:
```text ```text
"I want to build a [type] application that [core purpose]. "I want to build a [type] application that [core purpose].
Help me brainstorm features and create a comprehensive PRD." Help me brainstorm features and create a comprehensive PRD."
``` ```
**For Architecture Design**: **For Architecture Design**:
```text ```text
"Based on this PRD, design a scalable technical architecture "Based on this PRD, design a scalable technical architecture
that can handle [specific requirements]." that can handle [specific requirements]."
@@ -447,7 +483,7 @@ that can handle [specific requirements]."
**Prerequisites**: Planning documents must exist in `docs/` folder **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 - Documents created by PM/Architect (in Web or IDE) MUST be sharded for development
- Two methods to shard: - Two methods to shard:
a) **Manual**: Drag `shard-doc` task + document file into chat 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 - Source tree document and coding standards for dev agent reference
- Sharded docs for SM agent story creation - Sharded docs for SM agent story creation
**Resulting Folder Structure**: Resulting Folder Structure:
- `docs/prd/` - Broken down PRD sections - `docs/prd/` - Broken down PRD sections
- `docs/architecture/` - Broken down architecture sections - `docs/architecture/` - Broken down architecture sections
- `docs/stories/` - Generated user stories - `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**: **CRITICAL CONTEXT MANAGEMENT**:
- **Context windows matter!** Always use fresh, clean context windows - **Context windows matter!** Always use fresh, clean context windows
- **Model selection matters!** Use most powerful thinking model for SM story creation - **Model selection matters!** Use most powerful thinking model for SM story creation
- **ALWAYS start new chat between SM, Dev, and QA work** - **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` - **NEW CLEAN CHAT** → Select powerful model → `@sm` → `*create`
- SM executes create-next-story task - SM executes create-next-story task
- Review generated story in `docs/stories/` - Review generated story in `docs/stories/`
- Update status from "Draft" to "Approved" - Update status from "Draft" to "Approved"
**Step 2 - Story Implementation**: **Step 2 - Story Implementation**:
- **NEW CLEAN CHAT** → `@dev` - **NEW CLEAN CHAT** → `@dev`
- Agent asks which story to implement - Agent asks which story to implement
- Include story file content to save dev agent lookup time - Include story file content to save dev agent lookup time
- Dev follows tasks/subtasks, marking completion - Dev follows tasks/subtasks, marking completion
- Dev maintains File List of all changes - Dev maintains File List of all changes
- Dev marks story as "Review" when complete with all tests passing - Dev marks story as "Review" when complete with all tests passing
**Step 3 - Senior QA Review**: **Step 3 - Senior QA Review**:
- **NEW CLEAN CHAT** → `@qa` → execute review-story task - **NEW CLEAN CHAT** → `@qa` → execute review-story task
- QA performs senior developer code review - QA performs senior developer code review
@@ -494,7 +531,7 @@ that can handle [specific requirements]."
- QA appends results to story's QA Results section - QA appends results to story's QA Results section
- If approved: Status → "Done" - If approved: Status → "Done"
- If changes needed: Status stays "Review" with unchecked items for dev - If changes needed: Status stays "Review" with unchecked items for dev
**Step 4 - Repeat**: Continue SM → Dev → QA cycle until all epic stories complete **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. **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 ### Status Tracking Workflow
Stories progress through defined statuses: Stories progress through defined statuses:
- **Draft** → **Approved** → **InProgress** → **Done** - **Draft** → **Approved** → **InProgress** → **Done**
Each status change requires user verification and approval before proceeding. 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 ### Workflow Types
#### Greenfield Development #### Greenfield Development
- Business analysis and market research - Business analysis and market research
- Product requirements and feature definition - Product requirements and feature definition
- System architecture and design - System architecture and design
@@ -522,6 +561,7 @@ Each status change requires user verification and approval before proceeding.
**Complete Brownfield Workflow Options**: **Complete Brownfield Workflow Options**:
**Option 1: PRD-First (Recommended for Large Codebases/Monorepos)**: **Option 1: PRD-First (Recommended for Large Codebases/Monorepos)**:
1. **Upload project to Gemini Web** (GitHub URL, files, or zip) 1. **Upload project to Gemini Web** (GitHub URL, files, or zip)
2. **Create PRD first**: `@pm` → `*create-doc brownfield-prd` 2. **Create PRD first**: `@pm` → `*create-doc brownfield-prd`
3. **Focused documentation**: `@analyst` → `*document-project` 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 - Avoids bloating docs with unused code
**Option 2: Document-First (Good for Smaller Projects)**: **Option 2: Document-First (Good for Smaller Projects)**:
1. **Upload project to Gemini Web** 1. **Upload project to Gemini Web**
2. **Document everything**: `@analyst` → `*document-project` 2. **Document everything**: `@analyst` → `*document-project`
3. **Then create PRD**: `@pm` → `*create-doc brownfield-prd` 3. **Then create PRD**: `@pm` → `*create-doc brownfield-prd`
- More thorough but can create excessive documentation - More thorough but can create excessive documentation
2. **Requirements Gathering**: 4. **Requirements Gathering**:
- **Brownfield PRD**: Use PM agent with `brownfield-prd-tmpl` - **Brownfield PRD**: Use PM agent with `brownfield-prd-tmpl`
- **Analyzes**: Existing system, constraints, integration points - **Analyzes**: Existing system, constraints, integration points
- **Defines**: Enhancement scope, compatibility requirements, risk assessment - **Defines**: Enhancement scope, compatibility requirements, risk assessment
- **Creates**: Epic and story structure for changes - **Creates**: Epic and story structure for changes
3. **Architecture Planning**: 5. **Architecture Planning**:
- **Brownfield Architecture**: Use Architect agent with `brownfield-architecture-tmpl` - **Brownfield Architecture**: Use Architect agent with `brownfield-architecture-tmpl`
- **Integration Strategy**: How new features integrate with existing system - **Integration Strategy**: How new features integrate with existing system
- **Migration Planning**: Gradual rollout and backwards compatibility - **Migration Planning**: Gradual rollout and backwards compatibility
@@ -552,10 +593,12 @@ Each status change requires user verification and approval before proceeding.
**Brownfield-Specific Resources**: **Brownfield-Specific Resources**:
**Templates**: **Templates**:
- `brownfield-prd-tmpl.md`: Comprehensive enhancement planning with existing system analysis - `brownfield-prd-tmpl.md`: Comprehensive enhancement planning with existing system analysis
- `brownfield-architecture-tmpl.md`: Integration-focused architecture for existing systems - `brownfield-architecture-tmpl.md`: Integration-focused architecture for existing systems
**Tasks**: **Tasks**:
- `document-project`: Generates comprehensive documentation from existing codebase - `document-project`: Generates comprehensive documentation from existing codebase
- `brownfield-create-epic`: Creates single epic for focused enhancements (when full PRD is overkill) - `brownfield-create-epic`: Creates single epic for focused enhancements (when full PRD is overkill)
- `brownfield-create-story`: Creates individual story for small, isolated changes - `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**: **When to Use Each Approach**:
**Full Brownfield Workflow** (Recommended for): **Full Brownfield Workflow** (Recommended for):
- Major feature additions - Major feature additions
- System modernization - System modernization
- Complex integrations - Complex integrations
- Multiple related changes - Multiple related changes
**Quick Epic/Story Creation** (Use when): **Quick Epic/Story Creation** (Use when):
- Single, focused enhancement - Single, focused enhancement
- Isolated bug fixes - Isolated bug fixes
- Small feature additions - Small feature additions
- Well-documented existing system - Well-documented existing system
**Critical Success Factors**: **Critical Success Factors**:
1. **Documentation First**: Always run `document-project` if docs are outdated/missing 1. **Documentation First**: Always run `document-project` if docs are outdated/missing
2. **Context Matters**: Provide agents access to relevant code sections 2. **Context Matters**: Provide agents access to relevant code sections
3. **Integration Focus**: Emphasize compatibility and non-breaking changes 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 - `docs/architecture.md` - System Architecture Document
**Why These Names Matter**: **Why These Names Matter**:
- Agents automatically reference these files during development - Agents automatically reference these files during development
- Sharding tasks expect these specific filenames - Sharding tasks expect these specific filenames
- Workflow automation depends on standard naming - 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: Templates with Level 2 headings (`##`) can be automatically sharded:
**Original PRD**: **Original PRD**:
```markdown ```markdown
## Goals and Background Context ## Goals and Background Context
## Requirements ## Requirements
@@ -616,6 +664,7 @@ Templates with Level 2 headings (`##`) can be automatically sharded:
``` ```
**After Sharding**: **After Sharding**:
- `docs/prd/goals-and-background-context.md` - `docs/prd/goals-and-background-context.md`
- `docs/prd/requirements.md` - `docs/prd/requirements.md`
- `docs/prd/user-interface-design-goals.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 ### Environment-Specific Usage
**Web UI Best For**: **Web UI Best For**:
- Initial planning and documentation phases - Initial planning and documentation phases
- Cost-effective large document creation - Cost-effective large document creation
- Agent consultation and brainstorming - Agent consultation and brainstorming
- Multi-agent workflows with orchestrator - Multi-agent workflows with orchestrator
**IDE Best For**: **IDE Best For**:
- Active development and implementation - Active development and implementation
- File operations and project integration - File operations and project integration
- Story management and development cycles - 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: For full details, see `CONTRIBUTING.md`. Key points:
**Fork Workflow**: **Fork Workflow**:
1. Fork the repository 1. Fork the repository
2. Create feature branches 2. Create feature branches
3. Submit PRs to `next` branch (default) or `main` for critical fixes only 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 5. One feature/fix per PR
**PR Requirements**: **PR Requirements**:
- Clear descriptions (max 200 words) with What/Why/How/Testing - Clear descriptions (max 200 words) with What/Why/How/Testing
- Use conventional commits (feat:, fix:, docs:) - Use conventional commits (feat:, fix:, docs:)
- Atomic commits - one logical change per commit - Atomic commits - one logical change per commit
- Must align with guiding principles - Must align with guiding principles
**Core Principles** (from GUIDING-PRINCIPLES.md): **Core Principles** (from GUIDING-PRINCIPLES.md):
- **Dev Agents Must Be Lean**: Minimize dependencies, save context for code - **Dev Agents Must Be Lean**: Minimize dependencies, save context for code
- **Natural Language First**: Everything in markdown, no code in core - **Natural Language First**: Everything in markdown, no code in core
- **Core vs Expansion Packs**: Core for universal needs, packs for specialized domains - **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 ### Available Expansion Packs
**Technical Packs**: **Technical Packs**:
- **Infrastructure/DevOps**: Cloud architects, SRE experts, security specialists - **Infrastructure/DevOps**: Cloud architects, SRE experts, security specialists
- **Game Development**: Game designers, level designers, narrative writers - **Game Development**: Game designers, level designers, narrative writers
- **Mobile Development**: iOS/Android specialists, mobile UX experts - **Mobile Development**: iOS/Android specialists, mobile UX experts
- **Data Science**: ML engineers, data scientists, visualization experts - **Data Science**: ML engineers, data scientists, visualization experts
**Non-Technical Packs**: **Non-Technical Packs**:
- **Business Strategy**: Consultants, financial analysts, marketing strategists - **Business Strategy**: Consultants, financial analysts, marketing strategists
- **Creative Writing**: Plot architects, character developers, world builders - **Creative Writing**: Plot architects, character developers, world builders
- **Health & Wellness**: Fitness trainers, nutritionists, habit engineers - **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 - **Legal Support**: Contract analysts, compliance checkers
**Specialty Packs**: **Specialty Packs**:
- **Expansion Creator**: Tools to build your own expansion packs - **Expansion Creator**: Tools to build your own expansion packs
- **RPG Game Master**: Tabletop gaming assistance - **RPG Game Master**: Tabletop gaming assistance
- **Life Event Planning**: Wedding planners, event coordinators - **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 1. **Browse Available Packs**: Check `expansion-packs/` directory
2. **Get Inspiration**: See `docs/expansion-packs.md` for detailed examples and ideas 2. **Get Inspiration**: See `docs/expansion-packs.md` for detailed examples and ideas
3. **Install via CLI**: 3. **Install via CLI**:
```bash ```bash
npx bmad-method install npx bmad-method install
# Select "Install expansion pack" option # Select "Install expansion pack" option
``` ```
4. **Use in Your Workflow**: Installed packs integrate seamlessly with existing agents 4. **Use in Your Workflow**: Installed packs integrate seamlessly with existing agents
### Creating Custom Expansion Packs ### 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 ### 1. Check Plan Existence
[[LLM: When any agent starts or task begins, check if a workflow plan exists]]
```
Check for workflow plan: Check for workflow plan:
1. Look for docs/workflow-plan.md (default location) 1. Look for docs/workflow-plan.md (default location)
2. Check core-config.yaml for custom plan location 2. Return plan status to user (exists/not exists) - if not exists then HALT.
3. Return plan status (exists/not exists)
```
### 2. Parse Plan Status ### 2. Parse Plan Status
@@ -56,7 +52,7 @@ Check for workflow plan:
**Warning Templates:** **Warning Templates:**
``` ```text
SEQUENCE WARNING: SEQUENCE WARNING:
The workflow plan shows you should complete "{expected_step}" next. The workflow plan shows you should complete "{expected_step}" next.
You're attempting to: "{requested_action}" You're attempting to: "{requested_action}"
@@ -90,7 +86,7 @@ In flexible mode: Allow with confirmation
**For Agents (startup sequence)**: **For Agents (startup sequence)**:
``` ```text
1. Check if plan exists using this utility 1. Check if plan exists using this utility
2. If exists: 2. If exists:
- Parse current status - Parse current status
@@ -101,7 +97,7 @@ In flexible mode: Allow with confirmation
**For Tasks (pre-execution)**: **For Tasks (pre-execution)**:
``` ```text
1. Check if plan exists 1. Check if plan exists
2. If exists: 2. If exists:
- Verify this task aligns with plan - Verify this task aligns with plan
@@ -117,7 +113,7 @@ In flexible mode: Allow with confirmation
[[LLM: Standard format for showing plan status]] [[LLM: Standard format for showing plan status]]
``` ```text
📋 Workflow Plan Status 📋 Workflow Plan Status
━━━━━━━━━━━━━━━━━━━━ ━━━━━━━━━━━━━━━━━━━━
Workflow: {workflow_name} Workflow: {workflow_name}
@@ -170,7 +166,7 @@ If user wants to abandon plan:
### Example 1: Agent Startup Check ### Example 1: Agent Startup Check
``` ```text
BMad Master starting... BMad Master starting...
[Check for plan] [Check for plan]
@@ -184,7 +180,7 @@ Use *agent pm to switch, or *plan-status to see full progress.
### Example 2: Task Sequence Warning ### Example 2: Task Sequence Warning
``` ```text
User: *task create-next-story User: *task create-next-story
[Plan check triggered] [Plan check triggered]
@@ -200,7 +196,7 @@ Would you like to:
### Example 3: Automatic Plan Update ### Example 3: Automatic Plan Update
``` ```text
[After completing create-doc task for PRD] [After completing create-doc task for PRD]
✅ Plan Updated: Marked "Create PRD" as complete ✅ Plan Updated: Marked "Create PRD" as complete

208
common/tasks/create-doc2.md Normal file
View File

@@ -0,0 +1,208 @@
# Create Document from Template (YAML Driven)
## Purpose
Create documents using YAML templates to drive interactive, section-by-section collaboration between AI and user.
## Core Rules
1. **NEVER output YAML** - Final document contains only clean markdown
2. **Interactive by default** - Work section-by-section unless YOLO mode
3. **YAML template drives all behavior** - Parse template, follow instructions exactly
4. **Apply elicitation when specified** - Use advanced elicitation for marked sections
5. **Present sections cleanly** - Show content for review, then apply elicitation if flagged
## YAML Template Format
Templates are full YAML files with this structure:
```yaml
template:
id: template-name
name: Human Readable Name
output:
format: markdown
filename: docs/output.md
title: "{{variable}} Document Title"
sections:
- id: section-id
title: Section Title
instruction: "Detailed guidance for this section"
elicit: true
condition: "has ui"
choices:
repository: [Monorepo, Polyrepo]
```
## Processing Flow
### 1. Parse YAML Template
- Load template metadata (id, name, output settings)
- Extract `sections` list (required)
- Note any section with `elicit: true`, `condition: "text"`, `choices`, or `repeatable: true`
- Handle nested sections for complex document structure
- For repeatable sections, use the template structure defined in the section
### 2. Set User Preferences
**Interaction Mode:** Currently Interactive (type `#yolo` to toggle to YOLO mode)
**Output Location:** Confirm file output location from template (e.g., `docs/prd.md`). If environment doesn't support file writing (like web UI), will keep content in chat until complete.
### 3. Process Each Section
For each section in order:
**Interactive Mode:**
1. **Skip if condition unmet** - If `condition: "has ui"` and project has no UI, skip entirely
2. **Draft section content** - Use section `instruction` and handle choices/variables
3. **Handle repeatable sections** - If section has `repeatable: true`, generate multiple instances based on nested structure
4. **Present to user** - Show clean section content for review
5. **Provide detailed rationale** - Include thoughtful analysis highlighting (for example):
- Interesting or questionable decisions made
- Trade-offs and choices (what was chosen over alternatives and why)
- Areas that might need user attention or validation
- Key assumptions made during drafting
6. **Get user feedback** - Accept changes or proceed
7. **Apply elicitation if specified** - If `elicit: true`, present standardized 1-9 options:
- Option 1: Always "Proceed to next section"
- Options 2-9: MUST select 8 relevant methods from data/elicitation-methods (never create new ones)
- Include "Select 1-9 or just type your question/feedback:" to allow free chat
8. **Process elicitation results** - After user selects elicitation method, present results with options:
- Option 1: "Apply suggested changes and update section"
- Option 2: "Return to elicitation selection (2-9 options)"
- Free text: "Ask questions or follow-ups about this elicitation"
- Allow multiple elicitation rounds on same section
9. **Save to document** - If document-as-we-go mode, append approved content to file
10. **Continue to next section**
**YOLO Mode:**
- Process all sections at once, then present complete document
### 4. Final Output
- Present complete document with clean markdown only
- Save to file if specified
- No YAML, no template syntax, no processing instructions
## Section Types
**Simple section:**
```yaml
- id: requirements
title: Requirements
instruction: "Draft functional (FR1, FR2...) and non-functional (NFR1, NFR2...) requirements"
```
**Section with elicitation:**
```yaml
- id: technical-assumptions
title: Technical Assumptions
instruction: "Gather technical decisions that will guide the Architect"
elicit: true
choices:
architecture: [Monolith, Microservices, Serverless]
```
**Conditional section:**
```yaml
- id: ui-goals
title: User Interface Goals
instruction: "High-level UI/UX vision and design goals"
condition: "has ui requirements"
elicit: true
```
**Repeatable section with nested structure:**
```yaml
- id: epic-details
title: Epic {{epic_number}} {{epic_title}}
instruction: "Epic guidance with story and criteria requirements"
elicit: true
repeatable: true
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: criteria
title: Acceptance Criteria
type: numbered-list
item_template: "{{criterion_number}}: {{criteria}}"
repeatable: true
```
## Elicitation Loop
When user selects an elicitation method (options 2-9), follow this pattern:
1. **Execute the selected elicitation method** from data/elicitation-methods
2. **Present results** with insights and suggestions
3. **Provide follow-up options:**
- **1. Apply suggested changes and update section**
- **2. Return to elicitation selection** (show 2-9 options again)
- **Free text: Ask questions or follow-ups about this elicitation**
4. **Allow multiple rounds** - User can run multiple elicitation methods on the same section
5. **Only proceed to next section** when user explicitly chooses option 1 from the main menu
## Output Modes
**Document-as-we-go (Recommended):**
- Each approved section gets written to the document file immediately
- User can see document building in real-time
- Protects against context loss or chat restart
- File always contains latest approved content
**Chat-only:**
- All content stays in chat memory until document is complete
- Full document presented at end
- Risk of losing work if context runs out
## Template Processing
1. **Load YAML template** - Parse template metadata and sections
2. **Set document title** - Use template.output.title with variables
3. **Process sections in order** - Handle conditions, repeatability, nesting
4. **Apply instructions** - Use section.instruction for guidance
5. **Handle variables** - Replace {{variable}} placeholders
6. **Process choices** - Present options from choices object
7. **Generate content** - Create markdown following section structure
## Error Prevention
**❌ Don't:**
- Show YAML in final output
- Skip conditional checks
- Ignore elicitation flags
- Output template syntax
- Apply elicitation before user approves elicitation content
**✅ Do:**
- Process sections in order
- Present clean content only
- Apply elicitation AFTER user approves section content
- Handle choice objects properly
- Generate repeatable sections dynamically
- Skip sections where conditions aren't met
- Save to document file when in document-as-we-go mode
## Key Improvements
- **YAML templates** provide much richer structure than front matter
- **Document-as-we-go** protects against context loss
- **Elicitation after approval** ensures quality content first
- **Structured choices** replace inline {choice1|choice2} syntax
- **Nested sections** support complex document hierarchies

296
common/utils/bmad-doc-template.md Normal file
View File

@@ -0,0 +1,296 @@
# BMad Document Template Specification
## Overview
BMad document templates are defined in YAML format to drive interactive document generation and agent interaction. Templates separate structure definition from content generation, making them both human and LLM-agent-friendly.
## Template Structure
```yaml
template:
id: template-identifier
name: Human Readable Template Name
version: 1.0
output:
format: markdown
filename: default-path/to/{{filename}}.md
title: "{{variable}} Document Title"
workflow:
mode: interactive
elicitation: advanced-elicitation
sections:
- id: section-id
title: Section Title
instruction: |
Detailed instructions for the LLM on how to handle this section
# ... additional section properties
```
## Core Fields
### Template Metadata
- **id**: Unique identifier for the template
- **name**: Human-readable name displayed in UI
- **version**: Template version for tracking changes
- **output.format**: Default "markdown" for document templates
- **output.filename**: Default output file path (can include variables)
- **output.title**: Document title (becomes H1 in markdown)
### Workflow Configuration
- **workflow.mode**: Default interaction mode ("interactive" or "yolo")
- **workflow.elicitation**: Elicitation task to use ("advanced-elicitation")
## Section Properties
### Required Fields
- **id**: Unique section identifier
- **title**: Section heading text
- **instruction**: Detailed guidance for LLM on handling this section
### Optional Fields
#### Content Control
- **type**: Content type hint for structured sections
- **template**: Fixed template text for section content
- **item_template**: Template for repeatable items within section
- **prefix**: Prefix for numbered items (e.g., "FR", "NFR")
#### Behavior Flags
- **elicit**: Boolean - Apply elicitation after section rendered
- **repeatable**: Boolean - Section can be repeated multiple times
- **condition**: String - Condition for including section (e.g., "has ui requirements")
#### Content Guidance
- **examples**: Array of example content (not included in output)
- **choices**: Object with choice options for common decisions
- **placeholder**: Default placeholder text
#### Structure
- **sections**: Array of nested child sections
## Supported Types
### Content Types
- **bullet-list**: Unordered list items
- **numbered-list**: Ordered list with optional prefix
- **paragraphs**: Free-form paragraph text
- **table**: Structured table data
- **code-block**: Code or configuration blocks
- **template-text**: Fixed template with variable substitution
- **mermaid**: Mermaid diagram with specified type and details
### Special Types
- **repeatable-container**: Container for multiple instances
- **conditional-block**: Content shown based on conditions
- **choice-selector**: Present choices to user
## Advanced Features
### Variable Substitution
Use `{{variable_name}}` in titles, templates, and content:
```yaml
title: "Epic {{epic_number}} {{epic_title}}"
template: "As a {{user_type}}, I want {{action}}, so that {{benefit}}."
```
### Conditional Sections
```yaml
- id: ui-section
title: User Interface Design
condition: Project has UX/UI Requirements
instruction: Only include if project has UI components
```
### Choice Integration
```yaml
choices:
architecture: [Monolith, Microservices, Serverless]
testing: [Unit Only, Unit + Integration, Full Pyramid]
```
### Mermaid Diagrams
```yaml
- id: system-architecture
title: System Architecture Diagram
type: mermaid
instruction: Create a system architecture diagram showing key components and data flow
mermaid_type: flowchart
details: |
Show the following components:
- User interface layer
- API gateway
- Core services
- Database layer
- External integrations
```
**Supported mermaid_type values:**
**Core Diagram Types:**
- `flowchart` - Flow charts and process diagrams
- `sequenceDiagram` - Sequence diagrams for interactions
- `classDiagram` - Class relationship diagrams (UML)
- `stateDiagram` - State transition diagrams
- `erDiagram` - Entity relationship diagrams
- `gantt` - Gantt charts for timelines
- `pie` - Pie charts for data visualization
**Advanced Diagram Types:**
- `journey` - User journey maps
- `mindmap` - Mindmaps for brainstorming
- `timeline` - Timeline diagrams for chronological events
- `quadrantChart` - Quadrant charts for data categorization
- `xyChart` - XY charts (bar charts, line charts)
- `sankey` - Sankey diagrams for flow visualization
**Specialized Types:**
- `c4Context` - C4 context diagrams (experimental)
- `requirement` - Requirement diagrams
- `packet` - Network packet diagrams
- `block` - Block diagrams
- `kanban` - Kanban boards
### Repeatable Sections
```yaml
- id: epic-details
title: Epic {{epic_number}} {{epic_title}}
repeatable: true
sections:
- id: story
title: Story {{epic_number}}.{{story_number}} {{story_title}}
repeatable: true
sections:
- id: criteria
title: Acceptance Criteria
type: numbered-list
item_template: "{{criterion_number}}: {{criteria}}"
repeatable: true
```
### Examples with Code Blocks
````yaml
examples:
- "FR6: The system must authenticate users within 2 seconds"
- |
```mermaid
sequenceDiagram
participant User
participant API
participant DB
User->>API: POST /login
API->>DB: Validate credentials
DB-->>API: User data
API-->>User: JWT token
```
- |
**Architecture Decision Record**
**Decision**: Use PostgreSQL for primary database
**Rationale**: ACID compliance and JSON support needed
**Consequences**: Requires database management expertise
````
## Section Hierarchy
Templates define the complete document structure starting with the first H2 - each level in is the next H#:
```yaml
sections:
- id: overview
title: Project Overview
sections:
- id: goals
title: Goals
- id: scope
title: Scope
sections:
- id: in-scope
title: In Scope
- id: out-scope
title: Out of Scope
```
## Processing Flow
1. **Parse Template**: Load and validate YAML structure
2. **Initialize Workflow**: Set interaction mode and elicitation
3. **Process Sections**: Handle each section in order:
- Check conditions
- Apply instructions
- Generate content
- Handle choices and variables
- Apply elicitation if specified
- Process nested sections
4. **Generate Output**: Create clean markdown document
## Best Practices
### Template Design
- Keep instructions clear and specific
- Use examples for complex content
- Structure sections logically
- Include all necessary guidance for LLM
### Content Instructions
- Be explicit about expected format
- Include reasoning for decisions
- Specify interaction patterns
- Reference other documents when needed
### Variable Naming
- Use descriptive variable names
- Follow consistent naming conventions
- Document expected variable values
### Examples Usage
- Provide concrete examples for complex sections
- Include both simple and complex cases
- Use realistic project scenarios
- Include code blocks and diagrams when helpful
## Validation
Templates should be validated for:
- Valid YAML syntax
- Required fields present
- Consistent section IDs
- Proper nesting structure
- Valid variable references
## Migration from Legacy
When converting from markdown+frontmatter templates:
1. Extract embedded `[[LLM:]]` instructions to `instruction` fields
2. Convert `<<REPEAT>>` blocks to `repeatable: true` sections
3. Extract `^^CONDITIONS^^` to `condition` fields
4. Move `@{examples}` to `examples` arrays
5. Convert `{{placeholders}}` to proper variable syntax
This specification ensures templates are both human-readable and machine-processable while maintaining the flexibility needed for complex document generation.

731
dist/agents/analyst.txt vendored
View File

File diff suppressed because it is too large Load Diff

1005
dist/agents/bmad-master.txt vendored
View File

File diff suppressed because it is too large Load Diff

250
dist/agents/bmad-orchestrator.txt vendored
View File

@@ -185,91 +185,116 @@ dependencies:
- Provide optional reflective and brainstorming actions to enhance content quality - Provide optional reflective and brainstorming actions to enhance content quality
- Enable deeper exploration of ideas through structured elicitation techniques - Enable deeper exploration of ideas through structured elicitation techniques
- Support iterative refinement through multiple analytical perspectives - Support iterative refinement through multiple analytical perspectives
- Usable during template-driven document creation or any chat conversation
## Usage Scenarios
### Scenario 1: Template Document Creation
After outputting a section during document creation:
1. **Section Review**: Ask user to review the drafted section
2. **Offer Elicitation**: Present 9 carefully selected elicitation methods
3. **Simple Selection**: User types a number (0-8) to engage method, or 9 to proceed
4. **Execute & Loop**: Apply selected method, then re-offer choices until user proceeds
### Scenario 2: General Chat Elicitation
User can request advanced elicitation on any agent output:
- User says "do advanced elicitation" or similar
- Agent selects 9 relevant methods for the context
- Same simple 0-9 selection process
## Task Instructions ## Task Instructions
### 1. Section Context and Review ### 1. Intelligent Method Selection
[[LLM: When invoked after outputting a section: **Context Analysis**: Before presenting options, analyze:
1. First, provide a brief 1-2 sentence summary of what the user should look for in the section just presented (e.g., "Please review the technology choices for completeness and alignment with your project needs. Pay special attention to version numbers and any missing categories.") - **Content Type**: Technical specs, user stories, architecture, requirements, etc.
- **Complexity Level**: Simple, moderate, or complex content
- **Stakeholder Needs**: Who will use this information
- **Risk Level**: High-impact decisions vs routine items
- **Creative Potential**: Opportunities for innovation or alternatives
2. If the section contains Mermaid diagrams, explain each diagram briefly before offering elicitation options (e.g., "The component diagram shows the main system modules and their interactions. Notice how the API Gateway routes requests to different services.") **Method Selection Strategy**:
3. If the section contains multiple distinct items (like multiple components, multiple patterns, etc.), inform the user they can apply elicitation actions to: 1. **Always Include Core Methods** (choose 3-4):
- Expand or Contract for Audience
- Critique and Refine
- Identify Potential Risks
- Assess Alignment with Goals
2. **Context-Specific Methods** (choose 4-5):
- **Technical Content**: Tree of Thoughts, ReWOO, Meta-Prompting
- **User-Facing Content**: Agile Team Perspective, Stakeholder Roundtable
- **Creative Content**: Innovation Tournament, Escape Room Challenge
- **Strategic Content**: Red Team vs Blue Team, Hindsight Reflection
3. **Always Include**: "Proceed / No Further Actions" as option 9
### 2. Section Context and Review
When invoked after outputting a section:
1. **Provide Context Summary**: Give a brief 1-2 sentence summary of what the user should look for in the section just presented
2. **Explain Visual Elements**: If the section contains diagrams, explain them briefly before offering elicitation options
3. **Clarify Scope Options**: If the section contains multiple distinct items, inform the user they can apply elicitation actions to:
- The entire section as a whole - The entire section as a whole
- Individual items within the section (specify which item when selecting an action) - Individual items within the section (specify which item when selecting an action)
4. Then present the action list as specified below.]] ### 3. Present Elicitation Options
### 2. Ask for Review and Present Action List **Review Request Process:**
[[LLM: Ask the user to review the drafted section. In the SAME message, inform them that they can suggest additions, removals, or modifications, OR they can select an action by number from the 'Advanced Reflective, Elicitation & Brainstorming Actions'. If there are multiple items in the section, mention they can specify which item(s) to apply the action to. Then, present ONLY the numbered list (0-9) of these actions. Conclude by stating that selecting 9 will proceed to the next section. Await user selection. If an elicitation action (0-8) is chosen, execute it and then re-offer this combined review/elicitation choice. If option 9 is chosen, or if the user provides direct feedback, proceed accordingly.]] - Ask the user to review the drafted section
- In the SAME message, inform them they can suggest direct changes OR select an elicitation method
- Present 9 intelligently selected methods (0-8) plus "Proceed" (9)
- Keep descriptions short - just the method name
- Await simple numeric selection
**Present the numbered list (0-9) with this exact format:** **Action List Presentation Format:**
```text ```text
**Advanced Reflective, Elicitation & Brainstorming Actions** **Advanced Elicitation Options**
Choose an action (0-9 - 9 to bypass - HELP for explanation of these options): Choose a number (0-8) or 9 to proceed:
0. Expand or Contract for Audience 0. [Method Name]
1. Explain Reasoning (CoT Step-by-Step) 1. [Method Name]
2. Critique and Refine 2. [Method Name]
3. Analyze Logical Flow and Dependencies 3. [Method Name]
4. Assess Alignment with Overall Goals 4. [Method Name]
5. Identify Potential Risks and Unforeseen Issues 5. [Method Name]
6. Challenge from Critical Perspective (Self or Other Persona) 6. [Method Name]
7. Explore Diverse Alternatives (ToT-Inspired) 7. [Method Name]
8. Hindsight is 20/20: The 'If Only...' Reflection 8. [Method Name]
9. Proceed / No Further Actions 9. Proceed / No Further Actions
``` ```
### 2. Processing Guidelines **Response Handling:**
**Do NOT show:** - **Numbers 0-8**: Execute the selected method, then re-offer the choice
- **Number 9**: Proceed to next section or continue conversation
- **Direct Feedback**: Apply user's suggested changes and continue
- The full protocol text with `[[LLM: ...]]` instructions ### 4. Method Execution Framework
- Detailed explanations of each option unless executing or the user asks, when giving the definition you can modify to tie its relevance
- Any internal template markup
**After user selection from the list:** **Execution Process:**
- Execute the chosen action according to the protocol instructions below 1. **Retrieve Method**: Access the specific elicitation method from the elicitation-methods data file
- Ask if they want to select another action or proceed with option 9 once complete 2. **Apply Context**: Execute the method from your current role's perspective
- Continue until user selects option 9 or indicates completion 3. **Provide Results**: Deliver insights, critiques, or alternatives relevant to the content
4. **Re-offer Choice**: Present the same 9 options again until user selects 9 or gives direct feedback
## Action Definitions **Execution Guidelines:**
0. Expand or Contract for Audience - **Be Concise**: Focus on actionable insights, not lengthy explanations
[[LLM: Ask the user whether they want to 'expand' on the content (add more detail, elaborate) or 'contract' it (simplify, clarify, make more concise). Also, ask if there's a specific target audience they have in mind. Once clarified, perform the expansion or contraction from your current role's perspective, tailored to the specified audience if provided.]] - **Stay Relevant**: Tie all elicitation back to the specific content being analyzed
- **Identify Personas**: For multi-persona methods, clearly identify which viewpoint is speaking
1. Explain Reasoning (CoT Step-by-Step) - **Maintain Flow**: Keep the process moving efficiently
[[LLM: Explain the step-by-step thinking process, characteristic of your role, that you used to arrive at the current proposal for this content.]]
2. Critique and Refine
[[LLM: From your current role's perspective, review your last output or the current section for flaws, inconsistencies, or areas for improvement, and then suggest a refined version reflecting your expertise.]]
3. Analyze Logical Flow and Dependencies
[[LLM: From your role's standpoint, examine the content's structure for logical progression, internal consistency, and any relevant dependencies. Confirm if elements are presented in an effective order.]]
4. Assess Alignment with Overall Goals
[[LLM: Evaluate how well the current content contributes to the stated overall goals of the document, interpreting this from your specific role's perspective and identifying any misalignments you perceive.]]
5. Identify Potential Risks and Unforeseen Issues
[[LLM: Based on your role's expertise, brainstorm potential risks, overlooked edge cases, or unintended consequences related to the current content or proposal.]]
6. Challenge from Critical Perspective (Self or Other Persona)
[[LLM: Adopt a critical perspective on the current content. If the user specifies another role or persona (e.g., 'as a customer', 'as [Another Persona Name]'), critique the content or play devil's advocate from that specified viewpoint. If no other role is specified, play devil's advocate from your own current persona's viewpoint, arguing against the proposal or current content and highlighting weaknesses or counterarguments specific to your concerns. This can also randomly include YAGNI when appropriate, such as when trimming the scope of an MVP, the perspective might challenge the need for something to cut MVP scope.]]
7. Explore Diverse Alternatives (ToT-Inspired)
[[LLM: From your role's perspective, first broadly brainstorm a range of diverse approaches or solutions to the current topic. Then, from this wider exploration, select and present 2 distinct alternatives, detailing the pros, cons, and potential implications you foresee for each.]]
8. Hindsight is 20/20: The 'If Only...' Reflection
[[LLM: In your current persona, imagine it's a retrospective for a project based on the current content. What's the one 'if only we had known/done X...' that your role would humorously or dramatically highlight, along with the imagined consequences?]]
9. Proceed / No Further Actions
[[LLM: Acknowledge the user's choice to finalize the current work, accept the AI's last output as is, or move on to the next step without selecting another action from this list. Prepare to proceed accordingly.]]
==================== END: tasks#advanced-elicitation ==================== ==================== END: tasks#advanced-elicitation ====================
==================== START: tasks#create-doc ==================== ==================== START: tasks#create-doc ====================
@@ -1018,13 +1043,15 @@ BMad transforms you into a "Vibe CEO" - directing a team of specialized AI agent
### The Two-Phase Approach ### 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) - Use large context windows (Gemini's 1M tokens)
- Generate comprehensive documents (PRD, Architecture) - Generate comprehensive documents (PRD, Architecture)
- Leverage multiple agents for brainstorming - Leverage multiple agents for brainstorming
- Create once, use throughout development - Create once, use throughout development
**Phase 2: Development (IDE - Implementation)** #### Phase 2: Development (IDE - Implementation)
- Shard documents into manageable pieces - Shard documents into manageable pieces
- Execute focused SM → Dev cycles - Execute focused SM → Dev cycles
- One story at a time, sequential progress - One story at a time, sequential progress
@@ -1054,6 +1081,7 @@ BMad transforms you into a "Vibe CEO" - directing a team of specialized AI agent
### Quick Start Options ### Quick Start Options
#### Option 1: Web UI #### Option 1: Web UI
**Best for**: ChatGPT, Claude, Gemini users who want to start immediately **Best for**: ChatGPT, Claude, Gemini users who want to start immediately
1. Navigate to `dist/teams/` 1. Navigate to `dist/teams/`
@@ -1063,6 +1091,7 @@ BMad transforms you into a "Vibe CEO" - directing a team of specialized AI agent
5. Type `/help` to see available commands 5. Type `/help` to see available commands
#### Option 2: IDE Integration #### Option 2: IDE Integration
**Best for**: Cursor, Claude Code, Windsurf, Trae, Cline, Roo Code, Github Copilot users **Best for**: Cursor, Claude Code, Windsurf, Trae, Cline, Roo Code, Github Copilot users
```bash ```bash
@@ -1071,6 +1100,7 @@ npx bmad-method install
``` ```
**Installation Steps**: **Installation Steps**:
- Choose "Complete installation" - Choose "Complete installation"
- Select your IDE from supported options: - Select your IDE from supported options:
- **Cursor**: Native AI integration - **Cursor**: Native AI integration
@@ -1084,6 +1114,7 @@ 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. **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**: **Verify Installation**:
- `.bmad-core/` folder created with all agents - `.bmad-core/` folder created with all agents
- IDE-specific integration files created - IDE-specific integration files created
- All agent commands/rules/modes available - All agent commands/rules/modes available
@@ -1093,12 +1124,14 @@ npx bmad-method install
### Environment Selection Guide ### Environment Selection Guide
**Use Web UI for**: **Use Web UI for**:
- Initial planning and documentation (PRD, architecture) - Initial planning and documentation (PRD, architecture)
- Cost-effective document creation (especially with Gemini) - Cost-effective document creation (especially with Gemini)
- Brainstorming and analysis phases - Brainstorming and analysis phases
- Multi-agent consultation and planning - Multi-agent consultation and planning
**Use IDE for**: **Use IDE for**:
- Active development and coding - Active development and coding
- File operations and project integration - File operations and project integration
- Document sharding and story management - Document sharding and story management
@@ -1111,35 +1144,41 @@ npx bmad-method install
**Can you do everything in IDE?** Yes, but understand the tradeoffs: **Can you do everything in IDE?** Yes, but understand the tradeoffs:
**Pros of IDE-Only**: **Pros of IDE-Only**:
- Single environment workflow - Single environment workflow
- Direct file operations from start - Direct file operations from start
- No copy/paste between environments - No copy/paste between environments
- Immediate project integration - Immediate project integration
**Cons of IDE-Only**: **Cons of IDE-Only**:
- Higher token costs for large document creation - Higher token costs for large document creation
- Smaller context windows (varies by IDE/model) - Smaller context windows (varies by IDE/model)
- May hit limits during planning phases - May hit limits during planning phases
- Less cost-effective for brainstorming - Less cost-effective for brainstorming
**Using Web Agents in IDE**: **Using Web Agents in IDE**:
- **NOT RECOMMENDED**: Web agents (PM, Architect) have rich dependencies designed for large contexts - **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 - **Why it matters**: Dev agents are kept lean to maximize coding context
- **The principle**: "Dev agents code, planning agents plan" - mixing breaks this optimization - **The principle**: "Dev agents code, planning agents plan" - mixing breaks this optimization
**About bmad-master and bmad-orchestrator**: **About bmad-master and bmad-orchestrator**:
- **bmad-master**: CAN do any task without switching agents, BUT... - **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 - **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 - **Why specialization matters**: Each agent's personality and focus creates higher quality outputs
- **If using bmad-master/orchestrator**: Fine for planning phases, but... - **If using bmad-master/orchestrator**: Fine for planning phases, but...
**CRITICAL RULE for Development**: **CRITICAL RULE for Development**:
- **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator - **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator
- **ALWAYS use Dev agent for implementation** - 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 - **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 - **No exceptions**: Even if using bmad-master for everything else, switch to SM → Dev for implementation
**Best Practice for IDE-Only**: **Best Practice for IDE-Only**:
1. Use PM/Architect/UX agents for planning (better than bmad-master) 1. Use PM/Architect/UX agents for planning (better than bmad-master)
2. Create documents directly in project 2. Create documents directly in project
3. Shard immediately after creation 3. Shard immediately after creation
@@ -1163,17 +1202,20 @@ This configuration file acts as a map for BMad agents, telling them exactly wher
### Key Configuration Areas ### Key Configuration Areas
#### PRD Configuration #### PRD Configuration
- **prdVersion**: Tells agents if PRD follows v3 or v4 conventions - **prdVersion**: Tells agents if PRD follows v3 or v4 conventions
- **prdSharded**: Whether epics are embedded (false) or in separate files (true) - **prdSharded**: Whether epics are embedded (false) or in separate files (true)
- **prdShardedLocation**: Where to find sharded epic files - **prdShardedLocation**: Where to find sharded epic files
- **epicFilePattern**: Pattern for epic filenames (e.g., `epic-{n}*.md`) - **epicFilePattern**: Pattern for epic filenames (e.g., `epic-{n}*.md`)
#### Architecture Configuration #### Architecture Configuration
- **architectureVersion**: v3 (monolithic) or v4 (sharded) - **architectureVersion**: v3 (monolithic) or v4 (sharded)
- **architectureSharded**: Whether architecture is split into components - **architectureSharded**: Whether architecture is split into components
- **architectureShardedLocation**: Where sharded architecture files live - **architectureShardedLocation**: Where sharded architecture files live
#### Developer Files #### Developer Files
- **devLoadAlwaysFiles**: List of files the dev agent loads for every task - **devLoadAlwaysFiles**: List of files the dev agent loads for every task
- **devDebugLog**: Where dev agent logs repeated failures - **devDebugLog**: Where dev agent logs repeated failures
- **agentCoreDump**: Export location for chat conversations - **agentCoreDump**: Export location for chat conversations
@@ -1188,6 +1230,7 @@ This configuration file acts as a map for BMad agents, telling them exactly wher
### Common Configurations ### Common Configurations
**Legacy V3 Project**: **Legacy V3 Project**:
```yaml ```yaml
prdVersion: v3 prdVersion: v3
prdSharded: false prdSharded: false
@@ -1196,6 +1239,7 @@ architectureSharded: false
``` ```
**V4 Optimized Project**: **V4 Optimized Project**:
```yaml ```yaml
prdVersion: v4 prdVersion: v4
prdSharded: true prdSharded: true
@@ -1261,6 +1305,7 @@ You are the "Vibe CEO" - thinking like a CEO with unlimited resources and a sing
#### IDE-Specific Syntax #### IDE-Specific Syntax
**Agent Loading by IDE**: **Agent Loading by IDE**:
- **Claude Code**: `/agent-name` (e.g., `/bmad-master`) - **Claude Code**: `/agent-name` (e.g., `/bmad-master`)
- **Cursor**: `@agent-name` (e.g., `@bmad-master`) - **Cursor**: `@agent-name` (e.g., `@bmad-master`)
- **Windsurf**: `@agent-name` (e.g., `@bmad-master`) - **Windsurf**: `@agent-name` (e.g., `@bmad-master`)
@@ -1269,10 +1314,12 @@ 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. - **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**: **Chat Management Guidelines**:
- **Claude Code, Cursor, Windsurf, Trae**: Start new chats when switching agents - **Claude Code, Cursor, Windsurf, Trae**: Start new chats when switching agents
- **Roo Code**: Switch modes within the same conversation - **Roo Code**: Switch modes within the same conversation
**Common Task Commands**: **Common Task Commands**:
- `*help` - Show available commands - `*help` - Show available commands
- `*status` - Show current context/progress - `*status` - Show current context/progress
- `*exit` - Exit the agent mode - `*exit` - Exit the agent mode
@@ -1281,6 +1328,7 @@ You are the "Vibe CEO" - thinking like a CEO with unlimited resources and a sing
- `*create` - Run create-next-story task (SM agent) - `*create` - Run create-next-story task (SM agent)
**In Web UI**: **In Web UI**:
```text ```text
/pm create-doc prd /pm create-doc prd
/architect review system design /architect review system design
@@ -1294,16 +1342,19 @@ You are the "Vibe CEO" - thinking like a CEO with unlimited resources and a sing
### Pre-Built Teams ### Pre-Built Teams
#### Team All #### Team All
- **Includes**: All 10 agents + orchestrator - **Includes**: All 10 agents + orchestrator
- **Use Case**: Complete projects requiring all roles - **Use Case**: Complete projects requiring all roles
- **Bundle**: `team-all.txt` - **Bundle**: `team-all.txt`
#### Team Fullstack #### Team Fullstack
- **Includes**: PM, Architect, Developer, QA, UX Expert - **Includes**: PM, Architect, Developer, QA, UX Expert
- **Use Case**: End-to-end web/mobile development - **Use Case**: End-to-end web/mobile development
- **Bundle**: `team-fullstack.txt` - **Bundle**: `team-fullstack.txt`
#### Team No-UI #### Team No-UI
- **Includes**: PM, Architect, Developer, QA (no UX Expert) - **Includes**: PM, Architect, Developer, QA (no UX Expert)
- **Use Case**: Backend services, APIs, system development - **Use Case**: Backend services, APIs, system development
- **Bundle**: `team-no-ui.txt` - **Bundle**: `team-no-ui.txt`
@@ -1317,22 +1368,26 @@ The BMad-Method is built around a modular architecture centered on the `bmad-cor
### Key Architectural Components ### Key Architectural Components
#### 1. Agents (`bmad-core/agents/`) #### 1. Agents (`bmad-core/agents/`)
- **Purpose**: Each markdown file defines a specialized AI agent for a specific Agile role (PM, Dev, Architect, etc.) - **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 - **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 - **Dependencies**: Lists of tasks, templates, checklists, and data files the agent can use
- **Startup Instructions**: Can load project-specific documentation for immediate context - **Startup Instructions**: Can load project-specific documentation for immediate context
#### 2. Agent Teams (`bmad-core/agent-teams/`) #### 2. Agent Teams (`bmad-core/agent-teams/`)
- **Purpose**: Define collections of agents bundled together for specific purposes - **Purpose**: Define collections of agents bundled together for specific purposes
- **Examples**: `team-all.yaml` (comprehensive bundle), `team-fullstack.yaml` (full-stack development) - **Examples**: `team-all.yaml` (comprehensive bundle), `team-fullstack.yaml` (full-stack development)
- **Usage**: Creates pre-packaged contexts for web UI environments - **Usage**: Creates pre-packaged contexts for web UI environments
#### 3. Workflows (`bmad-core/workflows/`) #### 3. Workflows (`bmad-core/workflows/`)
- **Purpose**: YAML files defining prescribed sequences of steps for specific project types - **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 - **Types**: Greenfield (new projects) and Brownfield (existing projects) for UI, service, and fullstack development
- **Structure**: Defines agent interactions, artifacts created, and transition conditions - **Structure**: Defines agent interactions, artifacts created, and transition conditions
#### 4. Reusable Resources #### 4. Reusable Resources
- **Templates** (`bmad-core/templates/`): Markdown templates for PRDs, architecture specs, user stories - **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" - **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 - **Checklists** (`bmad-core/checklists/`): Quality assurance checklists for validation and review
@@ -1372,6 +1427,7 @@ BMad employs a sophisticated template system with three key components:
### Technical Preferences Integration ### Technical Preferences Integration
The `technical-preferences.md` file serves as a persistent technical profile that: The `technical-preferences.md` file serves as a persistent technical profile that:
- Ensures consistency across all agents and projects - Ensures consistency across all agents and projects
- Eliminates repetitive technology specification - Eliminates repetitive technology specification
- Provides personalized recommendations aligned with user preferences - Provides personalized recommendations aligned with user preferences
@@ -1380,6 +1436,7 @@ The `technical-preferences.md` file serves as a persistent technical profile tha
### Build and Delivery Process ### Build and Delivery Process
The `web-builder.js` tool creates web-ready bundles by: The `web-builder.js` tool creates web-ready bundles by:
1. Reading agent or team definition files 1. Reading agent or team definition files
2. Recursively resolving all dependencies 2. Recursively resolving all dependencies
3. Concatenating content into single text files with clear separators 3. Concatenating content into single text files with clear separators
@@ -1394,11 +1451,13 @@ This architecture enables seamless operation across environments while maintaini
**Ideal for cost efficiency with Gemini's massive context:** **Ideal for cost efficiency with Gemini's massive context:**
**For Brownfield Projects - Start Here!**: **For Brownfield Projects - Start Here!**:
1. **Upload entire project to Gemini Web** (GitHub URL, files, or zip) 1. **Upload entire project to Gemini Web** (GitHub URL, files, or zip)
2. **Document existing system**: `/analyst` → `*document-project` 2. **Document existing system**: `/analyst` → `*document-project`
3. **Creates comprehensive docs** from entire codebase analysis 3. **Creates comprehensive docs** from entire codebase analysis
**For All Projects**: **For All Projects**:
1. **Optional Analysis**: `/analyst` - Market research, competitive analysis 1. **Optional Analysis**: `/analyst` - Market research, competitive analysis
2. **Project Brief**: Create foundation document (Analyst or user) 2. **Project Brief**: Create foundation document (Analyst or user)
3. **PRD Creation**: `/pm create-doc prd` - Comprehensive product requirements 3. **PRD Creation**: `/pm create-doc prd` - Comprehensive product requirements
@@ -1409,12 +1468,14 @@ This architecture enables seamless operation across environments while maintaini
#### Example Planning Prompts #### Example Planning Prompts
**For PRD Creation**: **For PRD Creation**:
```text ```text
"I want to build a [type] application that [core purpose]. "I want to build a [type] application that [core purpose].
Help me brainstorm features and create a comprehensive PRD." Help me brainstorm features and create a comprehensive PRD."
``` ```
**For Architecture Design**: **For Architecture Design**:
```text ```text
"Based on this PRD, design a scalable technical architecture "Based on this PRD, design a scalable technical architecture
that can handle [specific requirements]." that can handle [specific requirements]."
@@ -1432,7 +1493,7 @@ that can handle [specific requirements]."
**Prerequisites**: Planning documents must exist in `docs/` folder **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 - Documents created by PM/Architect (in Web or IDE) MUST be sharded for development
- Two methods to shard: - Two methods to shard:
a) **Manual**: Drag `shard-doc` task + document file into chat a) **Manual**: Drag `shard-doc` task + document file into chat
@@ -1446,32 +1507,33 @@ that can handle [specific requirements]."
- Source tree document and coding standards for dev agent reference - Source tree document and coding standards for dev agent reference
- Sharded docs for SM agent story creation - Sharded docs for SM agent story creation
**Resulting Folder Structure**: Resulting Folder Structure:
- `docs/prd/` - Broken down PRD sections - `docs/prd/` - Broken down PRD sections
- `docs/architecture/` - Broken down architecture sections - `docs/architecture/` - Broken down architecture sections
- `docs/stories/` - Generated user stories - `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**: **CRITICAL CONTEXT MANAGEMENT**:
- **Context windows matter!** Always use fresh, clean context windows - **Context windows matter!** Always use fresh, clean context windows
- **Model selection matters!** Use most powerful thinking model for SM story creation - **Model selection matters!** Use most powerful thinking model for SM story creation
- **ALWAYS start new chat between SM, Dev, and QA work** - **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` - **NEW CLEAN CHAT** → Select powerful model → `@sm` → `*create`
- SM executes create-next-story task - SM executes create-next-story task
- Review generated story in `docs/stories/` - Review generated story in `docs/stories/`
- Update status from "Draft" to "Approved" - Update status from "Draft" to "Approved"
**Step 2 - Story Implementation**: **Step 2 - Story Implementation**:
- **NEW CLEAN CHAT** → `@dev` - **NEW CLEAN CHAT** → `@dev`
- Agent asks which story to implement - Agent asks which story to implement
- Include story file content to save dev agent lookup time - Include story file content to save dev agent lookup time
- Dev follows tasks/subtasks, marking completion - Dev follows tasks/subtasks, marking completion
- Dev maintains File List of all changes - Dev maintains File List of all changes
- Dev marks story as "Review" when complete with all tests passing - Dev marks story as "Review" when complete with all tests passing
**Step 3 - Senior QA Review**: **Step 3 - Senior QA Review**:
- **NEW CLEAN CHAT** → `@qa` → execute review-story task - **NEW CLEAN CHAT** → `@qa` → execute review-story task
- QA performs senior developer code review - QA performs senior developer code review
@@ -1479,7 +1541,7 @@ that can handle [specific requirements]."
- QA appends results to story's QA Results section - QA appends results to story's QA Results section
- If approved: Status → "Done" - If approved: Status → "Done"
- If changes needed: Status stays "Review" with unchecked items for dev - If changes needed: Status stays "Review" with unchecked items for dev
**Step 4 - Repeat**: Continue SM → Dev → QA cycle until all epic stories complete **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. **Important**: Only 1 story in progress at a time, worked sequentially until all epic stories complete.
@@ -1487,6 +1549,7 @@ that can handle [specific requirements]."
### Status Tracking Workflow ### Status Tracking Workflow
Stories progress through defined statuses: Stories progress through defined statuses:
- **Draft** → **Approved** → **InProgress** → **Done** - **Draft** → **Approved** → **InProgress** → **Done**
Each status change requires user verification and approval before proceeding. Each status change requires user verification and approval before proceeding.
@@ -1494,6 +1557,7 @@ Each status change requires user verification and approval before proceeding.
### Workflow Types ### Workflow Types
#### Greenfield Development #### Greenfield Development
- Business analysis and market research - Business analysis and market research
- Product requirements and feature definition - Product requirements and feature definition
- System architecture and design - System architecture and design
@@ -1507,6 +1571,7 @@ Each status change requires user verification and approval before proceeding.
**Complete Brownfield Workflow Options**: **Complete Brownfield Workflow Options**:
**Option 1: PRD-First (Recommended for Large Codebases/Monorepos)**: **Option 1: PRD-First (Recommended for Large Codebases/Monorepos)**:
1. **Upload project to Gemini Web** (GitHub URL, files, or zip) 1. **Upload project to Gemini Web** (GitHub URL, files, or zip)
2. **Create PRD first**: `@pm` → `*create-doc brownfield-prd` 2. **Create PRD first**: `@pm` → `*create-doc brownfield-prd`
3. **Focused documentation**: `@analyst` → `*document-project` 3. **Focused documentation**: `@analyst` → `*document-project`
@@ -1517,18 +1582,19 @@ Each status change requires user verification and approval before proceeding.
- Avoids bloating docs with unused code - Avoids bloating docs with unused code
**Option 2: Document-First (Good for Smaller Projects)**: **Option 2: Document-First (Good for Smaller Projects)**:
1. **Upload project to Gemini Web** 1. **Upload project to Gemini Web**
2. **Document everything**: `@analyst` → `*document-project` 2. **Document everything**: `@analyst` → `*document-project`
3. **Then create PRD**: `@pm` → `*create-doc brownfield-prd` 3. **Then create PRD**: `@pm` → `*create-doc brownfield-prd`
- More thorough but can create excessive documentation - More thorough but can create excessive documentation
2. **Requirements Gathering**: 4. **Requirements Gathering**:
- **Brownfield PRD**: Use PM agent with `brownfield-prd-tmpl` - **Brownfield PRD**: Use PM agent with `brownfield-prd-tmpl`
- **Analyzes**: Existing system, constraints, integration points - **Analyzes**: Existing system, constraints, integration points
- **Defines**: Enhancement scope, compatibility requirements, risk assessment - **Defines**: Enhancement scope, compatibility requirements, risk assessment
- **Creates**: Epic and story structure for changes - **Creates**: Epic and story structure for changes
3. **Architecture Planning**: 5. **Architecture Planning**:
- **Brownfield Architecture**: Use Architect agent with `brownfield-architecture-tmpl` - **Brownfield Architecture**: Use Architect agent with `brownfield-architecture-tmpl`
- **Integration Strategy**: How new features integrate with existing system - **Integration Strategy**: How new features integrate with existing system
- **Migration Planning**: Gradual rollout and backwards compatibility - **Migration Planning**: Gradual rollout and backwards compatibility
@@ -1537,10 +1603,12 @@ Each status change requires user verification and approval before proceeding.
**Brownfield-Specific Resources**: **Brownfield-Specific Resources**:
**Templates**: **Templates**:
- `brownfield-prd-tmpl.md`: Comprehensive enhancement planning with existing system analysis - `brownfield-prd-tmpl.md`: Comprehensive enhancement planning with existing system analysis
- `brownfield-architecture-tmpl.md`: Integration-focused architecture for existing systems - `brownfield-architecture-tmpl.md`: Integration-focused architecture for existing systems
**Tasks**: **Tasks**:
- `document-project`: Generates comprehensive documentation from existing codebase - `document-project`: Generates comprehensive documentation from existing codebase
- `brownfield-create-epic`: Creates single epic for focused enhancements (when full PRD is overkill) - `brownfield-create-epic`: Creates single epic for focused enhancements (when full PRD is overkill)
- `brownfield-create-story`: Creates individual story for small, isolated changes - `brownfield-create-story`: Creates individual story for small, isolated changes
@@ -1548,18 +1616,21 @@ Each status change requires user verification and approval before proceeding.
**When to Use Each Approach**: **When to Use Each Approach**:
**Full Brownfield Workflow** (Recommended for): **Full Brownfield Workflow** (Recommended for):
- Major feature additions - Major feature additions
- System modernization - System modernization
- Complex integrations - Complex integrations
- Multiple related changes - Multiple related changes
**Quick Epic/Story Creation** (Use when): **Quick Epic/Story Creation** (Use when):
- Single, focused enhancement - Single, focused enhancement
- Isolated bug fixes - Isolated bug fixes
- Small feature additions - Small feature additions
- Well-documented existing system - Well-documented existing system
**Critical Success Factors**: **Critical Success Factors**:
1. **Documentation First**: Always run `document-project` if docs are outdated/missing 1. **Documentation First**: Always run `document-project` if docs are outdated/missing
2. **Context Matters**: Provide agents access to relevant code sections 2. **Context Matters**: Provide agents access to relevant code sections
3. **Integration Focus**: Emphasize compatibility and non-breaking changes 3. **Integration Focus**: Emphasize compatibility and non-breaking changes
@@ -1575,6 +1646,7 @@ Each status change requires user verification and approval before proceeding.
- `docs/architecture.md` - System Architecture Document - `docs/architecture.md` - System Architecture Document
**Why These Names Matter**: **Why These Names Matter**:
- Agents automatically reference these files during development - Agents automatically reference these files during development
- Sharding tasks expect these specific filenames - Sharding tasks expect these specific filenames
- Workflow automation depends on standard naming - Workflow automation depends on standard naming
@@ -1593,6 +1665,7 @@ Each status change requires user verification and approval before proceeding.
Templates with Level 2 headings (`##`) can be automatically sharded: Templates with Level 2 headings (`##`) can be automatically sharded:
**Original PRD**: **Original PRD**:
```markdown ```markdown
## Goals and Background Context ## Goals and Background Context
## Requirements ## Requirements
@@ -1601,6 +1674,7 @@ Templates with Level 2 headings (`##`) can be automatically sharded:
``` ```
**After Sharding**: **After Sharding**:
- `docs/prd/goals-and-background-context.md` - `docs/prd/goals-and-background-context.md`
- `docs/prd/requirements.md` - `docs/prd/requirements.md`
- `docs/prd/user-interface-design-goals.md` - `docs/prd/user-interface-design-goals.md`
@@ -1613,12 +1687,14 @@ Use the `shard-doc` task or `@kayvan/markdown-tree-parser` tool for automatic sh
### Environment-Specific Usage ### Environment-Specific Usage
**Web UI Best For**: **Web UI Best For**:
- Initial planning and documentation phases - Initial planning and documentation phases
- Cost-effective large document creation - Cost-effective large document creation
- Agent consultation and brainstorming - Agent consultation and brainstorming
- Multi-agent workflows with orchestrator - Multi-agent workflows with orchestrator
**IDE Best For**: **IDE Best For**:
- Active development and implementation - Active development and implementation
- File operations and project integration - File operations and project integration
- Story management and development cycles - Story management and development cycles
@@ -1653,6 +1729,7 @@ Use the `shard-doc` task or `@kayvan/markdown-tree-parser` tool for automatic sh
For full details, see `CONTRIBUTING.md`. Key points: For full details, see `CONTRIBUTING.md`. Key points:
**Fork Workflow**: **Fork Workflow**:
1. Fork the repository 1. Fork the repository
2. Create feature branches 2. Create feature branches
3. Submit PRs to `next` branch (default) or `main` for critical fixes only 3. Submit PRs to `next` branch (default) or `main` for critical fixes only
@@ -1660,12 +1737,14 @@ For full details, see `CONTRIBUTING.md`. Key points:
5. One feature/fix per PR 5. One feature/fix per PR
**PR Requirements**: **PR Requirements**:
- Clear descriptions (max 200 words) with What/Why/How/Testing - Clear descriptions (max 200 words) with What/Why/How/Testing
- Use conventional commits (feat:, fix:, docs:) - Use conventional commits (feat:, fix:, docs:)
- Atomic commits - one logical change per commit - Atomic commits - one logical change per commit
- Must align with guiding principles - Must align with guiding principles
**Core Principles** (from GUIDING-PRINCIPLES.md): **Core Principles** (from GUIDING-PRINCIPLES.md):
- **Dev Agents Must Be Lean**: Minimize dependencies, save context for code - **Dev Agents Must Be Lean**: Minimize dependencies, save context for code
- **Natural Language First**: Everything in markdown, no code in core - **Natural Language First**: Everything in markdown, no code in core
- **Core vs Expansion Packs**: Core for universal needs, packs for specialized domains - **Core vs Expansion Packs**: Core for universal needs, packs for specialized domains
@@ -1687,12 +1766,14 @@ Expansion packs extend BMad-Method beyond traditional software development into
### Available Expansion Packs ### Available Expansion Packs
**Technical Packs**: **Technical Packs**:
- **Infrastructure/DevOps**: Cloud architects, SRE experts, security specialists - **Infrastructure/DevOps**: Cloud architects, SRE experts, security specialists
- **Game Development**: Game designers, level designers, narrative writers - **Game Development**: Game designers, level designers, narrative writers
- **Mobile Development**: iOS/Android specialists, mobile UX experts - **Mobile Development**: iOS/Android specialists, mobile UX experts
- **Data Science**: ML engineers, data scientists, visualization experts - **Data Science**: ML engineers, data scientists, visualization experts
**Non-Technical Packs**: **Non-Technical Packs**:
- **Business Strategy**: Consultants, financial analysts, marketing strategists - **Business Strategy**: Consultants, financial analysts, marketing strategists
- **Creative Writing**: Plot architects, character developers, world builders - **Creative Writing**: Plot architects, character developers, world builders
- **Health & Wellness**: Fitness trainers, nutritionists, habit engineers - **Health & Wellness**: Fitness trainers, nutritionists, habit engineers
@@ -1700,6 +1781,7 @@ Expansion packs extend BMad-Method beyond traditional software development into
- **Legal Support**: Contract analysts, compliance checkers - **Legal Support**: Contract analysts, compliance checkers
**Specialty Packs**: **Specialty Packs**:
- **Expansion Creator**: Tools to build your own expansion packs - **Expansion Creator**: Tools to build your own expansion packs
- **RPG Game Master**: Tabletop gaming assistance - **RPG Game Master**: Tabletop gaming assistance
- **Life Event Planning**: Wedding planners, event coordinators - **Life Event Planning**: Wedding planners, event coordinators
@@ -1709,11 +1791,13 @@ Expansion packs extend BMad-Method beyond traditional software development into
1. **Browse Available Packs**: Check `expansion-packs/` directory 1. **Browse Available Packs**: Check `expansion-packs/` directory
2. **Get Inspiration**: See `docs/expansion-packs.md` for detailed examples and ideas 2. **Get Inspiration**: See `docs/expansion-packs.md` for detailed examples and ideas
3. **Install via CLI**: 3. **Install via CLI**:
```bash ```bash
npx bmad-method install npx bmad-method install
# Select "Install expansion pack" option # Select "Install expansion pack" option
``` ```
4. **Use in Your Workflow**: Installed packs integrate seamlessly with existing agents 4. **Use in Your Workflow**: Installed packs integrate seamlessly with existing agents
### Creating Custom Expansion Packs ### Creating Custom Expansion Packs
@@ -1747,14 +1831,10 @@ Provides utilities for agents and tasks to interact with workflow plans, check p
### 1. Check Plan Existence ### 1. Check Plan Existence
[[LLM: When any agent starts or task begins, check if a workflow plan exists]]
```
Check for workflow plan: Check for workflow plan:
1. Look for docs/workflow-plan.md (default location) 1. Look for docs/workflow-plan.md (default location)
2. Check core-config.yaml for custom plan location 2. Return plan status to user (exists/not exists) - if not exists then HALT.
3. Return plan status (exists/not exists)
```
### 2. Parse Plan Status ### 2. Parse Plan Status
@@ -1795,7 +1875,7 @@ Check for workflow plan:
**Warning Templates:** **Warning Templates:**
``` ```text
SEQUENCE WARNING: SEQUENCE WARNING:
The workflow plan shows you should complete "{expected_step}" next. The workflow plan shows you should complete "{expected_step}" next.
You're attempting to: "{requested_action}" You're attempting to: "{requested_action}"
@@ -1829,7 +1909,7 @@ In flexible mode: Allow with confirmation
**For Agents (startup sequence)**: **For Agents (startup sequence)**:
``` ```text
1. Check if plan exists using this utility 1. Check if plan exists using this utility
2. If exists: 2. If exists:
- Parse current status - Parse current status
@@ -1840,7 +1920,7 @@ In flexible mode: Allow with confirmation
**For Tasks (pre-execution)**: **For Tasks (pre-execution)**:
``` ```text
1. Check if plan exists 1. Check if plan exists
2. If exists: 2. If exists:
- Verify this task aligns with plan - Verify this task aligns with plan
@@ -1856,7 +1936,7 @@ In flexible mode: Allow with confirmation
[[LLM: Standard format for showing plan status]] [[LLM: Standard format for showing plan status]]
``` ```text
📋 Workflow Plan Status 📋 Workflow Plan Status
━━━━━━━━━━━━━━━━━━━━ ━━━━━━━━━━━━━━━━━━━━
Workflow: {workflow_name} Workflow: {workflow_name}
@@ -1909,7 +1989,7 @@ If user wants to abandon plan:
### Example 1: Agent Startup Check ### Example 1: Agent Startup Check
``` ```text
BMad Master starting... BMad Master starting...
[Check for plan] [Check for plan]
@@ -1923,7 +2003,7 @@ Use *agent pm to switch, or *plan-status to see full progress.
### Example 2: Task Sequence Warning ### Example 2: Task Sequence Warning
``` ```text
User: *task create-next-story User: *task create-next-story
[Plan check triggered] [Plan check triggered]
@@ -1939,7 +2019,7 @@ Would you like to:
### Example 3: Automatic Plan Update ### Example 3: Automatic Plan Update
``` ```text
[After completing create-doc task for PRD] [After completing create-doc task for PRD]
✅ Plan Updated: Marked "Create PRD" as complete ✅ Plan Updated: Marked "Create PRD" as complete

525
dist/expansion-packs/bmad-2d-phaser-game-dev/teams/phaser-2d-nodejs-game-team.txt vendored
View File

@@ -104,7 +104,7 @@ commands:
- exit: Say goodbye as the Business Analyst, and then abandon inhabiting this persona - exit: Say goodbye as the Business Analyst, and then abandon inhabiting this persona
dependencies: dependencies:
tasks: tasks:
- brainstorming-techniques - facilitate-brainstorming-session
- create-deep-research-prompt - create-deep-research-prompt
- create-doc - create-doc
- advanced-elicitation - advanced-elicitation
@@ -113,8 +113,10 @@ dependencies:
- project-brief-tmpl - project-brief-tmpl
- market-research-tmpl - market-research-tmpl
- competitor-analysis-tmpl - competitor-analysis-tmpl
- brainstorming-output-tmpl
data: data:
- bmad-kb - bmad-kb
- brainstorming-techniques
utils: utils:
- template-format - template-format
``` ```
@@ -443,246 +445,144 @@ dependencies:
``` ```
==================== END: agents#game-sm ==================== ==================== END: agents#game-sm ====================
==================== START: tasks#brainstorming-techniques ==================== ==================== START: tasks#facilitate-brainstorming-session ====================
# Brainstorming Techniques Task ---
docOutputLocation: docs/brainstorming-session-results.md
template: brainstorming-output-tmpl
---
This task provides a comprehensive toolkit of creative brainstorming techniques for ideation and innovative thinking. The analyst can use these techniques to facilitate productive brainstorming sessions with users. # Facilitate Brainstorming Session Task
Facilitate interactive brainstorming sessions with users. Be creative and adaptive in applying techniques.
## Process ## Process
### 1. Session Setup ### Step 1: Session Setup
[[LLM: Begin by understanding the brainstorming context and goals. Ask clarifying questions if needed to determine the best approach.]] Ask 4 context questions (don't preview what happens next):
1. **Establish Context** 1. What are we brainstorming about?
2. Any constraints or parameters?
3. Goal: broad exploration or focused ideation?
4. Do you want a structured document output to reference later? (Y/N)
- Understand the problem space or opportunity area ### Step 2: Present Approach Options
- Identify any constraints or parameters
- Determine session goals (divergent exploration vs. focused ideation)
2. **Select Technique Approach** After getting answers to Step 1, present 4 approach options (numbered):
- Option A: User selects specific techniques
- Option B: Analyst recommends techniques based on context
- Option C: Random technique selection for creative variety
- Option D: Progressive technique flow (start broad, narrow down)
### 2. Core Brainstorming Techniques 1. User selects specific techniques
2. Analyst recommends techniques based on context
3. Random technique selection for creative variety
4. Progressive technique flow (start broad, narrow down)
#### Creative Expansion Techniques ### Step 3: Execute Techniques Interactively
1. **"What If" Scenarios** **KEY PRINCIPLES:**
[[LLM: Generate provocative what-if questions that challenge assumptions and expand thinking beyond current limitations.]]
- What if we had unlimited resources? - **FACILITATOR ROLE**: Guide user to generate their own ideas through questions, prompts, and examples
- What if this problem didn't exist? - **CONTINUOUS ENGAGEMENT**: Keep user engaged with chosen technique until they want to switch or are satisfied
- What if we approached this from a child's perspective? - **CAPTURE OUTPUT**: If document output requested, capture all ideas generated in each technique section
- What if we had to solve this in 24 hours?
2. **Analogical Thinking** **Technique Selection:**
[[LLM: Help user draw parallels between their challenge and other domains, industries, or natural systems.]] If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number (e.g., "7" for Mind Mapping).
- "How might this work like [X] but for [Y]?" **Technique Execution:**
- Nature-inspired solutions (biomimicry)
- Cross-industry pattern matching
- Historical precedent analysis
3. **Reversal/Inversion** 1. Apply selected technique according to data file description
[[LLM: Flip the problem or approach it from the opposite angle to reveal new insights.]] 2. Keep engaging with technique until user indicates they want to:
- Choose a different technique
- Apply current ideas to a new technique
- Move to convergent phase
- End session
- What if we did the exact opposite? **Output Capture (if requested):**
- How could we make this problem worse? (then reverse) For each technique used, capture:
- Start from the end goal and work backward
- Reverse roles or perspectives
4. **First Principles Thinking** - Technique name and duration
[[LLM: Break down to fundamental truths and rebuild from scratch.]] - Key ideas generated by user
- What are the absolute fundamentals here? - Insights and patterns identified
- What assumptions can we challenge? - User's reflections on the process
- If we started from zero, what would we build?
- What laws of physics/economics/human nature apply?
#### Structured Ideation Frameworks ### Step 4: Session Flow
1. **SCAMPER Method** 1. **Warm-up** (5-10 min) - Build creative confidence
[[LLM: Guide through each SCAMPER prompt systematically.]] 2. **Divergent** (20-30 min) - Generate quantity over quality
3. **Convergent** (15-20 min) - Group and categorize ideas
4. **Synthesis** (10-15 min) - Refine and develop concepts
- **S** = Substitute: What can be substituted? ### Step 5: Document Output (if requested)
- **C** = Combine: What can be combined or integrated?
- **A** = Adapt: What can be adapted from elsewhere?
- **M** = Modify/Magnify: What can be emphasized or reduced?
- **P** = Put to other uses: What else could this be used for?
- **E** = Eliminate: What can be removed or simplified?
- **R**= Reverse/Rearrange: What can be reversed or reordered?
2. **Six Thinking Hats** Generate structured document with these sections:
[[LLM: Cycle through different thinking modes, spending focused time in each.]]
- White Hat: Facts and information **Executive Summary**
- Red Hat: Emotions and intuition
- Black Hat: Caution and critical thinking
- Yellow Hat: Optimism and benefits
- Green Hat: Creativity and alternatives
- Blue Hat: Process and control
3. **Mind Mapping** - Session topic and goals
[[LLM: Create text-based mind maps with clear hierarchical structure.]] - Techniques used and duration
- Total ideas generated
- Key themes and patterns identified
```plaintext **Technique Sections** (for each technique used)
Central Concept
├── Branch 1
│ ├── Sub-idea 1.1
│ └── Sub-idea 1.2
├── Branch 2
│ ├── Sub-idea 2.1
│ └── Sub-idea 2.2
└── Branch 3
└── Sub-idea 3.1
```
#### Collaborative Techniques - Technique name and description
- Ideas generated (user's own words)
- Insights discovered
- Notable connections or patterns
1. **"Yes, And..." Building** **Idea Categorization**
[[LLM: Accept every idea and build upon it without judgment. Encourage wild ideas and defer criticism.]]
- Accept the premise of each idea - **Immediate Opportunities** - Ready to implement now
- Add to it with "Yes, and..." - **Future Innovations** - Requires development/research
- Build chains of connected ideas - **Moonshots** - Ambitious, transformative concepts
- Explore tangents freely - **Insights & Learnings** - Key realizations from session
2. **Brainwriting/Round Robin** **Action Planning**
[[LLM: Simulate multiple perspectives by generating ideas from different viewpoints.]]
- Generate ideas from stakeholder perspectives - Top 3 priority ideas with rationale
- Build on previous ideas in rounds - Next steps for each priority
- Combine unrelated ideas - Resources/research needed
- Cross-pollinate concepts - Timeline considerations
3. **Random Stimulation** **Reflection & Follow-up**
[[LLM: Use random words, images, or concepts as creative triggers.]]
- Random word association
- Picture/metaphor inspiration
- Forced connections between unrelated items
- Constraint-based creativity
#### Deep Exploration Techniques - What worked well in this session
- Areas for further exploration
1. **Five Whys**
[[LLM: Dig deeper into root causes and underlying motivations.]]
- Why does this problem exist? → Answer → Why? (repeat 5 times)
- Uncover hidden assumptions
- Find root causes, not symptoms
- Identify intervention points
2. **Morphological Analysis**
[[LLM: Break down into parameters and systematically explore combinations.]]
- List key parameters/dimensions
- Identify possible values for each
- Create combination matrix
- Explore unusual combinations
3. **Provocation Technique (PO)**
[[LLM: Make deliberately provocative statements to jar thinking.]]
- PO: Cars have square wheels
- PO: Customers pay us to take products
- PO: The problem solves itself
- Extract useful ideas from provocations
### 3. Technique Selection Guide
[[LLM: Help user select appropriate techniques based on their needs.]]
**For Initial Exploration:**
- What If Scenarios
- First Principles
- Mind Mapping
**For Stuck/Blocked Thinking:**
- Random Stimulation
- Reversal/Inversion
- Provocation Technique
**For Systematic Coverage:**
- SCAMPER
- Morphological Analysis
- Six Thinking Hats
**For Deep Understanding:**
- Five Whys
- Analogical Thinking
- First Principles
**For Team/Collaborative Settings:**
- Brainwriting
- "Yes, And..."
- Six Thinking Hats
### 4. Session Flow Management
[[LLM: Guide the brainstorming session with appropriate pacing and technique transitions.]]
1. **Warm-up Phase** (5-10 min)
- Start with accessible techniques
- Build creative confidence
- Establish "no judgment" atmosphere
2. **Divergent Phase** (20-30 min)
- Use expansion techniques
- Generate quantity over quality
- Encourage wild ideas
3. **Convergent Phase** (15-20 min)
- Group and categorize ideas
- Identify patterns and themes
- Select promising directions
4. **Synthesis Phase** (10-15 min)
- Combine complementary ideas
- Refine and develop concepts
- Prepare summary of insights
### 5. Output Format
[[LLM: Present brainstorming results in an organized, actionable format.]]
**Session Summary:**
- Techniques used
- Number of ideas generated
- Key themes identified
**Idea Categories:**
1. **Immediate Opportunities** - Ideas that could be implemented now
2. **Future Innovations** - Ideas requiring more development
3. **Moonshots** - Ambitious, transformative ideas
4. **Insights & Learnings** - Key realizations from the session
**Next Steps:**
- Which ideas to explore further
- Recommended follow-up techniques - Recommended follow-up techniques
- Suggested research areas - Questions that emerged for future sessions
## Important Notes ## Key Principles
- Maintain energy and momentum throughout the session - **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them
- Defer judgment - all ideas are valid during generation - **INTERACTIVE DIALOGUE**: Ask questions, wait for responses, build on their ideas
- Quantity leads to quality - aim for many ideas - **ONE TECHNIQUE AT A TIME**: Don't mix multiple techniques in one response
- **CONTINUOUS ENGAGEMENT**: Stay with one technique until user wants to switch
- **DRAW IDEAS OUT**: Use prompts and examples to help them generate their own ideas
- **REAL-TIME ADAPTATION**: Monitor engagement and adjust approach as needed
- Maintain energy and momentum
- Defer judgment during generation
- Quantity leads to quality (aim for 100 ideas in 60 minutes)
- Build on ideas collaboratively - Build on ideas collaboratively
- Document everything - even "silly" ideas can spark breakthroughs - Document everything if output requested
- Take breaks if energy flags
- End with clear next actions ## Advanced Engagement Strategies
==================== END: tasks#brainstorming-techniques ====================
**Energy Management**
- Check engagement levels: "How are you feeling about this direction?"
- Offer breaks or technique switches if energy flags
- Use encouraging language and celebrate idea generation
**Depth vs. Breadth**
- Ask follow-up questions to deepen ideas: "Tell me more about that..."
- Use "Yes, and..." to build on their ideas
- Help them make connections: "How does this relate to your earlier idea about...?"
**Transition Management**
- Always ask before switching techniques: "Ready to try a different approach?"
- Offer options: "Should we explore this idea deeper or generate more alternatives?"
- Respect their process and timing
==================== END: tasks#facilitate-brainstorming-session ====================
==================== START: tasks#create-deep-research-prompt ==================== ==================== START: tasks#create-deep-research-prompt ====================
# Create Deep Research Prompt Task # Create Deep Research Prompt Task
@@ -2311,6 +2211,158 @@ These replace the standard elicitation options when working on market research d
These replace the standard elicitation options when working on competitive analysis documents.]] These replace the standard elicitation options when working on competitive analysis documents.]]
==================== END: templates#competitor-analysis-tmpl ==================== ==================== END: templates#competitor-analysis-tmpl ====================
==================== START: templates#brainstorming-output-tmpl ====================
---
defaultOutput: docs/brainstorming-session-results.md
---
# Brainstorming Session Results
**Session Date:** [DATE]
**Facilitator:** [Agent Role] [Agent Name]
**Participant:** [USER NAME]
## Executive Summary
**Topic:** [SESSION TOPIC]
**Session Goals:** [STATED GOALS]
**Techniques Used:** [LIST OF TECHNIQUES AND DURATION]
**Total Ideas Generated:** [NUMBER]
**Key Themes Identified:**
- [THEME 1]
- [THEME 2]
- [THEME 3]
---
## Technique Sessions
### [TECHNIQUE NAME 1] - [DURATION]
**Description:** [BRIEF DESCRIPTION OF TECHNIQUE]
**Ideas Generated:**
1. [USER IDEA 1]
2. [USER IDEA 2]
3. [USER IDEA 3]
[etc.]
**Insights Discovered:**
- [INSIGHT 1]
- [INSIGHT 2]
**Notable Connections:**
- [CONNECTION OR PATTERN IDENTIFIED]
---
### [TECHNIQUE NAME 2] - [DURATION]
[Repeat format for each technique used]
---
## Idea Categorization
### Immediate Opportunities
*Ideas ready to implement now*
1. **[IDEA NAME]**
- Description: [BRIEF DESCRIPTION]
- Why immediate: [RATIONALE]
- Resources needed: [BASIC REQUIREMENTS]
### Future Innovations
*Ideas requiring development/research*
1. **[IDEA NAME]**
- Description: [BRIEF DESCRIPTION]
- Development needed: [WHAT'S REQUIRED]
- Timeline estimate: [ROUGH TIMEFRAME]
### Moonshots
*Ambitious, transformative concepts*
1. **[IDEA NAME]**
- Description: [BRIEF DESCRIPTION]
- Transformative potential: [WHY IT'S A MOONSHOT]
- Challenges to overcome: [MAJOR OBSTACLES]
### Insights & Learnings
*Key realizations from the session*
- [INSIGHT 1]: [DESCRIPTION AND IMPLICATIONS]
- [INSIGHT 2]: [DESCRIPTION AND IMPLICATIONS]
---
## Action Planning
### Top 3 Priority Ideas
**#1 Priority: [IDEA NAME]**
- Rationale: [WHY THIS IS TOP PRIORITY]
- Next steps: [SPECIFIC ACTIONS TO TAKE]
- Resources needed: [WHAT'S REQUIRED]
- Timeline: [WHEN TO START/COMPLETE]
**#2 Priority: [IDEA NAME]**
- [Same format]
**#3 Priority: [IDEA NAME]**
- [Same format]
---
## Reflection & Follow-up
### What Worked Well
- [SUCCESSFUL ASPECT 1]
- [SUCCESSFUL ASPECT 2]
### Areas for Further Exploration
- [AREA 1]: [WHY IT NEEDS MORE EXPLORATION]
- [AREA 2]: [WHY IT NEEDS MORE EXPLORATION]
### Recommended Follow-up Techniques
- [TECHNIQUE 1]: [WHY IT WOULD BE HELPFUL]
- [TECHNIQUE 2]: [WHY IT WOULD BE HELPFUL]
### Questions That Emerged
- [QUESTION 1]
- [QUESTION 2]
- [QUESTION 3]
### Next Session Planning
- **Suggested topics:** [FOLLOW-UP TOPICS]
- **Recommended timeframe:** [WHEN TO RECONVENE]
- **Preparation needed:** [WHAT TO RESEARCH/PREPARE]
---
*Session facilitated using the BMAD-METHOD brainstorming framework*
==================== END: templates#brainstorming-output-tmpl ====================
==================== START: data#bmad-kb ==================== ==================== START: data#bmad-kb ====================
# Game Development BMad Knowledge Base # Game Development BMad Knowledge Base
@@ -2568,6 +2620,45 @@ game-project/
This knowledge base provides the foundation for effective game development using the BMad-Method framework with specialized focus on 2D game creation using Phaser 3 and TypeScript. This knowledge base provides the foundation for effective game development using the BMad-Method framework with specialized focus on 2D game creation using Phaser 3 and TypeScript.
==================== END: data#bmad-kb ==================== ==================== END: data#bmad-kb ====================
==================== START: data#brainstorming-techniques ====================
# Brainstorming Techniques Data
## Creative Expansion
1. **What If Scenarios**: Ask one provocative question, get their response, then ask another
2. **Analogical Thinking**: Give one example analogy, ask them to find 2-3 more
3. **Reversal/Inversion**: Pose the reverse question, let them work through it
4. **First Principles Thinking**: Ask "What are the fundamentals?" and guide them to break it down
## Structured Frameworks
5. **SCAMPER Method**: Go through one letter at a time, wait for their ideas before moving to next
6. **Six Thinking Hats**: Present one hat, ask for their thoughts, then move to next hat
7. **Mind Mapping**: Start with central concept, ask them to suggest branches
## Collaborative Techniques
8. **"Yes, And..." Building**: They give idea, you "yes and" it, they "yes and" back - alternate
9. **Brainwriting/Round Robin**: They suggest idea, you build on it, ask them to build on yours
10. **Random Stimulation**: Give one random prompt/word, ask them to make connections
## Deep Exploration
11. **Five Whys**: Ask "why" and wait for their answer before asking next "why"
12. **Morphological Analysis**: Ask them to list parameters first, then explore combinations together
13. **Provocation Technique (PO)**: Give one provocative statement, ask them to extract useful ideas
## Advanced Techniques
14. **Forced Relationships**: Connect two unrelated concepts and ask them to find the bridge
15. **Assumption Reversal**: Challenge their core assumptions and ask them to build from there
16. **Role Playing**: Ask them to brainstorm from different stakeholder perspectives
17. **Time Shifting**: "How would you solve this in 1995? 2030?"
18. **Resource Constraints**: "What if you had only $10 and 1 hour?"
19. **Metaphor Mapping**: Use extended metaphors to explore solutions
20. **Question Storming**: Generate questions instead of answers first
==================== END: data#brainstorming-techniques ====================
==================== START: utils#template-format ==================== ==================== START: utils#template-format ====================
# Template Format Conventions # Template Format Conventions
@@ -3224,14 +3315,10 @@ Provides utilities for agents and tasks to interact with workflow plans, check p
### 1. Check Plan Existence ### 1. Check Plan Existence
[[LLM: When any agent starts or task begins, check if a workflow plan exists]]
```
Check for workflow plan: Check for workflow plan:
1. Look for docs/workflow-plan.md (default location) 1. Look for docs/workflow-plan.md (default location)
2. Check core-config.yaml for custom plan location 2. Return plan status to user (exists/not exists) - if not exists then HALT.
3. Return plan status (exists/not exists)
```
### 2. Parse Plan Status ### 2. Parse Plan Status
@@ -3272,7 +3359,7 @@ Check for workflow plan:
**Warning Templates:** **Warning Templates:**
``` ```text
SEQUENCE WARNING: SEQUENCE WARNING:
The workflow plan shows you should complete "{expected_step}" next. The workflow plan shows you should complete "{expected_step}" next.
You're attempting to: "{requested_action}" You're attempting to: "{requested_action}"
@@ -3306,7 +3393,7 @@ In flexible mode: Allow with confirmation
**For Agents (startup sequence)**: **For Agents (startup sequence)**:
``` ```text
1. Check if plan exists using this utility 1. Check if plan exists using this utility
2. If exists: 2. If exists:
- Parse current status - Parse current status
@@ -3317,7 +3404,7 @@ In flexible mode: Allow with confirmation
**For Tasks (pre-execution)**: **For Tasks (pre-execution)**:
``` ```text
1. Check if plan exists 1. Check if plan exists
2. If exists: 2. If exists:
- Verify this task aligns with plan - Verify this task aligns with plan
@@ -3333,7 +3420,7 @@ In flexible mode: Allow with confirmation
[[LLM: Standard format for showing plan status]] [[LLM: Standard format for showing plan status]]
``` ```text
📋 Workflow Plan Status 📋 Workflow Plan Status
━━━━━━━━━━━━━━━━━━━━ ━━━━━━━━━━━━━━━━━━━━
Workflow: {workflow_name} Workflow: {workflow_name}
@@ -3386,7 +3473,7 @@ If user wants to abandon plan:
### Example 1: Agent Startup Check ### Example 1: Agent Startup Check
``` ```text
BMad Master starting... BMad Master starting...
[Check for plan] [Check for plan]
@@ -3400,7 +3487,7 @@ Use *agent pm to switch, or *plan-status to see full progress.
### Example 2: Task Sequence Warning ### Example 2: Task Sequence Warning
``` ```text
User: *task create-next-story User: *task create-next-story
[Plan check triggered] [Plan check triggered]
@@ -3416,7 +3503,7 @@ Would you like to:
### Example 3: Automatic Plan Update ### Example 3: Automatic Plan Update
``` ```text
[After completing create-doc task for PRD] [After completing create-doc task for PRD]
✅ Plan Updated: Marked "Create PRD" as complete ✅ Plan Updated: Marked "Create PRD" as complete

143
dist/expansion-packs/bmad-creator-tools/agents/bmad-the-creator.txt vendored
View File

@@ -1328,91 +1328,116 @@ Embedded knowledge (automatic):
- Provide optional reflective and brainstorming actions to enhance content quality - Provide optional reflective and brainstorming actions to enhance content quality
- Enable deeper exploration of ideas through structured elicitation techniques - Enable deeper exploration of ideas through structured elicitation techniques
- Support iterative refinement through multiple analytical perspectives - Support iterative refinement through multiple analytical perspectives
- Usable during template-driven document creation or any chat conversation
## Usage Scenarios
### Scenario 1: Template Document Creation
After outputting a section during document creation:
1. **Section Review**: Ask user to review the drafted section
2. **Offer Elicitation**: Present 9 carefully selected elicitation methods
3. **Simple Selection**: User types a number (0-8) to engage method, or 9 to proceed
4. **Execute & Loop**: Apply selected method, then re-offer choices until user proceeds
### Scenario 2: General Chat Elicitation
User can request advanced elicitation on any agent output:
- User says "do advanced elicitation" or similar
- Agent selects 9 relevant methods for the context
- Same simple 0-9 selection process
## Task Instructions ## Task Instructions
### 1. Section Context and Review ### 1. Intelligent Method Selection
[[LLM: When invoked after outputting a section: **Context Analysis**: Before presenting options, analyze:
1. First, provide a brief 1-2 sentence summary of what the user should look for in the section just presented (e.g., "Please review the technology choices for completeness and alignment with your project needs. Pay special attention to version numbers and any missing categories.") - **Content Type**: Technical specs, user stories, architecture, requirements, etc.
- **Complexity Level**: Simple, moderate, or complex content
- **Stakeholder Needs**: Who will use this information
- **Risk Level**: High-impact decisions vs routine items
- **Creative Potential**: Opportunities for innovation or alternatives
2. If the section contains Mermaid diagrams, explain each diagram briefly before offering elicitation options (e.g., "The component diagram shows the main system modules and their interactions. Notice how the API Gateway routes requests to different services.") **Method Selection Strategy**:
3. If the section contains multiple distinct items (like multiple components, multiple patterns, etc.), inform the user they can apply elicitation actions to: 1. **Always Include Core Methods** (choose 3-4):
- Expand or Contract for Audience
- Critique and Refine
- Identify Potential Risks
- Assess Alignment with Goals
2. **Context-Specific Methods** (choose 4-5):
- **Technical Content**: Tree of Thoughts, ReWOO, Meta-Prompting
- **User-Facing Content**: Agile Team Perspective, Stakeholder Roundtable
- **Creative Content**: Innovation Tournament, Escape Room Challenge
- **Strategic Content**: Red Team vs Blue Team, Hindsight Reflection
3. **Always Include**: "Proceed / No Further Actions" as option 9
### 2. Section Context and Review
When invoked after outputting a section:
1. **Provide Context Summary**: Give a brief 1-2 sentence summary of what the user should look for in the section just presented
2. **Explain Visual Elements**: If the section contains diagrams, explain them briefly before offering elicitation options
3. **Clarify Scope Options**: If the section contains multiple distinct items, inform the user they can apply elicitation actions to:
- The entire section as a whole - The entire section as a whole
- Individual items within the section (specify which item when selecting an action) - Individual items within the section (specify which item when selecting an action)
4. Then present the action list as specified below.]] ### 3. Present Elicitation Options
### 2. Ask for Review and Present Action List **Review Request Process:**
[[LLM: Ask the user to review the drafted section. In the SAME message, inform them that they can suggest additions, removals, or modifications, OR they can select an action by number from the 'Advanced Reflective, Elicitation & Brainstorming Actions'. If there are multiple items in the section, mention they can specify which item(s) to apply the action to. Then, present ONLY the numbered list (0-9) of these actions. Conclude by stating that selecting 9 will proceed to the next section. Await user selection. If an elicitation action (0-8) is chosen, execute it and then re-offer this combined review/elicitation choice. If option 9 is chosen, or if the user provides direct feedback, proceed accordingly.]] - Ask the user to review the drafted section
- In the SAME message, inform them they can suggest direct changes OR select an elicitation method
- Present 9 intelligently selected methods (0-8) plus "Proceed" (9)
- Keep descriptions short - just the method name
- Await simple numeric selection
**Present the numbered list (0-9) with this exact format:** **Action List Presentation Format:**
```text ```text
**Advanced Reflective, Elicitation & Brainstorming Actions** **Advanced Elicitation Options**
Choose an action (0-9 - 9 to bypass - HELP for explanation of these options): Choose a number (0-8) or 9 to proceed:
0. Expand or Contract for Audience 0. [Method Name]
1. Explain Reasoning (CoT Step-by-Step) 1. [Method Name]
2. Critique and Refine 2. [Method Name]
3. Analyze Logical Flow and Dependencies 3. [Method Name]
4. Assess Alignment with Overall Goals 4. [Method Name]
5. Identify Potential Risks and Unforeseen Issues 5. [Method Name]
6. Challenge from Critical Perspective (Self or Other Persona) 6. [Method Name]
7. Explore Diverse Alternatives (ToT-Inspired) 7. [Method Name]
8. Hindsight is 20/20: The 'If Only...' Reflection 8. [Method Name]
9. Proceed / No Further Actions 9. Proceed / No Further Actions
``` ```
### 2. Processing Guidelines **Response Handling:**
**Do NOT show:** - **Numbers 0-8**: Execute the selected method, then re-offer the choice
- **Number 9**: Proceed to next section or continue conversation
- **Direct Feedback**: Apply user's suggested changes and continue
- The full protocol text with `[[LLM: ...]]` instructions ### 4. Method Execution Framework
- Detailed explanations of each option unless executing or the user asks, when giving the definition you can modify to tie its relevance
- Any internal template markup
**After user selection from the list:** **Execution Process:**
- Execute the chosen action according to the protocol instructions below 1. **Retrieve Method**: Access the specific elicitation method from the elicitation-methods data file
- Ask if they want to select another action or proceed with option 9 once complete 2. **Apply Context**: Execute the method from your current role's perspective
- Continue until user selects option 9 or indicates completion 3. **Provide Results**: Deliver insights, critiques, or alternatives relevant to the content
4. **Re-offer Choice**: Present the same 9 options again until user selects 9 or gives direct feedback
## Action Definitions **Execution Guidelines:**
0. Expand or Contract for Audience - **Be Concise**: Focus on actionable insights, not lengthy explanations
[[LLM: Ask the user whether they want to 'expand' on the content (add more detail, elaborate) or 'contract' it (simplify, clarify, make more concise). Also, ask if there's a specific target audience they have in mind. Once clarified, perform the expansion or contraction from your current role's perspective, tailored to the specified audience if provided.]] - **Stay Relevant**: Tie all elicitation back to the specific content being analyzed
- **Identify Personas**: For multi-persona methods, clearly identify which viewpoint is speaking
1. Explain Reasoning (CoT Step-by-Step) - **Maintain Flow**: Keep the process moving efficiently
[[LLM: Explain the step-by-step thinking process, characteristic of your role, that you used to arrive at the current proposal for this content.]]
2. Critique and Refine
[[LLM: From your current role's perspective, review your last output or the current section for flaws, inconsistencies, or areas for improvement, and then suggest a refined version reflecting your expertise.]]
3. Analyze Logical Flow and Dependencies
[[LLM: From your role's standpoint, examine the content's structure for logical progression, internal consistency, and any relevant dependencies. Confirm if elements are presented in an effective order.]]
4. Assess Alignment with Overall Goals
[[LLM: Evaluate how well the current content contributes to the stated overall goals of the document, interpreting this from your specific role's perspective and identifying any misalignments you perceive.]]
5. Identify Potential Risks and Unforeseen Issues
[[LLM: Based on your role's expertise, brainstorm potential risks, overlooked edge cases, or unintended consequences related to the current content or proposal.]]
6. Challenge from Critical Perspective (Self or Other Persona)
[[LLM: Adopt a critical perspective on the current content. If the user specifies another role or persona (e.g., 'as a customer', 'as [Another Persona Name]'), critique the content or play devil's advocate from that specified viewpoint. If no other role is specified, play devil's advocate from your own current persona's viewpoint, arguing against the proposal or current content and highlighting weaknesses or counterarguments specific to your concerns. This can also randomly include YAGNI when appropriate, such as when trimming the scope of an MVP, the perspective might challenge the need for something to cut MVP scope.]]
7. Explore Diverse Alternatives (ToT-Inspired)
[[LLM: From your role's perspective, first broadly brainstorm a range of diverse approaches or solutions to the current topic. Then, from this wider exploration, select and present 2 distinct alternatives, detailing the pros, cons, and potential implications you foresee for each.]]
8. Hindsight is 20/20: The 'If Only...' Reflection
[[LLM: In your current persona, imagine it's a retrospective for a project based on the current content. What's the one 'if only we had known/done X...' that your role would humorously or dramatically highlight, along with the imagined consequences?]]
9. Proceed / No Further Actions
[[LLM: Acknowledge the user's choice to finalize the current work, accept the AI's last output as is, or move on to the next step without selecting another action from this list. Prepare to proceed accordingly.]]
==================== END: tasks#advanced-elicitation ==================== ==================== END: tasks#advanced-elicitation ====================
==================== START: tasks#create-deep-research-prompt ==================== ==================== START: tasks#create-deep-research-prompt ====================

753
dist/teams/team-all.txt vendored
View File

File diff suppressed because it is too large Load Diff

753
dist/teams/team-fullstack.txt vendored
View File

File diff suppressed because it is too large Load Diff

250
dist/teams/team-ide-minimal.txt vendored
View File

@@ -420,91 +420,116 @@ dependencies:
- Provide optional reflective and brainstorming actions to enhance content quality - Provide optional reflective and brainstorming actions to enhance content quality
- Enable deeper exploration of ideas through structured elicitation techniques - Enable deeper exploration of ideas through structured elicitation techniques
- Support iterative refinement through multiple analytical perspectives - Support iterative refinement through multiple analytical perspectives
- Usable during template-driven document creation or any chat conversation
## Usage Scenarios
### Scenario 1: Template Document Creation
After outputting a section during document creation:
1. **Section Review**: Ask user to review the drafted section
2. **Offer Elicitation**: Present 9 carefully selected elicitation methods
3. **Simple Selection**: User types a number (0-8) to engage method, or 9 to proceed
4. **Execute & Loop**: Apply selected method, then re-offer choices until user proceeds
### Scenario 2: General Chat Elicitation
User can request advanced elicitation on any agent output:
- User says "do advanced elicitation" or similar
- Agent selects 9 relevant methods for the context
- Same simple 0-9 selection process
## Task Instructions ## Task Instructions
### 1. Section Context and Review ### 1. Intelligent Method Selection
[[LLM: When invoked after outputting a section: **Context Analysis**: Before presenting options, analyze:
1. First, provide a brief 1-2 sentence summary of what the user should look for in the section just presented (e.g., "Please review the technology choices for completeness and alignment with your project needs. Pay special attention to version numbers and any missing categories.") - **Content Type**: Technical specs, user stories, architecture, requirements, etc.
- **Complexity Level**: Simple, moderate, or complex content
- **Stakeholder Needs**: Who will use this information
- **Risk Level**: High-impact decisions vs routine items
- **Creative Potential**: Opportunities for innovation or alternatives
2. If the section contains Mermaid diagrams, explain each diagram briefly before offering elicitation options (e.g., "The component diagram shows the main system modules and their interactions. Notice how the API Gateway routes requests to different services.") **Method Selection Strategy**:
3. If the section contains multiple distinct items (like multiple components, multiple patterns, etc.), inform the user they can apply elicitation actions to: 1. **Always Include Core Methods** (choose 3-4):
- Expand or Contract for Audience
- Critique and Refine
- Identify Potential Risks
- Assess Alignment with Goals
2. **Context-Specific Methods** (choose 4-5):
- **Technical Content**: Tree of Thoughts, ReWOO, Meta-Prompting
- **User-Facing Content**: Agile Team Perspective, Stakeholder Roundtable
- **Creative Content**: Innovation Tournament, Escape Room Challenge
- **Strategic Content**: Red Team vs Blue Team, Hindsight Reflection
3. **Always Include**: "Proceed / No Further Actions" as option 9
### 2. Section Context and Review
When invoked after outputting a section:
1. **Provide Context Summary**: Give a brief 1-2 sentence summary of what the user should look for in the section just presented
2. **Explain Visual Elements**: If the section contains diagrams, explain them briefly before offering elicitation options
3. **Clarify Scope Options**: If the section contains multiple distinct items, inform the user they can apply elicitation actions to:
- The entire section as a whole - The entire section as a whole
- Individual items within the section (specify which item when selecting an action) - Individual items within the section (specify which item when selecting an action)
4. Then present the action list as specified below.]] ### 3. Present Elicitation Options
### 2. Ask for Review and Present Action List **Review Request Process:**
[[LLM: Ask the user to review the drafted section. In the SAME message, inform them that they can suggest additions, removals, or modifications, OR they can select an action by number from the 'Advanced Reflective, Elicitation & Brainstorming Actions'. If there are multiple items in the section, mention they can specify which item(s) to apply the action to. Then, present ONLY the numbered list (0-9) of these actions. Conclude by stating that selecting 9 will proceed to the next section. Await user selection. If an elicitation action (0-8) is chosen, execute it and then re-offer this combined review/elicitation choice. If option 9 is chosen, or if the user provides direct feedback, proceed accordingly.]] - Ask the user to review the drafted section
- In the SAME message, inform them they can suggest direct changes OR select an elicitation method
- Present 9 intelligently selected methods (0-8) plus "Proceed" (9)
- Keep descriptions short - just the method name
- Await simple numeric selection
**Present the numbered list (0-9) with this exact format:** **Action List Presentation Format:**
```text ```text
**Advanced Reflective, Elicitation & Brainstorming Actions** **Advanced Elicitation Options**
Choose an action (0-9 - 9 to bypass - HELP for explanation of these options): Choose a number (0-8) or 9 to proceed:
0. Expand or Contract for Audience 0. [Method Name]
1. Explain Reasoning (CoT Step-by-Step) 1. [Method Name]
2. Critique and Refine 2. [Method Name]
3. Analyze Logical Flow and Dependencies 3. [Method Name]
4. Assess Alignment with Overall Goals 4. [Method Name]
5. Identify Potential Risks and Unforeseen Issues 5. [Method Name]
6. Challenge from Critical Perspective (Self or Other Persona) 6. [Method Name]
7. Explore Diverse Alternatives (ToT-Inspired) 7. [Method Name]
8. Hindsight is 20/20: The 'If Only...' Reflection 8. [Method Name]
9. Proceed / No Further Actions 9. Proceed / No Further Actions
``` ```
### 2. Processing Guidelines **Response Handling:**
**Do NOT show:** - **Numbers 0-8**: Execute the selected method, then re-offer the choice
- **Number 9**: Proceed to next section or continue conversation
- **Direct Feedback**: Apply user's suggested changes and continue
- The full protocol text with `[[LLM: ...]]` instructions ### 4. Method Execution Framework
- Detailed explanations of each option unless executing or the user asks, when giving the definition you can modify to tie its relevance
- Any internal template markup
**After user selection from the list:** **Execution Process:**
- Execute the chosen action according to the protocol instructions below 1. **Retrieve Method**: Access the specific elicitation method from the elicitation-methods data file
- Ask if they want to select another action or proceed with option 9 once complete 2. **Apply Context**: Execute the method from your current role's perspective
- Continue until user selects option 9 or indicates completion 3. **Provide Results**: Deliver insights, critiques, or alternatives relevant to the content
4. **Re-offer Choice**: Present the same 9 options again until user selects 9 or gives direct feedback
## Action Definitions **Execution Guidelines:**
0. Expand or Contract for Audience - **Be Concise**: Focus on actionable insights, not lengthy explanations
[[LLM: Ask the user whether they want to 'expand' on the content (add more detail, elaborate) or 'contract' it (simplify, clarify, make more concise). Also, ask if there's a specific target audience they have in mind. Once clarified, perform the expansion or contraction from your current role's perspective, tailored to the specified audience if provided.]] - **Stay Relevant**: Tie all elicitation back to the specific content being analyzed
- **Identify Personas**: For multi-persona methods, clearly identify which viewpoint is speaking
1. Explain Reasoning (CoT Step-by-Step) - **Maintain Flow**: Keep the process moving efficiently
[[LLM: Explain the step-by-step thinking process, characteristic of your role, that you used to arrive at the current proposal for this content.]]
2. Critique and Refine
[[LLM: From your current role's perspective, review your last output or the current section for flaws, inconsistencies, or areas for improvement, and then suggest a refined version reflecting your expertise.]]
3. Analyze Logical Flow and Dependencies
[[LLM: From your role's standpoint, examine the content's structure for logical progression, internal consistency, and any relevant dependencies. Confirm if elements are presented in an effective order.]]
4. Assess Alignment with Overall Goals
[[LLM: Evaluate how well the current content contributes to the stated overall goals of the document, interpreting this from your specific role's perspective and identifying any misalignments you perceive.]]
5. Identify Potential Risks and Unforeseen Issues
[[LLM: Based on your role's expertise, brainstorm potential risks, overlooked edge cases, or unintended consequences related to the current content or proposal.]]
6. Challenge from Critical Perspective (Self or Other Persona)
[[LLM: Adopt a critical perspective on the current content. If the user specifies another role or persona (e.g., 'as a customer', 'as [Another Persona Name]'), critique the content or play devil's advocate from that specified viewpoint. If no other role is specified, play devil's advocate from your own current persona's viewpoint, arguing against the proposal or current content and highlighting weaknesses or counterarguments specific to your concerns. This can also randomly include YAGNI when appropriate, such as when trimming the scope of an MVP, the perspective might challenge the need for something to cut MVP scope.]]
7. Explore Diverse Alternatives (ToT-Inspired)
[[LLM: From your role's perspective, first broadly brainstorm a range of diverse approaches or solutions to the current topic. Then, from this wider exploration, select and present 2 distinct alternatives, detailing the pros, cons, and potential implications you foresee for each.]]
8. Hindsight is 20/20: The 'If Only...' Reflection
[[LLM: In your current persona, imagine it's a retrospective for a project based on the current content. What's the one 'if only we had known/done X...' that your role would humorously or dramatically highlight, along with the imagined consequences?]]
9. Proceed / No Further Actions
[[LLM: Acknowledge the user's choice to finalize the current work, accept the AI's last output as is, or move on to the next step without selecting another action from this list. Prepare to proceed accordingly.]]
==================== END: tasks#advanced-elicitation ==================== ==================== END: tasks#advanced-elicitation ====================
==================== START: tasks#create-doc ==================== ==================== START: tasks#create-doc ====================
@@ -1253,13 +1278,15 @@ BMad transforms you into a "Vibe CEO" - directing a team of specialized AI agent
### The Two-Phase Approach ### 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) - Use large context windows (Gemini's 1M tokens)
- Generate comprehensive documents (PRD, Architecture) - Generate comprehensive documents (PRD, Architecture)
- Leverage multiple agents for brainstorming - Leverage multiple agents for brainstorming
- Create once, use throughout development - Create once, use throughout development
**Phase 2: Development (IDE - Implementation)** #### Phase 2: Development (IDE - Implementation)
- Shard documents into manageable pieces - Shard documents into manageable pieces
- Execute focused SM → Dev cycles - Execute focused SM → Dev cycles
- One story at a time, sequential progress - One story at a time, sequential progress
@@ -1289,6 +1316,7 @@ BMad transforms you into a "Vibe CEO" - directing a team of specialized AI agent
### Quick Start Options ### Quick Start Options
#### Option 1: Web UI #### Option 1: Web UI
**Best for**: ChatGPT, Claude, Gemini users who want to start immediately **Best for**: ChatGPT, Claude, Gemini users who want to start immediately
1. Navigate to `dist/teams/` 1. Navigate to `dist/teams/`
@@ -1298,6 +1326,7 @@ BMad transforms you into a "Vibe CEO" - directing a team of specialized AI agent
5. Type `/help` to see available commands 5. Type `/help` to see available commands
#### Option 2: IDE Integration #### Option 2: IDE Integration
**Best for**: Cursor, Claude Code, Windsurf, Trae, Cline, Roo Code, Github Copilot users **Best for**: Cursor, Claude Code, Windsurf, Trae, Cline, Roo Code, Github Copilot users
```bash ```bash
@@ -1306,6 +1335,7 @@ npx bmad-method install
``` ```
**Installation Steps**: **Installation Steps**:
- Choose "Complete installation" - Choose "Complete installation"
- Select your IDE from supported options: - Select your IDE from supported options:
- **Cursor**: Native AI integration - **Cursor**: Native AI integration
@@ -1319,6 +1349,7 @@ 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. **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**: **Verify Installation**:
- `.bmad-core/` folder created with all agents - `.bmad-core/` folder created with all agents
- IDE-specific integration files created - IDE-specific integration files created
- All agent commands/rules/modes available - All agent commands/rules/modes available
@@ -1328,12 +1359,14 @@ npx bmad-method install
### Environment Selection Guide ### Environment Selection Guide
**Use Web UI for**: **Use Web UI for**:
- Initial planning and documentation (PRD, architecture) - Initial planning and documentation (PRD, architecture)
- Cost-effective document creation (especially with Gemini) - Cost-effective document creation (especially with Gemini)
- Brainstorming and analysis phases - Brainstorming and analysis phases
- Multi-agent consultation and planning - Multi-agent consultation and planning
**Use IDE for**: **Use IDE for**:
- Active development and coding - Active development and coding
- File operations and project integration - File operations and project integration
- Document sharding and story management - Document sharding and story management
@@ -1346,35 +1379,41 @@ npx bmad-method install
**Can you do everything in IDE?** Yes, but understand the tradeoffs: **Can you do everything in IDE?** Yes, but understand the tradeoffs:
**Pros of IDE-Only**: **Pros of IDE-Only**:
- Single environment workflow - Single environment workflow
- Direct file operations from start - Direct file operations from start
- No copy/paste between environments - No copy/paste between environments
- Immediate project integration - Immediate project integration
**Cons of IDE-Only**: **Cons of IDE-Only**:
- Higher token costs for large document creation - Higher token costs for large document creation
- Smaller context windows (varies by IDE/model) - Smaller context windows (varies by IDE/model)
- May hit limits during planning phases - May hit limits during planning phases
- Less cost-effective for brainstorming - Less cost-effective for brainstorming
**Using Web Agents in IDE**: **Using Web Agents in IDE**:
- **NOT RECOMMENDED**: Web agents (PM, Architect) have rich dependencies designed for large contexts - **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 - **Why it matters**: Dev agents are kept lean to maximize coding context
- **The principle**: "Dev agents code, planning agents plan" - mixing breaks this optimization - **The principle**: "Dev agents code, planning agents plan" - mixing breaks this optimization
**About bmad-master and bmad-orchestrator**: **About bmad-master and bmad-orchestrator**:
- **bmad-master**: CAN do any task without switching agents, BUT... - **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 - **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 - **Why specialization matters**: Each agent's personality and focus creates higher quality outputs
- **If using bmad-master/orchestrator**: Fine for planning phases, but... - **If using bmad-master/orchestrator**: Fine for planning phases, but...
**CRITICAL RULE for Development**: **CRITICAL RULE for Development**:
- **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator - **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator
- **ALWAYS use Dev agent for implementation** - 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 - **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 - **No exceptions**: Even if using bmad-master for everything else, switch to SM → Dev for implementation
**Best Practice for IDE-Only**: **Best Practice for IDE-Only**:
1. Use PM/Architect/UX agents for planning (better than bmad-master) 1. Use PM/Architect/UX agents for planning (better than bmad-master)
2. Create documents directly in project 2. Create documents directly in project
3. Shard immediately after creation 3. Shard immediately after creation
@@ -1398,17 +1437,20 @@ This configuration file acts as a map for BMad agents, telling them exactly wher
### Key Configuration Areas ### Key Configuration Areas
#### PRD Configuration #### PRD Configuration
- **prdVersion**: Tells agents if PRD follows v3 or v4 conventions - **prdVersion**: Tells agents if PRD follows v3 or v4 conventions
- **prdSharded**: Whether epics are embedded (false) or in separate files (true) - **prdSharded**: Whether epics are embedded (false) or in separate files (true)
- **prdShardedLocation**: Where to find sharded epic files - **prdShardedLocation**: Where to find sharded epic files
- **epicFilePattern**: Pattern for epic filenames (e.g., `epic-{n}*.md`) - **epicFilePattern**: Pattern for epic filenames (e.g., `epic-{n}*.md`)
#### Architecture Configuration #### Architecture Configuration
- **architectureVersion**: v3 (monolithic) or v4 (sharded) - **architectureVersion**: v3 (monolithic) or v4 (sharded)
- **architectureSharded**: Whether architecture is split into components - **architectureSharded**: Whether architecture is split into components
- **architectureShardedLocation**: Where sharded architecture files live - **architectureShardedLocation**: Where sharded architecture files live
#### Developer Files #### Developer Files
- **devLoadAlwaysFiles**: List of files the dev agent loads for every task - **devLoadAlwaysFiles**: List of files the dev agent loads for every task
- **devDebugLog**: Where dev agent logs repeated failures - **devDebugLog**: Where dev agent logs repeated failures
- **agentCoreDump**: Export location for chat conversations - **agentCoreDump**: Export location for chat conversations
@@ -1423,6 +1465,7 @@ This configuration file acts as a map for BMad agents, telling them exactly wher
### Common Configurations ### Common Configurations
**Legacy V3 Project**: **Legacy V3 Project**:
```yaml ```yaml
prdVersion: v3 prdVersion: v3
prdSharded: false prdSharded: false
@@ -1431,6 +1474,7 @@ architectureSharded: false
``` ```
**V4 Optimized Project**: **V4 Optimized Project**:
```yaml ```yaml
prdVersion: v4 prdVersion: v4
prdSharded: true prdSharded: true
@@ -1496,6 +1540,7 @@ You are the "Vibe CEO" - thinking like a CEO with unlimited resources and a sing
#### IDE-Specific Syntax #### IDE-Specific Syntax
**Agent Loading by IDE**: **Agent Loading by IDE**:
- **Claude Code**: `/agent-name` (e.g., `/bmad-master`) - **Claude Code**: `/agent-name` (e.g., `/bmad-master`)
- **Cursor**: `@agent-name` (e.g., `@bmad-master`) - **Cursor**: `@agent-name` (e.g., `@bmad-master`)
- **Windsurf**: `@agent-name` (e.g., `@bmad-master`) - **Windsurf**: `@agent-name` (e.g., `@bmad-master`)
@@ -1504,10 +1549,12 @@ 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. - **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**: **Chat Management Guidelines**:
- **Claude Code, Cursor, Windsurf, Trae**: Start new chats when switching agents - **Claude Code, Cursor, Windsurf, Trae**: Start new chats when switching agents
- **Roo Code**: Switch modes within the same conversation - **Roo Code**: Switch modes within the same conversation
**Common Task Commands**: **Common Task Commands**:
- `*help` - Show available commands - `*help` - Show available commands
- `*status` - Show current context/progress - `*status` - Show current context/progress
- `*exit` - Exit the agent mode - `*exit` - Exit the agent mode
@@ -1516,6 +1563,7 @@ You are the "Vibe CEO" - thinking like a CEO with unlimited resources and a sing
- `*create` - Run create-next-story task (SM agent) - `*create` - Run create-next-story task (SM agent)
**In Web UI**: **In Web UI**:
```text ```text
/pm create-doc prd /pm create-doc prd
/architect review system design /architect review system design
@@ -1529,16 +1577,19 @@ You are the "Vibe CEO" - thinking like a CEO with unlimited resources and a sing
### Pre-Built Teams ### Pre-Built Teams
#### Team All #### Team All
- **Includes**: All 10 agents + orchestrator - **Includes**: All 10 agents + orchestrator
- **Use Case**: Complete projects requiring all roles - **Use Case**: Complete projects requiring all roles
- **Bundle**: `team-all.txt` - **Bundle**: `team-all.txt`
#### Team Fullstack #### Team Fullstack
- **Includes**: PM, Architect, Developer, QA, UX Expert - **Includes**: PM, Architect, Developer, QA, UX Expert
- **Use Case**: End-to-end web/mobile development - **Use Case**: End-to-end web/mobile development
- **Bundle**: `team-fullstack.txt` - **Bundle**: `team-fullstack.txt`
#### Team No-UI #### Team No-UI
- **Includes**: PM, Architect, Developer, QA (no UX Expert) - **Includes**: PM, Architect, Developer, QA (no UX Expert)
- **Use Case**: Backend services, APIs, system development - **Use Case**: Backend services, APIs, system development
- **Bundle**: `team-no-ui.txt` - **Bundle**: `team-no-ui.txt`
@@ -1552,22 +1603,26 @@ The BMad-Method is built around a modular architecture centered on the `bmad-cor
### Key Architectural Components ### Key Architectural Components
#### 1. Agents (`bmad-core/agents/`) #### 1. Agents (`bmad-core/agents/`)
- **Purpose**: Each markdown file defines a specialized AI agent for a specific Agile role (PM, Dev, Architect, etc.) - **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 - **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 - **Dependencies**: Lists of tasks, templates, checklists, and data files the agent can use
- **Startup Instructions**: Can load project-specific documentation for immediate context - **Startup Instructions**: Can load project-specific documentation for immediate context
#### 2. Agent Teams (`bmad-core/agent-teams/`) #### 2. Agent Teams (`bmad-core/agent-teams/`)
- **Purpose**: Define collections of agents bundled together for specific purposes - **Purpose**: Define collections of agents bundled together for specific purposes
- **Examples**: `team-all.yaml` (comprehensive bundle), `team-fullstack.yaml` (full-stack development) - **Examples**: `team-all.yaml` (comprehensive bundle), `team-fullstack.yaml` (full-stack development)
- **Usage**: Creates pre-packaged contexts for web UI environments - **Usage**: Creates pre-packaged contexts for web UI environments
#### 3. Workflows (`bmad-core/workflows/`) #### 3. Workflows (`bmad-core/workflows/`)
- **Purpose**: YAML files defining prescribed sequences of steps for specific project types - **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 - **Types**: Greenfield (new projects) and Brownfield (existing projects) for UI, service, and fullstack development
- **Structure**: Defines agent interactions, artifacts created, and transition conditions - **Structure**: Defines agent interactions, artifacts created, and transition conditions
#### 4. Reusable Resources #### 4. Reusable Resources
- **Templates** (`bmad-core/templates/`): Markdown templates for PRDs, architecture specs, user stories - **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" - **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 - **Checklists** (`bmad-core/checklists/`): Quality assurance checklists for validation and review
@@ -1607,6 +1662,7 @@ BMad employs a sophisticated template system with three key components:
### Technical Preferences Integration ### Technical Preferences Integration
The `technical-preferences.md` file serves as a persistent technical profile that: The `technical-preferences.md` file serves as a persistent technical profile that:
- Ensures consistency across all agents and projects - Ensures consistency across all agents and projects
- Eliminates repetitive technology specification - Eliminates repetitive technology specification
- Provides personalized recommendations aligned with user preferences - Provides personalized recommendations aligned with user preferences
@@ -1615,6 +1671,7 @@ The `technical-preferences.md` file serves as a persistent technical profile tha
### Build and Delivery Process ### Build and Delivery Process
The `web-builder.js` tool creates web-ready bundles by: The `web-builder.js` tool creates web-ready bundles by:
1. Reading agent or team definition files 1. Reading agent or team definition files
2. Recursively resolving all dependencies 2. Recursively resolving all dependencies
3. Concatenating content into single text files with clear separators 3. Concatenating content into single text files with clear separators
@@ -1629,11 +1686,13 @@ This architecture enables seamless operation across environments while maintaini
**Ideal for cost efficiency with Gemini's massive context:** **Ideal for cost efficiency with Gemini's massive context:**
**For Brownfield Projects - Start Here!**: **For Brownfield Projects - Start Here!**:
1. **Upload entire project to Gemini Web** (GitHub URL, files, or zip) 1. **Upload entire project to Gemini Web** (GitHub URL, files, or zip)
2. **Document existing system**: `/analyst` → `*document-project` 2. **Document existing system**: `/analyst` → `*document-project`
3. **Creates comprehensive docs** from entire codebase analysis 3. **Creates comprehensive docs** from entire codebase analysis
**For All Projects**: **For All Projects**:
1. **Optional Analysis**: `/analyst` - Market research, competitive analysis 1. **Optional Analysis**: `/analyst` - Market research, competitive analysis
2. **Project Brief**: Create foundation document (Analyst or user) 2. **Project Brief**: Create foundation document (Analyst or user)
3. **PRD Creation**: `/pm create-doc prd` - Comprehensive product requirements 3. **PRD Creation**: `/pm create-doc prd` - Comprehensive product requirements
@@ -1644,12 +1703,14 @@ This architecture enables seamless operation across environments while maintaini
#### Example Planning Prompts #### Example Planning Prompts
**For PRD Creation**: **For PRD Creation**:
```text ```text
"I want to build a [type] application that [core purpose]. "I want to build a [type] application that [core purpose].
Help me brainstorm features and create a comprehensive PRD." Help me brainstorm features and create a comprehensive PRD."
``` ```
**For Architecture Design**: **For Architecture Design**:
```text ```text
"Based on this PRD, design a scalable technical architecture "Based on this PRD, design a scalable technical architecture
that can handle [specific requirements]." that can handle [specific requirements]."
@@ -1667,7 +1728,7 @@ that can handle [specific requirements]."
**Prerequisites**: Planning documents must exist in `docs/` folder **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 - Documents created by PM/Architect (in Web or IDE) MUST be sharded for development
- Two methods to shard: - Two methods to shard:
a) **Manual**: Drag `shard-doc` task + document file into chat a) **Manual**: Drag `shard-doc` task + document file into chat
@@ -1681,32 +1742,33 @@ that can handle [specific requirements]."
- Source tree document and coding standards for dev agent reference - Source tree document and coding standards for dev agent reference
- Sharded docs for SM agent story creation - Sharded docs for SM agent story creation
**Resulting Folder Structure**: Resulting Folder Structure:
- `docs/prd/` - Broken down PRD sections - `docs/prd/` - Broken down PRD sections
- `docs/architecture/` - Broken down architecture sections - `docs/architecture/` - Broken down architecture sections
- `docs/stories/` - Generated user stories - `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**: **CRITICAL CONTEXT MANAGEMENT**:
- **Context windows matter!** Always use fresh, clean context windows - **Context windows matter!** Always use fresh, clean context windows
- **Model selection matters!** Use most powerful thinking model for SM story creation - **Model selection matters!** Use most powerful thinking model for SM story creation
- **ALWAYS start new chat between SM, Dev, and QA work** - **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` - **NEW CLEAN CHAT** → Select powerful model → `@sm` → `*create`
- SM executes create-next-story task - SM executes create-next-story task
- Review generated story in `docs/stories/` - Review generated story in `docs/stories/`
- Update status from "Draft" to "Approved" - Update status from "Draft" to "Approved"
**Step 2 - Story Implementation**: **Step 2 - Story Implementation**:
- **NEW CLEAN CHAT** → `@dev` - **NEW CLEAN CHAT** → `@dev`
- Agent asks which story to implement - Agent asks which story to implement
- Include story file content to save dev agent lookup time - Include story file content to save dev agent lookup time
- Dev follows tasks/subtasks, marking completion - Dev follows tasks/subtasks, marking completion
- Dev maintains File List of all changes - Dev maintains File List of all changes
- Dev marks story as "Review" when complete with all tests passing - Dev marks story as "Review" when complete with all tests passing
**Step 3 - Senior QA Review**: **Step 3 - Senior QA Review**:
- **NEW CLEAN CHAT** → `@qa` → execute review-story task - **NEW CLEAN CHAT** → `@qa` → execute review-story task
- QA performs senior developer code review - QA performs senior developer code review
@@ -1714,7 +1776,7 @@ that can handle [specific requirements]."
- QA appends results to story's QA Results section - QA appends results to story's QA Results section
- If approved: Status → "Done" - If approved: Status → "Done"
- If changes needed: Status stays "Review" with unchecked items for dev - If changes needed: Status stays "Review" with unchecked items for dev
**Step 4 - Repeat**: Continue SM → Dev → QA cycle until all epic stories complete **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. **Important**: Only 1 story in progress at a time, worked sequentially until all epic stories complete.
@@ -1722,6 +1784,7 @@ that can handle [specific requirements]."
### Status Tracking Workflow ### Status Tracking Workflow
Stories progress through defined statuses: Stories progress through defined statuses:
- **Draft** → **Approved** → **InProgress** → **Done** - **Draft** → **Approved** → **InProgress** → **Done**
Each status change requires user verification and approval before proceeding. Each status change requires user verification and approval before proceeding.
@@ -1729,6 +1792,7 @@ Each status change requires user verification and approval before proceeding.
### Workflow Types ### Workflow Types
#### Greenfield Development #### Greenfield Development
- Business analysis and market research - Business analysis and market research
- Product requirements and feature definition - Product requirements and feature definition
- System architecture and design - System architecture and design
@@ -1742,6 +1806,7 @@ Each status change requires user verification and approval before proceeding.
**Complete Brownfield Workflow Options**: **Complete Brownfield Workflow Options**:
**Option 1: PRD-First (Recommended for Large Codebases/Monorepos)**: **Option 1: PRD-First (Recommended for Large Codebases/Monorepos)**:
1. **Upload project to Gemini Web** (GitHub URL, files, or zip) 1. **Upload project to Gemini Web** (GitHub URL, files, or zip)
2. **Create PRD first**: `@pm` → `*create-doc brownfield-prd` 2. **Create PRD first**: `@pm` → `*create-doc brownfield-prd`
3. **Focused documentation**: `@analyst` → `*document-project` 3. **Focused documentation**: `@analyst` → `*document-project`
@@ -1752,18 +1817,19 @@ Each status change requires user verification and approval before proceeding.
- Avoids bloating docs with unused code - Avoids bloating docs with unused code
**Option 2: Document-First (Good for Smaller Projects)**: **Option 2: Document-First (Good for Smaller Projects)**:
1. **Upload project to Gemini Web** 1. **Upload project to Gemini Web**
2. **Document everything**: `@analyst` → `*document-project` 2. **Document everything**: `@analyst` → `*document-project`
3. **Then create PRD**: `@pm` → `*create-doc brownfield-prd` 3. **Then create PRD**: `@pm` → `*create-doc brownfield-prd`
- More thorough but can create excessive documentation - More thorough but can create excessive documentation
2. **Requirements Gathering**: 4. **Requirements Gathering**:
- **Brownfield PRD**: Use PM agent with `brownfield-prd-tmpl` - **Brownfield PRD**: Use PM agent with `brownfield-prd-tmpl`
- **Analyzes**: Existing system, constraints, integration points - **Analyzes**: Existing system, constraints, integration points
- **Defines**: Enhancement scope, compatibility requirements, risk assessment - **Defines**: Enhancement scope, compatibility requirements, risk assessment
- **Creates**: Epic and story structure for changes - **Creates**: Epic and story structure for changes
3. **Architecture Planning**: 5. **Architecture Planning**:
- **Brownfield Architecture**: Use Architect agent with `brownfield-architecture-tmpl` - **Brownfield Architecture**: Use Architect agent with `brownfield-architecture-tmpl`
- **Integration Strategy**: How new features integrate with existing system - **Integration Strategy**: How new features integrate with existing system
- **Migration Planning**: Gradual rollout and backwards compatibility - **Migration Planning**: Gradual rollout and backwards compatibility
@@ -1772,10 +1838,12 @@ Each status change requires user verification and approval before proceeding.
**Brownfield-Specific Resources**: **Brownfield-Specific Resources**:
**Templates**: **Templates**:
- `brownfield-prd-tmpl.md`: Comprehensive enhancement planning with existing system analysis - `brownfield-prd-tmpl.md`: Comprehensive enhancement planning with existing system analysis
- `brownfield-architecture-tmpl.md`: Integration-focused architecture for existing systems - `brownfield-architecture-tmpl.md`: Integration-focused architecture for existing systems
**Tasks**: **Tasks**:
- `document-project`: Generates comprehensive documentation from existing codebase - `document-project`: Generates comprehensive documentation from existing codebase
- `brownfield-create-epic`: Creates single epic for focused enhancements (when full PRD is overkill) - `brownfield-create-epic`: Creates single epic for focused enhancements (when full PRD is overkill)
- `brownfield-create-story`: Creates individual story for small, isolated changes - `brownfield-create-story`: Creates individual story for small, isolated changes
@@ -1783,18 +1851,21 @@ Each status change requires user verification and approval before proceeding.
**When to Use Each Approach**: **When to Use Each Approach**:
**Full Brownfield Workflow** (Recommended for): **Full Brownfield Workflow** (Recommended for):
- Major feature additions - Major feature additions
- System modernization - System modernization
- Complex integrations - Complex integrations
- Multiple related changes - Multiple related changes
**Quick Epic/Story Creation** (Use when): **Quick Epic/Story Creation** (Use when):
- Single, focused enhancement - Single, focused enhancement
- Isolated bug fixes - Isolated bug fixes
- Small feature additions - Small feature additions
- Well-documented existing system - Well-documented existing system
**Critical Success Factors**: **Critical Success Factors**:
1. **Documentation First**: Always run `document-project` if docs are outdated/missing 1. **Documentation First**: Always run `document-project` if docs are outdated/missing
2. **Context Matters**: Provide agents access to relevant code sections 2. **Context Matters**: Provide agents access to relevant code sections
3. **Integration Focus**: Emphasize compatibility and non-breaking changes 3. **Integration Focus**: Emphasize compatibility and non-breaking changes
@@ -1810,6 +1881,7 @@ Each status change requires user verification and approval before proceeding.
- `docs/architecture.md` - System Architecture Document - `docs/architecture.md` - System Architecture Document
**Why These Names Matter**: **Why These Names Matter**:
- Agents automatically reference these files during development - Agents automatically reference these files during development
- Sharding tasks expect these specific filenames - Sharding tasks expect these specific filenames
- Workflow automation depends on standard naming - Workflow automation depends on standard naming
@@ -1828,6 +1900,7 @@ Each status change requires user verification and approval before proceeding.
Templates with Level 2 headings (`##`) can be automatically sharded: Templates with Level 2 headings (`##`) can be automatically sharded:
**Original PRD**: **Original PRD**:
```markdown ```markdown
## Goals and Background Context ## Goals and Background Context
## Requirements ## Requirements
@@ -1836,6 +1909,7 @@ Templates with Level 2 headings (`##`) can be automatically sharded:
``` ```
**After Sharding**: **After Sharding**:
- `docs/prd/goals-and-background-context.md` - `docs/prd/goals-and-background-context.md`
- `docs/prd/requirements.md` - `docs/prd/requirements.md`
- `docs/prd/user-interface-design-goals.md` - `docs/prd/user-interface-design-goals.md`
@@ -1848,12 +1922,14 @@ Use the `shard-doc` task or `@kayvan/markdown-tree-parser` tool for automatic sh
### Environment-Specific Usage ### Environment-Specific Usage
**Web UI Best For**: **Web UI Best For**:
- Initial planning and documentation phases - Initial planning and documentation phases
- Cost-effective large document creation - Cost-effective large document creation
- Agent consultation and brainstorming - Agent consultation and brainstorming
- Multi-agent workflows with orchestrator - Multi-agent workflows with orchestrator
**IDE Best For**: **IDE Best For**:
- Active development and implementation - Active development and implementation
- File operations and project integration - File operations and project integration
- Story management and development cycles - Story management and development cycles
@@ -1888,6 +1964,7 @@ Use the `shard-doc` task or `@kayvan/markdown-tree-parser` tool for automatic sh
For full details, see `CONTRIBUTING.md`. Key points: For full details, see `CONTRIBUTING.md`. Key points:
**Fork Workflow**: **Fork Workflow**:
1. Fork the repository 1. Fork the repository
2. Create feature branches 2. Create feature branches
3. Submit PRs to `next` branch (default) or `main` for critical fixes only 3. Submit PRs to `next` branch (default) or `main` for critical fixes only
@@ -1895,12 +1972,14 @@ For full details, see `CONTRIBUTING.md`. Key points:
5. One feature/fix per PR 5. One feature/fix per PR
**PR Requirements**: **PR Requirements**:
- Clear descriptions (max 200 words) with What/Why/How/Testing - Clear descriptions (max 200 words) with What/Why/How/Testing
- Use conventional commits (feat:, fix:, docs:) - Use conventional commits (feat:, fix:, docs:)
- Atomic commits - one logical change per commit - Atomic commits - one logical change per commit
- Must align with guiding principles - Must align with guiding principles
**Core Principles** (from GUIDING-PRINCIPLES.md): **Core Principles** (from GUIDING-PRINCIPLES.md):
- **Dev Agents Must Be Lean**: Minimize dependencies, save context for code - **Dev Agents Must Be Lean**: Minimize dependencies, save context for code
- **Natural Language First**: Everything in markdown, no code in core - **Natural Language First**: Everything in markdown, no code in core
- **Core vs Expansion Packs**: Core for universal needs, packs for specialized domains - **Core vs Expansion Packs**: Core for universal needs, packs for specialized domains
@@ -1922,12 +2001,14 @@ Expansion packs extend BMad-Method beyond traditional software development into
### Available Expansion Packs ### Available Expansion Packs
**Technical Packs**: **Technical Packs**:
- **Infrastructure/DevOps**: Cloud architects, SRE experts, security specialists - **Infrastructure/DevOps**: Cloud architects, SRE experts, security specialists
- **Game Development**: Game designers, level designers, narrative writers - **Game Development**: Game designers, level designers, narrative writers
- **Mobile Development**: iOS/Android specialists, mobile UX experts - **Mobile Development**: iOS/Android specialists, mobile UX experts
- **Data Science**: ML engineers, data scientists, visualization experts - **Data Science**: ML engineers, data scientists, visualization experts
**Non-Technical Packs**: **Non-Technical Packs**:
- **Business Strategy**: Consultants, financial analysts, marketing strategists - **Business Strategy**: Consultants, financial analysts, marketing strategists
- **Creative Writing**: Plot architects, character developers, world builders - **Creative Writing**: Plot architects, character developers, world builders
- **Health & Wellness**: Fitness trainers, nutritionists, habit engineers - **Health & Wellness**: Fitness trainers, nutritionists, habit engineers
@@ -1935,6 +2016,7 @@ Expansion packs extend BMad-Method beyond traditional software development into
- **Legal Support**: Contract analysts, compliance checkers - **Legal Support**: Contract analysts, compliance checkers
**Specialty Packs**: **Specialty Packs**:
- **Expansion Creator**: Tools to build your own expansion packs - **Expansion Creator**: Tools to build your own expansion packs
- **RPG Game Master**: Tabletop gaming assistance - **RPG Game Master**: Tabletop gaming assistance
- **Life Event Planning**: Wedding planners, event coordinators - **Life Event Planning**: Wedding planners, event coordinators
@@ -1944,11 +2026,13 @@ Expansion packs extend BMad-Method beyond traditional software development into
1. **Browse Available Packs**: Check `expansion-packs/` directory 1. **Browse Available Packs**: Check `expansion-packs/` directory
2. **Get Inspiration**: See `docs/expansion-packs.md` for detailed examples and ideas 2. **Get Inspiration**: See `docs/expansion-packs.md` for detailed examples and ideas
3. **Install via CLI**: 3. **Install via CLI**:
```bash ```bash
npx bmad-method install npx bmad-method install
# Select "Install expansion pack" option # Select "Install expansion pack" option
``` ```
4. **Use in Your Workflow**: Installed packs integrate seamlessly with existing agents 4. **Use in Your Workflow**: Installed packs integrate seamlessly with existing agents
### Creating Custom Expansion Packs ### Creating Custom Expansion Packs
@@ -1982,14 +2066,10 @@ Provides utilities for agents and tasks to interact with workflow plans, check p
### 1. Check Plan Existence ### 1. Check Plan Existence
[[LLM: When any agent starts or task begins, check if a workflow plan exists]]
```
Check for workflow plan: Check for workflow plan:
1. Look for docs/workflow-plan.md (default location) 1. Look for docs/workflow-plan.md (default location)
2. Check core-config.yaml for custom plan location 2. Return plan status to user (exists/not exists) - if not exists then HALT.
3. Return plan status (exists/not exists)
```
### 2. Parse Plan Status ### 2. Parse Plan Status
@@ -2030,7 +2110,7 @@ Check for workflow plan:
**Warning Templates:** **Warning Templates:**
``` ```text
SEQUENCE WARNING: SEQUENCE WARNING:
The workflow plan shows you should complete "{expected_step}" next. The workflow plan shows you should complete "{expected_step}" next.
You're attempting to: "{requested_action}" You're attempting to: "{requested_action}"
@@ -2064,7 +2144,7 @@ In flexible mode: Allow with confirmation
**For Agents (startup sequence)**: **For Agents (startup sequence)**:
``` ```text
1. Check if plan exists using this utility 1. Check if plan exists using this utility
2. If exists: 2. If exists:
- Parse current status - Parse current status
@@ -2075,7 +2155,7 @@ In flexible mode: Allow with confirmation
**For Tasks (pre-execution)**: **For Tasks (pre-execution)**:
``` ```text
1. Check if plan exists 1. Check if plan exists
2. If exists: 2. If exists:
- Verify this task aligns with plan - Verify this task aligns with plan
@@ -2091,7 +2171,7 @@ In flexible mode: Allow with confirmation
[[LLM: Standard format for showing plan status]] [[LLM: Standard format for showing plan status]]
``` ```text
📋 Workflow Plan Status 📋 Workflow Plan Status
━━━━━━━━━━━━━━━━━━━━ ━━━━━━━━━━━━━━━━━━━━
Workflow: {workflow_name} Workflow: {workflow_name}
@@ -2144,7 +2224,7 @@ If user wants to abandon plan:
### Example 1: Agent Startup Check ### Example 1: Agent Startup Check
``` ```text
BMad Master starting... BMad Master starting...
[Check for plan] [Check for plan]
@@ -2158,7 +2238,7 @@ Use *agent pm to switch, or *plan-status to see full progress.
### Example 2: Task Sequence Warning ### Example 2: Task Sequence Warning
``` ```text
User: *task create-next-story User: *task create-next-story
[Plan check triggered] [Plan check triggered]
@@ -2174,7 +2254,7 @@ Would you like to:
### Example 3: Automatic Plan Update ### Example 3: Automatic Plan Update
``` ```text
[After completing create-doc task for PRD] [After completing create-doc task for PRD]
✅ Plan Updated: Marked "Create PRD" as complete ✅ Plan Updated: Marked "Create PRD" as complete

753
dist/teams/team-no-ui.txt vendored
View File

File diff suppressed because it is too large Load Diff