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

installer updates part 1

Browse Source
This commit is contained in:
Brian Madison
2025-06-27 23:38:34 -05:00
parent 6cdecec61f
commit 1ea367619a
38 changed files with 569 additions and 2332 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.claude/commands/bmad-master.md
View File

@@ -58,7 +58,6 @@ dependencies:
- brainstorming-techniques
- brownfield-create-epic
- brownfield-create-story
- core-dump
- correct-course
- create-deep-research-prompt
- create-doc

74
bmad-core/tasks/core-dump.md
View File

@@ -1,74 +0,0 @@
# Core Dump Task
## Purpose
To create a concise memory recording file (`.ai/core-dump-n.md`) that captures the essential context of the current agent session, enabling seamless continuation of work in future agent sessions. This task ensures persistent context across agent conversations while maintaining minimal token usage for efficient context loading.
## Inputs for this Task
- Current session conversation history and accomplishments
- Files created, modified, or deleted during the session
- Key decisions made and procedures followed
- Current project state and next logical steps
- User requests and agent responses that shaped the session
## Task Execution Instructions
### 0. Check Existing Core Dump
Before proceeding, check if `.ai/core-dump.md` already exists:
- If file exists, ask user: "Core dump file exists. Should I: 1. Overwrite, 2. Update, 3. Append or 4. Create new?"
- **Overwrite**: Replace entire file with new content
- **Update**: Merge new session info with existing content, updating relevant sections
- **Append**: Add new session as a separate entry while preserving existing content
- **Create New**: Create a new file, appending the next possible -# to the file, such as core-dump-3.md if 1 and 2 already exist.
- If file doesn't exist, proceed with creation of `core-dump-1.md`
### 1. Analyze Session Context
- Review the entire conversation to identify key accomplishments
- Note any specific tasks, procedures, or workflows that were executed
- Identify important decisions made or problems solved
- Capture the user's working style and preferences observed during the session
### 2. Document What Was Accomplished
- **Primary Actions**: List the main tasks completed concisely
- **Story Progress**: For story work, use format "Tasks Complete: 1-6, 8. Next Task Pending: 7, 9"
- **Problem Solving**: Document any challenges encountered and how they were resolved
- **User Communications**: Summarize key user requests, preferences, and discussion points
### 3. Record File System Changes (Concise Format)
- **Files Created**: `filename.ext` (brief purpose/size)
- **Files Modified**: `filename.ext` (what changed)
- **Files Deleted**: `filename.ext` (why removed)
- Focus on essential details, avoid verbose descriptions
### 4. Capture Current Project State
- **Project Progress**: Where the project stands after this session
- **Current Issues**: Any blockers or problems that need resolution
- **Next Logical Steps**: What would be the natural next actions to take
### 5. Create/Update Core Dump File
Based on user's choice from step 0, handle the file accordingly:
### 6. Optimize for Minimal Context
- Keep descriptions concise but informative
- Use abbreviated formats where possible (file sizes, task numbers)
- Focus on actionable information rather than detailed explanations
- Avoid redundant information that can be found in project documentation
- Prioritize information that would be lost without this recording
- Ensure the file can be quickly scanned and understood
### 7. Validate Completeness
- Verify all significant session activities are captured
- Ensure a future agent could understand the current state
- Check that file changes are accurately recorded
- Confirm next steps are clear and actionable
- Verify user communication style and preferences are noted

97
bmad-core/tasks/execute-checklist.md
View File

@@ -1,97 +0,0 @@
# Checklist Validation Task
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
## Instructions
1. **Initial Assessment**
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder
- Confirm if they want to work through the checklist:
- Section by section (interactive mode - very time consuming)
- All at once (YOLO mode - recommended for checklists, there will be a summary of sections at the end to discuss)
2. **Document and Artifact Gathering**
- Each checklist will specify its required documents/artifacts at the beginning
- Follow the checklist's specific instructions for what to gather, generally a file can be resolved in the docs folder, if not or unsure, halt and ask or confirm with the user.
3. **Checklist Processing**
If in interactive mode:
- Work through each section of the checklist one at a time
- For each section:
- Review all items in the section following instructions for that section embedded in the checklist
- Check each item against the relevant documentation or artifacts as appropriate
- Present summary of findings for that section, highlighting warnings, errors and non applicable items (rationale for non-applicability).
- Get user confirmation before proceeding to next section or if any thing major do we need to halt and take corrective action
If in YOLO mode:
- Process all sections at once
- Create a comprehensive report of all findings
- Present the complete analysis to the user
4. **Validation Approach**
For each checklist item:
- Read and understand the requirement
- Look for evidence in the documentation that satisfies the requirement
- Consider both explicit mentions and implicit coverage
- Aside from this, follow all checklist llm instructions
- Mark items as:
- ✅ PASS: Requirement clearly met
- ❌ FAIL: Requirement not met or insufficient coverage
- ⚠️ PARTIAL: Some aspects covered but needs improvement
- N/A: Not applicable to this case
5. **Section Analysis**
For each section:
- think step by step to calculate pass rate
- Identify common themes in failed items
- Provide specific recommendations for improvement
- In interactive mode, discuss findings with user
- Document any user decisions or explanations
6. **Final Report**
Prepare a summary that includes:
- Overall checklist completion status
- Pass rates by section
- List of failed items with context
- Specific recommendations for improvement
- Any sections or items marked as N/A with justification
## Checklist Execution Methodology
Each checklist now contains embedded LLM prompts and instructions that will:
1. **Guide thorough thinking** - Prompts ensure deep analysis of each section
2. **Request specific artifacts** - Clear instructions on what documents/access is needed
3. **Provide contextual guidance** - Section-specific prompts for better validation
4. **Generate comprehensive reports** - Final summary with detailed findings
The LLM will:
- Execute the complete checklist validation
- Present a final report with pass/fail rates and key findings
- Offer to provide detailed analysis of any section, especially those with warnings or failures

10
bmad-core/utils/file-resolution-context.md
View File

@@ -1,10 +0,0 @@
# File Resolution Context
Update the installer/upgrader so that when agents are added to a project (under Add these two lines to any agent's `activation-instructions` for ide installation:
```yaml
- IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}.md where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
- REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), or ask for clarification if ambiguous.
```
and add `root: .bmad-core` as the first root yml property.

223
bmad-core/utils/workflow-management.md
View File

@@ -1,223 +0,0 @@
# Workflow Management
This utility enables the BMAD orchestrator to manage and execute team workflows.
## Important: Dynamic Workflow Loading
The BMAD orchestrator MUST read the available workflows from the current team configuration's `workflows` field. Do not use hardcoded workflow lists. Each team bundle defines its own set of supported workflows based on the agents it includes.
**Critical Distinction**:
- When asked "what workflows are available?", show ONLY the workflows defined in the current team bundle's configuration
- Use `/agent-list` to show agents in the current bundle
- Use `/workflows` to show workflows in the current bundle, NOT any creation tasks
### Workflow Descriptions
When displaying workflows, use these descriptions based on the workflow ID:
- **greenfield-fullstack**: Build a new full-stack application from concept to development
- **brownfield-fullstack**: Enhance an existing full-stack application with new features
- **greenfield-service**: Build a new backend service or API from concept to development
- **brownfield-service**: Enhance an existing backend service or API
- **greenfield-ui**: Build a new frontend/UI application from concept to development
- **brownfield-ui**: Enhance an existing frontend/UI application
## Workflow Commands
### /workflows
Lists all available workflows for the current team. The available workflows are determined by the team configuration and may include workflows such as:
- greenfield-fullstack
- brownfield-fullstack
- greenfield-service
- brownfield-service
- greenfield-ui
- brownfield-ui
The actual list depends on which team bundle is loaded. When responding to this command, display the workflows that are configured in the current team's `workflows` field.
Example response format:
```text
Available workflows for [Team Name]:
1. [workflow-id] - [Brief description based on workflow type]
2. [workflow-id] - [Brief description based on workflow type]
[... etc. ...]
Use /workflow-start {number or id} to begin a workflow.
```
### /workflow-start {workflow-id}
Starts a specific workflow and transitions to the first agent.
Example: `/workflow-start greenfield-fullstack`
### /workflow-status
Shows current workflow progress, completed artifacts, and next steps.
Example response:
```text
Current Workflow: Greenfield Full-Stack Development
Stage: Product Planning (2 of 6)
Completed:
✓ Discovery & Requirements
- project-brief (completed by Mary)
In Progress:
⚡ Product Planning
- Create PRD (John) - awaiting input
Next: Technical Architecture
```
### /workflow-resume
Resumes a workflow from where it left off, useful when starting a new chat.
User can provide completed artifacts:
```text
User: /workflow-resume greenfield-fullstack
I have completed: project-brief, PRD
BMad: I see you've completed Discovery and part of Product Planning.
Based on the greenfield-fullstack workflow, the next step is:
- UX Strategy with Sally (ux-expert)
Would you like me to load Sally to continue?
```
### /workflow-next
Shows the next recommended agent and action in the current workflow.
## Workflow Execution Flow
### 1. Starting a Workflow
When a workflow is started:
1. Load the workflow definition
2. Identify the first stage and step
3. Transition to the required agent
4. Provide context about expected inputs/outputs
5. Guide artifact creation
### 2. Stage Transitions
After each artifact is completed:
1. Mark the step as complete
2. Check transition conditions
3. If stage is complete, move to next stage
4. Load the appropriate agent
5. Pass relevant artifacts as context
### 3. Artifact Tracking
Track all created artifacts:
```yaml
workflow_state:
current_workflow: greenfield-fullstack
current_stage: planning
current_step: 2
artifacts:
project-brief:
status: completed
created_by: analyst
timestamp: 2024-01-15T10:30:00.000Z
prd:
status: in-progress
created_by: pm
started: 2024-01-15T11:00:00.000Z
```
### 4. Workflow Interruption Handling
When user returns after interruption:
1. Ask if continuing previous workflow
2. Request any completed artifacts
3. Analyze provided artifacts
4. Determine workflow position
5. Suggest next appropriate step
Example:
```text
User: I'm working on a new app. Here's my PRD and architecture doc.
BMad: I see you have a PRD and architecture document. Based on these artifacts,
it looks like you're following the greenfield-fullstack workflow and have completed
stages 1-3. The next recommended step would be:
Stage 4: Validation & Refinement
- Load Sarah (Product Owner) to validate all artifacts
Would you like to continue with this workflow?
```
## Workflow Context Passing
When transitioning between agents, pass:
1. Previous artifacts created
2. Current workflow stage
3. Expected outputs
4. Any decisions or constraints identified
Example transition:
```text
BMad: Great! John has completed the PRD. According to the greenfield-fullstack workflow,
the next step is UX Strategy with Sally.
/ux-expert
Sally: I see we're in the Product Planning stage of the greenfield-fullstack workflow.
I have access to:
- Project Brief from Mary
- PRD from John
Let's create the UX strategy and UI specifications. First, let me review
the PRD to understand the features we're designing for...
```
## Multi-Path Workflows
Some workflows may have multiple paths:
```yaml
conditional_paths:
- condition: project_type == 'mobile'
next_stage: mobile-specific-design
- condition: project_type == 'web'
next_stage: web-architecture
- default: fullstack-architecture
```
Handle these by asking clarifying questions when needed.
## Workflow Best Practices
1. **Always show progress** - Users should know where they are
2. **Explain transitions** - Why moving to next agent
3. **Preserve context** - Pass relevant information forward
4. **Allow flexibility** - Users can skip or modify steps
5. **Track everything** - Maintain complete workflow state
## Integration with Agents
Each agent should be workflow-aware:
- Know which workflow is active
- Understand their role in the workflow
- Access previous artifacts
- Know expected outputs
- Guide toward workflow goals
This creates a seamless experience where the entire team works together toward the workflow's objectives.

4
bmad-core/tasks/create-doc.md → common/tasks/create-doc.md
View File

@@ -31,9 +31,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the `{root}/templates directory`
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `{root}/utils/template-format` conventions
### 4. Template Processing Rules

8
expansion-packs/expansion-creator/common-tasks/execute-checklist.md → common/tasks/execute-checklist.md
View File

@@ -2,13 +2,9 @@
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -17,7 +13,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

0
bmad-core/utils/template-format.md → common/utils/template-format.md
View File

69
common/utils/workflow-management.md Normal file
View File

@@ -0,0 +1,69 @@
# Workflow Management
Enables BMAD orchestrator to manage and execute team workflows.
## Dynamic Workflow Loading
Read available workflows from current team configuration's `workflows` field. Each team bundle defines its own supported workflows.
**Key Commands**:
- `/workflows` - List workflows in current bundle or workflows folder
- `/agent-list` - Show agents in current bundle
## Workflow Commands
### /workflows
Lists available workflows with titles and descriptions.
### /workflow-start {workflow-id}
Starts workflow and transitions to first agent.
### /workflow-status
Shows current progress, completed artifacts, and next steps.
### /workflow-resume
Resumes workflow from last position. User can provide completed artifacts.
### /workflow-next
Shows next recommended agent and action.
## Execution Flow
1. **Starting**: Load definition → Identify first stage → Transition to agent → Guide artifact creation
2. **Stage Transitions**: Mark complete → Check conditions → Load next agent → Pass artifacts
3. **Artifact Tracking**: Track status, creator, timestamps in workflow_state
4. **Interruption Handling**: Analyze provided artifacts → Determine position → Suggest next step
## Context Passing
When transitioning, pass:
- Previous artifacts
- Current workflow stage
- Expected outputs
- Decisions/constraints
## Multi-Path Workflows
Handle conditional paths by asking clarifying questions when needed.
## Best Practices
1. Show progress
2. Explain transitions
3. Preserve context
4. Allow flexibility
5. Track state
## Agent Integration
Agents should be workflow-aware: know active workflow, their role, access artifacts, understand expected outputs.

4
dist/agents/analyst.txt vendored
View File

@@ -681,9 +681,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the ../templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `../utils/template-format` conventions
### 4. Template Processing Rules

12
dist/agents/architect.txt vendored
View File

@@ -136,9 +136,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the ../templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `../utils/template-format` conventions
### 4. Template Processing Rules
@@ -808,13 +808,9 @@ Apply the advanced elicitation task after major sections to refine based on user
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -823,7 +819,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

305
dist/agents/bmad-master.txt vendored
View File

@@ -788,83 +788,6 @@ The story creation is successful when:
- Stories should take no more than 4 hours of focused development work
==================== END: tasks#brownfield-create-story ====================
==================== START: tasks#core-dump ====================
# Core Dump Task
## Purpose
To create a concise memory recording file (`.ai/core-dump-n.md`) that captures the essential context of the current agent session, enabling seamless continuation of work in future agent sessions. This task ensures persistent context across agent conversations while maintaining minimal token usage for efficient context loading.
## Inputs for this Task
- Current session conversation history and accomplishments
- Files created, modified, or deleted during the session
- Key decisions made and procedures followed
- Current project state and next logical steps
- User requests and agent responses that shaped the session
## Task Execution Instructions
### 0. Check Existing Core Dump
Before proceeding, check if `.ai/core-dump.md` already exists:
- If file exists, ask user: "Core dump file exists. Should I: 1. Overwrite, 2. Update, 3. Append or 4. Create new?"
- **Overwrite**: Replace entire file with new content
- **Update**: Merge new session info with existing content, updating relevant sections
- **Append**: Add new session as a separate entry while preserving existing content
- **Create New**: Create a new file, appending the next possible -# to the file, such as core-dump-3.md if 1 and 2 already exist.
- If file doesn't exist, proceed with creation of `core-dump-1.md`
### 1. Analyze Session Context
- Review the entire conversation to identify key accomplishments
- Note any specific tasks, procedures, or workflows that were executed
- Identify important decisions made or problems solved
- Capture the user's working style and preferences observed during the session
### 2. Document What Was Accomplished
- **Primary Actions**: List the main tasks completed concisely
- **Story Progress**: For story work, use format "Tasks Complete: 1-6, 8. Next Task Pending: 7, 9"
- **Problem Solving**: Document any challenges encountered and how they were resolved
- **User Communications**: Summarize key user requests, preferences, and discussion points
### 3. Record File System Changes (Concise Format)
- **Files Created**: `filename.ext` (brief purpose/size)
- **Files Modified**: `filename.ext` (what changed)
- **Files Deleted**: `filename.ext` (why removed)
- Focus on essential details, avoid verbose descriptions
### 4. Capture Current Project State
- **Project Progress**: Where the project stands after this session
- **Current Issues**: Any blockers or problems that need resolution
- **Next Logical Steps**: What would be the natural next actions to take
### 5. Create/Update Core Dump File
Based on user's choice from step 0, handle the file accordingly:
### 6. Optimize for Minimal Context
- Keep descriptions concise but informative
- Use abbreviated formats where possible (file sizes, task numbers)
- Focus on actionable information rather than detailed explanations
- Avoid redundant information that can be found in project documentation
- Prioritize information that would be lost without this recording
- Ensure the file can be quickly scanned and understood
### 7. Validate Completeness
- Verify all significant session activities are captured
- Ensure a future agent could understand the current state
- Check that file changes are accurately recorded
- Confirm next steps are clear and actionable
- Verify user communication style and preferences are noted
==================== END: tasks#core-dump ====================
==================== START: tasks#correct-course ====================
# Correct Course Task
@@ -1279,9 +1202,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the ../templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `../utils/template-format` conventions
### 4. Template Processing Rules
@@ -1902,13 +1825,9 @@ Provide a summary to the user including:
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -1917,7 +1836,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder
@@ -9187,225 +9106,71 @@ Templates in the BMAD method use standardized markup for AI processing. These co
==================== START: utils#workflow-management ====================
# Workflow Management
This utility enables the BMAD orchestrator to manage and execute team workflows.
Enables BMAD orchestrator to manage and execute team workflows.
## Important: Dynamic Workflow Loading
## Dynamic Workflow Loading
The BMAD orchestrator MUST read the available workflows from the current team configuration's `workflows` field. Do not use hardcoded workflow lists. Each team bundle defines its own set of supported workflows based on the agents it includes.
Read available workflows from current team configuration's `workflows` field. Each team bundle defines its own supported workflows.
**Critical Distinction**:
**Key Commands**:
- When asked "what workflows are available?", show ONLY the workflows defined in the current team bundle's configuration
- Use `/agent-list` to show agents in the current bundle
- Use `/workflows` to show workflows in the current bundle, NOT any creation tasks
### Workflow Descriptions
When displaying workflows, use these descriptions based on the workflow ID:
- **greenfield-fullstack**: Build a new full-stack application from concept to development
- **brownfield-fullstack**: Enhance an existing full-stack application with new features
- **greenfield-service**: Build a new backend service or API from concept to development
- **brownfield-service**: Enhance an existing backend service or API
- **greenfield-ui**: Build a new frontend/UI application from concept to development
- **brownfield-ui**: Enhance an existing frontend/UI application
- `/workflows` - List workflows in current bundle or workflows folder
- `/agent-list` - Show agents in current bundle
## Workflow Commands
### /workflows
Lists all available workflows for the current team. The available workflows are determined by the team configuration and may include workflows such as:
- greenfield-fullstack
- brownfield-fullstack
- greenfield-service
- brownfield-service
- greenfield-ui
- brownfield-ui
The actual list depends on which team bundle is loaded. When responding to this command, display the workflows that are configured in the current team's `workflows` field.
Example response format:
```text
Available workflows for [Team Name]:
1. [workflow-id] - [Brief description based on workflow type]
2. [workflow-id] - [Brief description based on workflow type]
[... etc. ...]
Use /workflow-start {number or id} to begin a workflow.
```
Lists available workflows with titles and descriptions.
### /workflow-start {workflow-id}
Starts a specific workflow and transitions to the first agent.
Example: `/workflow-start greenfield-fullstack`
Starts workflow and transitions to first agent.
### /workflow-status
Shows current workflow progress, completed artifacts, and next steps.
Example response:
```text
Current Workflow: Greenfield Full-Stack Development
Stage: Product Planning (2 of 6)
Completed:
✓ Discovery & Requirements
- project-brief (completed by Mary)
In Progress:
⚡ Product Planning
- Create PRD (John) - awaiting input
Next: Technical Architecture
```
Shows current progress, completed artifacts, and next steps.
### /workflow-resume
Resumes a workflow from where it left off, useful when starting a new chat.
User can provide completed artifacts:
```text
User: /workflow-resume greenfield-fullstack
I have completed: project-brief, PRD
BMad: I see you've completed Discovery and part of Product Planning.
Based on the greenfield-fullstack workflow, the next step is:
- UX Strategy with Sally (ux-expert)
Would you like me to load Sally to continue?
```
Resumes workflow from last position. User can provide completed artifacts.
### /workflow-next
Shows the next recommended agent and action in the current workflow.
Shows next recommended agent and action.
## Workflow Execution Flow
## Execution Flow
### 1. Starting a Workflow
1. **Starting**: Load definition → Identify first stage → Transition to agent → Guide artifact creation
When a workflow is started:
2. **Stage Transitions**: Mark complete → Check conditions → Load next agent → Pass artifacts
1. Load the workflow definition
2. Identify the first stage and step
3. Transition to the required agent
4. Provide context about expected inputs/outputs
5. Guide artifact creation
3. **Artifact Tracking**: Track status, creator, timestamps in workflow_state
### 2. Stage Transitions
4. **Interruption Handling**: Analyze provided artifacts → Determine position → Suggest next step
After each artifact is completed:
## Context Passing
1. Mark the step as complete
2. Check transition conditions
3. If stage is complete, move to next stage
4. Load the appropriate agent
5. Pass relevant artifacts as context
When transitioning, pass:
### 3. Artifact Tracking
Track all created artifacts:
```yaml
workflow_state:
current_workflow: greenfield-fullstack
current_stage: planning
current_step: 2
artifacts:
project-brief:
status: completed
created_by: analyst
timestamp: 2024-01-15T10:30:00.000Z
prd:
status: in-progress
created_by: pm
started: 2024-01-15T11:00:00.000Z
```
### 4. Workflow Interruption Handling
When user returns after interruption:
1. Ask if continuing previous workflow
2. Request any completed artifacts
3. Analyze provided artifacts
4. Determine workflow position
5. Suggest next appropriate step
Example:
```text
User: I'm working on a new app. Here's my PRD and architecture doc.
BMad: I see you have a PRD and architecture document. Based on these artifacts,
it looks like you're following the greenfield-fullstack workflow and have completed
stages 1-3. The next recommended step would be:
Stage 4: Validation & Refinement
- Load Sarah (Product Owner) to validate all artifacts
Would you like to continue with this workflow?
```
## Workflow Context Passing
When transitioning between agents, pass:
1. Previous artifacts created
2. Current workflow stage
3. Expected outputs
4. Any decisions or constraints identified
Example transition:
```text
BMad: Great! John has completed the PRD. According to the greenfield-fullstack workflow,
the next step is UX Strategy with Sally.
/ux-expert
Sally: I see we're in the Product Planning stage of the greenfield-fullstack workflow.
I have access to:
- Project Brief from Mary
- PRD from John
Let's create the UX strategy and UI specifications. First, let me review
the PRD to understand the features we're designing for...
```
- Previous artifacts
- Current workflow stage
- Expected outputs
- Decisions/constraints
## Multi-Path Workflows
Some workflows may have multiple paths:
Handle conditional paths by asking clarifying questions when needed.
```yaml
conditional_paths:
- condition: project_type == 'mobile'
next_stage: mobile-specific-design
- condition: project_type == 'web'
next_stage: web-architecture
- default: fullstack-architecture
```
## Best Practices
Handle these by asking clarifying questions when needed.
1. Show progress
2. Explain transitions
3. Preserve context
4. Allow flexibility
5. Track state
## Workflow Best Practices
## Agent Integration
1. **Always show progress** - Users should know where they are
2. **Explain transitions** - Why moving to next agent
3. **Preserve context** - Pass relevant information forward
4. **Allow flexibility** - Users can skip or modify steps
5. **Track everything** - Maintain complete workflow state
## Integration with Agents
Each agent should be workflow-aware:
- Know which workflow is active
- Understand their role in the workflow
- Access previous artifacts
- Know expected outputs
- Guide toward workflow goals
This creates a seamless experience where the entire team works together toward the workflow's objectives.
Agents should be workflow-aware: know active workflow, their role, access artifacts, understand expected outputs.
==================== END: utils#workflow-management ====================

220
dist/agents/bmad-orchestrator.txt vendored
View File

@@ -292,9 +292,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the ../templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `../utils/template-format` conventions
### 4. Template Processing Rules
@@ -1161,227 +1161,73 @@ Use the **expansion-creator** pack to build your own:
==================== START: utils#workflow-management ====================
# Workflow Management
This utility enables the BMAD orchestrator to manage and execute team workflows.
Enables BMAD orchestrator to manage and execute team workflows.
## Important: Dynamic Workflow Loading
## Dynamic Workflow Loading
The BMAD orchestrator MUST read the available workflows from the current team configuration's `workflows` field. Do not use hardcoded workflow lists. Each team bundle defines its own set of supported workflows based on the agents it includes.
Read available workflows from current team configuration's `workflows` field. Each team bundle defines its own supported workflows.
**Critical Distinction**:
**Key Commands**:
- When asked "what workflows are available?", show ONLY the workflows defined in the current team bundle's configuration
- Use `/agent-list` to show agents in the current bundle
- Use `/workflows` to show workflows in the current bundle, NOT any creation tasks
### Workflow Descriptions
When displaying workflows, use these descriptions based on the workflow ID:
- **greenfield-fullstack**: Build a new full-stack application from concept to development
- **brownfield-fullstack**: Enhance an existing full-stack application with new features
- **greenfield-service**: Build a new backend service or API from concept to development
- **brownfield-service**: Enhance an existing backend service or API
- **greenfield-ui**: Build a new frontend/UI application from concept to development
- **brownfield-ui**: Enhance an existing frontend/UI application
- `/workflows` - List workflows in current bundle or workflows folder
- `/agent-list` - Show agents in current bundle
## Workflow Commands
### /workflows
Lists all available workflows for the current team. The available workflows are determined by the team configuration and may include workflows such as:
- greenfield-fullstack
- brownfield-fullstack
- greenfield-service
- brownfield-service
- greenfield-ui
- brownfield-ui
The actual list depends on which team bundle is loaded. When responding to this command, display the workflows that are configured in the current team's `workflows` field.
Example response format:
```text
Available workflows for [Team Name]:
1. [workflow-id] - [Brief description based on workflow type]
2. [workflow-id] - [Brief description based on workflow type]
[... etc. ...]
Use /workflow-start {number or id} to begin a workflow.
```
Lists available workflows with titles and descriptions.
### /workflow-start {workflow-id}
Starts a specific workflow and transitions to the first agent.
Example: `/workflow-start greenfield-fullstack`
Starts workflow and transitions to first agent.
### /workflow-status
Shows current workflow progress, completed artifacts, and next steps.
Example response:
```text
Current Workflow: Greenfield Full-Stack Development
Stage: Product Planning (2 of 6)
Completed:
✓ Discovery & Requirements
- project-brief (completed by Mary)
In Progress:
⚡ Product Planning
- Create PRD (John) - awaiting input
Next: Technical Architecture
```
Shows current progress, completed artifacts, and next steps.
### /workflow-resume
Resumes a workflow from where it left off, useful when starting a new chat.
User can provide completed artifacts:
```text
User: /workflow-resume greenfield-fullstack
I have completed: project-brief, PRD
BMad: I see you've completed Discovery and part of Product Planning.
Based on the greenfield-fullstack workflow, the next step is:
- UX Strategy with Sally (ux-expert)
Would you like me to load Sally to continue?
```
Resumes workflow from last position. User can provide completed artifacts.
### /workflow-next
Shows the next recommended agent and action in the current workflow.
Shows next recommended agent and action.
## Workflow Execution Flow
## Execution Flow
### 1. Starting a Workflow
1. **Starting**: Load definition → Identify first stage → Transition to agent → Guide artifact creation
When a workflow is started:
2. **Stage Transitions**: Mark complete → Check conditions → Load next agent → Pass artifacts
1. Load the workflow definition
2. Identify the first stage and step
3. Transition to the required agent
4. Provide context about expected inputs/outputs
5. Guide artifact creation
3. **Artifact Tracking**: Track status, creator, timestamps in workflow_state
### 2. Stage Transitions
4. **Interruption Handling**: Analyze provided artifacts → Determine position → Suggest next step
After each artifact is completed:
## Context Passing
1. Mark the step as complete
2. Check transition conditions
3. If stage is complete, move to next stage
4. Load the appropriate agent
5. Pass relevant artifacts as context
When transitioning, pass:
### 3. Artifact Tracking
Track all created artifacts:
```yaml
workflow_state:
current_workflow: greenfield-fullstack
current_stage: planning
current_step: 2
artifacts:
project-brief:
status: completed
created_by: analyst
timestamp: 2024-01-15T10:30:00.000Z
prd:
status: in-progress
created_by: pm
started: 2024-01-15T11:00:00.000Z
```
### 4. Workflow Interruption Handling
When user returns after interruption:
1. Ask if continuing previous workflow
2. Request any completed artifacts
3. Analyze provided artifacts
4. Determine workflow position
5. Suggest next appropriate step
Example:
```text
User: I'm working on a new app. Here's my PRD and architecture doc.
BMad: I see you have a PRD and architecture document. Based on these artifacts,
it looks like you're following the greenfield-fullstack workflow and have completed
stages 1-3. The next recommended step would be:
Stage 4: Validation & Refinement
- Load Sarah (Product Owner) to validate all artifacts
Would you like to continue with this workflow?
```
## Workflow Context Passing
When transitioning between agents, pass:
1. Previous artifacts created
2. Current workflow stage
3. Expected outputs
4. Any decisions or constraints identified
Example transition:
```text
BMad: Great! John has completed the PRD. According to the greenfield-fullstack workflow,
the next step is UX Strategy with Sally.
/ux-expert
Sally: I see we're in the Product Planning stage of the greenfield-fullstack workflow.
I have access to:
- Project Brief from Mary
- PRD from John
Let's create the UX strategy and UI specifications. First, let me review
the PRD to understand the features we're designing for...
```
- Previous artifacts
- Current workflow stage
- Expected outputs
- Decisions/constraints
## Multi-Path Workflows
Some workflows may have multiple paths:
Handle conditional paths by asking clarifying questions when needed.
```yaml
conditional_paths:
- condition: project_type == 'mobile'
next_stage: mobile-specific-design
- condition: project_type == 'web'
next_stage: web-architecture
- default: fullstack-architecture
```
## Best Practices
Handle these by asking clarifying questions when needed.
1. Show progress
2. Explain transitions
3. Preserve context
4. Allow flexibility
5. Track state
## Workflow Best Practices
## Agent Integration
1. **Always show progress** - Users should know where they are
2. **Explain transitions** - Why moving to next agent
3. **Preserve context** - Pass relevant information forward
4. **Allow flexibility** - Users can skip or modify steps
5. **Track everything** - Maintain complete workflow state
## Integration with Agents
Each agent should be workflow-aware:
- Know which workflow is active
- Understand their role in the workflow
- Access previous artifacts
- Know expected outputs
- Guide toward workflow goals
This creates a seamless experience where the entire team works together toward the workflow's objectives.
Agents should be workflow-aware: know active workflow, their role, access artifacts, understand expected outputs.
==================== END: utils#workflow-management ====================
==================== START: utils#template-format ====================

8
dist/agents/dev.txt vendored
View File

@@ -102,13 +102,9 @@ dependencies:
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -117,7 +113,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

12
dist/agents/pm.txt vendored
View File

@@ -133,9 +133,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the ../templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `../utils/template-format` conventions
### 4. Template Processing Rules
@@ -874,13 +874,9 @@ The story creation is successful when:
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -889,7 +885,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

8
dist/agents/po.txt vendored
View File

@@ -106,13 +106,9 @@ dependencies:
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -121,7 +117,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

8
dist/agents/sm.txt vendored
View File

@@ -349,13 +349,9 @@ Provide a summary to the user including:
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -364,7 +360,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

12
dist/agents/ux-expert.txt vendored
View File

@@ -493,9 +493,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the ../templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `../utils/template-format` conventions
### 4. Template Processing Rules
@@ -541,13 +541,9 @@ If template specifies a checklist:
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -556,7 +552,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

12
dist/expansion-packs/bmad-2d-phaser-game-dev/agents/game-designer.txt vendored
View File

@@ -133,9 +133,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the ../templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `../utils/template-format` conventions
### 4. Template Processing Rules
@@ -181,13 +181,9 @@ If template specifies a checklist:
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -196,7 +192,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

8
dist/expansion-packs/bmad-2d-phaser-game-dev/agents/game-developer.txt vendored
View File

@@ -112,13 +112,9 @@ dependencies:
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -127,7 +123,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

8
dist/expansion-packs/bmad-2d-phaser-game-dev/agents/game-sm.txt vendored
View File

@@ -316,13 +316,9 @@ This task ensures game development stories are immediately actionable and enable
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -331,7 +327,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

228
dist/expansion-packs/bmad-2d-phaser-game-dev/teams/phaser-2d-nodejs-game-team.txt vendored
View File

@@ -1006,9 +1006,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the ../templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `../utils/template-format` conventions
### 4. Template Processing Rules
@@ -2638,227 +2638,73 @@ Or ask me about anything else related to BMAD-METHOD!
==================== START: utils#workflow-management ====================
# Workflow Management
This utility enables the BMAD orchestrator to manage and execute team workflows.
Enables BMAD orchestrator to manage and execute team workflows.
## Important: Dynamic Workflow Loading
## Dynamic Workflow Loading
The BMAD orchestrator MUST read the available workflows from the current team configuration's `workflows` field. Do not use hardcoded workflow lists. Each team bundle defines its own set of supported workflows based on the agents it includes.
Read available workflows from current team configuration's `workflows` field. Each team bundle defines its own supported workflows.
**Critical Distinction**:
**Key Commands**:
- When asked "what workflows are available?", show ONLY the workflows defined in the current team bundle's configuration
- Use `/agent-list` to show agents in the current bundle
- Use `/workflows` to show workflows in the current bundle, NOT any creation tasks
### Workflow Descriptions
When displaying workflows, use these descriptions based on the workflow ID:
- **greenfield-fullstack**: Build a new full-stack application from concept to development
- **brownfield-fullstack**: Enhance an existing full-stack application with new features
- **greenfield-service**: Build a new backend service or API from concept to development
- **brownfield-service**: Enhance an existing backend service or API
- **greenfield-ui**: Build a new frontend/UI application from concept to development
- **brownfield-ui**: Enhance an existing frontend/UI application
- `/workflows` - List workflows in current bundle or workflows folder
- `/agent-list` - Show agents in current bundle
## Workflow Commands
### /workflows
Lists all available workflows for the current team. The available workflows are determined by the team configuration and may include workflows such as:
- greenfield-fullstack
- brownfield-fullstack
- greenfield-service
- brownfield-service
- greenfield-ui
- brownfield-ui
The actual list depends on which team bundle is loaded. When responding to this command, display the workflows that are configured in the current team's `workflows` field.
Example response format:
```text
Available workflows for [Team Name]:
1. [workflow-id] - [Brief description based on workflow type]
2. [workflow-id] - [Brief description based on workflow type]
[... etc. ...]
Use /workflow-start {number or id} to begin a workflow.
```
Lists available workflows with titles and descriptions.
### /workflow-start {workflow-id}
Starts a specific workflow and transitions to the first agent.
Example: `/workflow-start greenfield-fullstack`
Starts workflow and transitions to first agent.
### /workflow-status
Shows current workflow progress, completed artifacts, and next steps.
Example response:
```text
Current Workflow: Greenfield Full-Stack Development
Stage: Product Planning (2 of 6)
Completed:
✓ Discovery & Requirements
- project-brief (completed by Mary)
In Progress:
⚡ Product Planning
- Create PRD (John) - awaiting input
Next: Technical Architecture
```
Shows current progress, completed artifacts, and next steps.
### /workflow-resume
Resumes a workflow from where it left off, useful when starting a new chat.
User can provide completed artifacts:
```text
User: /workflow-resume greenfield-fullstack
I have completed: project-brief, PRD
BMad: I see you've completed Discovery and part of Product Planning.
Based on the greenfield-fullstack workflow, the next step is:
- UX Strategy with Sally (ux-expert)
Would you like me to load Sally to continue?
```
Resumes workflow from last position. User can provide completed artifacts.
### /workflow-next
Shows the next recommended agent and action in the current workflow.
Shows next recommended agent and action.
## Workflow Execution Flow
## Execution Flow
### 1. Starting a Workflow
1. **Starting**: Load definition → Identify first stage → Transition to agent → Guide artifact creation
When a workflow is started:
2. **Stage Transitions**: Mark complete → Check conditions → Load next agent → Pass artifacts
1. Load the workflow definition
2. Identify the first stage and step
3. Transition to the required agent
4. Provide context about expected inputs/outputs
5. Guide artifact creation
3. **Artifact Tracking**: Track status, creator, timestamps in workflow_state
### 2. Stage Transitions
4. **Interruption Handling**: Analyze provided artifacts → Determine position → Suggest next step
After each artifact is completed:
## Context Passing
1. Mark the step as complete
2. Check transition conditions
3. If stage is complete, move to next stage
4. Load the appropriate agent
5. Pass relevant artifacts as context
When transitioning, pass:
### 3. Artifact Tracking
Track all created artifacts:
```yaml
workflow_state:
current_workflow: greenfield-fullstack
current_stage: planning
current_step: 2
artifacts:
project-brief:
status: completed
created_by: analyst
timestamp: 2024-01-15T10:30:00.000Z
prd:
status: in-progress
created_by: pm
started: 2024-01-15T11:00:00.000Z
```
### 4. Workflow Interruption Handling
When user returns after interruption:
1. Ask if continuing previous workflow
2. Request any completed artifacts
3. Analyze provided artifacts
4. Determine workflow position
5. Suggest next appropriate step
Example:
```text
User: I'm working on a new app. Here's my PRD and architecture doc.
BMad: I see you have a PRD and architecture document. Based on these artifacts,
it looks like you're following the greenfield-fullstack workflow and have completed
stages 1-3. The next recommended step would be:
Stage 4: Validation & Refinement
- Load Sarah (Product Owner) to validate all artifacts
Would you like to continue with this workflow?
```
## Workflow Context Passing
When transitioning between agents, pass:
1. Previous artifacts created
2. Current workflow stage
3. Expected outputs
4. Any decisions or constraints identified
Example transition:
```text
BMad: Great! John has completed the PRD. According to the greenfield-fullstack workflow,
the next step is UX Strategy with Sally.
/ux-expert
Sally: I see we're in the Product Planning stage of the greenfield-fullstack workflow.
I have access to:
- Project Brief from Mary
- PRD from John
Let's create the UX strategy and UI specifications. First, let me review
the PRD to understand the features we're designing for...
```
- Previous artifacts
- Current workflow stage
- Expected outputs
- Decisions/constraints
## Multi-Path Workflows
Some workflows may have multiple paths:
Handle conditional paths by asking clarifying questions when needed.
```yaml
conditional_paths:
- condition: project_type == 'mobile'
next_stage: mobile-specific-design
- condition: project_type == 'web'
next_stage: web-architecture
- default: fullstack-architecture
```
## Best Practices
Handle these by asking clarifying questions when needed.
1. Show progress
2. Explain transitions
3. Preserve context
4. Allow flexibility
5. Track state
## Workflow Best Practices
## Agent Integration
1. **Always show progress** - Users should know where they are
2. **Explain transitions** - Why moving to next agent
3. **Preserve context** - Pass relevant information forward
4. **Allow flexibility** - Users can skip or modify steps
5. **Track everything** - Maintain complete workflow state
## Integration with Agents
Each agent should be workflow-aware:
- Know which workflow is active
- Understand their role in the workflow
- Access previous artifacts
- Know expected outputs
- Guide toward workflow goals
This creates a seamless experience where the entire team works together toward the workflow's objectives.
Agents should be workflow-aware: know active workflow, their role, access artifacts, understand expected outputs.
==================== END: utils#workflow-management ====================
==================== START: tasks#execute-checklist ====================
@@ -2866,13 +2712,9 @@ This creates a seamless experience where the entire team works together toward t
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -2881,7 +2723,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

4
dist/expansion-packs/bmad-infrastructure-devops/agents/infra-devops-platform.txt vendored
View File

@@ -134,9 +134,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the ../templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `../utils/template-format` conventions
### 4. Template Processing Rules

228
dist/teams/team-all.txt vendored
View File

@@ -784,9 +784,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the ../templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `../utils/template-format` conventions
### 4. Template Processing Rules
@@ -1653,227 +1653,73 @@ Use the **expansion-creator** pack to build your own:
==================== START: utils#workflow-management ====================
# Workflow Management
This utility enables the BMAD orchestrator to manage and execute team workflows.
Enables BMAD orchestrator to manage and execute team workflows.
## Important: Dynamic Workflow Loading
## Dynamic Workflow Loading
The BMAD orchestrator MUST read the available workflows from the current team configuration's `workflows` field. Do not use hardcoded workflow lists. Each team bundle defines its own set of supported workflows based on the agents it includes.
Read available workflows from current team configuration's `workflows` field. Each team bundle defines its own supported workflows.
**Critical Distinction**:
**Key Commands**:
- When asked "what workflows are available?", show ONLY the workflows defined in the current team bundle's configuration
- Use `/agent-list` to show agents in the current bundle
- Use `/workflows` to show workflows in the current bundle, NOT any creation tasks
### Workflow Descriptions
When displaying workflows, use these descriptions based on the workflow ID:
- **greenfield-fullstack**: Build a new full-stack application from concept to development
- **brownfield-fullstack**: Enhance an existing full-stack application with new features
- **greenfield-service**: Build a new backend service or API from concept to development
- **brownfield-service**: Enhance an existing backend service or API
- **greenfield-ui**: Build a new frontend/UI application from concept to development
- **brownfield-ui**: Enhance an existing frontend/UI application
- `/workflows` - List workflows in current bundle or workflows folder
- `/agent-list` - Show agents in current bundle
## Workflow Commands
### /workflows
Lists all available workflows for the current team. The available workflows are determined by the team configuration and may include workflows such as:
- greenfield-fullstack
- brownfield-fullstack
- greenfield-service
- brownfield-service
- greenfield-ui
- brownfield-ui
The actual list depends on which team bundle is loaded. When responding to this command, display the workflows that are configured in the current team's `workflows` field.
Example response format:
```text
Available workflows for [Team Name]:
1. [workflow-id] - [Brief description based on workflow type]
2. [workflow-id] - [Brief description based on workflow type]
[... etc. ...]
Use /workflow-start {number or id} to begin a workflow.
```
Lists available workflows with titles and descriptions.
### /workflow-start {workflow-id}
Starts a specific workflow and transitions to the first agent.
Example: `/workflow-start greenfield-fullstack`
Starts workflow and transitions to first agent.
### /workflow-status
Shows current workflow progress, completed artifacts, and next steps.
Example response:
```text
Current Workflow: Greenfield Full-Stack Development
Stage: Product Planning (2 of 6)
Completed:
✓ Discovery & Requirements
- project-brief (completed by Mary)
In Progress:
⚡ Product Planning
- Create PRD (John) - awaiting input
Next: Technical Architecture
```
Shows current progress, completed artifacts, and next steps.
### /workflow-resume
Resumes a workflow from where it left off, useful when starting a new chat.
User can provide completed artifacts:
```text
User: /workflow-resume greenfield-fullstack
I have completed: project-brief, PRD
BMad: I see you've completed Discovery and part of Product Planning.
Based on the greenfield-fullstack workflow, the next step is:
- UX Strategy with Sally (ux-expert)
Would you like me to load Sally to continue?
```
Resumes workflow from last position. User can provide completed artifacts.
### /workflow-next
Shows the next recommended agent and action in the current workflow.
Shows next recommended agent and action.
## Workflow Execution Flow
## Execution Flow
### 1. Starting a Workflow
1. **Starting**: Load definition → Identify first stage → Transition to agent → Guide artifact creation
When a workflow is started:
2. **Stage Transitions**: Mark complete → Check conditions → Load next agent → Pass artifacts
1. Load the workflow definition
2. Identify the first stage and step
3. Transition to the required agent
4. Provide context about expected inputs/outputs
5. Guide artifact creation
3. **Artifact Tracking**: Track status, creator, timestamps in workflow_state
### 2. Stage Transitions
4. **Interruption Handling**: Analyze provided artifacts → Determine position → Suggest next step
After each artifact is completed:
## Context Passing
1. Mark the step as complete
2. Check transition conditions
3. If stage is complete, move to next stage
4. Load the appropriate agent
5. Pass relevant artifacts as context
When transitioning, pass:
### 3. Artifact Tracking
Track all created artifacts:
```yaml
workflow_state:
current_workflow: greenfield-fullstack
current_stage: planning
current_step: 2
artifacts:
project-brief:
status: completed
created_by: analyst
timestamp: 2024-01-15T10:30:00.000Z
prd:
status: in-progress
created_by: pm
started: 2024-01-15T11:00:00.000Z
```
### 4. Workflow Interruption Handling
When user returns after interruption:
1. Ask if continuing previous workflow
2. Request any completed artifacts
3. Analyze provided artifacts
4. Determine workflow position
5. Suggest next appropriate step
Example:
```text
User: I'm working on a new app. Here's my PRD and architecture doc.
BMad: I see you have a PRD and architecture document. Based on these artifacts,
it looks like you're following the greenfield-fullstack workflow and have completed
stages 1-3. The next recommended step would be:
Stage 4: Validation & Refinement
- Load Sarah (Product Owner) to validate all artifacts
Would you like to continue with this workflow?
```
## Workflow Context Passing
When transitioning between agents, pass:
1. Previous artifacts created
2. Current workflow stage
3. Expected outputs
4. Any decisions or constraints identified
Example transition:
```text
BMad: Great! John has completed the PRD. According to the greenfield-fullstack workflow,
the next step is UX Strategy with Sally.
/ux-expert
Sally: I see we're in the Product Planning stage of the greenfield-fullstack workflow.
I have access to:
- Project Brief from Mary
- PRD from John
Let's create the UX strategy and UI specifications. First, let me review
the PRD to understand the features we're designing for...
```
- Previous artifacts
- Current workflow stage
- Expected outputs
- Decisions/constraints
## Multi-Path Workflows
Some workflows may have multiple paths:
Handle conditional paths by asking clarifying questions when needed.
```yaml
conditional_paths:
- condition: project_type == 'mobile'
next_stage: mobile-specific-design
- condition: project_type == 'web'
next_stage: web-architecture
- default: fullstack-architecture
```
## Best Practices
Handle these by asking clarifying questions when needed.
1. Show progress
2. Explain transitions
3. Preserve context
4. Allow flexibility
5. Track state
## Workflow Best Practices
## Agent Integration
1. **Always show progress** - Users should know where they are
2. **Explain transitions** - Why moving to next agent
3. **Preserve context** - Pass relevant information forward
4. **Allow flexibility** - Users can skip or modify steps
5. **Track everything** - Maintain complete workflow state
## Integration with Agents
Each agent should be workflow-aware:
- Know which workflow is active
- Understand their role in the workflow
- Access previous artifacts
- Know expected outputs
- Guide toward workflow goals
This creates a seamless experience where the entire team works together toward the workflow's objectives.
Agents should be workflow-aware: know active workflow, their role, access artifacts, understand expected outputs.
==================== END: utils#workflow-management ====================
==================== START: utils#template-format ====================
@@ -3568,13 +3414,9 @@ These replace the standard elicitation options when working on competitive analy
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -3583,7 +3425,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

228
dist/teams/team-fullstack.txt vendored
View File

@@ -628,9 +628,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the ../templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `../utils/template-format` conventions
### 4. Template Processing Rules
@@ -1497,227 +1497,73 @@ Use the **expansion-creator** pack to build your own:
==================== START: utils#workflow-management ====================
# Workflow Management
This utility enables the BMAD orchestrator to manage and execute team workflows.
Enables BMAD orchestrator to manage and execute team workflows.
## Important: Dynamic Workflow Loading
## Dynamic Workflow Loading
The BMAD orchestrator MUST read the available workflows from the current team configuration's `workflows` field. Do not use hardcoded workflow lists. Each team bundle defines its own set of supported workflows based on the agents it includes.
Read available workflows from current team configuration's `workflows` field. Each team bundle defines its own supported workflows.
**Critical Distinction**:
**Key Commands**:
- When asked "what workflows are available?", show ONLY the workflows defined in the current team bundle's configuration
- Use `/agent-list` to show agents in the current bundle
- Use `/workflows` to show workflows in the current bundle, NOT any creation tasks
### Workflow Descriptions
When displaying workflows, use these descriptions based on the workflow ID:
- **greenfield-fullstack**: Build a new full-stack application from concept to development
- **brownfield-fullstack**: Enhance an existing full-stack application with new features
- **greenfield-service**: Build a new backend service or API from concept to development
- **brownfield-service**: Enhance an existing backend service or API
- **greenfield-ui**: Build a new frontend/UI application from concept to development
- **brownfield-ui**: Enhance an existing frontend/UI application
- `/workflows` - List workflows in current bundle or workflows folder
- `/agent-list` - Show agents in current bundle
## Workflow Commands
### /workflows
Lists all available workflows for the current team. The available workflows are determined by the team configuration and may include workflows such as:
- greenfield-fullstack
- brownfield-fullstack
- greenfield-service
- brownfield-service
- greenfield-ui
- brownfield-ui
The actual list depends on which team bundle is loaded. When responding to this command, display the workflows that are configured in the current team's `workflows` field.
Example response format:
```text
Available workflows for [Team Name]:
1. [workflow-id] - [Brief description based on workflow type]
2. [workflow-id] - [Brief description based on workflow type]
[... etc. ...]
Use /workflow-start {number or id} to begin a workflow.
```
Lists available workflows with titles and descriptions.
### /workflow-start {workflow-id}
Starts a specific workflow and transitions to the first agent.
Example: `/workflow-start greenfield-fullstack`
Starts workflow and transitions to first agent.
### /workflow-status
Shows current workflow progress, completed artifacts, and next steps.
Example response:
```text
Current Workflow: Greenfield Full-Stack Development
Stage: Product Planning (2 of 6)
Completed:
✓ Discovery & Requirements
- project-brief (completed by Mary)
In Progress:
⚡ Product Planning
- Create PRD (John) - awaiting input
Next: Technical Architecture
```
Shows current progress, completed artifacts, and next steps.
### /workflow-resume
Resumes a workflow from where it left off, useful when starting a new chat.
User can provide completed artifacts:
```text
User: /workflow-resume greenfield-fullstack
I have completed: project-brief, PRD
BMad: I see you've completed Discovery and part of Product Planning.
Based on the greenfield-fullstack workflow, the next step is:
- UX Strategy with Sally (ux-expert)
Would you like me to load Sally to continue?
```
Resumes workflow from last position. User can provide completed artifacts.
### /workflow-next
Shows the next recommended agent and action in the current workflow.
Shows next recommended agent and action.
## Workflow Execution Flow
## Execution Flow
### 1. Starting a Workflow
1. **Starting**: Load definition → Identify first stage → Transition to agent → Guide artifact creation
When a workflow is started:
2. **Stage Transitions**: Mark complete → Check conditions → Load next agent → Pass artifacts
1. Load the workflow definition
2. Identify the first stage and step
3. Transition to the required agent
4. Provide context about expected inputs/outputs
5. Guide artifact creation
3. **Artifact Tracking**: Track status, creator, timestamps in workflow_state
### 2. Stage Transitions
4. **Interruption Handling**: Analyze provided artifacts → Determine position → Suggest next step
After each artifact is completed:
## Context Passing
1. Mark the step as complete
2. Check transition conditions
3. If stage is complete, move to next stage
4. Load the appropriate agent
5. Pass relevant artifacts as context
When transitioning, pass:
### 3. Artifact Tracking
Track all created artifacts:
```yaml
workflow_state:
current_workflow: greenfield-fullstack
current_stage: planning
current_step: 2
artifacts:
project-brief:
status: completed
created_by: analyst
timestamp: 2024-01-15T10:30:00.000Z
prd:
status: in-progress
created_by: pm
started: 2024-01-15T11:00:00.000Z
```
### 4. Workflow Interruption Handling
When user returns after interruption:
1. Ask if continuing previous workflow
2. Request any completed artifacts
3. Analyze provided artifacts
4. Determine workflow position
5. Suggest next appropriate step
Example:
```text
User: I'm working on a new app. Here's my PRD and architecture doc.
BMad: I see you have a PRD and architecture document. Based on these artifacts,
it looks like you're following the greenfield-fullstack workflow and have completed
stages 1-3. The next recommended step would be:
Stage 4: Validation & Refinement
- Load Sarah (Product Owner) to validate all artifacts
Would you like to continue with this workflow?
```
## Workflow Context Passing
When transitioning between agents, pass:
1. Previous artifacts created
2. Current workflow stage
3. Expected outputs
4. Any decisions or constraints identified
Example transition:
```text
BMad: Great! John has completed the PRD. According to the greenfield-fullstack workflow,
the next step is UX Strategy with Sally.
/ux-expert
Sally: I see we're in the Product Planning stage of the greenfield-fullstack workflow.
I have access to:
- Project Brief from Mary
- PRD from John
Let's create the UX strategy and UI specifications. First, let me review
the PRD to understand the features we're designing for...
```
- Previous artifacts
- Current workflow stage
- Expected outputs
- Decisions/constraints
## Multi-Path Workflows
Some workflows may have multiple paths:
Handle conditional paths by asking clarifying questions when needed.
```yaml
conditional_paths:
- condition: project_type == 'mobile'
next_stage: mobile-specific-design
- condition: project_type == 'web'
next_stage: web-architecture
- default: fullstack-architecture
```
## Best Practices
Handle these by asking clarifying questions when needed.
1. Show progress
2. Explain transitions
3. Preserve context
4. Allow flexibility
5. Track state
## Workflow Best Practices
## Agent Integration
1. **Always show progress** - Users should know where they are
2. **Explain transitions** - Why moving to next agent
3. **Preserve context** - Pass relevant information forward
4. **Allow flexibility** - Users can skip or modify steps
5. **Track everything** - Maintain complete workflow state
## Integration with Agents
Each agent should be workflow-aware:
- Know which workflow is active
- Understand their role in the workflow
- Access previous artifacts
- Know expected outputs
- Guide toward workflow goals
This creates a seamless experience where the entire team works together toward the workflow's objectives.
Agents should be workflow-aware: know active workflow, their role, access artifacts, understand expected outputs.
==================== END: utils#workflow-management ====================
==================== START: utils#template-format ====================
@@ -3801,13 +3647,9 @@ The story creation is successful when:
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -3816,7 +3658,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

228
dist/teams/team-ide-minimal.txt vendored
View File

@@ -528,9 +528,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the ../templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `../utils/template-format` conventions
### 4. Template Processing Rules
@@ -1397,227 +1397,73 @@ Use the **expansion-creator** pack to build your own:
==================== START: utils#workflow-management ====================
# Workflow Management
This utility enables the BMAD orchestrator to manage and execute team workflows.
Enables BMAD orchestrator to manage and execute team workflows.
## Important: Dynamic Workflow Loading
## Dynamic Workflow Loading
The BMAD orchestrator MUST read the available workflows from the current team configuration's `workflows` field. Do not use hardcoded workflow lists. Each team bundle defines its own set of supported workflows based on the agents it includes.
Read available workflows from current team configuration's `workflows` field. Each team bundle defines its own supported workflows.
**Critical Distinction**:
**Key Commands**:
- When asked "what workflows are available?", show ONLY the workflows defined in the current team bundle's configuration
- Use `/agent-list` to show agents in the current bundle
- Use `/workflows` to show workflows in the current bundle, NOT any creation tasks
### Workflow Descriptions
When displaying workflows, use these descriptions based on the workflow ID:
- **greenfield-fullstack**: Build a new full-stack application from concept to development
- **brownfield-fullstack**: Enhance an existing full-stack application with new features
- **greenfield-service**: Build a new backend service or API from concept to development
- **brownfield-service**: Enhance an existing backend service or API
- **greenfield-ui**: Build a new frontend/UI application from concept to development
- **brownfield-ui**: Enhance an existing frontend/UI application
- `/workflows` - List workflows in current bundle or workflows folder
- `/agent-list` - Show agents in current bundle
## Workflow Commands
### /workflows
Lists all available workflows for the current team. The available workflows are determined by the team configuration and may include workflows such as:
- greenfield-fullstack
- brownfield-fullstack
- greenfield-service
- brownfield-service
- greenfield-ui
- brownfield-ui
The actual list depends on which team bundle is loaded. When responding to this command, display the workflows that are configured in the current team's `workflows` field.
Example response format:
```text
Available workflows for [Team Name]:
1. [workflow-id] - [Brief description based on workflow type]
2. [workflow-id] - [Brief description based on workflow type]
[... etc. ...]
Use /workflow-start {number or id} to begin a workflow.
```
Lists available workflows with titles and descriptions.
### /workflow-start {workflow-id}
Starts a specific workflow and transitions to the first agent.
Example: `/workflow-start greenfield-fullstack`
Starts workflow and transitions to first agent.
### /workflow-status
Shows current workflow progress, completed artifacts, and next steps.
Example response:
```text
Current Workflow: Greenfield Full-Stack Development
Stage: Product Planning (2 of 6)
Completed:
✓ Discovery & Requirements
- project-brief (completed by Mary)
In Progress:
⚡ Product Planning
- Create PRD (John) - awaiting input
Next: Technical Architecture
```
Shows current progress, completed artifacts, and next steps.
### /workflow-resume
Resumes a workflow from where it left off, useful when starting a new chat.
User can provide completed artifacts:
```text
User: /workflow-resume greenfield-fullstack
I have completed: project-brief, PRD
BMad: I see you've completed Discovery and part of Product Planning.
Based on the greenfield-fullstack workflow, the next step is:
- UX Strategy with Sally (ux-expert)
Would you like me to load Sally to continue?
```
Resumes workflow from last position. User can provide completed artifacts.
### /workflow-next
Shows the next recommended agent and action in the current workflow.
Shows next recommended agent and action.
## Workflow Execution Flow
## Execution Flow
### 1. Starting a Workflow
1. **Starting**: Load definition → Identify first stage → Transition to agent → Guide artifact creation
When a workflow is started:
2. **Stage Transitions**: Mark complete → Check conditions → Load next agent → Pass artifacts
1. Load the workflow definition
2. Identify the first stage and step
3. Transition to the required agent
4. Provide context about expected inputs/outputs
5. Guide artifact creation
3. **Artifact Tracking**: Track status, creator, timestamps in workflow_state
### 2. Stage Transitions
4. **Interruption Handling**: Analyze provided artifacts → Determine position → Suggest next step
After each artifact is completed:
## Context Passing
1. Mark the step as complete
2. Check transition conditions
3. If stage is complete, move to next stage
4. Load the appropriate agent
5. Pass relevant artifacts as context
When transitioning, pass:
### 3. Artifact Tracking
Track all created artifacts:
```yaml
workflow_state:
current_workflow: greenfield-fullstack
current_stage: planning
current_step: 2
artifacts:
project-brief:
status: completed
created_by: analyst
timestamp: 2024-01-15T10:30:00.000Z
prd:
status: in-progress
created_by: pm
started: 2024-01-15T11:00:00.000Z
```
### 4. Workflow Interruption Handling
When user returns after interruption:
1. Ask if continuing previous workflow
2. Request any completed artifacts
3. Analyze provided artifacts
4. Determine workflow position
5. Suggest next appropriate step
Example:
```text
User: I'm working on a new app. Here's my PRD and architecture doc.
BMad: I see you have a PRD and architecture document. Based on these artifacts,
it looks like you're following the greenfield-fullstack workflow and have completed
stages 1-3. The next recommended step would be:
Stage 4: Validation & Refinement
- Load Sarah (Product Owner) to validate all artifacts
Would you like to continue with this workflow?
```
## Workflow Context Passing
When transitioning between agents, pass:
1. Previous artifacts created
2. Current workflow stage
3. Expected outputs
4. Any decisions or constraints identified
Example transition:
```text
BMad: Great! John has completed the PRD. According to the greenfield-fullstack workflow,
the next step is UX Strategy with Sally.
/ux-expert
Sally: I see we're in the Product Planning stage of the greenfield-fullstack workflow.
I have access to:
- Project Brief from Mary
- PRD from John
Let's create the UX strategy and UI specifications. First, let me review
the PRD to understand the features we're designing for...
```
- Previous artifacts
- Current workflow stage
- Expected outputs
- Decisions/constraints
## Multi-Path Workflows
Some workflows may have multiple paths:
Handle conditional paths by asking clarifying questions when needed.
```yaml
conditional_paths:
- condition: project_type == 'mobile'
next_stage: mobile-specific-design
- condition: project_type == 'web'
next_stage: web-architecture
- default: fullstack-architecture
```
## Best Practices
Handle these by asking clarifying questions when needed.
1. Show progress
2. Explain transitions
3. Preserve context
4. Allow flexibility
5. Track state
## Workflow Best Practices
## Agent Integration
1. **Always show progress** - Users should know where they are
2. **Explain transitions** - Why moving to next agent
3. **Preserve context** - Pass relevant information forward
4. **Allow flexibility** - Users can skip or modify steps
5. **Track everything** - Maintain complete workflow state
## Integration with Agents
Each agent should be workflow-aware:
- Know which workflow is active
- Understand their role in the workflow
- Access previous artifacts
- Know expected outputs
- Guide toward workflow goals
This creates a seamless experience where the entire team works together toward the workflow's objectives.
Agents should be workflow-aware: know active workflow, their role, access artifacts, understand expected outputs.
==================== END: utils#workflow-management ====================
==================== START: utils#template-format ====================
@@ -1654,13 +1500,9 @@ Templates in the BMAD method use standardized markup for AI processing. These co
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -1669,7 +1511,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

228
dist/teams/team-no-ui.txt vendored
View File

@@ -560,9 +560,9 @@ Confirm with the user their preferred interaction style:
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Load specified template from `templates#*` or the ../templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
- Process template markup according to `utils#template-format` or `../utils/template-format` conventions
### 4. Template Processing Rules
@@ -1429,227 +1429,73 @@ Use the **expansion-creator** pack to build your own:
==================== START: utils#workflow-management ====================
# Workflow Management
This utility enables the BMAD orchestrator to manage and execute team workflows.
Enables BMAD orchestrator to manage and execute team workflows.
## Important: Dynamic Workflow Loading
## Dynamic Workflow Loading
The BMAD orchestrator MUST read the available workflows from the current team configuration's `workflows` field. Do not use hardcoded workflow lists. Each team bundle defines its own set of supported workflows based on the agents it includes.
Read available workflows from current team configuration's `workflows` field. Each team bundle defines its own supported workflows.
**Critical Distinction**:
**Key Commands**:
- When asked "what workflows are available?", show ONLY the workflows defined in the current team bundle's configuration
- Use `/agent-list` to show agents in the current bundle
- Use `/workflows` to show workflows in the current bundle, NOT any creation tasks
### Workflow Descriptions
When displaying workflows, use these descriptions based on the workflow ID:
- **greenfield-fullstack**: Build a new full-stack application from concept to development
- **brownfield-fullstack**: Enhance an existing full-stack application with new features
- **greenfield-service**: Build a new backend service or API from concept to development
- **brownfield-service**: Enhance an existing backend service or API
- **greenfield-ui**: Build a new frontend/UI application from concept to development
- **brownfield-ui**: Enhance an existing frontend/UI application
- `/workflows` - List workflows in current bundle or workflows folder
- `/agent-list` - Show agents in current bundle
## Workflow Commands
### /workflows
Lists all available workflows for the current team. The available workflows are determined by the team configuration and may include workflows such as:
- greenfield-fullstack
- brownfield-fullstack
- greenfield-service
- brownfield-service
- greenfield-ui
- brownfield-ui
The actual list depends on which team bundle is loaded. When responding to this command, display the workflows that are configured in the current team's `workflows` field.
Example response format:
```text
Available workflows for [Team Name]:
1. [workflow-id] - [Brief description based on workflow type]
2. [workflow-id] - [Brief description based on workflow type]
[... etc. ...]
Use /workflow-start {number or id} to begin a workflow.
```
Lists available workflows with titles and descriptions.
### /workflow-start {workflow-id}
Starts a specific workflow and transitions to the first agent.
Example: `/workflow-start greenfield-fullstack`
Starts workflow and transitions to first agent.
### /workflow-status
Shows current workflow progress, completed artifacts, and next steps.
Example response:
```text
Current Workflow: Greenfield Full-Stack Development
Stage: Product Planning (2 of 6)
Completed:
✓ Discovery & Requirements
- project-brief (completed by Mary)
In Progress:
⚡ Product Planning
- Create PRD (John) - awaiting input
Next: Technical Architecture
```
Shows current progress, completed artifacts, and next steps.
### /workflow-resume
Resumes a workflow from where it left off, useful when starting a new chat.
User can provide completed artifacts:
```text
User: /workflow-resume greenfield-fullstack
I have completed: project-brief, PRD
BMad: I see you've completed Discovery and part of Product Planning.
Based on the greenfield-fullstack workflow, the next step is:
- UX Strategy with Sally (ux-expert)
Would you like me to load Sally to continue?
```
Resumes workflow from last position. User can provide completed artifacts.
### /workflow-next
Shows the next recommended agent and action in the current workflow.
Shows next recommended agent and action.
## Workflow Execution Flow
## Execution Flow
### 1. Starting a Workflow
1. **Starting**: Load definition → Identify first stage → Transition to agent → Guide artifact creation
When a workflow is started:
2. **Stage Transitions**: Mark complete → Check conditions → Load next agent → Pass artifacts
1. Load the workflow definition
2. Identify the first stage and step
3. Transition to the required agent
4. Provide context about expected inputs/outputs
5. Guide artifact creation
3. **Artifact Tracking**: Track status, creator, timestamps in workflow_state
### 2. Stage Transitions
4. **Interruption Handling**: Analyze provided artifacts → Determine position → Suggest next step
After each artifact is completed:
## Context Passing
1. Mark the step as complete
2. Check transition conditions
3. If stage is complete, move to next stage
4. Load the appropriate agent
5. Pass relevant artifacts as context
When transitioning, pass:
### 3. Artifact Tracking
Track all created artifacts:
```yaml
workflow_state:
current_workflow: greenfield-fullstack
current_stage: planning
current_step: 2
artifacts:
project-brief:
status: completed
created_by: analyst
timestamp: 2024-01-15T10:30:00.000Z
prd:
status: in-progress
created_by: pm
started: 2024-01-15T11:00:00.000Z
```
### 4. Workflow Interruption Handling
When user returns after interruption:
1. Ask if continuing previous workflow
2. Request any completed artifacts
3. Analyze provided artifacts
4. Determine workflow position
5. Suggest next appropriate step
Example:
```text
User: I'm working on a new app. Here's my PRD and architecture doc.
BMad: I see you have a PRD and architecture document. Based on these artifacts,
it looks like you're following the greenfield-fullstack workflow and have completed
stages 1-3. The next recommended step would be:
Stage 4: Validation & Refinement
- Load Sarah (Product Owner) to validate all artifacts
Would you like to continue with this workflow?
```
## Workflow Context Passing
When transitioning between agents, pass:
1. Previous artifacts created
2. Current workflow stage
3. Expected outputs
4. Any decisions or constraints identified
Example transition:
```text
BMad: Great! John has completed the PRD. According to the greenfield-fullstack workflow,
the next step is UX Strategy with Sally.
/ux-expert
Sally: I see we're in the Product Planning stage of the greenfield-fullstack workflow.
I have access to:
- Project Brief from Mary
- PRD from John
Let's create the UX strategy and UI specifications. First, let me review
the PRD to understand the features we're designing for...
```
- Previous artifacts
- Current workflow stage
- Expected outputs
- Decisions/constraints
## Multi-Path Workflows
Some workflows may have multiple paths:
Handle conditional paths by asking clarifying questions when needed.
```yaml
conditional_paths:
- condition: project_type == 'mobile'
next_stage: mobile-specific-design
- condition: project_type == 'web'
next_stage: web-architecture
- default: fullstack-architecture
```
## Best Practices
Handle these by asking clarifying questions when needed.
1. Show progress
2. Explain transitions
3. Preserve context
4. Allow flexibility
5. Track state
## Workflow Best Practices
## Agent Integration
1. **Always show progress** - Users should know where they are
2. **Explain transitions** - Why moving to next agent
3. **Preserve context** - Pass relevant information forward
4. **Allow flexibility** - Users can skip or modify steps
5. **Track everything** - Maintain complete workflow state
## Integration with Agents
Each agent should be workflow-aware:
- Know which workflow is active
- Understand their role in the workflow
- Access previous artifacts
- Know expected outputs
- Guide toward workflow goals
This creates a seamless experience where the entire team works together toward the workflow's objectives.
Agents should be workflow-aware: know active workflow, their role, access artifacts, understand expected outputs.
==================== END: utils#workflow-management ====================
==================== START: utils#template-format ====================
@@ -3733,13 +3579,9 @@ The story creation is successful when:
This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
## Context
The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
## Available Checklists
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the {root}/checklists folder to select the appropriate one to run.
## Instructions
@@ -3748,7 +3590,7 @@ If the user asks or does not specify a specific checklist, list the checklists a
- If user or the task being run provides a checklist name:
- Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
- If multiple matches found, ask user to clarify
- Load the appropriate checklist from bmad-core/checklists/
- Load the appropriate checklist from {root}/checklists/
- If no checklist specified:
- Ask the user which checklist they want to use
- Present the available options from the files in the checklists folder

74
expansion-packs/bmad-infrastructure-devops/tasks/create-doc.md
View File

@@ -1,74 +0,0 @@
# Create Document from Template Task
## Purpose
- Generate documents from any specified template following embedded instructions from the perspective of the selected agent persona
## Instructions
### 1. Identify Template and Context
- Determine which template to use (user-provided or list available for selection to user)
- Agent-specific templates are listed in the agent's dependencies under `templates`. For each template listed, consider it a document the agent can create. So if an agent has:
@{example}
dependencies:
templates: - prd-tmpl - architecture-tmpl
@{/example}
You would offer to create "PRD" and "Architecture" documents when the user asks what you can help with.
- Gather all relevant inputs, or ask for them, or else rely on user providing necessary details to complete the document
- Understand the document purpose and target audience
### 2. Determine Interaction Mode
Confirm with the user their preferred interaction style:
- **Incremental:** Work through chunks of the document.
- **YOLO Mode:** Draft complete document making reasonable assumptions in one shot. (Can be entered also after starting incremental by just typing /yolo)
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
### 4. Template Processing Rules
#### CRITICAL: Never display template markup, LLM instructions, or examples to users
- Replace all {{placeholders}} with actual content
- Execute all [[LLM: instructions]] internally
- Process `<<REPEAT>>` sections as needed
- Evaluate ^^CONDITION^^ blocks and include only if applicable
- Use @{examples} for guidance but never output them
### 5. Content Generation
- **Incremental Mode**: Present each major section for review before proceeding
- **YOLO Mode**: Generate all sections, then review complete document with user
- Apply any elicitation protocols specified in template
- Incorporate user feedback and iterate as needed
### 6. Validation
If template specifies a checklist:
- Run the appropriate checklist against completed document
- Document completion status for each item
- Address any deficiencies found
- Present validation summary to user
### 7. Final Presentation
- Present clean, formatted content only
- Ensure all sections are complete
- DO NOT truncate or summarize content
- Begin directly with document content (no preamble)
- Include any handoff prompts specified in template
## Important Notes
- Template markup is for AI processing only - never expose to users

74
expansion-packs/expansion-creator/common-tasks/create-doc.md
View File

@@ -1,74 +0,0 @@
# Create Document from Template Task
## Purpose
- Generate documents from any specified template following embedded instructions from the perspective of the selected agent persona
## Instructions
### 1. Identify Template and Context
- Determine which template to use (user-provided or list available for selection to user)
- Agent-specific templates are listed in the agent's dependencies under `templates`. For each template listed, consider it a document the agent can create. So if an agent has:
@{example}
dependencies:
templates: - prd-tmpl - architecture-tmpl
@{/example}
You would offer to create "PRD" and "Architecture" documents when the user asks what you can help with.
- Gather all relevant inputs, or ask for them, or else rely on user providing necessary details to complete the document
- Understand the document purpose and target audience
### 2. Determine Interaction Mode
Confirm with the user their preferred interaction style:
- **Incremental:** Work through chunks of the document.
- **YOLO Mode:** Draft complete document making reasonable assumptions in one shot. (Can be entered also after starting incremental by just typing /yolo)
### 3. Execute Template
- Load specified template from `templates#*` or the /templates directory
- Follow ALL embedded LLM instructions within the template
- Process template markup according to `utils#template-format` conventions
### 4. Template Processing Rules
#### CRITICAL: Never display template markup, LLM instructions, or examples to users
- Replace all {{placeholders}} with actual content
- Execute all [[LLM: instructions]] internally
- Process `<<REPEAT>>` sections as needed
- Evaluate ^^CONDITION^^ blocks and include only if applicable
- Use @{examples} for guidance but never output them
### 5. Content Generation
- **Incremental Mode**: Present each major section for review before proceeding
- **YOLO Mode**: Generate all sections, then review complete document with user
- Apply any elicitation protocols specified in template
- Incorporate user feedback and iterate as needed
### 6. Validation
If template specifies a checklist:
- Run the appropriate checklist against completed document
- Document completion status for each item
- Address any deficiencies found
- Present validation summary to user
### 7. Final Presentation
- Present clean, formatted content only
- Ensure all sections are complete
- DO NOT truncate or summarize content
- Begin directly with document content (no preamble)
- Include any handoff prompts specified in template
## Important Notes
- Template markup is for AI processing only - never expose to users

10
expansion-packs/expansion-creator/tasks/generate-expansion-pack.md
View File

@@ -436,17 +436,17 @@ IMPORTANT: Work through plan.md checklist systematically!
**Step 2: Copy Core Utilities**
Before proceeding, copy these essential files from bmad-core:
Before proceeding, copy these essential files from common:
```bash
# Copy core task utilities
cp bmad-core/tasks/create-doc.md expansion-packs/{pack-name}/tasks/
cp bmad-core/tasks/execute-checklist.md expansion-packs/{pack-name}/tasks/
cp common/tasks/create-doc.md expansion-packs/{pack-name}/tasks/
cp common/tasks/execute-checklist.md expansion-packs/{pack-name}/tasks/
# Copy core utility files
mkdir -p expansion-packs/{pack-name}/utils
cp bmad-core/utils/template-format.md expansion-packs/{pack-name}/utils/
cp bmad-core/utils/workflow-management.md expansion-packs/{pack-name}/utils/
cp common/utils/template-format.md expansion-packs/{pack-name}/utils/
cp common/utils/workflow-management.md expansion-packs/{pack-name}/utils/
```
**Step 3: Technical Implementation**

26
expansion-packs/expansion-creator/utils/template-format.md
View File

@@ -1,26 +0,0 @@
# Template Format Conventions
Templates in the BMAD method use standardized markup for AI processing. These conventions ensure consistent document generation.
## Template Markup Elements
- **{{placeholders}}**: Variables to be replaced with actual content
- **[[LLM: instructions]]**: Internal processing instructions for AI agents (never shown to users)
- **REPEAT** sections: Content blocks that may be repeated as needed
- **^^CONDITION^^** blocks: Conditional content included only if criteria are met
- **@{examples}**: Example content for guidance (never output to users)
## Processing Rules
- Replace all {{placeholders}} with project-specific content
- Execute all [[LLM: instructions]] internally without showing users
- Process conditional and repeat blocks as specified
- Use examples for guidance but never include them in final output
- Present only clean, formatted content to users
## Critical Guidelines
- **NEVER display template markup, LLM instructions, or examples to users**
- Template elements are for AI processing only
- Focus on faithful template execution and clean output
- All template-specific instructions are embedded within templates

223
expansion-packs/expansion-creator/utils/workflow-management.md
View File

@@ -1,223 +0,0 @@
# Workflow Management
This utility enables the BMAD orchestrator to manage and execute team workflows.
## Important: Dynamic Workflow Loading
The BMAD orchestrator MUST read the available workflows from the current team configuration's `workflows` field. Do not use hardcoded workflow lists. Each team bundle defines its own set of supported workflows based on the agents it includes.
**Critical Distinction**:
- When asked "what workflows are available?", show ONLY the workflows defined in the current team bundle's configuration
- Use `/agent-list` to show agents in the current bundle
- Use `/workflows` to show workflows in the current bundle, NOT any creation tasks
### Workflow Descriptions
When displaying workflows, use these descriptions based on the workflow ID:
- **greenfield-fullstack**: Build a new full-stack application from concept to development
- **brownfield-fullstack**: Enhance an existing full-stack application with new features
- **greenfield-service**: Build a new backend service or API from concept to development
- **brownfield-service**: Enhance an existing backend service or API
- **greenfield-ui**: Build a new frontend/UI application from concept to development
- **brownfield-ui**: Enhance an existing frontend/UI application
## Workflow Commands
### /workflows
Lists all available workflows for the current team. The available workflows are determined by the team configuration and may include workflows such as:
- greenfield-fullstack
- brownfield-fullstack
- greenfield-service
- brownfield-service
- greenfield-ui
- brownfield-ui
The actual list depends on which team bundle is loaded. When responding to this command, display the workflows that are configured in the current team's `workflows` field.
Example response format:
```text
Available workflows for [Team Name]:
1. [workflow-id] - [Brief description based on workflow type]
2. [workflow-id] - [Brief description based on workflow type]
[... etc. ...]
Use /workflow-start {number or id} to begin a workflow.
```
### /workflow-start {workflow-id}
Starts a specific workflow and transitions to the first agent.
Example: `/workflow-start greenfield-fullstack`
### /workflow-status
Shows current workflow progress, completed artifacts, and next steps.
Example response:
```text
Current Workflow: Greenfield Full-Stack Development
Stage: Product Planning (2 of 6)
Completed:
✓ Discovery & Requirements
- project-brief (completed by Mary)
In Progress:
⚡ Product Planning
- Create PRD (John) - awaiting input
Next: Technical Architecture
```
### /workflow-resume
Resumes a workflow from where it left off, useful when starting a new chat.
User can provide completed artifacts:
```text
User: /workflow-resume greenfield-fullstack
I have completed: project-brief, PRD
BMad: I see you've completed Discovery and part of Product Planning.
Based on the greenfield-fullstack workflow, the next step is:
- UX Strategy with Sally (ux-expert)
Would you like me to load Sally to continue?
```
### /workflow-next
Shows the next recommended agent and action in the current workflow.
## Workflow Execution Flow
### 1. Starting a Workflow
When a workflow is started:
1. Load the workflow definition
2. Identify the first stage and step
3. Transition to the required agent
4. Provide context about expected inputs/outputs
5. Guide artifact creation
### 2. Stage Transitions
After each artifact is completed:
1. Mark the step as complete
2. Check transition conditions
3. If stage is complete, move to next stage
4. Load the appropriate agent
5. Pass relevant artifacts as context
### 3. Artifact Tracking
Track all created artifacts:
```yaml
workflow_state:
current_workflow: greenfield-fullstack
current_stage: planning
current_step: 2
artifacts:
project-brief:
status: completed
created_by: analyst
timestamp: 2024-01-15T10:30:00.000Z
prd:
status: in-progress
created_by: pm
started: 2024-01-15T11:00:00.000Z
```
### 4. Workflow Interruption Handling
When user returns after interruption:
1. Ask if continuing previous workflow
2. Request any completed artifacts
3. Analyze provided artifacts
4. Determine workflow position
5. Suggest next appropriate step
Example:
```text
User: I'm working on a new app. Here's my PRD and architecture doc.
BMad: I see you have a PRD and architecture document. Based on these artifacts,
it looks like you're following the greenfield-fullstack workflow and have completed
stages 1-3. The next recommended step would be:
Stage 4: Validation & Refinement
- Load Sarah (Product Owner) to validate all artifacts
Would you like to continue with this workflow?
```
## Workflow Context Passing
When transitioning between agents, pass:
1. Previous artifacts created
2. Current workflow stage
3. Expected outputs
4. Any decisions or constraints identified
Example transition:
```text
BMad: Great! John has completed the PRD. According to the greenfield-fullstack workflow,
the next step is UX Strategy with Sally.
/ux-expert
Sally: I see we're in the Product Planning stage of the greenfield-fullstack workflow.
I have access to:
- Project Brief from Mary
- PRD from John
Let's create the UX strategy and UI specifications. First, let me review
the PRD to understand the features we're designing for...
```
## Multi-Path Workflows
Some workflows may have multiple paths:
```yaml
conditional_paths:
- condition: project_type == 'mobile'
next_stage: mobile-specific-design
- condition: project_type == 'web'
next_stage: web-architecture
- default: fullstack-architecture
```
Handle these by asking clarifying questions when needed.
## Workflow Best Practices
1. **Always show progress** - Users should know where they are
2. **Explain transitions** - Why moving to next agent
3. **Preserve context** - Pass relevant information forward
4. **Allow flexibility** - Users can skip or modify steps
5. **Track everything** - Maintain complete workflow state
## Integration with Agents
Each agent should be workflow-aware:
- Know which workflow is active
- Understand their role in the workflow
- Access previous artifacts
- Know expected outputs
- Guide toward workflow goals
This creates a seamless experience where the entire team works together toward the workflow's objectives.

61
tools/builders/web-builder.js
View File

@@ -9,8 +9,8 @@ class WebBuilder {
this.resolver = new DependencyResolver(this.rootDir);
this.templatePath = path.join(
this.rootDir,
"bmad-core",
"utils",
"tools",
"md-assets",
"web-agent-startup-instructions.md"
);
}
@@ -125,22 +125,26 @@ class WebBuilder {
// Remove the properties if they exist at root level
delete parsed.root;
delete parsed['IDE-FILE-RESOLUTION'];
delete parsed['REQUEST-RESOLUTION'];
delete parsed["IDE-FILE-RESOLUTION"];
delete parsed["REQUEST-RESOLUTION"];
// Also remove from activation-instructions if they exist
if (parsed['activation-instructions'] && Array.isArray(parsed['activation-instructions'])) {
parsed['activation-instructions'] = parsed['activation-instructions'].filter(instruction => {
return !instruction.startsWith('IDE-FILE-RESOLUTION:') &&
!instruction.startsWith('REQUEST-RESOLUTION:');
});
if (parsed["activation-instructions"] && Array.isArray(parsed["activation-instructions"])) {
parsed["activation-instructions"] = parsed["activation-instructions"].filter(
(instruction) => {
return (
!instruction.startsWith("IDE-FILE-RESOLUTION:") &&
!instruction.startsWith("REQUEST-RESOLUTION:")
);
}
);
}
// Reconstruct the YAML
const cleanedYaml = yaml.dump(parsed, { lineWidth: -1 });
// Get the agent name from the YAML for the header
const agentName = parsed.agent?.id || 'agent';
const agentName = parsed.agent?.id || "agent";
// Build the new content with just the agent header and YAML
const newHeader = `# ${agentName}\n\nCRITICAL: Read the full YML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:\n\n`;
@@ -341,6 +345,28 @@ class WebBuilder {
}
}
// If not found in core, try common folder
if (!found) {
for (const ext of extensions) {
const commonPath = path.join(
this.rootDir,
"common",
resourceType,
`${resourceName}${ext}`
);
try {
const commonContent = await fs.readFile(commonPath, "utf8");
sections.push(
this.formatSection(`${resourceType}#${resourceName}`, commonContent)
);
found = true;
break;
} catch (error) {
// Not in common either, continue
}
}
}
if (!found) {
console.warn(
` ⚠ Dependency ${resourceType}#${resourceName} not found in expansion pack or core`
@@ -516,6 +542,21 @@ class WebBuilder {
}
}
// If not found in core, try common folder
if (!found) {
for (const ext of extensions) {
const commonPath = path.join(this.rootDir, "common", dep.type, `${dep.name}${ext}`);
try {
const content = await fs.readFile(commonPath, "utf8");
sections.push(this.formatSection(key, content));
found = true;
break;
} catch (error) {
// Not in common either, continue
}
}
}
if (!found) {
console.warn(` ⚠ Dependency ${key} not found in expansion pack or core`);
}

4
tools/installer/config/install.config.yml
View File

@@ -12,8 +12,8 @@ agent-dependencies:
core-files:
- bmad-core/utils/template-format.md
dev:
- bmad-core/templates/story-tmpl.md
- bmad-core/checklists/story-dod-checklist.md
- common/templates/story-tmpl.md
- common/checklists/story-dod-checklist.md
pm:
- bmad-core/templates/prd-tmpl.md
- bmad-core/templates/brownfield-prd-tmpl.md

1
tools/installer/lib/file-manager.js
View File

@@ -90,6 +90,7 @@ class FileManager {
agent: config.agent || null,
ide_setup: config.ide || null,
ides_setup: config.ides || [],
expansion_packs: config.expansionPacks || [],
files: [],
};

148
tools/installer/lib/installer.js
View File

@@ -226,6 +226,10 @@ class Installer {
const bmadCoreDestDir = path.join(installDir, ".bmad-core");
await fileManager.copyDirectory(sourceDir, bmadCoreDestDir);
// Copy common/ items to .bmad-core
spinner.text = "Copying common utilities...";
await this.copyCommonItems(installDir, ".bmad-core", spinner);
// Get list of all files for manifest
const glob = require("glob");
files = glob
@@ -283,6 +287,11 @@ class Installer {
}
}
}
// Copy common/ items to .bmad-core
spinner.text = "Copying common utilities...";
const commonFiles = await this.copyCommonItems(installDir, ".bmad-core", spinner);
files.push(...commonFiles);
} else if (config.installType === "team") {
// Team installation
spinner.text = `Installing ${config.team} team...`;
@@ -313,6 +322,11 @@ class Installer {
}
}
}
// Copy common/ items to .bmad-core
spinner.text = "Copying common utilities...";
const commonFiles = await this.copyCommonItems(installDir, ".bmad-core", spinner);
files.push(...commonFiles);
} else if (config.installType === "expansion-only") {
// Expansion-only installation - create minimal .bmad-core structure
spinner.text = "Creating minimal .bmad-core structure for expansion packs...";
@@ -341,6 +355,10 @@ class Installer {
);
files.push(...copiedFiles.map(f => `.bmad-core/${f}`));
}
// Copy common/ items to .bmad-core
spinner.text = "Copying common utilities...";
await this.copyCommonItems(installDir, ".bmad-core", spinner);
}
// Install expansion packs if requested
@@ -607,8 +625,10 @@ class Installer {
console.log(chalk.green("✓ .bmad-core framework installed with all agents and workflows"));
if (config.expansionPacks && config.expansionPacks.length > 0) {
const packNames = config.expansionPacks.join(", ");
console.log(chalk.green(`✓ Expansion packs installed: ${packNames}`));
console.log(chalk.green(`✓ Expansion packs installed:`));
for (const packId of config.expansionPacks) {
console.log(chalk.green(` - ${packId} → .${packId}/`));
}
}
if (config.includeWebBundles && config.webBundlesDirectory) {
@@ -799,7 +819,11 @@ class Installer {
const expansionPackDir = path.dirname(pack.manifestPath);
// Define the folders to copy from expansion packs to .bmad-core
// Create dedicated dot folder for this expansion pack
const expansionDotFolder = path.join(installDir, `.${packId}`);
await fileManager.ensureDirectory(expansionDotFolder);
// Define the folders to copy from expansion packs
const foldersToSync = [
'agents',
'agent-teams',
@@ -824,21 +848,32 @@ class Installer {
nodir: true
});
// Copy each file to the destination
// Copy each file to the expansion pack's dot folder
for (const file of files) {
const sourcePath = path.join(sourceFolder, file);
const destPath = path.join(installDir, '.bmad-core', folder, file);
const destPath = path.join(expansionDotFolder, folder, file);
if (await fileManager.copyFile(sourcePath, destPath)) {
installedFiles.push(path.join('.bmad-core', folder, file));
installedFiles.push(path.join(`.${packId}`, folder, file));
}
}
}
}
// Web bundles are now available in the dist/ directory and don't need to be copied
// Copy manifest to the expansion pack's dot folder
const manifestDestPath = path.join(expansionDotFolder, 'manifest.yml');
if (await fileManager.copyFile(pack.manifestPath, manifestDestPath)) {
installedFiles.push(path.join(`.${packId}`, 'manifest.yml'));
}
console.log(chalk.green(`✓ Installed expansion pack: ${pack.name}`));
// Copy common/ items to expansion pack folder
spinner.text = `Copying common utilities to ${packId}...`;
await this.copyCommonItems(installDir, `.${packId}`, spinner);
// Check and resolve core dependencies
await this.resolveExpansionPackCoreDependencies(installDir, expansionDotFolder, packId, spinner);
console.log(chalk.green(`✓ Installed expansion pack: ${pack.name} to ${`.${packId}`}`));
} catch (error) {
console.error(chalk.red(`Failed to install expansion pack ${packId}: ${error.message}`));
}
@@ -847,6 +882,61 @@ class Installer {
return installedFiles;
}
async resolveExpansionPackCoreDependencies(installDir, expansionDotFolder, packId, spinner) {
const glob = require('glob');
const yaml = require('yaml');
const fs = require('fs').promises;
// Find all agent files in the expansion pack
const agentFiles = glob.sync('agents/*.md', {
cwd: expansionDotFolder
});
for (const agentFile of agentFiles) {
const agentPath = path.join(expansionDotFolder, agentFile);
const agentContent = await fs.readFile(agentPath, 'utf8');
// Extract YAML frontmatter to check dependencies
const yamlMatch = agentContent.match(/```yaml\n([\s\S]*?)```/);
if (yamlMatch) {
try {
const agentConfig = yaml.parse(yamlMatch[1]);
const dependencies = agentConfig.dependencies || {};
// Check for core dependencies (those that don't exist in the expansion pack)
for (const depType of ['tasks', 'templates', 'checklists', 'workflows', 'utils', 'data']) {
const deps = dependencies[depType] || [];
for (const dep of deps) {
const depFileName = dep.endsWith('.md') ? dep : `${dep}.md`;
const expansionDepPath = path.join(expansionDotFolder, depType, depFileName);
// Check if dependency exists in expansion pack
if (!(await fileManager.pathExists(expansionDepPath))) {
// Try to find it in core
const coreDepPath = path.join(configLoader.getBmadCorePath(), depType, depFileName);
if (await fileManager.pathExists(coreDepPath)) {
spinner.text = `Copying core dependency ${dep} for ${packId}...`;
// Copy from core to expansion pack dot folder
const destPath = path.join(expansionDotFolder, depType, depFileName);
await fileManager.copyFile(coreDepPath, destPath);
console.log(chalk.dim(` Added core dependency: ${depType}/${depFileName}`));
} else {
console.warn(chalk.yellow(` Warning: Dependency ${depType}/${dep} not found in core or expansion pack`));
}
}
}
}
} catch (error) {
console.warn(chalk.yellow(` Warning: Could not parse agent dependencies: ${error.message}`));
}
}
}
}
getWebBundleInfo(config) {
const webBundleType = config.webBundleType || 'all';
@@ -944,6 +1034,48 @@ class Installer {
}
}
async copyCommonItems(installDir, targetSubdir, spinner) {
const glob = require('glob');
const fs = require('fs').promises;
const sourceBase = path.dirname(path.dirname(path.dirname(path.dirname(__filename)))); // Go up to project root
const commonPath = path.join(sourceBase, 'common');
const targetPath = path.join(installDir, targetSubdir);
const copiedFiles = [];
// Check if common/ exists
if (!(await fileManager.pathExists(commonPath))) {
console.warn(chalk.yellow('Warning: common/ folder not found'));
return copiedFiles;
}
// Copy all items from common/ to target
const commonItems = glob.sync('**/*', {
cwd: commonPath,
nodir: true
});
for (const item of commonItems) {
const sourcePath = path.join(commonPath, item);
const destPath = path.join(targetPath, item);
// Read the file content
const content = await fs.readFile(sourcePath, 'utf8');
// Replace {root} with the target subdirectory
const updatedContent = content.replace(/\{root\}/g, targetSubdir);
// Ensure directory exists
await fileManager.ensureDirectory(path.dirname(destPath));
// Write the updated content
await fs.writeFile(destPath, updatedContent, 'utf8');
copiedFiles.push(path.join(targetSubdir, item));
}
console.log(chalk.dim(` Added ${commonItems.length} common utilities`));
return copiedFiles;
}
async findInstallation() {
// Look for .bmad-core in current directory or parent directories
let currentDir = process.cwd();

15
tools/lib/dependency-resolver.js
View File

@@ -6,6 +6,7 @@ class DependencyResolver {
constructor(rootDir) {
this.rootDir = rootDir;
this.bmadCore = path.join(rootDir, 'bmad-core');
this.common = path.join(rootDir, 'common');
this.cache = new Map();
}
@@ -123,6 +124,7 @@ class DependencyResolver {
let content = null;
let filePath = null;
// First try bmad-core
for (const ext of extensions) {
try {
filePath = path.join(this.bmadCore, type, `${id}${ext}`);
@@ -133,6 +135,19 @@ class DependencyResolver {
}
}
// If not found in bmad-core, try common folder
if (!content) {
for (const ext of extensions) {
try {
filePath = path.join(this.common, type, `${id}${ext}`);
content = await fs.readFile(filePath, 'utf8');
break;
} catch (e) {
// Try next extension
}
}
}
if (!content) {
console.warn(`Resource not found: ${type}/${id}`);
return null;

0
bmad-core/utils/web-agent-startup-instructions.md → tools/md-assets/web-agent-startup-instructions.md
View File