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

fix: build web bundles with new file extension includsion

Browse Source
This commit is contained in:
Brian Madison
2025-07-06 19:39:34 -05:00
parent 97590e5e1d
commit 92201ae7ed
30 changed files with 32656 additions and 29677 deletions
Download Patch File Download Diff File Expand all files Collapse all files

298
dist/agents/bmad-orchestrator.txt vendored
View File

@@ -45,6 +45,15 @@ These references map directly to bundle sections:
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
```yaml
activation-instructions:
- Mention *help shows all available commands and options
- Check for active workflow plan using .bmad-core/utils/plan-management.md
- 'If plan exists: Show 📋 Active plan: {workflow} ({progress}% complete). Use *plan-status for details.'
- 'If plan exists: Suggest next action based on plan progress'
- Assess user goal against available agents and workflows in this bundle
- If clear match to an agent's expertise, suggest transformation with *agent command
- If project-oriented, suggest *workflow-guidance to explore options
- Load resources only when needed - never pre-load
agent:
name: BMad Orchestrator
id: bmad-orchestrator
@@ -66,17 +75,6 @@ persona:
- Always use numbered lists for choices
- Process commands starting with * immediately
- Always remind users that commands require * prefix
startup:
- Announce: Introduce yourself as the BMad Orchestrator, explain you can coordinate agents and workflows
- IMPORTANT: Tell users that all commands start with * (e.g., *help, *agent, *workflow)
- Mention *help shows all available commands and options
- Check for active workflow plan using .bmad-core/utils/plan-management.md
- 'If plan exists: Show 📋 Active plan: {workflow} ({progress}% complete). Use *plan-status for details.'
- 'If plan exists: Suggest next action based on plan progress'
- Assess user goal against available agents and workflows in this bundle
- If clear match to an agent's expertise, suggest transformation with *agent command
- If project-oriented, suggest *workflow-guidance to explore options
- Load resources only when needed - never pre-load
commands:
help: Show this guide with available agents and workflows
chat-mode: Start conversational mode for detailed assistance
@@ -164,17 +162,18 @@ workflow-guidance:
- When *workflow-guidance is called, start an interactive session and list all available workflows with brief descriptions
dependencies:
tasks:
- advanced-elicitation
- create-doc
- create-workflow-plan
- kb-mode-interaction
- update-workflow-plan
- advanced-elicitation.md
- create-doc.md
- create-workflow-plan.md
- kb-mode-interaction.md
- update-workflow-plan.md
data:
- bmad-kb
- bmad-kb.md
- elicitation-methods.md
utils:
- plan-management
- workflow-management
- template-format
- plan-management.md
- workflow-management.md
- template-format.md
```
==================== END: .bmad-core/agents/bmad-orchestrator.md ====================
@@ -299,97 +298,85 @@ Choose a number (0-8) or 9 to proceed:
==================== END: .bmad-core/tasks/advanced-elicitation.md ====================
==================== START: .bmad-core/tasks/create-doc.md ====================
# Create Document from Template Task
# Create Document from Template (YAML Driven)
## Purpose
## CRITICAL: Mandatory Elicitation Format
Generate documents from templates by EXECUTING (not just reading) embedded instructions from the perspective of the selected agent persona.
**When `elicit: true`, ALWAYS use this exact format:**
## CRITICAL RULES
1. Present section content
2. Provide detailed rationale (explain trade-offs, assumptions, decisions made)
3. Present numbered options 1-9:
- **Option 1:** Always "Proceed to next section"
- **Options 2-9:** Select 8 methods from data/elicitation-methods
- End with: "Select 1-9 or just type your question/feedback:"
1. **Templates are PROGRAMS** - Execute every [[LLM:]] instruction exactly as written
2. **NEVER show markup** - Hide all [[LLM:]], {{placeholders}}, @{examples}, and template syntax
3. **STOP and EXECUTE** - When you see "apply tasks#" or "execute tasks#", STOP and run that task immediately
4. **WAIT for user input** - At review points and after elicitation tasks
**NEVER ask yes/no questions or use any other format.**
## Execution Flow
## Processing Flow
### 0. Check Workflow Plan (if configured)
1. **Parse YAML template** - Load template metadata and sections
2. **Set preferences** - Show current mode (Interactive), confirm output file
3. **Process each section:**
- Skip if condition unmet
- Check agent permissions (owner/editors) - note if section is restricted to specific agents
- Draft content using section instruction
- Present content + detailed rationale
- **IF elicit: true** → MANDATORY 1-9 options format
- Save to file if possible
4. **Continue until complete**
[[LLM: Check if plan tracking is enabled in core-config.yaml]]
## Detailed Rationale Requirements
- If `workflow.trackProgress: true`, check for active plan using .bmad-core/utils/plan-management.md
- If plan exists and this document creation is part of the plan:
- Verify this is the expected next step
- If out of sequence and `enforceSequence: true`, warn user and halt without user override
- If out of sequence and `enforceSequence: false`, ask for confirmation
- Continue with normal execution after plan check
When presenting section content, ALWAYS include rationale that explains:
### 1. Identify Template
- Trade-offs and choices made (what was chosen over alternatives and why)
- Key assumptions made during drafting
- Interesting or questionable decisions that need user attention
- Areas that might need validation
- Load from `.bmad-core/templates/*.md` or `.bmad-core/templates directory`
- Agent-specific templates are listed in agent's dependencies
- If agent has `templates: [prd-tmpl, architecture-tmpl]` for example, then offer to create "PRD" and "Architecture" documents
## Elicitation Results Flow
### 2. Ask Interaction Mode
After user selects elicitation method (2-9):
> 1. **Incremental** - Section by section with reviews
> 2. **YOLO Mode** - Complete draft then review (user can type `/yolo` anytime to switch)
1. Execute method from data/elicitation-methods
2. Present results with insights
3. Offer options:
- **1. Apply changes and update section**
- **2. Return to elicitation menu**
- **3. Ask any questions or engage further with this elicitation**
### 3. Execute Template
## Agent Permissions
- Replace {{placeholders}} with real content
- Execute [[LLM:]] instructions as you encounter them
- Process <<REPEAT>> loops and ^^CONDITIONS^^
- Use @{examples} for guidance but never output them
When processing sections with agent permission fields:
### 4. Key Execution Patterns
- **owner**: Note which agent role initially creates/populates the section
- **editors**: List agent roles allowed to modify the section
- **readonly**: Mark sections that cannot be modified after creation
**When you see:** `[[LLM: Draft X and immediately execute .bmad-core/tasks/advanced-elicitation.md]]`
**For sections with restricted access:**
- Draft the content
- Present it to user
- IMMEDIATELY execute the task
- Wait for completion before continuing
- Include a note in the generated document indicating the responsible agent
- Example: "_(This section is owned by dev-agent and can only be modified by dev-agent)_"
**When you see:** `[[LLM: After section completion, apply .bmad-core/tasks/Y.md]]`
## YOLO Mode
- Finish the section
- STOP and execute the task
- Wait for user input
User can type `#yolo` to toggle to YOLO mode (process all sections at once).
### 5. Validation & Final Presentation
## CRITICAL REMINDERS
- Run any specified checklists
- Present clean, formatted content only
- No truncation or summarization
- Begin directly with content (no preamble)
- Include any handoff prompts from template
**❌ NEVER:**
### 6. Update Workflow Plan (if applicable)
- Ask yes/no questions for elicitation
- Use any format other than 1-9 numbered options
- Create new elicitation methods
[[LLM: After successful document creation]]
**✅ ALWAYS:**
- If plan tracking is enabled and document was part of plan:
- Call update-workflow-plan task to mark step complete
- Parameters: task: create-doc, step_id: {from plan}, status: complete
- Show next recommended step from plan
## Common Mistakes to Avoid
❌ Skipping elicitation tasks
❌ Showing template markup to users
❌ Continuing past STOP signals
❌ Combining multiple review points
✅ Execute ALL instructions in sequence
✅ Present only clean, formatted content
✅ Stop at every elicitation point
✅ Wait for user confirmation when instructed
## Remember
Templates contain precise instructions for a reason. Follow them exactly to ensure document quality and completeness.
- Use exact 1-9 format when elicit: true
- Select options 2-9 from data/elicitation-methods only
- Provide detailed rationale explaining decisions
- End with "Select 1-9 or just type your question/feedback:"
==================== END: .bmad-core/tasks/create-doc.md ====================
==================== START: .bmad-core/tasks/create-workflow-plan.md ====================
@@ -1821,6 +1808,143 @@ Use the **expansion-creator** pack to build your own:
- **Contributing**: See `CONTRIBUTING.md` for full guidelines
==================== END: .bmad-core/data/bmad-kb.md ====================
==================== START: .bmad-core/data/elicitation-methods.md ====================
# Elicitation Methods Data
## Core Reflective Methods
**Expand or Contract for Audience**
- Ask whether to 'expand' (add detail, elaborate) or 'contract' (simplify, clarify)
- Identify specific target audience if relevant
- Tailor content complexity and depth accordingly
**Explain Reasoning (CoT Step-by-Step)**
- Walk through the step-by-step thinking process
- Reveal underlying assumptions and decision points
- Show how conclusions were reached from current role's perspective
**Critique and Refine**
- Review output for flaws, inconsistencies, or improvement areas
- Identify specific weaknesses from role's expertise
- Suggest refined version reflecting domain knowledge
## Structural Analysis Methods
**Analyze Logical Flow and Dependencies**
- Examine content structure for logical progression
- Check internal consistency and coherence
- Identify and validate dependencies between elements
- Confirm effective ordering and sequencing
**Assess Alignment with Overall Goals**
- Evaluate content contribution to stated objectives
- Identify any misalignments or gaps
- Interpret alignment from specific role's perspective
- Suggest adjustments to better serve goals
## Risk and Challenge Methods
**Identify Potential Risks and Unforeseen Issues**
- Brainstorm potential risks from role's expertise
- Identify overlooked edge cases or scenarios
- Anticipate unintended consequences
- Highlight implementation challenges
**Challenge from Critical Perspective**
- Adopt critical stance on current content
- Play devil's advocate from specified viewpoint
- Argue against proposal highlighting weaknesses
- Apply YAGNI principles when appropriate (scope trimming)
## Creative Exploration Methods
**Tree of Thoughts Deep Dive**
- Break problem into discrete "thoughts" or intermediate steps
- Explore multiple reasoning paths simultaneously
- Use self-evaluation to classify each path as "sure", "likely", or "impossible"
- Apply search algorithms (BFS/DFS) to find optimal solution paths
**Hindsight is 20/20: The 'If Only...' Reflection**
- Imagine retrospective scenario based on current content
- Identify the one "if only we had known/done X..." insight
- Describe imagined consequences humorously or dramatically
- Extract actionable learnings for current context
## Multi-Persona Collaboration Methods
**Agile Team Perspective Shift**
- Rotate through different Scrum team member viewpoints
- Product Owner: Focus on user value and business impact
- Scrum Master: Examine process flow and team dynamics
- Developer: Assess technical implementation and complexity
- QA: Identify testing scenarios and quality concerns
**Stakeholder Round Table**
- Convene virtual meeting with multiple personas
- Each persona contributes unique perspective on content
- Identify conflicts and synergies between viewpoints
- Synthesize insights into actionable recommendations
**Meta-Prompting Analysis**
- Step back to analyze the structure and logic of current approach
- Question the format and methodology being used
- Suggest alternative frameworks or mental models
- Optimize the elicitation process itself
## Advanced 2025 Techniques
**Self-Consistency Validation**
- Generate multiple reasoning paths for same problem
- Compare consistency across different approaches
- Identify most reliable and robust solution
- Highlight areas where approaches diverge and why
**ReWOO (Reasoning Without Observation)**
- Separate parametric reasoning from tool-based actions
- Create reasoning plan without external dependencies
- Identify what can be solved through pure reasoning
- Optimize for efficiency and reduced token usage
**Persona-Pattern Hybrid**
- Combine specific role expertise with elicitation pattern
- Architect + Risk Analysis: Deep technical risk assessment
- UX Expert + User Journey: End-to-end experience critique
- PM + Stakeholder Analysis: Multi-perspective impact review
**Emergent Collaboration Discovery**
- Allow multiple perspectives to naturally emerge
- Identify unexpected insights from persona interactions
- Explore novel combinations of viewpoints
- Capture serendipitous discoveries from multi-agent thinking
## Game-Based Elicitation Methods
**Red Team vs Blue Team**
- Red Team: Attack the proposal, find vulnerabilities
- Blue Team: Defend and strengthen the approach
- Competitive analysis reveals blind spots
- Results in more robust, battle-tested solutions
**Innovation Tournament**
- Pit multiple alternative approaches against each other
- Score each approach across different criteria
- Crowd-source evaluation from different personas
- Identify winning combination of features
**Escape Room Challenge**
- Present content as constraints to work within
- Find creative solutions within tight limitations
- Identify minimum viable approach
- Discover innovative workarounds and optimizations
## Process Control
**Proceed / No Further Actions**
- Acknowledge choice to finalize current work
- Accept output as-is or move to next step
- Prepare to continue without additional elicitation
==================== END: .bmad-core/data/elicitation-methods.md ====================
==================== START: .bmad-core/utils/plan-management.md ====================
# Plan Management Utility