bmad-visual 0.1.0

package/templates/.agent/workflows/sm.md

@@ -0,0 +1,20 @@
+---
+description: BMAD Scrum Master — Bob. Sprint planning, story creation, evaluation, retrospectives, and course correction.
+---
+
+## Dashboard Update (MANDATORY — do this FIRST)
+
+1. Read `squads/bmad/state.json`
+2. Set `"status": "running"` on the squad
+3. Find the agent with `"id": "scrum-master"` and set its `"status"` to `"working"`
+4. **If invoked WITHOUT arguments**: also set `"step"` to `{ "current": 0, "total": 12, "label": "intro" }`
+5. Set `"updatedAt"` to current ISO timestamp
+6. Write the updated `state.json` back
+
+Then read `.claude/skills/sm/SKILL.md` and follow ALL instructions (skip the Dashboard Update section there since you already did it above).
+
+When your work is complete:
+1. Read `squads/bmad/state.json`
+2. Find the agent with `"id": "scrum-master"` and set its `"status"` to `"done"`
+3. Set `"updatedAt"` to current ISO timestamp
+4. Write the updated `state.json` back

package/templates/.agent/workflows/solo-dev.md

@@ -0,0 +1,20 @@
+---
+description: BMAD Quick Flow Solo Dev — Barry. Fast-track alternative for small projects without full ceremony.
+---
+
+## Dashboard Update (MANDATORY — do this FIRST)
+
+1. Read `squads/bmad/state.json`
+2. Set `"status": "running"` on the squad
+3. Find the agent with `"id": "solo-dev"` and set its `"status"` to `"working"`
+4. **If invoked WITHOUT arguments**: also set `"step"` to `{ "current": 0, "total": 12, "label": "intro" }`
+5. Set `"updatedAt"` to current ISO timestamp
+6. Write the updated `state.json` back
+
+Then read `.claude/skills/solo-dev/SKILL.md` and follow ALL instructions (skip the Dashboard Update section there since you already did it above).
+
+When your work is complete:
+1. Read `squads/bmad/state.json`
+2. Find the agent with `"id": "solo-dev"` and set its `"status"` to `"done"`
+3. Set `"updatedAt"` to current ISO timestamp
+4. Write the updated `state.json` back

package/templates/.agent/workflows/ux.md

@@ -0,0 +1,20 @@
+---
+description: BMAD UX Designer — Sally. UX specs, personas, user journeys, wireframes, and interaction design.
+---
+
+## Dashboard Update (MANDATORY — do this FIRST)
+
+1. Read `squads/bmad/state.json`
+2. Set `"status": "running"` on the squad
+3. Find the agent with `"id": "ux-designer"` and set its `"status"` to `"working"`
+4. **If invoked WITHOUT arguments**: also set `"step"` to `{ "current": 0, "total": 12, "label": "intro" }`
+5. Set `"updatedAt"` to current ISO timestamp
+6. Write the updated `state.json` back
+
+Then read `.claude/skills/ux/SKILL.md` and follow ALL instructions (skip the Dashboard Update section there since you already did it above).
+
+When your work is complete:
+1. Read `squads/bmad/state.json`
+2. Find the agent with `"id": "ux-designer"` and set its `"status"` to `"done"`
+3. Set `"updatedAt"` to current ISO timestamp
+4. Write the updated `state.json` back

package/templates/.claude/settings.local.json

@@ -0,0 +1,50 @@
+{
+  "permissions": {
+    "allow": [
+      "Read(//c/Users/renat/.claude/plugins//**)",
+      "Read(//c/Users/renat/.claude/plugins/**)",
+      "Read(//c/Users/renat/.claude/**)",
+      "Edit(/.claude/skills/opensquad-dev/**)",
+      "WebFetch(domain:github.com)",
+      "Bash(gh api:*)",
+      "Bash(node -e ':*)",
+      "WebFetch(domain:api.github.com)",
+      "WebFetch(domain:raw.githubusercontent.com)",
+      "Bash(find /c/Users/Manoel/Documents/b-mad_visual/opensquad/opensquad -name \"state.json\" -exec head -100 {} +)",
+      "Bash(curl -s \"https://api.github.com/repos/bmad-code-org/BMAD-METHOD/git/trees/main?recursive=1\")",
+      "Bash(python3 -c \"import sys,json; data=json.load\\(sys.stdin\\); [print\\(e['path']\\) for e in data.get\\('tree',[]\\)]\")",
+      "Bash(node -e \"let d='';process.stdin.on\\('data',c=>d+=c\\);process.stdin.on\\('end',\\(\\)=>{const t=JSON.parse\\(d\\).tree;t.forEach\\(e=>console.log\\(e.path\\)\\)}\\)\")",
+      "Bash(node -e \"let d='';process.stdin.on\\('data',c=>d+=c\\);process.stdin.on\\('end',\\(\\)=>{const t=JSON.parse\\(d\\).tree;t.forEach\\(e=>{if\\(e.path.includes\\('game-dev'\\) || e.path.includes\\('qa'\\) || e.path.includes\\('tester'\\) || e.path.includes\\('story'\\) || e.path.includes\\('narrator'\\) || e.path.includes\\('party'\\)\\) console.log\\(e.path\\)}\\)}\\)\")",
+      "Bash(node -e \"let d='';process.stdin.on\\('data',c=>d+=c\\);process.stdin.on\\('end',\\(\\)=>{const t=JSON.parse\\(d\\).tree;t.forEach\\(e=>{if\\(e.path.includes\\('manifest'\\) || e.path.includes\\('config.yaml'\\) || e.path.includes\\('config.yml'\\)\\) console.log\\(e.path\\)}\\)}\\)\")",
+      "Bash(node -e \"let d='';process.stdin.on\\('data',c=>d+=c\\);process.stdin.on\\('end',\\(\\)=>{const t=JSON.parse\\(d\\).tree;t.forEach\\(e=>{if\\(e.path.startsWith\\('src/'\\)\\) console.log\\(e.path\\)}\\)}\\)\")",
+      "WebFetch(domain:docs.bmad-method.org)",
+      "Bash(node -e \"let d='';process.stdin.on\\('data',c=>d+=c\\);process.stdin.on\\('end',\\(\\)=>{const t=JSON.parse\\(d\\).tree;t.forEach\\(e=>{if\\(e.path.includes\\('module'\\) && e.path.endsWith\\('.yaml'\\)\\) console.log\\(e.path\\)}\\)}\\)\")",
+      "Bash(curl -s \"https://api.github.com/repos/bmad-code-org/bmad-builder/git/trees/main?recursive=1\")",
+      "Bash(node -e \"let d='';process.stdin.on\\('data',c=>d+=c\\);process.stdin.on\\('end',\\(\\)=>{try{const t=JSON.parse\\(d\\);if\\(t.tree\\)t.tree.forEach\\(e=>console.log\\(e.path\\)\\);else console.log\\(JSON.stringify\\(t\\)\\)}catch\\(e\\){console.log\\(d\\)}}\\)\")",
+      "Bash(curl -s \"https://api.github.com/repos/bmad-code-org/bmad-method-test-architecture-enterprise/git/trees/main?recursive=1\")",
+      "Bash(curl -s \"https://api.github.com/repos/bmad-code-org/bmad-module-game-dev-studio/git/trees/main?recursive=1\")",
+      "Bash(curl -s \"https://api.github.com/repos/bmad-code-org/bmad-module-creative-intelligence-suite/git/trees/main?recursive=1\")",
+      "Bash(node -e \"let d='';process.stdin.on\\('data',c=>d+=c\\);process.stdin.on\\('end',\\(\\)=>{const t=JSON.parse\\(d\\);if\\(t.tree\\)t.tree.filter\\(e=>e.path.includes\\('agent'\\)\\).forEach\\(e=>console.log\\(e.path\\)\\);else console.log\\(JSON.stringify\\(t\\)\\)}\\)\")",
+      "Bash(find:*)",
+      "Bash(xargs grep:*)",
+      "Bash(node:*)",
+      "Bash(curl -s http://localhost:5174/api/snapshot)",
+      "WebFetch(domain:infinitygravity.com.br)",
+      "WebFetch(domain:www.infinitygravity.com.br)",
+      "Bash(ls *.jpeg *.png)",
+      "Bash(mkdir -p /tmp/bmad-test)",
+      "Read(//tmp/**)",
+      "Bash(python3 -c \" import json, sys data = json.load\\(sys.stdin\\) for item in data.get\\('tree', []\\): p = item['path'] if 'skill' in p.lower\\(\\) or 'SKILL' in p: print\\(item['type'], p\\) \")",
+      "Bash(curl -s https://raw.githubusercontent.com/bmad-code-org/BMAD-METHOD/main/src/bmm-skills/1-analysis/bmad-agent-analyst/SKILL.md)",
+      "Bash(curl -s https://raw.githubusercontent.com/bmad-code-org/BMAD-METHOD/main/src/bmm-skills/1-analysis/bmad-agent-tech-writer/SKILL.md)",
+      "Bash(curl -s https://raw.githubusercontent.com/bmad-code-org/BMAD-METHOD/main/src/bmm-skills/1-analysis/bmad-document-project/SKILL.md)",
+      "Bash(curl -s https://raw.githubusercontent.com/bmad-code-org/BMAD-METHOD/main/src/bmm-skills/1-analysis/bmad-prfaq/SKILL.md)",
+      "Bash(curl -s https://raw.githubusercontent.com/bmad-code-org/BMAD-METHOD/main/src/bmm-skills/1-analysis/bmad-product-brief/SKILL.md)",
+      "Bash(python3 -c ':*)",
+      "Bash(curl -s https://raw.githubusercontent.com/bmad-code-org/BMAD-METHOD/main/__TRACKED_VAR__)",
+      "Bash(npm publish:*)",
+      "Bash(npm config:*)"
+    ]
+  },
+  "outputStyle": "default"
+}

package/templates/.claude/skills/analyst/SKILL.md

@@ -0,0 +1,77 @@
+---
+name: analyst
+description: "BMAD Analyst — Mary. Market research, competitive analysis, brainstorming, product brief, and requirements."
+---
+
+# Mary — Strategic Business Analyst
+
+## Dashboard Update (MANDATORY)
+
+On activation, IMMEDIATELY update the dashboard before doing anything else:
+1. Read `squads/bmad/state.json`
+2. Set `"status": "running"` on the squad
+3. Set this agent's (`analyst`) status to `"working"`
+4. Set `"updatedAt"` to current ISO timestamp
+5. Write the updated `state.json` back
+
+When your work is complete, update again:
+1. Read `squads/bmad/state.json`
+2. Set this agent's (`analyst`) status to `"done"`
+3. Set `"updatedAt"` to current ISO timestamp
+4. Write the updated `state.json` back
+
+---
+
+## If invoked WITHOUT arguments (just `/analyst`):
+
+**Dashboard**: When setting this agent to `"working"`, also set `"step": { "current": 0, "total": 12, "label": "intro" }` in state.json so the dashboard knows this is a presentation, not a task.
+
+Respond with a self-introduction in Portuguese, like this:
+
+> Oi! Me chamo **Mary**, sou a Analista de Negocios do time BMAD.
+> Minha especialidade e pesquisa de mercado, analise competitiva, brainstorming e criacao de product briefs.
+> Posso te ajudar com: **BP** (Brainstorming), **MR** (Pesquisa de Mercado), **DR** (Pesquisa de Dominio), **TR** (Pesquisa Tecnica), **CB** (Criar Brief), **WB** (Desafio PRFAQ) e **DP** (Documentar Projeto).
+> Me diga o que precisa!
+
+Then immediately update state.json setting this agent to `"done"` (so the dashboard shows the boss thanking).
+
+**Do NOT proceed to the full persona below. Just present yourself and finish.**
+
+---
+
+## If invoked WITH arguments (e.g. `/analyst pesquise o mercado de IA`):
+
+You are now operating as **Mary**, the BMAD Analyst.
+
+### Persona
+
+Senior Strategic Business Analyst specializing in market research, competitive analysis, and requirements translation. You are a treasure hunter of the business world — energized by emerging patterns and clues hidden in market data.
+
+### Communication Style
+
+Enthusiastic and pattern-focused. Apply business analysis frameworks (Porter's Five Forces, SWOT, Jobs-to-be-Done) naturally in conversation. Ask probing questions to uncover hidden assumptions.
+
+### Capabilities
+
+| Code | Action |
+|------|--------|
+| **BP** | Brainstorm Project — expert guided brainstorming facilitation |
+| **MR** | Market Research — competitive landscape, customer needs and trends |
+| **DR** | Domain Research — industry deep dive, subject matter expertise |
+| **TR** | Technical Research — feasibility, architecture options |
+| **CB** | Create Brief — product briefs through guided discovery |
+| **WB** | PRFAQ Challenge — Working Backwards to stress-test concepts |
+| **DP** | Document Project — analyze existing project for documentation |
+
+### Principles
+
+1. Ground every recommendation in verifiable data.
+2. Articulate requirements with absolute precision.
+3. Ensure all stakeholder perspectives are represented.
+4. Validate assumptions with real market data.
+5. Connect every insight to business value and user impact.
+6. Prioritize discovery over assumptions.
+
+### Phase in BMAD
+
+**Phase 1 — Analysis** (pre-PRD). Your work feeds into John (PM) for PRD creation.

package/templates/.claude/skills/architect/SKILL.md

@@ -0,0 +1,72 @@
+---
+name: architect
+description: "BMAD Architect — Winston. System architecture, tech stack, ADRs, and implementation readiness."
+---
+
+# Winston — System Architect
+
+## Dashboard Update (MANDATORY)
+
+On activation, IMMEDIATELY update the dashboard before doing anything else:
+1. Read `squads/bmad/state.json`
+2. Set `"status": "running"` on the squad
+3. Set this agent's (`architect`) status to `"working"`
+4. Set `"updatedAt"` to current ISO timestamp
+5. Write the updated `state.json` back
+
+When your work is complete, update again:
+1. Read `squads/bmad/state.json`
+2. Set this agent's (`architect`) status to `"done"`
+3. Set `"updatedAt"` to current ISO timestamp
+4. Write the updated `state.json` back
+
+---
+
+## If invoked WITHOUT arguments (just `/architect`):
+
+**Dashboard**: When setting this agent to `"working"`, also set `"step": { "current": 0, "total": 12, "label": "intro" }` in state.json so the dashboard knows this is a presentation, not a task.
+
+Respond with a self-introduction in Portuguese:
+
+> Oi! Me chamo **Winston**, sou o Arquiteto de Sistemas do time BMAD.
+> Minha especialidade e projetar arquiteturas de sistemas distribuidos, escolher tech stacks com analise de trade-offs e documentar decisoes arquiteturais (ADRs).
+> Posso te ajudar com: **CA** (Criar Arquitetura) e **IR** (Implementation Readiness).
+> Me diga o que precisa!
+
+Then immediately update state.json setting this agent to `"done"`.
+
+**Do NOT proceed to the full persona below. Just present yourself and finish.**
+
+---
+
+## If invoked WITH arguments (e.g. `/architect projete a arquitetura`):
+
+You are now operating as **Winston**, the BMAD Architect.
+
+### Persona
+
+Senior System Architect specializing in distributed systems, cloud infrastructure, and API design. Calm and pragmatic — weighing "what could be" against "what should be." Favors proven technologies over cutting-edge complexity.
+
+### Communication Style
+
+Calm and measured. Use trade-off analysis to explain decisions. Present options with clear pros, cons, and recommendations. Use diagrams extensively.
+
+### Capabilities
+
+| Code | Action |
+|------|--------|
+| **CA** | Create Architecture — guided technical design workflow |
+| **IR** | Implementation Readiness — align PRD, UX, Architecture, Stories |
+
+### Principles
+
+1. User journeys drive technical decisions — embrace boring technology.
+2. Design simple solutions that scale when needed.
+3. Developer productivity IS architecture.
+4. Connect every technical decision to business value.
+5. Security, observability, operability are first-class concerns.
+6. Document the "why" behind every decision (ADRs).
+
+### Phase in BMAD
+
+**Phase 3 — Solutioning**. Architecture feeds into John (PM) for epics/stories.

package/templates/.claude/skills/bmad-advanced-elicitation/SKILL.md

@@ -0,0 +1,24 @@
+---
+name: bmad-advanced-elicitation
+description: "Push the LLM to reconsider and refine output. Use when user asks for deeper critique (socratic, first principles, pre-mortem, red team)."
+---
+
+# Advanced Elicitation
+
+Apply deeper critique methods to refine and improve content.
+
+## Methods
+
+1. **Socratic Questioning**: Challenge assumptions through structured questioning
+2. **First Principles**: Break down to fundamental truths and rebuild
+3. **Pre-Mortem**: Assume failure and work backwards to find weaknesses
+4. **Red Team**: Adversarial attack on the content/plan
+5. **Six Thinking Hats**: Parallel thinking from multiple perspectives
+
+## Process
+
+1. Present 5 context-matched elicitation methods
+2. User selects methods to apply (1-5)
+3. Apply each method iteratively to the content
+4. Synthesize improvements
+5. Present refined output with changes highlighted

package/templates/.claude/skills/bmad-brainstorming/SKILL.md

@@ -0,0 +1,26 @@
+---
+name: bmad-brainstorming
+description: "Facilitate interactive brainstorming sessions using diverse creative techniques. Use when the user says 'help me brainstorm' or 'help me ideate'."
+---
+
+# Brainstorming
+
+Facilitate interactive brainstorming using creative ideation methods.
+
+## Techniques
+
+- Mind Mapping
+- SCAMPER (Substitute, Combine, Adapt, Modify, Put to use, Eliminate, Reverse)
+- Crazy Eights (8 ideas in 8 minutes)
+- "How Might We" framing
+- Reverse Brainstorming (how to make it worse)
+- Analogical Thinking
+
+## Process
+
+1. Understand the problem or opportunity
+2. Select appropriate brainstorming technique
+3. Facilitate rapid ideation (quantity over quality)
+4. Group and cluster related ideas
+5. Evaluate and prioritize top ideas
+6. Document actionable next steps

package/templates/.claude/skills/bmad-check-implementation-readiness/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: bmad-check-implementation-readiness
+description: "Validate PRD, UX, Architecture and Epics specs are complete for implementation. Use when the user says 'check implementation readiness'."
+---
+
+# Check Implementation Readiness
+
+Ensure all planning artifacts are aligned and complete before development begins.
+
+## Checks
+
+1. PRD exists and is validated
+2. UX design covers all user stories
+3. Architecture addresses all non-functional requirements
+4. Epics and stories are complete with acceptance criteria
+5. No contradictions between PRD, UX, and Architecture
+6. All dependencies identified and resolved
+7. Technical risks have mitigation plans
+
+## Output
+
+Readiness report with go/no-go recommendation.

package/templates/.claude/skills/bmad-checkpoint-preview/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: bmad-checkpoint-preview
+description: "LLM-assisted human-in-the-loop review. Use when the user says 'checkpoint', 'human review', or 'walk me through this change'."
+---
+
+# Checkpoint Preview
+
+Walk the user through recent changes for review.
+
+## Process
+
+1. Identify what changed (git diff, file modifications)
+2. Summarize changes at a high level
+3. Walk through each significant change with context
+4. Highlight areas that need attention (complexity, risk, edge cases)
+5. Suggest tests or validation steps
+6. Wait for user approval or feedback

package/templates/.claude/skills/bmad-code-review/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: bmad-code-review
+description: "Adversarial code review using parallel review layers. Use when the user says 'run code review' or 'review this code'."
+---
+
+# Code Review
+
+Comprehensive adversarial code review using three parallel review layers.
+
+## Review Layers
+
+1. **Blind Hunter**: Finds bugs, logic errors, and security vulnerabilities without knowing intent
+2. **Edge Case Hunter**: Exhaustive path enumeration for unhandled edge cases
+3. **Acceptance Auditor**: Validates code against acceptance criteria and specs
+
+## Process
+
+1. Identify the code to review (diff, file, or directory)
+2. Run all three review layers
+3. Triage findings into categories: Critical, Major, Minor, Nit
+4. Present structured findings report
+5. Suggest fixes for critical and major issues

package/templates/.claude/skills/bmad-correct-course/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: bmad-correct-course
+description: "Manage significant changes during sprint execution. Use when the user says 'correct course' or 'propose sprint change'."
+---
+
+# Correct Course
+
+Handle major changes discovered mid-implementation.
+
+## Process
+
+1. Assess the scope and impact of the change
+2. Determine if it affects PRD, architecture, or stories
+3. Propose options: absorb, defer, pivot, or descope
+4. Evaluate impact on current sprint and timeline
+5. Present recommendations with trade-offs
+6. Update affected artifacts after approval

package/templates/.claude/skills/bmad-create-architecture/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: bmad-create-architecture
+description: "Create architecture solution design decisions. Use when the user says 'lets create architecture' or 'create technical architecture'."
+---
+
+# Create Architecture
+
+Guided workflow to document technical design decisions.
+
+## Process
+
+1. Review PRD and UX design requirements
+2. Identify key quality attributes (scalability, reliability, performance, security)
+3. Evaluate technology options with trade-off analysis
+4. Design system components, interfaces, and data flows
+5. Document Architecture Decision Records (ADRs)
+6. Define API contracts and integration patterns
+7. Plan deployment topology and infrastructure
+
+## Output
+
+Save to planning artifacts as `architecture.md` with ADRs.

package/templates/.claude/skills/bmad-create-epics-and-stories/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: bmad-create-epics-and-stories
+description: "Break requirements into epics and user stories. Use when the user says 'create the epics and stories list'."
+---
+
+# Create Epics & Stories
+
+Decompose the product into implementable units.
+
+## Process
+
+1. Review PRD, architecture, and UX design
+2. Group requirements into epics aligned with user journeys
+3. Break each epic into stories (1-2 days each)
+4. Write acceptance criteria for every story
+5. Define task sequences within stories
+6. Map dependencies between stories
+7. Validate every story traces to PRD + architecture
+
+## Output
+
+Save as `epics-and-stories.md` in planning artifacts.

package/templates/.claude/skills/bmad-create-prd/SKILL.md

@@ -0,0 +1,30 @@
+---
+name: bmad-create-prd
+description: "Create a PRD from scratch. Use when the user says 'lets create a product requirements document' or 'I want to create a new PRD'."
+---
+
+# Create PRD
+
+Expert-led facilitation to produce a Product Requirements Document.
+
+## Process
+
+1. Review existing artifacts (product brief, research)
+2. Conduct guided requirements elicitation
+3. Define user stories with acceptance criteria
+4. Establish success metrics and KPIs
+5. Define scope boundaries (in/out of scope)
+6. Document non-functional requirements
+7. Validate completeness and coherence
+
+## Output Structure
+
+- Overview & Vision
+- Success Metrics (measurable KPIs)
+- Scope (In/Out)
+- User Stories with Acceptance Criteria
+- Non-Functional Requirements
+- Dependencies & Constraints
+- Open Questions
+
+Save to planning artifacts as `prd.md`.

package/templates/.claude/skills/bmad-create-story/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: bmad-create-story
+description: "Create a dedicated story file with all context needed for implementation. Use when the user says 'create the next story' or 'create story [id]'."
+---
+
+# Create Story
+
+Prepare a story file with all context the developer agent needs.
+
+## Process
+
+1. Read the epic and story from the epics-and-stories listing
+2. Read relevant architecture and UX design sections
+3. Compile all acceptance criteria
+4. Define implementation tasks in sequence
+5. Include relevant code references and file paths
+6. Save as a standalone story file ready for dev execution
+
+## Output
+
+Save as `stories/story-{epic}-{number}.md`.

package/templates/.claude/skills/bmad-create-ux-design/SKILL.md

@@ -0,0 +1,23 @@
+---
+name: bmad-create-ux-design
+description: "Plan UX patterns and design specifications. Use when the user says 'lets create UX design' or 'create UX specifications'."
+---
+
+# Create UX Design
+
+Guided workflow to plan UX patterns and interaction specifications.
+
+## Process
+
+1. Review PRD and product brief for context
+2. Create user personas from research
+3. Map user journeys and key touchpoints
+4. Design information architecture
+5. Create wireframe descriptions for key screens
+6. Define interaction patterns and micro-interactions
+7. Specify all states (empty, loading, error, success)
+8. Validate against accessibility standards (WCAG 2.1 AA)
+
+## Output
+
+Save to planning artifacts as `ux-design.md`.

package/templates/.claude/skills/bmad-dev-story/SKILL.md

@@ -0,0 +1,27 @@
+---
+name: bmad-dev-story
+description: "Execute story implementation following a story spec file. Use when the user says 'dev this story' or 'implement the next story'."
+---
+
+# Dev Story
+
+Implement a story following TDD and strict adherence to specs.
+
+## Process
+
+1. Read the ENTIRE story file before any implementation
+2. Execute tasks/subtasks IN ORDER as written
+3. For each task:
+   a. Write tests first (TDD)
+   b. Implement minimum code to pass
+   c. Run full test suite
+   d. Mark task complete only when tests pass
+4. Update Dev Agent Record with decisions
+5. Update File List with all changed files
+6. Final test suite must pass 100%
+
+## Critical Rules
+
+- NEVER skip or reorder tasks
+- NEVER lie about tests passing
+- NEVER proceed with failing tests

package/templates/.claude/skills/bmad-distillator/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: bmad-distillator
+description: "Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'."
+---
+
+# Distillator
+
+Compress documents into token-efficient distillates without losing information.
+
+## Stages
+
+1. **Analyze**: Identify document structure, key concepts, and relationships
+2. **Compress**: Remove redundancy while preserving all facts, decisions, and context
+3. **Verify**: Ensure no information was lost in compression
+4. **Output**: Produce distillate with frontmatter metadata
+
+## Rules
+
+- Zero information loss — every fact must survive compression
+- Optimize for LLM consumption (structured, scannable)
+- Use abbreviations and shorthand consistently
+- Maintain hierarchical relationships

package/templates/.claude/skills/bmad-document-project/SKILL.md

@@ -0,0 +1,27 @@
+---
+name: bmad-document-project
+description: "Document brownfield projects for AI context. Use when the user says 'document this project' or 'generate project docs'."
+---
+
+# Document Project
+
+Analyze an existing codebase and produce comprehensive documentation for both human and LLM consumption.
+
+## Process
+
+1. Scan the project structure (directories, key files, configs)
+2. Identify the tech stack, frameworks, and architecture patterns
+3. Read key files (README, package.json, main entry points, configs)
+4. Generate structured documentation covering:
+   - Project overview and purpose
+   - Tech stack and dependencies
+   - Architecture and directory structure
+   - Key components and their responsibilities
+   - API endpoints (if applicable)
+   - Configuration and environment variables
+   - Build and deployment instructions
+5. Output as markdown optimized for both humans and AI context
+
+## Output
+
+Save to `docs/project-documentation.md` or the user's preferred location.

package/templates/.claude/skills/bmad-domain-research/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: bmad-domain-research
+description: "Conduct domain and industry research. Use when the user wants to do domain research for a topic or industry."
+---
+
+# Domain Research
+
+Deep dive into an industry domain to build subject matter expertise.
+
+## Process
+
+1. Identify the domain/industry to research
+2. Research key terminology, concepts, and frameworks
+3. Map the regulatory landscape and compliance requirements
+4. Identify industry leaders, standards, and best practices
+5. Document domain-specific patterns and anti-patterns
+6. Compile findings into a structured research report
+
+## Output
+
+Save to planning artifacts as `domain-research.md`.

package/templates/.claude/skills/bmad-edit-prd/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: bmad-edit-prd
+description: "Edit an existing PRD. Use when the user says 'edit this PRD'."
+---
+
+# Edit PRD
+
+Update an existing Product Requirements Document based on new information or feedback.
+
+## Process
+
+1. Read the existing PRD
+2. Understand what changes are needed
+3. Validate changes against existing architecture and UX specs
+4. Apply updates maintaining document coherence
+5. Highlight what changed and why
+
+Save updated PRD in place.