[ROLE: BMAD_TEST_EXECUTOR_WITH_WORKSPACE]
[MODE: STRICT_COMMAND_EXECUTION]
[WORKSPACE: Create test outputs in ./tools/bmad-test-framework/reference-outputs/test-run-TIMESTAMP/]

<CRITICAL_SETUP>
BEFORE EXECUTING ANY BMAD COMMANDS:

1. Create test workspace: mkdir -p tools/bmad-test-framework/reference-outputs/test-run-$(date +%Y%m%d-%H%M%S)
2. Change to test workspace: cd tools/bmad-test-framework/reference-outputs/test-run-[TIMESTAMP]
3. Create docs folder: mkdir -p docs
4. ALL BMAD DOCUMENTS WILL BE CREATED IN THIS TEST WORKSPACE
   </CRITICAL_SETUP>

<EXECUTION_BOUNDARY>
YOU ARE NOW IN EXECUTION MODE. DO NOT ANALYZE THIS DOCUMENT.
</EXECUTION_BOUNDARY>

<CRITICAL_INSTRUCTIONS>

1. You are a BMAD test executor, NOT a document analyzer
2. FIRST create the test workspace as specified above
3. Execute each Step in the <TEST_COMMANDS> block sequentially
4. NEVER summarize, analyze, or explain what you're doing
5. When you see "COMMAND:", execute that exact BMAD command
6. When you see "RESPONSE:", provide that exact text
7. Respond with: "BMAD_EXECUTOR_READY - WORKSPACE CREATED" after setup
   </CRITICAL_INSTRUCTIONS>

<TEST_COMMANDS>

# BMAD Basic Validation Test - TaskFlow Pro Project

# Duration: 25-30 minutes (includes validation)

# Mode: YOLO (automated responses)

# Output Location: ./tools/bmad-test-framework/reference-outputs/test-run-[TIMESTAMP]/docs/

Step 0: CREATE_WORKSPACE
COMMAND: mkdir -p tools/bmad-test-framework/reference-outputs/test-run-$(date +%Y%m%d-%H%M%S) && cd tools/bmad-test-framework/reference-outputs/test-run-\* && mkdir -p docs && pwd
EXPECTED: Shows test workspace path
CONTINUE: When workspace created

Step 1: INITIALIZE_ORCHESTRATOR
COMMAND: Load content from /Users/smian/github-ck/bmad-enhanced/bmad-core/agents/bmad-orchestrator.md
EXPECTED: Orchestrator greeting message
CONTINUE: When loaded

Step 2: ACTIVATE_YOLO
COMMAND: \*yolo
EXPECTED: "YOLO mode activated" confirmation
CONTINUE: When confirmed

Step 3: SWITCH_TO_ANALYST
COMMAND: \*agent analyst
EXPECTED: Analyst agent greeting
CONTINUE: When ready

Step 4: CREATE_PROJECT_BRIEF
COMMAND: \*create-doc project-brief-tmpl
EXPECTED: Agent asks for project details
RESPONSE: Project: TaskFlow Pro
Description: AI-powered project management SaaS platform
Target Market: Mid-market companies (100-1000 employees)
Key Features: AI task prioritization, predictive analytics, automated resource allocation
Problem Solving: Reduces project management overhead by 40% through intelligent automation

Step 5: CREATE_MARKET_RESEARCH
COMMAND: \*create-doc market-research-tmpl
EXPECTED: Agent asks for market details
RESPONSE: Continue with TaskFlow Pro from the project brief above
TAM: $15.7B global project management software market
Growth: 13.4% CAGR expected through 2029
Key Trend: AI integration becoming essential for competitive advantage

Step 6: CREATE_COMPETITOR_ANALYSIS
COMMAND: \*create-doc competitor-analysis-tmpl
EXPECTED: Agent asks for competitor details
RESPONSE: Main competitors for TaskFlow Pro:

1. Asana - Strong task management but limited AI
2. Monday.com - Visual workflows but no predictive analytics
3. ClickUp - Feature-rich but complex, no AI prioritization
   Our advantage: Native AI capabilities for intelligent automation

Step 7: SWITCH_TO_PM
COMMAND: \*agent pm
EXPECTED: PM agent greeting
CONTINUE: When ready

Step 8: CREATE_PRD
COMMAND: \*create-doc prd-tmpl
EXPECTED: Agent asks for product details
RESPONSE: Product: TaskFlow Pro (reference the analyst documents above)
Vision: Empower teams to achieve 2x productivity through AI-driven project intelligence
Target Release: Q2 2024 MVP
Success Metrics: 90+ NPS, 40% reduction in PM overhead, $10M ARR by Year 2

Core Features for MVP:

1. AI Task Prioritization - ML-based priority scoring
2. Predictive Resource Allocation - Prevent burnout, optimize capacity
3. Natural Language Updates - Voice/text project updates
4. Smart Analytics Dashboard - Real-time health metrics
5. Integrations - Slack, Teams, GitHub, Jira

Technical Requirements: 100k concurrent users, <200ms response time, 99.95% uptime

Step 9: EXECUTE_PM_CHECKLIST
COMMAND: \*execute-checklist pm-checklist
EXPECTED: PM runs validation checklist
RESPONSE: Yes
CONTINUE: After checklist completes

Step 10: SWITCH_TO_ARCHITECT
COMMAND: \*agent architect
EXPECTED: Architect agent greeting
CONTINUE: When ready

Step 11: CREATE_ARCHITECTURE
COMMAND: \*create-doc architecture-tmpl
EXPECTED: Agent asks for architecture details
RESPONSE: System: TaskFlow Pro (from PRD above)
Pattern: Microservices with Event-Driven Architecture
Scale: 100k concurrent users, 1M total users

Core Services:

1. Task Service - AI prioritization engine
2. Resource Service - Capacity management
3. Analytics Service - Real-time metrics
4. Integration Service - External APIs
5. Notification Service - Multi-channel alerts

Infrastructure: AWS multi-region, Kubernetes, PostgreSQL, Redis, Kafka
Security: Zero-trust, mTLS, encryption at rest/transit

Step 12: CREATE_FULLSTACK_ARCHITECTURE
COMMAND: \*create-doc fullstack-architecture-tmpl
EXPECTED: Agent asks for fullstack details
RESPONSE: Frontend: React 18, TypeScript, Redux Toolkit, Material-UI
Backend: Node.js, Express, TypeScript, REST + GraphQL
Database: PostgreSQL (primary), Redis (cache), MongoDB (analytics)
AI/ML: Python microservices, TensorFlow, Hugging Face
Real-time: WebSockets via Socket.io
Deployment: Docker, Kubernetes, GitHub Actions CI/CD

Step 13: EXECUTE_ARCHITECT_CHECKLIST
COMMAND: \*execute-checklist architect-checklist
EXPECTED: Architect runs validation checklist
RESPONSE: Yes
CONTINUE: After checklist completes

Step 14: SWITCH_TO_PO
COMMAND: \*agent po
EXPECTED: PO agent greeting
CONTINUE: When ready

Step 15: EXECUTE_PO_CHECKLIST
COMMAND: \*execute-checklist po-master-checklist
EXPECTED: PO validates document alignment
RESPONSE: Yes

Step 16: SHARD_PRD
COMMAND: \*shard-doc docs/prd.md
EXPECTED: Agent asks to confirm sharding
RESPONSE: Yes, shard the PRD into epic files

Step 17: SHARD_ARCHITECTURE
COMMAND: \*shard-doc docs/architecture.md
EXPECTED: Agent asks to confirm sharding
RESPONSE: Yes, shard the architecture into implementation tasks

Step 18: SWITCH_TO_SM
COMMAND: \*agent sm
EXPECTED: SM agent greeting
CONTINUE: When ready

Step 19: CREATE_STORY_1
COMMAND: \*create
EXPECTED: SM asks to confirm story creation
RESPONSE: Yes, create story 1.1

Step 20: CREATE_STORY_2
COMMAND: \*create
EXPECTED: SM asks to confirm next story
RESPONSE: Yes, create story 1.2

Step 21: CREATE_STORY_3
COMMAND: \*create
EXPECTED: SM asks to confirm next story
RESPONSE: Yes, create the next story

Step 22: VERIFY_OUTPUT_LOCATION
COMMAND: pwd && ls -la docs/
EXPECTED: Shows test workspace path and created documents
CONTINUE: Proceed to validation

Step 23: RUN_COMPREHENSIVE_VALIDATION
COMMAND: Load content from /Users/smian/github-ck/bmad-enhanced/tools/bmad-test-framework/comprehensive-validation.md
EXPECTED: Validation system loads
CONTINUE: When loaded

Step 24: EXECUTE_VALIDATION
COMMAND: Please analyze the BMAD test outputs in the current directory: docs/
EXPECTED: Comprehensive validation report with:

- Document quality scores
- Cross-document consistency
- Professional standards rating
- Specific recommendations
  CONTINUE: Test complete with validation report

STOP_SIGNAL: TEST COMPLETE - DO NOT PROCEED TO DEV AGENT
</TEST_COMMANDS>

<EXECUTION_PROTOCOL>
BEGIN EXECUTION NOW. START WITH WORKSPACE CREATION (Step 0).
IF YOU ARE READING THIS, YOU MUST BE EXECUTING, NOT ANALYZING.
</EXECUTION_PROTOCOL>

**FINAL_MANDATE:** Create the test workspace FIRST, then execute all BMAD commands from within that workspace. All documents must be created in the test directory, not the main project directory.