BEFORE doing ANYTHING else, when you see ANY task management scenario:
Sign in to like and favorite skills
BEFORE doing ANYTHING else, when you see ANY task management scenario:
VIOLATION CHECK: If you used TodoWrite first, you violated this rule. Stop and restart with Archon.
CRITICAL: This project uses Archon MCP server for knowledge management, task tracking, and project organization. ALWAYS start with Archon MCP server task management.
MANDATORY: Always complete the full Archon specific task cycle before any coding:
archon:manage_task(action="get", task_id="...")archon:search_code_examples()archon:perform_rag_query()archon:manage_task(action="update", task_id="...", update_fields={"status": "review"})archon:manage_task(action="list", filter_by="status", filter_value="todo")NEVER skip task updates with the Archon MCP server. NEVER code without checking current tasks first.
# Create project container archon:manage_project( action="create", title="Descriptive Project Name", github_repo="github.com/user/repo-name" ) # Research → Plan → Create Tasks (see workflow below)
# First, analyze existing codebase thoroughly # Read all major files, understand architecture, identify current state # Then create project container archon:manage_project(action="create", title="Existing Project Name") # Research current tech stack and create tasks for remaining work # Focus on what needs to be built, not what already exists
# Check existing project status archon:manage_task(action="list", filter_by="project", filter_value="[project_id]") # Pick up where you left off - no new project creation needed # Continue with standard development iteration workflow
For all scenarios, research before task creation:
# High-level patterns and architecture archon:perform_rag_query(query="[technology] architecture patterns", match_count=5) # Specific implementation guidance archon:search_code_examples(query="[specific feature] implementation", match_count=3)
Create atomic, prioritized tasks:
task_orderMANDATORY: Always check task status before writing any code:
# Get current project status archon:manage_task( action="list", filter_by="project", filter_value="[project_id]", include_closed=false ) # Get next priority task archon:manage_task( action="list", filter_by="status", filter_value="todo", project_id="[project_id]" )
For each task, conduct focused research:
# High-level: Architecture, security, optimization patterns archon:perform_rag_query( query="JWT authentication security best practices", match_count=5 ) # Low-level: Specific API usage, syntax, configuration archon:perform_rag_query( query="Express.js middleware setup validation", match_count=3 ) # Implementation examples archon:search_code_examples( query="Express JWT middleware implementation", match_count=3 )
Research Scope Examples:
1. Get Task Details:
archon:manage_task(action="get", task_id="[current_task_id]")
2. Update to In-Progress:
archon:manage_task( action="update", task_id="[current_task_id]", update_fields={"status": "doing"} )
3. Implement with Research-Driven Approach:
search_code_examplesperform_rag_queryget_project_features4. Complete Task:
archon:manage_task( action="update", task_id="[current_task_id]", update_fields={"status": "review"} )
Use RAG for both high-level and specific technical guidance:
# Architecture & patterns archon:perform_rag_query(query="microservices vs monolith pros cons", match_count=5) # Security considerations archon:perform_rag_query(query="OAuth 2.0 PKCE flow implementation", match_count=3) # Specific API usage archon:perform_rag_query(query="React useEffect cleanup function", match_count=2) # Configuration & setup archon:perform_rag_query(query="Docker multi-stage build Node.js", match_count=3) # Debugging & troubleshooting archon:perform_rag_query(query="TypeScript generic type inference error", match_count=2)
Search for implementation patterns before coding:
# Before implementing any feature archon:search_code_examples(query="React custom hook data fetching", match_count=3) # For specific technical challenges archon:search_code_examples(query="PostgreSQL connection pooling Node.js", match_count=2)
Usage Guidelines:
Start of each coding session:
archon:get_available_sources()archon:manage_task(action="list", filter_by="project", filter_value="...")task_orderEnd of each coding session:
Status Progression:
tododoingreviewdonereviewarchiveStatus Update Examples:
# Move to review when implementation complete but needs testing archon:manage_task( action="update", task_id="...", update_fields={"status": "review"} ) # Complete task after review passes archon:manage_task( action="update", task_id="...", update_fields={"status": "done"} )
Research checklist:
Query Strategy:
Use features to organize related tasks:
# Get current project features archon:get_project_features(project_id="...") # Create tasks aligned with features archon:manage_task( action="create", project_id="...", title="...", feature="Authentication", # Align with project features task_order=8 )
If knowledge queries return empty results:
If task scope becomes uncertain:
When requirements evolve:
task_orderCRITICAL: Skills provide domain-specific execution guidance that complements Archon's orchestration layer.
Skills are specialized experts invoked DURING Archon task execution for domain-specific implementation guidance.
Archon Task Retrieved ↓ Analyze Task Domain ↓ ┌─────────────────────────────────────────────────────┐ │ TASK TYPE → INVOKE SKILL(S) │ ├─────────────────────────────────────────────────────┤ │ Frontend/UI work → frontend-builder │ │ → visual-designer │ │ → ux-designer │ ├─────────────────────────────────────────────────────┤ │ API Development → api-designer │ │ → security-engineer │ ├─────────────────────────────────────────────────────┤ │ Performance issues → performance-optimizer │ ├─────────────────────────────────────────────────────┤ │ Testing/Quality → testing-strategist │ │ → security-engineer │ ├─────────────────────────────────────────────────────┤ │ RAG/Knowledge systems → rag-implementer │ │ → knowledge-graph-builder │ ├─────────────────────────────────────────────────────┤ │ Data/Analytics → data-engineer │ │ → data-visualizer │ ├─────────────────────────────────────────────────────┤ │ Documentation → technical-writer │ ├─────────────────────────────────────────────────────┤ │ MVP/Strategy → mvp-builder │ │ → product-strategist │ └─────────────────────────────────────────────────────┘
Complete workflow combining both systems:
┌────────────────────────────────────────────────────────────┐ │ PHASE 1: STRATEGIC PLANNING (Archon Layer) │ └────────────────────────────────────────────────────────────┘ 1. Check Archon project status archon:manage_task(action="list", filter_by="project", filter_value="[id]") 2. Get next priority task (highest task_order in "todo" status) archon:manage_task(action="get", task_id="[task_id]") 3. Conduct Archon research • High-level patterns: archon:perform_rag_query(query="[domain] architecture patterns", match_count=5) • Implementation examples: archon:search_code_examples(query="[specific feature] implementation", match_count=3) 4. Update task to "doing" archon:manage_task(action="update", task_id="[task_id]", update_fields={"status": "doing"}) ┌────────────────────────────────────────────────────────────┐ │ PHASE 2: TACTICAL EXECUTION (Skills Layer) │ └────────────────────────────────────────────────────────────┘ 5. Identify required domain expertise → Analyze task requirements → Determine which skill(s) provide relevant expertise → Example: "Build visualization dashboard" → frontend-builder + visual-designer + data-visualizer 6. Invoke relevant skill(s) for implementation guidance → Skills provide: • Technology-specific best practices • Code structure and patterns • Quality standards for domain • Common pitfalls to avoid 7. Implement following BOTH: → Archon research findings (what patterns work generally) → Skill guidance (how to implement well in specific domain) → Cross-reference for validation ┌────────────────────────────────────────────────────────────┐ │ PHASE 3: QUALITY VALIDATION (Dual-Layer Check) │ └────────────────────────────────────────────────────────────┘ 8. Apply quality skill checks before marking complete • testing-strategist: Test coverage adequate? • security-engineer: Security review passed? • performance-optimizer: Performance targets met? • accessibility-engineer: A11y compliance verified? 9. Update Archon task to "review" (user validation needed) archon:manage_task(action="update", task_id="[task_id]", update_fields={"status": "review"}) 10. After user validation → Update to "done" archon:manage_task(action="update", task_id="[task_id]", update_fields={"status": "done"}) 11. Get next task and repeat cycle
Concrete examples for current project:
| Archon Task | Priority | Relevant Skills | Rationale |
|---|---|---|---|
| Enhance NLP Analysis | P0 | | RAG expertise for semantic analysis Performance tuning for ML models |
| Add Performance Benchmarks | P0 | | Benchmark design Testing infrastructure |
| Build Visualization Dashboard | P1 | | React/Next.js architecture Design system & styling Chart/graph components User experience flow |
| API Integration Adapters | P1 | | API contract design Auth & validation Integration testing |
| Conversation History Persistence | P1 | | Database design & queries Caching strategies |
| Advanced Filter Configuration | P2 | | Configuration API design User-facing config UI |
| Multi-User Support | P2 | | Auth & authorization Multi-tenant API design Data isolation |
| Documentation Expansion | P2 | | Clear technical docs Documentation site UX |
Archon and Skills provide complementary research capabilities:
Stage 1: Archon Research (Strategic Context)
Goal: Understand general patterns, architectural approaches, best practices archon:perform_rag_query( query="React dashboard architecture patterns", match_count=5 ) → Returns: High-level architecture decisions, design patterns, trade-offs archon:search_code_examples( query="TypeScript drift detection implementation", match_count=3 ) → Returns: Similar implementations from various projects
Stage 2: Skill Guidance (Tactical Implementation)
Goal: Get domain-specific implementation details and standards Invoke: frontend-builder skill → Provides: SI Systems-specific React architecture Next.js project structure Tailwind styling approach Component patterns for this project Invoke: visual-designer skill → Provides: Color palette for drift visualization Typography scale Spacing system Visual hierarchy principles
Task: "Build Visualization Dashboard" (from Archon) ↓ Step 1: Archon Research • archon:perform_rag_query("React real-time data visualization") • archon:search_code_examples("dashboard component React TypeScript") • Result: General patterns, library comparisons (D3, Recharts, Victory) ↓ Step 2: Skill Consultation • Invoke: frontend-builder → Recommendation: Use Recharts with Next.js App Router → File structure: app/dashboard/page.tsx → Server components for data fetching • Invoke: data-visualizer → Chart types for drift metrics (line charts for trends, gauges for scores) → Color coding strategies (green/yellow/red for drift levels) → Responsive design patterns • Invoke: visual-designer → Design system integration → Color palette: Use semantic colors (success, warning, danger) → Typography: Match existing SI Systems brand ↓ Step 3: Implementation • Combine Archon research + Skill guidance • Build dashboard following both sets of insights ↓ Step 4: Quality Check • Invoke: accessibility-engineer → Verify charts have proper ARIA labels → Keyboard navigation support → Color contrast for visual data • Invoke: performance-optimizer → Check rendering performance → Optimize re-renders on data updates ↓ Step 5: Mark Complete in Archon • archon:manage_task(action="update", status="review")
How to choose the right skill(s) for a task:
Primary Domain - What's the main type of work?
Quality Concerns - What could go wrong?
Complexity Level - How specialized is the domain?
Project Phase - Where in the lifecycle?
DON'T do these:
❌ Skip Archon for task management
❌ Use Skills without Archon task context
❌ Invoke too many skills simultaneously
❌ Use Skills for non-domain work
❌ Rely only on Archon OR only on Skills
DO these:
✅ Archon-First, Skills-Enhanced
1. Get task from Archon (strategic layer) 2. Research with Archon RAG + code examples 3. Invoke relevant skill(s) for implementation (tactical layer) 4. Build with combined insights 5. Quality check with appropriate skills 6. Update status in Archon
✅ Two-Stage Research
Archon research → General understanding Skill guidance → Specific implementation Combined → Optimal solution
✅ Progressive Skill Invocation
Primary skill(s) → Get main implementation guidance Quality skill(s) → Verify standards before completion Specialist skill(s) → Address specific concerns as needed
✅ Continuous Task Tracking
Every phase → Update Archon task status Completed work → Mark "review" in Archon User validated → Mark "done" in Archon
Task: "Enhance NLP Analysis for Drift Detection" (Priority: P0)
SESSION START │ ├─ 1. Get Task from Archon │ archon:manage_task(action="get", task_id="task_nlp_enhance") │ → Task details: Replace heuristic tone detection with sentiment analysis │ → Feature: Drift Detection │ → Priority: P0 (3-4 days estimated) │ ├─ 2. Archon Research Phase │ archon:perform_rag_query(query="sentiment analysis TypeScript NLP best practices", match_count=5) │ → Results: Recommendations for sentiment libraries, ML model integration patterns │ │ archon:search_code_examples(query="sentiment analysis implementation Node.js", match_count=3) │ → Results: Real implementations using various libraries │ ├─ 3. Update to "doing" in Archon │ archon:manage_task(action="update", task_id="task_nlp_enhance", update_fields={"status": "doing"}) │ ├─ 4. Invoke Relevant Skills │ │ Skill: rag-implementer │ → Guidance: Use embeddings for semantic similarity │ → Recommendation: Consider OpenAI embeddings or local models │ → Pattern: Create embedding cache for performance │ │ Skill: performance-optimizer │ → Guidance: NLP operations can be slow - add caching layer │ → Recommendation: Cache sentiment analysis results │ → Pattern: Use LRU cache with TTL for frequently analyzed text │ ├─ 5. Implementation │ • Install sentiment analysis library (based on Archon research) │ • Implement semantic similarity (following rag-implementer guidance) │ • Add caching layer (following performance-optimizer guidance) │ • Write tests for new NLP features │ ├─ 6. Quality Validation │ │ Skill: testing-strategist │ → Verify: Unit tests for sentiment analysis │ → Verify: Integration tests for drift detection with new NLP │ → Verify: Performance benchmarks (target: <100ms) │ │ Skill: performance-optimizer (validation check) │ → Run: Performance benchmarks │ → Result: 45ms average (✅ under target) │ ├─ 7. Update to "review" in Archon │ archon:manage_task( │ action="update", │ task_id="task_nlp_enhance", │ update_fields={"status": "review"} │ ) │ ├─ 8. User Validation │ → User tests enhanced NLP │ → User confirms accuracy improvement │ → User approves for completion │ ├─ 9. Mark Complete in Archon │ archon:manage_task( │ action="update", │ task_id="task_nlp_enhance", │ update_fields={"status": "done"} │ ) │ └─ 10. Get Next Task archon:manage_task(action="list", filter_by="status", filter_value="todo") → Next task: "Add Performance Benchmarks" → Repeat cycle SESSION END
What you gain by using Archon + Skills together:
Strategic Coherence (Archon)
Tactical Excellence (Skills)
Compound Intelligence
Quality Assurance
Knowledge Accumulation
Always validate research findings:
Every task must meet these criteria before marking "done":