Multi-AI Pipeline Orchestrator
You are starting the multi-AI pipeline. Follow this process exactly.
Reference Documents
First, read the standards that guide all reviews:
skill/multi-ai/reference/standards.md- Coding standards and review criteria
Step 1: Clean Up Previous Task
Remove old .task/ directory if it exists:
bash1rm -rf .task 2mkdir -p .task
Step 2: Capture User Request
Write the user's request to .task/user-request.txt.
Step 3: Create Initial Plan
Write .task/plan.json:
json1{ 2 "id": "plan-YYYYMMDD-HHMMSS", 3 "title": "Short descriptive title", 4 "description": "What the user wants to achieve", 5 "requirements": ["req1", "req2"], 6 "created_at": "ISO8601", 7 "created_by": "claude" 8}
Step 4: Refine Plan
Research the codebase and create .task/plan-refined.json:
json1{ 2 "id": "plan-001", 3 "title": "Feature title", 4 "description": "What the user wants", 5 "requirements": ["req1", "req2"], 6 "technical_approach": "Detailed how-to", 7 "files_to_modify": ["path/to/file.ts"], 8 "files_to_create": ["path/to/new.ts"], 9 "dependencies": [], 10 "estimated_complexity": "low|medium|high", 11 "potential_challenges": ["Challenge and mitigation"], 12 "refined_by": "claude", 13 "refined_at": "ISO8601" 14}
Step 5: Sequential Plan Reviews
Run reviews in sequence. Fix issues after each before continuing:
-
Invoke /review-sonnet
- Read
.task/review-sonnet.jsonresult - If
needs_changes: fix issues in plan, update.task/plan-refined.json
- Read
-
Invoke /review-codex
- Read
.task/review-codex.jsonresult - If
needs_changes: fix issues and restart from step 5.1 - If
approved: continue to implementation
- Read
Step 6: Implement
Invoke /implement-sonnet
This skill will:
- Read the approved plan from
.task/plan-refined.json - Implement the code
- Add tests
- Output to
.task/impl-result.json
Step 7: Sequential Code Reviews
Run reviews in sequence. Fix issues after each before continuing:
-
Invoke /review-sonnet
- Read
.task/review-sonnet.jsonresult - If
needs_changes: fix code issues
- Read
-
Invoke /review-codex
- Read
.task/review-codex.jsonresult - If
needs_changes: fix issues and restart from step 7.1 - If
approved: continue to completion
- Read
Step 8: Complete
Write .task/state.json:
json1{ 2 "state": "complete", 3 "plan_id": "plan-001", 4 "completed_at": "ISO8601" 5}
Report success to the user with:
- Summary of what was implemented
- Files changed
- Tests added
Important Rules
- Follow this process exactly - no shortcuts
- Fix ALL issues raised by reviewers before continuing
- If codex rejects, restart the review cycle from sonnet
- Keep the user informed of progress at each major step
State Files Reference
| File | Purpose |
|---|---|
.task/user-request.txt | Original user request |
.task/plan.json | Initial plan |
.task/plan-refined.json | Refined plan with technical details |
.task/impl-result.json | Implementation result |
.task/review-sonnet.json | Sonnet review output |
.task/review-codex.json | Codex review output |
.task/state.json | Pipeline state |
Reference Directory
| Path | Purpose |
|---|---|
skill/multi-ai/reference/standards.md | Review criteria and coding standards |
skill/multi-ai/reference/schemas/ | JSON schemas for structured output |