/multi-workflow Command
Multi-model collaborative development workflow (Research → Ideation → Plan → Execute → Optimize → Review), with intelligent routing: Frontend → Gemini, Backend → Codex.Command Syntax
Description of the task to develop
Collaborative Models
- ace-tool MCP - Code retrieval + Prompt enhancement
- Codex - Backend logic, algorithms, debugging (Backend authority)
- Gemini - Frontend UI/UX, visual design (Frontend expert)
- Claude (self) - Orchestration, planning, execution, delivery
Execution Workflow
Phase 1: Research & Analysis
[Mode: Research] - Understand requirements and gather context:
- Prompt Enhancement: Call
mcp__ace-tool__enhance_prompt - Context Retrieval: Call
mcp__ace-tool__search_context - Requirement Completeness Score (0-10):
- ≥7: Continue
- <7: Stop, ask clarifying questions
Phase 2: Solution Ideation
[Mode: Ideation] - Multi-model parallel analysis:
Parallel Calls (run_in_background: true):
- Codex: Technical feasibility, solutions, risks
- Gemini: UI feasibility, solutions, UX evaluation
CODEX_SESSION and GEMINI_SESSION)
Synthesize both analyses, output solution comparison (at least 2 options), wait for user selection.
Phase 3: Detailed Planning
[Mode: Plan] - Multi-model collaborative planning:
Parallel Calls (resume session with resume <SESSION_ID>):
- Codex: Backend architecture
- Gemini: Frontend architecture
.claude/plan/task-name.md after user approval.
Phase 4: Implementation
[Mode: Execute] - Code development:
- Strictly follow approved plan
- Follow existing project code standards
- Request feedback at key milestones
Phase 5: Code Optimization
[Mode: Optimize] - Multi-model parallel review:
Parallel Calls:
- Codex: Security, performance, error handling
- Gemini: Accessibility, design consistency
Phase 6: Quality Review
[Mode: Review] - Final evaluation:
- Check completion against plan
- Run tests to verify functionality
- Report issues and recommendations
- Request final user confirmation
Communication Guidelines
- Start responses with mode label
[Mode: X], initial is[Mode: Research] - Follow strict sequence:
Research → Ideation → Plan → Execute → Optimize → Review - Request user confirmation after each phase completion
- Force stop when score < 7 or user does not approve
- Use
AskUserQuestiontool for user interaction
Examples
Key Rules
- Phase sequence cannot be skipped (unless user explicitly instructs)
- External models have zero filesystem write access
- Force stop when score < 7 or user does not approve
Related
- Commands:
/multi-plan,/multi-execute,/multi-backend,/multi-frontend