multi-ai
Start the multi-AI pipeline with a given request. Guides through plan -> review -> implement -> review workflow.
Best use case
multi-ai is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Start the multi-AI pipeline with a given request. Guides through plan -> review -> implement -> review workflow.
Teams using multi-ai should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/multi-ai/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How multi-ai Compares
| Feature / Agent | multi-ai | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Start the multi-AI pipeline with a given request. Guides through plan -> review -> implement -> review workflow.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# 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:
```bash
rm -rf .task
mkdir -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`:
```json
{
"id": "plan-YYYYMMDD-HHMMSS",
"title": "Short descriptive title",
"description": "What the user wants to achieve",
"requirements": ["req1", "req2"],
"created_at": "ISO8601",
"created_by": "claude"
}
```
## Step 4: Refine Plan
Research the codebase and create `.task/plan-refined.json`:
```json
{
"id": "plan-001",
"title": "Feature title",
"description": "What the user wants",
"requirements": ["req1", "req2"],
"technical_approach": "Detailed how-to",
"files_to_modify": ["path/to/file.ts"],
"files_to_create": ["path/to/new.ts"],
"dependencies": [],
"estimated_complexity": "low|medium|high",
"potential_challenges": ["Challenge and mitigation"],
"refined_by": "claude",
"refined_at": "ISO8601"
}
```
## Step 5: Sequential Plan Reviews
Run reviews in sequence. Fix issues after each before continuing:
1. **Invoke /review-sonnet**
- Read `.task/review-sonnet.json` result
- If `needs_changes`: fix issues in plan, update `.task/plan-refined.json`
2. **Invoke /review-codex**
- Read `.task/review-codex.json` result
- If `needs_changes`: fix issues and **restart from step 5.1**
- If `approved`: continue to implementation
## 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:
1. **Invoke /review-sonnet**
- Read `.task/review-sonnet.json` result
- If `needs_changes`: fix code issues
2. **Invoke /review-codex**
- Read `.task/review-codex.json` result
- If `needs_changes`: fix issues and **restart from step 7.1**
- If `approved`: continue to completion
## Step 8: Complete
Write `.task/state.json`:
```json
{
"state": "complete",
"plan_id": "plan-001",
"completed_at": "ISO8601"
}
```
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 |Related Skills
error-debugging-multi-agent-review
Use when working with error debugging multi agent review
agent-multi-repo-swarm
Agent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarm
multimodal-doc-converter
Parse and convert multimodal documents (PDF, DOCX, etc.) into structured Markdown with minimal information loss. Use this skill when users need to: (1) convert documents containing text, images, and audio into Markdown format, (2) extract and OCR text from embedded images, (3) recognize and render mathematical formulas, (4) transcribe embedded audio files, (5) preserve document structure and reading order during conversion. Trigger on requests like "convert this PDF to markdown", "extract content from this document", "turn this docx into markdown with OCR".
ai-multimodal
Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (better image analysis than Claude models, captioning, reasoning, object detection, design extraction, OCR, visual Q&A, segmentation, handle multiple images), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image with Imagen 4, editing, composition, refinement), generate videos (text-to-video with Veo 3, 8-second clips with native audio). Use when working with audio/video files, analyzing images or screenshots (instead of default vision capabilities of Claude, only fallback to Claude's vision capabilities if needed), processing PDF documents, extracting structured data from media, creating images/videos from text prompts, or implementing multimodal AI features. Supports Gemini 3/2.5, Imagen 4, and Veo 3 models with context windows up to 2M tokens.
u08983-ethical-dilemma-navigation-for-multilingual-translation-services
Operate the "Ethical Dilemma Navigation for multilingual translation services" capability in production for multilingual translation services workflows. Use when mission execution explicitly requires this capability and outcomes must be reproducible, policy-gated, and handoff-ready.
multipar-cli
Comprehensive guide for MultiPar CLI - PAR2 recovery file creation and verification tool. Use when creating redundancy archives, verifying file integrity, or repairing corrupted files. Triggers on: multipar, par2, recovery files, file verification, par2j, parity archive, data recovery, file repair.
github-multi-repo
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration
ado-multi-project
Organize specs and tasks across multiple Azure DevOps projects with intelligent content-based mapping. Use when working with project-per-team, area-path-based, or team-based ADO architectures. Handles cross-project coordination and folder structure organization.
multi-platform-apps-multi-platform
Build and deploy the same feature consistently across web, mobile, and desktop platforms using API-first architecture and parallel implementation strategies.
u0542-engineering-multi-agent-negotiation-mediator
Operate the "Engineering Multi-Agent Negotiation Mediator" capability in production for workflows. Use when mission execution explicitly requires this capability and outcomes must be reproducible, policy-gated, and handoff-ready.
multi-perspective
Execute the same request with 5 different specialized agents in parallel, then synthesize results with a reviewer agent to produce the best possible outcome. Use when users want comprehensive analysis from multiple perspectives, ensemble-style problem solving, or want to compare different approaches to the same task. Triggers on phrases like "multiple perspectives", "5 agents", "ensemble analysis", "compare approaches", or "/multi-perspective".
multi-model-reviewer
協調多個 AI 模型（ChatGPT、Gemini、Codex、QWEN、Claude）進行三角驗證，確保「Specification == Program == Test」一致性。過濾假警報後輸出報告，大幅減少人工介入時間。