How do I install the AI Orchestration skill?

Run npx skillmds@latest add diegosouzapw/ai-orchestration in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is AI Orchestration safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with AI Orchestration?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is AI Orchestration free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published AI Orchestration?

diegosouzapw (@diegosouzapw) published this skill. Their other Agent Skills are listed on their SkillMD profile.

AI Orchestration by diegosouzapw — Agent Skill

Name: AI Orchestration
Rating: 4.2 (5 reviews)
Author: diegosouzapw

AI Orchestration

Multi-model AI collaboration via orchestrator MCP. Use when seeking second opinions, debugging complex issues, building consensus on architectural decisions, conducting code reviews, or needing external validation on analysis.

diegosouzapw Updated Sep 8, 2026 54 repo stars

File contents

AI CLI Orchestration

Query external AI models (claude, codex, gemini) for second opinions, debugging, consensus building, and expert validation.

Tools Overview

Tool	Mode	Description
`ai_call`	Synchronous	Call AI and wait for result
`ai_spawn`	Async	Start AI in background, get job ID
`ai_fetch`	Async	Get result from spawned AI (with timeout)
`ai_list`	Utility	List all running/completed AI jobs
`ai_review`	Convenience	Spawn all 3 AIs in parallel with same prompt

Role Hierarchy

CLI	Role	Mode	Capabilities
claude	Worker/Peer	Full	Can execute any tool/command
codex	Reviewer	Read-only	Code review, analysis, suggestions
gemini	Researcher	Read-only	Web search, documentation lookup

Parallel Execution (Recommended)

# Spawn all 3 models in parallel
claude_job = ai_spawn(cli="claude", prompt="Analyze this code for bugs...")
codex_job = ai_spawn(cli="codex", prompt="Review this code for patterns...")
gemini_job = ai_spawn(cli="gemini", prompt="Research best practices for...")

# All running simultaneously! Fetch results:
claude_result = ai_fetch(job_id=claude_job.job_id, timeout=120)
codex_result = ai_fetch(job_id=codex_job.job_id, timeout=120)
gemini_result = ai_fetch(job_id=gemini_job.job_id, timeout=120)

# Total time = slowest model (~60s) instead of sum (~180s)

Or use ai_review for convenience:

review = ai_review(prompt="Analyze this architecture decision...", files=["src/"])
claude_result = ai_fetch(job_id=review.jobs["claude"].job_id, timeout=120)

When to Use External Models

Do use when: Stuck on complex bugs, architectural decisions with tradeoffs, need validation before major refactoring, security-sensitive code, want diverse perspectives

Don't use when: Simple work, already confident, just executing known solution

References

Tool parameters: See references/tools.md
Usage patterns: See references/patterns.md
Sub-agents: See references/sub-agents.md

Tips

Use parallel for multi-model: ai_spawn + ai_fetch is 3x faster than sequential
Be specific: Include file paths, error messages, and context
Use appropriate CLI: codex for code review, gemini for web search
Delegate complex work: Use sub-agents for structured analysis
Remember read-only: Codex and Gemini cannot execute commands or modify files
Include files: Use the files parameter to provide code context
Monitor jobs: Use ai_list() to check status of all running jobs

---name: ai-orchestrationdescription: Multi-model AI collaboration via orchestrator MCP. Use when seeking second opinions, debugging complex issues, building consensus on architectural decisions, conducting code reviews, or needing external validation on analysis.---# AI CLI OrchestrationQuery external AI models (claude, codex, gemini) for second opinions, debugging, consensus building, and expert validation.## Tools Overview| Tool | Mode | Description || ----------- | ----------- | -------------------------------------------- || `ai_call` | Synchronous | Call AI and wait for result || `ai_spawn` | Async | Start AI in background, get job ID || `ai_fetch` | Async | Get result from spawned AI (with timeout) || `ai_list` | Utility | List all running/completed AI jobs || `ai_review` | Convenience | Spawn all 3 AIs in parallel with same prompt |## Role Hierarchy| CLI | Role | Mode | Capabilities || ------ | ----------- | --------- | ---------------------------------- || claude | Worker/Peer | Full | Can execute any tool/command || codex | Reviewer | Read-only | Code review, analysis, suggestions || gemini | Researcher | Read-only | Web search, documentation lookup |## Parallel Execution (Recommended)```python# Spawn all 3 models in parallelclaude_job = ai_spawn(cli="claude", prompt="Analyze this code for bugs...")codex_job = ai_spawn(cli="codex", prompt="Review this code for patterns...")gemini_job = ai_spawn(cli="gemini", prompt="Research best practices for...")# All running simultaneously! Fetch results:claude_result = ai_fetch(job_id=claude_job.job_id, timeout=120)codex_result = ai_fetch(job_id=codex_job.job_id, timeout=120)gemini_result = ai_fetch(job_id=gemini_job.job_id, timeout=120)# Total time = slowest model (~60s) instead of sum (~180s)```Or use `ai_review` for convenience:```pythonreview = ai_review(prompt="Analyze this architecture decision...", files=["src/"])claude_result = ai_fetch(job_id=review.jobs["claude"].job_id, timeout=120)```## When to Use External Models**Do use when:** Stuck on complex bugs, architectural decisions with tradeoffs, need validation before major refactoring, security-sensitive code, want diverse perspectives**Don't use when:** Simple work, already confident, just executing known solution## References- **Tool parameters**: See [references/tools.md](references/tools.md)- **Usage patterns**: See [references/patterns.md](references/patterns.md)- **Sub-agents**: See [references/sub-agents.md](references/sub-agents.md)## Tips- **Use parallel for multi-model**: `ai_spawn` + `ai_fetch` is 3x faster than sequential- **Be specific**: Include file paths, error messages, and context- **Use appropriate CLI**: codex for code review, gemini for web search- **Delegate complex work**: Use sub-agents for structured analysis- **Remember read-only**: Codex and Gemini cannot execute commands or modify files- **Include files**: Use the `files` parameter to provide code context- **Monitor jobs**: Use `ai_list()` to check status of all running jobs

Frequently asked questions