# Multi-agent system design (/ai--multi-agent)

/ai--multi-agent is a Claude Code skill in the AI & Agents section. Designs a system of several AI agents with an orchestration pattern, contracts between agents and failure handling, or advises a single agent instead.

- Web version: https://skills.sgomez.dev/en/s/ai--multi-agent
- Section: [AI & Agents](https://skills.sgomez.dev/en/ai.md)
- Author: Santiago Gómez de la Torre
- License: MIT
- Source: https://github.com/sgomez-dev/claude-skills/blob/main/skills/ai/multi-agent.md
- Updated 10 Jul 2026

## How to ask for it

- `/ai--multi-agent design an orchestrator that splits work across agents`
- `/ai--multi-agent how do I hand off a conversation between two agents?`
- `/ai--multi-agent what happens if one of my agents fails mid-flow`

## Install

macOS · Linux:

```
curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash
```

Windows:

```
irm https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.ps1 | iex
```

Claude Code plugin:

```
/plugin marketplace add sgomez-dev/claude-skills
/plugin install ai-skills@claude-skills-collection
```

## Permissions

- Reads: `**/*`
- Writes: `**/*`
- Runs: —
- Network: No
- Destructive: No

## Author's description

Design multi-agent systems: orchestrator patterns, handoffs, shared state, failure modes

- [How we review this](https://skills.sgomez.dev/en/methodology.md)