cc-skill:crewai-multi-agent
Claude Code skill · anthropic · active
This skill helps you build a multi-agent system using CrewAI, where several AI agents with different roles collaborate to solve a complex problem. It guides you through defining what each agent is, what they do, how they work together (either in sequence or with a manager), and what tools they need.
Someone who needs to automate complex work that requires multiple perspectives or specialized roles, like market research with a researcher and a writer, or customer support with specialists handling different categories.
When you mention CrewAI, multi-agent systems, agent crews, agent roles, or talk about building systems where multiple agents with different jobs work together.
- "Build a CrewAI crew that researches competitors and then writes a summary report"
- "I need a multi-agent system where one agent finds data and another analyzes it"
- "Design a hierarchical crew for customer support that routes issues to specialists"
You see code that defines distinct Agent objects with specific roles, Task objects with clear expected outputs, and a Crew object that orchestrates them together, typically with verbose output enabled so you can watch each step.
Deploy this skill
no laptop requiredRun this skill on a schedule in the cloud. Pipe output to Telegram, email, or any webhook. Every run is logged here with full output, cost, and thumbs feedback.
How this performs
Cloud-automation runs, real outputs, and feedback.
No cloud runs yet for this skill.
Once you deploy it (above), every run will show up here with the actual output, exact cost, and a thumbs button so you can rate quality over time.
Claude Code skill at /Users/olanrewajukareem/.claude/skills/crewai-multi-agent/SKILL.md. Auto-triggered by description matching when you type in Claude Code, OR embedded into agent system prompts (LeadFlow framework skills are wired this way). Auto-synced from disk every 6h via launchd.
Use this skill when building multi-agent systems with CrewAI, including agent definition, task design, crew composition (sequential vs hierarchical), tool integration, and memory. Triggers on "CrewAI", "Crew AI", "multi-agent system", "agent crew", "
Local Claude Code use (optional)
Install the SKILL.md file locally so this skill is available the next time you open Claude Code on your Mac. Most users skip this and just use cloud deployments above.
Save this skill to ~/.claude/skills/crewai-multi-agent/SKILL.md so Claude Code auto-loads it whenever its description matches your prompt.
{
"source": "global",
"description": "Use this skill when building multi-agent systems with CrewAI, including agent definition, task design, crew composition (sequential vs hierarchical), tool integration, and memory. Triggers on \"CrewAI\", \"Crew AI\", \"multi-agent system\", \"agent crew\", \"agent role\", \"agent task\", \"sequential crew\", \"hierarchical crew\". Different from langgraph-patterns (state graphs) and agent-sdk-patterns (Claude Agent SDK)."
}{
"method": "embed_in_prompt",
"skill_path": "/Users/olanrewajukareem/.claude/skills/crewai-multi-agent/SKILL.md"
}That means either: (a) the system has not had a task that matched its strengths, (b) a more cost-effective alternative was picked by the router, or (c) the related automation is toggled OFF on /automations. The Recommender reviews idle tools weekly and may suggest killing it.