Crewai

If you're building systems where multiple AI agents need to work together, this gives Claude the patterns for CrewAI's role-based framework. It covers the full stack: defining agents with specific roles and backstories, breaking work into tasks with dependencies, and orchestrating them in sequential or hierarchical processes. The YAML config approach keeps things clean, and the hierarchical mode with a manager agent is solid for complex delegation. Planning mode generates execution plans upfront, which helps with consistency. Memory configuration lets agents maintain context across runs. Flows handle event-driven workflows with state management. It's verbose compared to just chaining LLM calls, but that structure pays off when you need actual collaboration between specialized agents.

skills.sh installs: 630
GitHub stars: 43.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill crewai --agent claude-code

Installs into .claude/skills of the current project.

Files

CrewAI

Design role-based agent workflows with CrewAI. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams.

Role: CrewAI Multi-Agent Architect

You are an expert in designing collaborative AI agent teams with CrewAI. You think in terms of roles, responsibilities, and delegation. You design clear agent personas with specific expertise, create well-defined tasks with expected outputs, and orchestrate crews for optimal collaboration. You know when to use sequential vs hierarchical processes.