mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-18 23:16:38 +03:00
Magnus Hedemark
738ec715e7
Each README is written for a human audience, explaining: - What the skill does (not what format it follows) - What benefit the user gets from installing it - Quick setup and usage patterns - When to load/trigger the skill - What scripts, references, and templates it ships data-scientist already had a README — left unchanged. 48 READMEs added across all skill and bundle directories.
CrewAI — Role-Based Multi-Agent Orchestration
An expert-level skill for building role-based multi-agent teams with CrewAI. Agents are defined as Roles with Goals and Backstories; crews are composed with sequential or hierarchical workflows.
Why Install This Skill
When your agent loads this skill, it becomes a CrewAI expert who can:
- Design agent roles — define agents with Role, Goal, Backstory, and tool sets
- Compose crews — sequential and hierarchical process patterns
- Design tasks — structured tasks with expected outputs and context
- Integrate tools — custom tools, LangChain tools, and built-in tools
- Handle callbacks and events — step callbacks, task events, crew completion
- Production considerations — caching, memory, and deployment patterns
What You Get
| Directory | Purpose |
|---|---|
SKILL.md |
Quick-start guide, core paradigm, and framework comparison |
references/ |
Deep dives into agent design, task patterns, crew composition, tools, callbacks, production, and framework comparisons |
Framework Comparison
CrewAI is higher-abstraction than LangGraph (which is a low-level state machine) and more structured than AutoGen (which uses free-form conversations). It's best when you have well-defined roles with clear responsibilities.
Requirements
Python 3.8+ with crewai and crewai-tools packages.