AI model or service

CrewAI agent skills for Claude Code, Codex and other agents.

Framework for orchestrating role-playing, collaborative multi-agent AI systems.
skills
32
official
1
Type
AI model or service
Website
crewai.com
Official GitHub
crewAIInc

CrewAI skills, ranked

Ranked by score. Sort bymost stars,trending,newest,recently updated

Official (1 skill)

Official CrewAI skills
#SkillRepositoryStarsUsed inTokensAuto-checkLicenceUpdated
1

Patterns and techniques for adding governance, safety, and trust controls to AI agent systems.

github/awesome-copilot40k2 repos~4.6kAutomated safety check: PassMITtoday

Community

Community CrewAI skills
#SkillRepositoryStarsUsed inTokensAuto-checkLicenceUpdated
2

Adds persistent memory to AI apps with the Mem0 Python and TypeScript SDKs: store, search, update and delete user memories, with framework integrations.

mem0ai/mem067k1 repo~1.9kAutomated safety check: PassApache-2.0yesterday
3

Migrate existing AI agent projects (LangChain, LangGraph, OpenAI Agents SDK, Claude Agent SDK, CrewAI) to EdgeOne Makers platform conventions.

TencentEdgeOne/edgeone-makers-tools1.9k1 repo~4.1kAutomated safety check: PassMIT14 days ago
4

Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior.

JuliusBrussee/caveman110k1 repo~2.6kAutomated safety check: WarnApache-2.0today
5

Scans Python agent code for framework imports and recommends the matching Omnigent executor type, or says when the framework is not natively supported yet.

omnigent-ai/omnigent11k—~610Automated safety check: PassApache-2.0today
6

This skill guides building AI agent endpoints on EdgeOne Makers — five framework routes (DeepAgents, LangGraph, CrewAI, OpenAI Agents SDK, Claude Agent SDK), platform-injected context.store /…

TencentEdgeOne/edgeone-makers-tools1.9k1 repo~5.6kAutomated safety check: NotesMIT14 days ago
7

Deposit and bridge funds into a wallet or protocol using Swapper Finance.

swapperfinance/swapper-toolkit852—~1.8kAutomated safety check: PassMIT6 mo ago
8

Build production-ready AI agent backends using the CloudBase Agent Python SDK — create agents with LangGraph/CrewAI/LlamaIndex, serve them via FastAPI with AG-UI protocol streaming +…

TencentCloudBase/CloudBase-AI-Toolkit1.1k2 repos~2.9kAutomated safety check: NotesMITyesterday
9

Multi-agent orchestration framework for autonomous AI collaboration.

Orchestra-Research/AI-Research-SKILLs13k2 repos~3.4kAutomated safety check: PassMIT3 mo ago
10

SOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, memory, delegation.

agentsope/SkillAlchemy457—~4.8kAutomated safety check: PassMIT1 mo ago
11

EdgeOne Makers platform development router — the single entry point for building, storing data, and deploying on Tencent EdgeOne Makers.

TencentEdgeOne/edgeone-makers-tools1.9k1 repo~516Automated safety check: PassMIT14 days ago
12

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies.

davila7/claude-code-templates32k3 repos~1.5kAutomated safety check: PassMITtoday
13

Build and deploy AI agents with CloudBase Agent SDK (TypeScript & Python).

TencentCloudBase/CloudBase-AI-Toolkit1.1k2 repos~476Automated safety check: PassMITyesterday
14

EdgeOne Makers 全栈开发技能包 —— 涵盖 AI Agent 开发(DeepAgents、LangGraph、 Claude SDK、OpenAI Agents、CrewAI)、云函数(Node.js/Go/Python)、边缘函数、 KV 存储、中间件及快速部署,帮助 AI 编程助手准确高效地在 EdgeOne 平台上构建和发布应用。

TencentEdgeOne/edgeone-makers-tools1.9k—~344Automated safety check: PassMIT14 days ago
15

Agent orchestration patterns for agentic loops, multi-agent coordination, alternative frameworks, and multi-scenario workflows.

yonatangross/orchestkit288—~2.8kAutomated safety check: PassMITyesterday
16

Expert in designing and building autonomous AI agents. An agent skill from omer-metin/skills-for-antigravity.

omer-metin/skills-for-antigravity162—~558Automated safety check: PassApache-2.08 mo ago
17

Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" Synthesizes the ecosystem sections of 7 landmark-project SOPs (LangGraph…

agentsope/SkillAlchemy457—~5.8kAutomated safety check: PassMIT1 mo ago
18

Tool skill — the first move in any LM-debugging session: dump the actual rendered prompt the framework sent to the model, before changing anything else.

agentsope/SkillAlchemy457—~8.4kAutomated safety check: PassMIT1 mo ago
19

Cross-framework enhancement overlay for choosing a multi-agent topology BEFORE writing any agent.

agentsope/SkillAlchemy457—~4.7kAutomated safety check: PassMIT1 mo ago
20

Enhancement overlay for multi-agent / tool-using coder agents.

agentsope/SkillAlchemy457—~4.5kAutomated safety check: PassMIT1 mo ago
21

Step-by-step guide for adding a new agent framework adapter to Agent Kernel.

yaalalabs/agent-kernel191—~5.7kAutomated safety check: PassApache-2.0today
22

AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents.

aiskillstore/marketplace4304 repos~1kAutomated safety check: PassNo licencetoday
23

Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles.

agentsope/SkillAlchemy457—~7.1kAutomated safety check: PassMIT1 mo ago
24

Decision protocol for wrapping a REST / GraphQL / RPC API as a tool an LLM agent can call.

agentsope/SkillAlchemy457—~5.9kAutomated safety check: PassMIT1 mo ago
25

Decision protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried (timeout, framework resume, user re-run, model duplicate emit), the second call is a no-op…

agentsope/SkillAlchemy457—~8.4kAutomated safety check: PassMIT1 mo ago
26

Decision protocol for managing the context/session state of an AI coding tool: when to /clear, when to keep context, and how to detect "context bleed" — the failure mode where stale conversation…

agentsope/SkillAlchemy457—~6.3kAutomated safety check: PassMIT1 mo ago
27

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies.

aiskillstore/marketplace4303 repos~2.8kAutomated safety check: PassNo licencetoday
28

Decision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines — "given list L, run f(item) for each item in parallel, then combine".

agentsope/SkillAlchemy457—~8.1kAutomated safety check: PassMIT1 mo ago
29

Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com.

neo4j-contrib/neo4j-skills114—~5.8kAutomated safety check: PassMITtoday
30

Build role-based multi-agent systems with CrewAI. An agent skill from magnus919/agent-skills.

magnus919/agent-skills111—~1.7kAutomated safety check: PassMITyesterday
31

ADK 框架适配层。为 LangChain / EINO / AutoGen / AgentScope / CrewAI 提供框架特定的 代码模板、惯用模式、API 映射和项目结构,供 agent-dev-workshop Phase 5 代码生成使用。

hashgraph-online/awesome-codex-plugins1.2k—~528Automated safety check: PassApache-2.0yesterday
32

交互式 AI Agent 开发工作坊:通过 6 阶段深度协作对话,引导用户完成 Agent 需求分析、架构设计、 工具定义、Prompt 与编排设计、代码生成、验证迭代,产出可直接运行的 Agent 项目。

hashgraph-online/awesome-codex-plugins1.2k—~1.8kAutomated safety check: PassApache-2.0yesterday

Questions, answered from the data.

What is the best CrewAI skill?

Agent Governance (official) from github/awesome-copilot ranks first of the 32 CrewAI skills listed here, with the highest score: its repository has 40k GitHub stars, 2 other GitHub owners carry a copy, its SKILL.md loads about 4.6k tokens and it passes the automated safety check with no findings. Next come Mem0 Platform SDK and Edgeone Makers Migration.

Is there an official CrewAI skill?

1 of the 32 CrewAI skills are official, published by the vendor's own GitHub organization: Agent Governance.

How are these skills ranked?

By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.