How do I install the Crewai skill?

Run npx skillmds@latest add akillness/crewai in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Crewai skill do?

Agent engineering skill for CrewAI It is listed under AI & ML on SkillMD.

Is Crewai safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Crewai?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Crewai free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Crewai?

akillness (@akillness) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Crewai by akillness — Agent Skill

Name: Crewai
Author: akillness

File contents

crewai

CrewAI is a leading agent framework in the 2026 AI agent engineering landscape (54.8k★).

When to use this skill

Role-based multi-agent crews: Agent (role/goal/backstory) + Task + Crew + Process
Flows: event-driven orchestration with @start/@listen/@router decorators for production pipelines
YAML-first configuration (agents.yaml / tasks.yaml) scaffolded by the crewai CLI
Memory and knowledge stores per agent/crew
crewai-tools package + MCP tool support
Official CrewAI Skills for coding agents (npx skills add crewaiinc/skills)
Standalone — no LangChain dependency
Ecosystem overlap: langgraph-workflow covers graph orchestration; crewai covers role/crew paradigm — complementary; langchain-bmad routes between framework skills

Installation

uv pip install crewai   # extras: 'crewai[tools]'

Core API

crewai create crew my_crew
cd my_crew && crewai install
# edit src/my_crew/config/agents.yaml + tasks.yaml
crewai run

Instructions

Step 1: Initialize the environment

Verify you have Python installed and set up properly. Use the correct package manager (pip, npm, pnpm, uv) as specified in the installation section.

Step 2: Establish the agent flow

Architecture pattern: Two-layer: Crews (autonomous role-based collaboration, sequential/hierarchical process) and Flows (deterministic event-driven control flow that can embed crews)

Step 3: Implement tool integrations and policies

Integrate necessary tools, environment keys, and safety gates according to your architectural needs. Position in the ecosystem: Most-adopted role-based multi-agent framework; alternatives: agno (perf/platform focus), langgraph (graph control), autogen (maintenance mode)

Examples

Example 1: Minimal Agent Run

crewai create crew my_crew
cd my_crew && crewai install
# edit src/my_crew/config/agents.yaml + tasks.yaml
crewai run

Best practices

Follow the primary installation commands for CrewAI to ensure dependencies are resolved correctly.
Configure model providers and API keys securely before starting the runtime.
Use appropriate sandboxing or permission isolation if executing AI-generated code.

References

---name: crewaidescription: Agent engineering skill for CrewAIlicense: MIT---# crewaiCrewAI is a leading agent framework in the 2026 AI agent engineering landscape (54.8k★).## When to use this skill- Role-based multi-agent crews: Agent (role/goal/backstory) + Task + Crew + Process- Flows: event-driven orchestration with @start/@listen/@router decorators for production pipelines- YAML-first configuration (agents.yaml / tasks.yaml) scaffolded by the crewai CLI- Memory and knowledge stores per agent/crew- crewai-tools package + MCP tool support- Official CrewAI Skills for coding agents (npx skills add crewaiinc/skills)- Standalone — no LangChain dependency- Ecosystem overlap: langgraph-workflow covers graph orchestration; crewai covers role/crew paradigm — complementary; langchain-bmad routes between framework skills## Installation```bashuv pip install crewai # extras: 'crewai[tools]'```## Core API```pythoncrewai create crew my_crewcd my_crew && crewai install# edit src/my_crew/config/agents.yaml + tasks.yamlcrewai run```## Instructions### Step 1: Initialize the environmentVerify you have Python installed and set up properly. Use the correct package manager (pip, npm, pnpm, uv) as specified in the installation section.### Step 2: Establish the agent flowArchitecture pattern: Two-layer: Crews (autonomous role-based collaboration, sequential/hierarchical process) and Flows (deterministic event-driven control flow that can embed crews)### Step 3: Implement tool integrations and policiesIntegrate necessary tools, environment keys, and safety gates according to your architectural needs. Position in the ecosystem: Most-adopted role-based multi-agent framework; alternatives: agno (perf/platform focus), langgraph (graph control), autogen (maintenance mode)## Examples### Example 1: Minimal Agent Run```pythoncrewai create crew my_crewcd my_crew && crewai install# edit src/my_crew/config/agents.yaml + tasks.yamlcrewai run```## Best practices1. Follow the primary installation commands for CrewAI to ensure dependencies are resolved correctly.2. Configure model providers and API keys securely before starting the runtime.3. Use appropriate sandboxing or permission isolation if executing AI-generated code.## References- [https://github.com/crewAIInc/crewAI](https://github.com/crewAIInc/crewAI)- [https://docs.crewai.com](https://docs.crewai.com)

Frequently asked questions

Crewai