Skip to main content
affpapa.org
RU EN
skill

agents-crewai — Claude Code skill: build agent crews

A Claude skill for assembling teams of autonomous agents with roles, memory, and sequential or hierarchical task execution.

Install into Claude Code · claude-code-templates All methods and platforms ↓ 
npx claude-code-templates@latest --skill ai-research/agents-crewai
Open on GitHub

What agents-crewai does

The skill covers CrewAI, a framework where each agent gets a role, a goal and a backstory, and tasks run one after another or through a manager. It ships code examples: defining agents, tasks, a crew, and starting it with kickoff. Memory comes in short-term, long-term and entity flavours, and task output can be written to a file.

Dependencies are crewai>=1.2.0 and crewai-tools>=1.2.0. There is no LangChain underneath, so the install stays small. Hierarchical mode needs a separate model for the manager — the examples use manager_llm="gpt-4o", so you need access to it.

Reach for this when a single agent stops being enough: research, writing and review split across roles. A straight pipeline with no delegation gains nothing from the extra structure.

What it helps with

  • split a job across agents with distinct roles
  • feed one task's output into the next task
  • keep memory alive between crew runs
  • let a manager agent hand out tasks
  • give an agent web search or PDF reading tools

Example prompts for the agent

  • Build a CrewAI crew with a researcher and a technical writer: the first finds five trends, the second drafts a post from them
  • Set up a hierarchical process where a manager delegates to an analyst and an editor
  • Add web search and page scraping tools to the researcher agent with crewai-tools

How to install agents-crewai

1claude-code-templates

npx claude-code-templates@latest --skill ai-research/agents-crewai

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill agents-crewai -a claude-code

3Manually: put the files in place

~/.claude/skills/agents-crewai/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/agents-crewai/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about agents-crewai

How do I install agents-crewai in Claude?

Use the templates CLI: npx claude-code-templates@latest --skill ai-research/agents-crewai. Or run npx skills add davila7/claude-code-templates --skill agents-crewai -a claude-code. The skill file then sits at ~/.claude/skills/agents-crewai/SKILL.md.

What does agents-crewai do?

It walks through building CrewAI agent teams: roles, tasks, memory, and two execution modes — sequential and hierarchical.

Does it need LangChain?

No. CrewAI has no LangChain dependencies, so the install is just the crewai and crewai-tools packages.

Similar skills

All skills for Agent setup: memory, context, orchestration →
multi-agent-orchestration qodex-ai Guides the architecture of multi-agent setups, delegating specialized roles and combining outputs. Helpful for multi-stage workflows across multiple LLMs. CX Codex +1 2,100installs agent-orchestration OrchestKit A skill of patterns for autonomous agent loops, multi-agent coordination and multi-scenario runs. Useful when you build agent pipelines and pick a framework. CX Codex +1 1,400installs check-crewai-api crewAIInc A skill that checks crewai code against 1.15.x instead of the 0.x syntax assistants still remember. Useful when an import or a parameter quietly does nothing. CX Codex +1 650installs design-agent crewAIInc Teaches your AI assistant how to configure CrewAI agents: define roles, set goals and backstories, assign tools, and adjust execution limits without token waste. CX Codex +1 8,300installs ai-agents-architect sickn33 A skill that breaks an agent into parts: ReAct loop, planning, memory layers, multi-agent orchestration. Useful once your agent exists and you need to decide how it fails. CX Codex +1 1,500installs open-multi-agent-orchestration reason-machines A skill that teaches your agent to build AI agent teams on the open-multi-agent TypeScript framework: roles, models, task dependencies. CX Codex +1 710installs

From the same set205

The whole set →
troubleshooting-guide Writes a troubleshooting document with diagnostic steps, common failures and shell commands for checking a system. Useful when a service needs a runbook. 397installs performance-budget-guard A Claude hook that measures your Next.js JS bundle after a build and blocks the deploy when it goes over the performance budget. 393installs memory-spring-cleaning Walks through CLAUDE.md and markdown docs, checks the rules written there against the actual code, and drops what no longer holds. 391installs interactive-documentation A slash command that builds documentation with runnable code examples, playgrounds and API testing. Useful once a plain README stops being enough. 372installs testing-patterns A Claude skill that hands the agent Jest testing patterns: data factories, module mocks and the red-green-refactor loop. 365installs code-review-checklist A skill that walks a reviewer through context, functionality, quality, security, performance and tests. Useful on pull requests and audits. 365installs vercel-environment-sync A hook that inspects environment variables after an .env edit and points you to the right Vercel sync commands. Useful when local and deployed values drift apart. 363installs log Writes a finished task's report into your tracker or notes: time spent, status, commits. Useful when the coding happens in Claude but the record lives in Linear or Obsidian. 351installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor