This skill provides guidance on setting up CrewAI projects efficiently. It is for developers who want to understand the correct workflow for initiating their CrewAI projects using the CLI.
$ npx skills add https://github.com/crewaiinc/skills --skill getting-startedThis skill teaches the correct workflow for initiating CrewAI projects, from choosing the right abstraction level (LLM.call() vs Agent.kickoff() vs Crew.kickoff() vs Flow) to CLI scaffolding and configuration. It covers YAML setup for agents and tasks, wiring @CrewBase crews, writing Flows with @start/@listen decorators, and variable interpolation patterns. The skill addresses common setup issues developers face when starting new CrewAI projects, helping them select appropriate abstraction levels and properly configure their project structure. It's designed for developers who want to follow best practices and understand CrewAI architecture decisions from the start.
Run `crewai create flow <project_name>` to scaffold a project.
Scaffold a new CrewAI project using the CLI.
Modify generated files for a CrewAI project.
Learn about directory structure and configuration for CrewAI.
$ npx skills add https://github.com/crewaiinc/skills --skill getting-startedgit clone https://github.com/crewaiinc/skillsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Check the GitHub repository or documentation for usage examples.
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan