Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Starting a CrewAI project and choosing the architecture v1.0.0

Use this resource to choose the right CrewAI abstraction and create a ready-to-run project

New

  • 313 downloads
  • 108 likes
  • 216 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install crewai-project-architecture

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent requires scaffolding the project with crewai create flow, then helps you choose between a direct LLM call, a single agent, a crew or a flow. It wires the YAML configuration, the @CrewBase class and the @start and @listen methods.

Mostly picked by

Updated November 2, 2026

Card for the “Starting a CrewAI project and choosing the architecture” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: decision tree, LLM and agent calls, CLI reference
  • references/: crew YAML configuration, flow routing, tools and MCP servers

Good fit for

  • You are new to CrewAI and do not know where to start
  • You move from a standalone script to a structured project

Not for

    Tags

    • crewai
    • getting started
    • architecture
    • flow
    • yaml

    About

    You say

    “I want a tool that summarises a PDF with an LLM: which CrewAI abstraction should I use, and create the project.”

    Card for the “Starting a CrewAI project and choosing the architecture” skill

    Skill published by crewaiinc under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to choose the right CrewAI abstraction and create a ready-to-run project
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/conversational-flows.md11.5 KB
    • references/crew-yaml-config.md4.2 KB
    • references/flow-routing.md11.9 KB
    • references/mcp-servers.md11.1 KB
    • references/tools-catalog.md9.8 KB
    • SKILL.md25.4 KB

    Origin and licence

    Listed unmodified

    Author
    crewaiinc
    Source
    github.com/crewaiinc/skills/tree/bebb6e8fc10bb8d07961969fb7bfd7d6091b421a/skills/getting-started
    Licence
    MIT

    Notice

    « getting-started » (crewaiinc, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.