getting-started 是做什麼的？
CrewAI 架構決策與專案骨架。用於開始新的 CrewAI 專案時，選擇 LLM.call()、Agent.kickoff()、Crew.kickoff() 或 Flow；使用 'crewai create flow' 建立骨架；設定 YAML 設定檔 (agents.yaml、tasks.yaml)；接線 @CrewBase crew.py；編寫 Flow main.py 搭配 @start/@listen；或使用 {variable} 插值。
CrewAI 架構決策與專案骨架。用於開始新的 CrewAI 專案時，選擇 LLM.call()、Agent.kickoff()、Crew.kickoff() 或 Flow；使用 'crewai create flow' 建立骨架；設定 YAML 設定檔 (agents.yaml、tasks.yaml)；接線 @CrewBase crew.py；編寫 Flow main.py 搭配 @start/@listen；或使用 {variable} 插值。
此技能專為使用 CrewAI 框架的開發者設計，提供從零開始建立多代理系統的完整指引。它涵蓋了架構決策的核心差異，例如何時使用低階的 LLM.call() 直接呼叫語言模型、何時透過 Agent.kickoff() 啟動單一代理任務、以及何時利用 Crew.kickoff() 協調多代理協作或 Flow 來建構複雜的工作流程。此外，技能詳細說明了使用 'crewai create flow' 指令自動產生專案骨架的過程，並指導如何設定以 YAML 為基礎的代理與任務設定檔（agents.yaml 與 tasks.yaml），以及透過 @CrewBase 裝飾器在 crew.py 中連接這些設定。對於開發自訂流程的場景，它也解釋了如何在 main.py 中使用 @start 與 @listen 裝飾器來定義工作流程的觸發與回應邏輯，並支援 {variable} 語法進行動態變數插值。此技能適用於 Claude Code、Cursor 等 AI 編碼代理，無論是初學者還是經驗豐富的使用者，都能藉此快速搭建可擴展的多代理系統。
npx skills add https://github.com/crewaiinc/skills/tree/main/skills/getting-startedInstalled? Explore more 生產力與協作 skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →
CrewAI 架構決策與專案骨架。用於開始新的 CrewAI 專案時，選擇 LLM.call()、Agent.kickoff()、Crew.kickoff() 或 Flow；使用 'crewai create flow' 建立骨架；設定 YAML 設定檔 (agents.yaml、tasks.yaml)；接線 @CrewBase crew.py；編寫 Flow main.py 搭配 @start/@listen；或使用 {variable} 插值。
This repo contains 3 individual skills — each has its own dedicated page.
Query the official CrewAI documentation for answers. Use when the user has a CrewAI question that isn't fully covered by the getting-started, design-agent, design-task skills — e.g., specific API details, configuration options, advanced features, troubleshooting errors, enterprise features, tool references, or anything where the latest docs are the best source of truth.
CrewAI agent design and configuration. Use when creating, configuring, or debugging crewAI agents — choosing role/goal/backstory, selecting LLMs, assigning tools, tuning max_iter/max_rpm/max_execution_time, enabling planning/code execution/delegation, setting up knowledge sources, using guardrails, or configuring agents in YAML vs code.
CrewAI task design and configuration. Use when creating, configuring, or debugging crewAI tasks — writing descriptions and expected_output, setting up task dependencies with context, configuring output formats (output_pydantic, output_json, output_file), using guardrails for validation, enabling human_input, async execution, markdown formatting, or debugging task execution issues.
Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.
Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.
Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.
Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.
Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.
List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.