swarm 是做什麼的？
並行分發多個獨立項目：建立表格，分散給子代理，匯總結果。一行代表一個工作單元。
並行分發多個獨立項目：建立表格，分散給子代理，匯總結果。一行代表一個工作單元。
langchain-ai/swarm 是一個 AI Agent 技能，專為需要高效率處理大量獨立工項的場景設計。此技能的核心運作模式是「分而治之」：使用者先定義一個任務表格（每個表格列為一個獨立工作單元），接著系統會自動將這些工作單元並行分發給多個子代理（subagents）處理，最後再將所有結果匯總。對於需要批次資料處理、大規模測試或平行內容生成的開發者來說，這項工具能顯著縮短執行時間，並可與 Claude Code、Cursor 等主流 AI 代理平台整合。其架構基於 LangChain 框架，確保靈活性與可擴充性，協助使用者專注於問題定義而非流程管理。
npx skills add https://github.com/langchain-ai/langchain-skills/tree/main/skills/swarmInstalled? Explore more 生產力與協作 skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →
並行分發多個獨立項目：建立表格，分散給子代理，匯總結果。一行代表一個工作單元。
This repo contains 11 individual skills — each has its own dedicated page.
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.
INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. Covers required packages, minimum versions, environment requirements, versioning best practices, and common community tool packages for both Python and TypeScript.
Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval/validation workflows, and the 4-tier error handling strategy.
INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.
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.