langchain-fundamentals — Skills

What it does

HITL: middleware=[HumanInTheLoopMiddleware(interrupton={"dangeroustool": True})] — requires checkpointer + threadid

Resume after interrupt: agent.invoke(Command(resume={"decisions": [{"type": "approve"}]}), config=config)

Custom middleware: @wraptoolcall decorator (Python) or createMiddleware({ wrapToolCall: ... }) (TypeScript)

Source

Repository: https://github.com/langchain-ai/langchain-skills

langchain-fundamentals FAQ

What does the langchain-fundamentals skill do?

Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling. HITL: middleware=[HumanInTheLoopMiddleware(interrupton={"dangeroustool": True})] — requires checkpointer + threadid Resume after interrupt: agent.invoke(Command(resume={"decisions": [{"type": "approve"}]}), config=config)

What does langchain-fundamentals require?

HITL: middleware=[HumanInTheLoopMiddleware(interrupton={"dangeroustool": True})] — requires checkpointer + threadid Use this when you need recent data or facts. description: "Search the web for current information about a topic. Use this when you need recent data or facts.",

How do I install langchain-fundamentals?

Run: npx -y skills add https://github.com/langchain-ai/langchain-skills --skill langchain-fundamentals --agent claude-code — the source lives at github.com/langchain-ai/langchain-skills.

Maintain langchain-fundamentals?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[![langchain-fundamentals on getagentictools](https://getagentictools.com/badge/skills/langchain-ai-langchain-skills-langchain-fundamentals.svg)](https://getagentictools.com/skills/langchain-ai-langchain-skills-langchain-fundamentals?ref=badge)

npx agentictools info skills/langchain-ai-langchain-skills-langchain-fundamentals

The second line is the CLI lookup for this page — handy in READMEs and docs.