Langgraph Docs

Pulls documentation directly from LangGraph's official docs to help you build stateful agents and multi-agent systems. It works by first fetching the documentation index from langchain.com, then intelligently selecting the most relevant guides based on whether you're asking implementation questions, conceptual stuff, or need API references. The workflow is straightforward: grab the index, pick 2-4 relevant URLs, fetch them, and apply the content to your problem. Honestly, this is one of those skills that saves you from the classic problem of having LangGraph docs open in twelve tabs while you're trying to remember how state persistence works or how to wire up human-in-the-loop patterns.

skills.sh installs: 4.6K
GitHub stars: 31.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add langchain-ai/deepagents --skill langgraph-docs --agent claude-code

Installs into .claude/skills of the current project.

Files

langgraph-docs

Workflow

1. Fetch the Documentation Index

Use fetch_url to read: https://docs.langchain.com/llms.txt

This returns a structured list of all available documentation with descriptions.

2. Select Relevant Documentation

Identify 2-4 most relevant URLs from the index. Prioritize:

Implementation questions — specific how-to guides
Conceptual questions — core concept pages
End-to-end examples — tutorials
API details — reference docs

3. Fetch and Apply

Use fetch_url on the selected URLs, then complete the user's request using the documentation content.

If fetch_url fails or returns empty content, retry once. If it fails again, inform the user and suggest checking https://langchain-ai.github.io/langgraph/ directly.

SKILL.md on GitHub