langgraph-docs
Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance.
Install
With your agent
Install OMGSkills skill "langchain-ai/deepagents:langgraph-docs" into this agent's normal skills directory: use the OMGSkills MCP get_skill tool, install only the pinned_install commit and path, verify SKILL.md against pinned_install.skill_md_sha, and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/langchain-ai/deepagents /tmp/deepagents && ln -s /tmp/deepagents/libs/code/examples/skills/langgraph-docs ~/.claude/skills/langgraph-docsFrom README
langgraph-docs Workflow Fetch the Documentation Index Use fetchurl to read: https://docs.langchain.com/llms.txt This returns a structured list of all available documentation with descriptions. 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 Fetch and Apply Use fetchurl on the selected URLs, then complete the user's request using the documentation content. If fetchurl fails or returns empty content, retry once. If it fails again, inform the user and suggest checking https://langchain-ai.github.io/langgraph/ directly.
More from this repo
code-review
Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.
coding-prefs
Read the user's coding preferences from /memory/coding-prefs.md before making non-trivial style decisions, and append...
competitor-analysis
Used to analyze competitors in a given market segment.