Help us improve
Share bugs, ideas, or general feedback.
From langgraph-docs
Access up-to-date LangGraph Python documentation to provide accurate implementation guidance. Use when requests involve LangGraph concepts, APIs, or implementation questions including (1) building agents with LangGraph, (2) creating state graphs and workflows, (3) using LangGraph checkpointing and persistence, (4) implementing human-in-the-loop patterns, (5) deploying LangGraph applications, or (6) any LangGraph-specific questions requiring current documentation.
npx claudepluginhub mineru98/langgraph-skills --plugin langgraph-docsHow this skill is triggered — by the user, by Claude, or both
Slash command
/langgraph-docs:langgraph-docsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill provides access to the official LangGraph Python documentation to answer questions and guide implementation with accurate, up-to-date information.
Builds production-grade AI agents with LangGraph: graph construction, state management, persistence, human-in-the-loop, and the ReAct agent pattern.
Builds production-grade stateful multi-actor AI agents with LangGraph, covering graph construction, state management, persistence, cycles, branches, human-in-the-loop, and ReAct patterns.
Provides LangGraph 1.x LTS patterns for state management, routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming, subgraphs, and functional API. Use for LangGraph pipelines, multi-agent systems, AI workflows.
Share bugs, ideas, or general feedback.
This skill provides access to the official LangGraph Python documentation to answer questions and guide implementation with accurate, up-to-date information.
Use the WebFetch tool to read the documentation index:
WebFetch with url="https://docs.langchain.com/llms.txt" and prompt="Extract the full list of documentation URLs with their descriptions"
This index provides a structured list of all available LangGraph documentation with descriptions.
Based on the user's question, identify 2-4 most relevant documentation URLs from the index. Prioritize:
Use the WebFetch tool to read each selected documentation URL:
WebFetch with url="[selected-doc-url]" and prompt="Extract all content including code examples, explanations, and API details"
Read 2-4 documentation pages to gather comprehensive context.
After reading the documentation: