langgraph-docs
langchain-ai/deepagents
Access LangGraph Python documentation to build stateful agents and multi-agent workflows.
What is langgraph-docs?
Fetches and references LangGraph Python documentation for building stateful agents, creating multi-agent workflows, and implementing human-in-the-loop patterns. Use when you need guidance on graph-based agent architecture, state management, or agent orchestration.
- Fetches LangGraph documentation index from langchain.com
- Identifies and retrieves relevant documentation pages for your query
- Provides implementation guidance for stateful agent patterns
- Supports multi-agent workflow design and orchestration
- Explains human-in-the-loop integration patterns
- References LangGraph API details and core concepts
How to install langgraph-docs
npx skills add https://github.com/langchain-ai/deepagents --skill langgraph-docsHow to use langgraph-docs
- 1.Ask a question about LangGraph, graph agents, state machines, or agent orchestration
- 2.The skill fetches the LangGraph documentation index
- 3.Relevant documentation pages are identified and retrieved
- 4.Implementation guidance or API details are provided based on the fetched content
- 5.Review the documentation content to apply to your use case
Use cases
- Building a stateful agent that maintains conversation context across multiple turns
- Creating a multi-agent system where agents coordinate through a shared graph structure
- Implementing approval workflows where humans review and modify agent decisions
- Designing state machines for complex agent decision logic
- Learning LangGraph API patterns and best practices
- Python developers building AI agents
- Engineers designing multi-agent systems
- Teams implementing human-in-the-loop AI workflows
- Developers new to graph-based agent architecture
langgraph-docs FAQ
The skill will retry once. If it fails again, visit https://langchain-ai.github.io/langgraph/ directly for the official documentation.
This skill focuses on LangGraph Python documentation. For other languages, consult the official LangGraph documentation directly.
Implementation questions, conceptual explanations, end-to-end examples, and API reference details for LangGraph.
It prioritizes implementation guides for how-to questions, core concept pages for conceptual questions, tutorials for end-to-end examples, and reference docs for API details.
Full instructions (SKILL.md)
Source of truth, from langchain-ai/deepagents.
name: langgraph-docs description: 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.
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.
Related skills
More from langchain-ai/deepagents and the wider catalog.
query-writing
Write and execute SQL queries from simple SELECTs to complex JOINs and aggregations.
schema-exploration
Explore database schema, discover tables, columns, data types, and entity relationships.
skill-creator
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations.
social-media
Draft engaging social media posts with research-backed content and generated images for LinkedIn, Twitter/X, and other platforms.
web-research
Delegate web research across multiple subagents, synthesize findings, and produce cited reports.
deep-agents-core
Framework for building multi-step AI agents with built-in planning, memory, and skill management