LangChain Skills skills
Official LangChain skills — framework-selection, deep-agents (core/memory/orchestration), langchain-fundamentals/middleware/RAG, langgraph-fundamentals/persistence/HITL skills-hub.ai mirrors 11 skills from LangChain Skills daily — every skill links back to its upstream GitHub source. Install with one command across Claude Code, Cursor, Codex, Windsurf, and any MCP-compatible tool.
Upstream: github.com/langchain-ai/langchain-skills
Installing a LangChain Skills skill
Pick a skill below, then run the install command for your AI coding tool. The skills-hub CLI writes the SKILL.md to the right directory and tracks the install in .skills.json so your team gets reproducible installs.
# Install a LangChain Skills skill
npx @skills-hub-ai/cli install <skill-slug>
# Browse all LangChain Skills skills via API
curl https://skills-hub.ai/api/v1/skills?source=langchain
# Browse all sources
open https://skills-hub.ai/sourcesTop LangChain Skills skills
See all →The most-installed skills from LangChain Skills, ranked by adoption.
01langgraph-fundamentals
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
Buildfrom LangChain Skills02deep-agents-core
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
Buildfrom LangChain Skills03langchain-dependencies
INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. Covers required packages, minimum versions, environment requirements, versioning best practices, and common community tool packages for both Python and TypeScript.
Buildfrom LangChain Skills04deep-agents-orchestration
INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
Buildfrom LangChain Skills05langchain-middleware
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
Buildfrom LangChain Skills06langgraph-human-in-the-loop
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval/validation workflows, and the 4-tier error handling strategy.
Buildfrom LangChain Skills07langgraph-persistence
INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.
Buildfrom LangChain Skills08langchain-fundamentals
Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.
Buildfrom LangChain Skills09deep-agents-memory
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
Buildfrom LangChain Skills10framework-selection
INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.
Buildfrom LangChain Skills11langchain-rag
INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).
Buildfrom LangChain Skills
About this source
skills-hub.ai mirrors skills from 90+ official GitHub repositories every day. Each imported skill is parsed from a SKILL.md file in the source repo, gets a security scan and quality score on import, and links back to its upstream source of truth.
Last sync: Apr 30, 2026, 10:12 PM (success).
LangChain Skills skills — frequently asked
What are LangChain Skills skills?
LangChain Skills skills are AI coding skills published by LangChain Skills (Official LangChain skills — framework-selection, deep-agents (core/memory/orchestration), langchain-fundamentals/middleware/RAG, langgraph-fundamentals/persistence/HITL) and mirrored daily on skills-hub.ai. They are SKILL.md files that follow the open Agent Skills standard, so they work in Claude Code, Cursor, Codex CLI, Windsurf, Copilot, and any MCP-compatible tool.
How many LangChain Skills skills are available?
skills-hub.ai indexes 11 skills from LangChain Skills, synced daily from the upstream GitHub repository (https://github.com/langchain-ai/langchain-skills).
How do I install a LangChain Skills skill?
Run `npx @skills-hub-ai/cli install <skill-slug>` in your project. The CLI writes the SKILL.md to the right directory for your AI tool and adds it to your `.skills.json` lockfile so your team gets the same skills at the same versions.
Are these official LangChain Skills skills?
Yes. Every skill from this source is mirrored from LangChain Skills's own GitHub repository (https://github.com/langchain-ai/langchain-skills). Each skill page links back to the upstream source of truth, so you can verify the original.