langchain-aiOfficial·26 Agent Skills Included

langchain-skills

Build production AI agents with LangChain, LangGraph, and Deep Agents

Guides AI coding agents to build, test, and deploy LangChain, LangGraph, and Deep Agents applications with correct, up-to-date patterns. Covers quickstarts, RAG pipelines, persistence, human-in-the-loop approvals, memory, subagent orchestration, and evaluation engineering. Eliminates outdated API usage, broken imports, and version conflicts by routing every task to the right skill before writing code.

1,190|90

↗

npx skills add langchain-ai/langchain-skills --all -g -y

Available:

Tells the AI agent to always invoke the matching skill before writing code and maps each LangChain, LangGraph, and Deep Agents task to the correct sub-skill.

All Skills in This Repository (26)

Pure Emerald Level Indicators

📦 In Repo

langchain-ai

LangGraph Persistence & Memory

Checkpoint LangGraph graph state at each super-step for durable execution.

LangChain Fundamentals

Create and configure LangChain agents with tools, middleware, and checkpointers.

LangChain Middleware & HITL

Implement middleware patterns for LangChain agents with human approval and structured output.

LangSmith Evaluators

Create and run LLM-as-Judge and custom code evaluators in LangSmith.

LangChain RAG Pipeline

Orchestrate document loading, splitting, embedding, and vector store management for RAG pipelines.

LangGraph Fundamentals

Build stateful agent workflows with LangGraph StateGraph and reducers.

Deep Agents Orchestration

Delegate tasks to subagents with TodoList planning and human approval gates.

Deep Agents Memory & Filesystem

Provide agents with ephemeral, persistent, and filesystem storage via pluggable backends.

LangChain Dependencies

Guide installation and version management for LangChain ecosystem packages.

Framework Selection

Guide LangChain framework layer selection using a decision tree.

LangSmith Dataset

Generate evaluation datasets from exported LangSmith trace JSONL files.

LangGraph Execution Control

Manage LangGraph execution flows with Send API parallel tasks, interrupts, and streaming.

Official

Advanced

Frequently Asked Questions

FAQPage Schema

How to install langchain-skills?▼

Run `npx skills add langchain-ai/langchain-skills --all -g -y` in your terminal to install all skills globally for your coding agent.

What do LangChain skills do?▼

They give your AI coding agent current, tested patterns for building agents with LangChain, LangGraph, and Deep Agents, including RAG, memory, persistence, and human approval workflows.

Do these skills work with Claude Code and Cursor?▼

Yes. They follow the universal Agent Skills standard and work with Claude Code, Cursor, Windsurf, and any agent supporting the specification.

Do the skills support both Python and TypeScript?▼

Yes. Every core skill includes parallel Python and TypeScript examples, with dedicated quickstarts for each language.

Can I build agents without deep LangChain experience?▼

Yes. The ecosystem-primer skill picks the right framework for your task and routes your agent to the correct guide automatically.