LangChain agent skills
Build agents, retrieval pipelines, memory, and evaluations with LangChain, LangGraph, and LangSmith guidance.
Published by LangChain
What these skills help with
Build agents, retrieval pipelines, memory, and evaluations with LangChain, LangGraph, and LangSmith guidance.
Build agent workflows
Combine agent tools, state, and orchestration patterns.
Add persistent memory
Keep useful context across agent runs.
Develop retrieval pipelines
Connect document retrieval to an application workflow.
Explore LangChain skills
View all
Deep Agents Core
Build Deep Agents applications with create_deep_agent, harness architecture, skill instructions, and configuration.
Deep Agents Memory
Configure Deep Agent memory, persistent state, and filesystem access using LangChain backends.
Deep Agents Orchestration
Coordinate Deep Agent subagents, task planning, and human approvals with SubAgentMiddleware, TodoList, and human-in-the-loop middleware.
Install LangChain skills
Download the complete source, choose a skill folder, and follow the setup instructions for your assistant.
Read the source repository
Check prerequisites, supported tools, and installation steps from the publisher.
langchain-ai/langchain-skillsDownload the source files
Keep scripts and references with the SKILL.md file. Some skills require a service account or API credentials.
Download source ZIP
LangChain skill workflows
Pause for a human decision
Add an approval checkpoint before an agent proceeds with a task.
Resume interrupted work
Use LangGraph persistence to continue a run from saved state.
Evaluate an agent in production
Set up LangSmith online evaluations to inspect ongoing behavior.
Agent skills FAQ
An agent skill is a folder of instructions, usually headed by a SKILL.md file, that helps an AI assistant perform a specific task. A skill may also include scripts, examples, and reference files.
