agents-langchain — Claude Code skill: what it does, how to install
This skill guides LangChain projects with agents, chains, tool calls, and RAG. Use it when building chatbots, document Q&A, or autonomous workflows.
npx claude-code-templates@latest --skill ai-research/agents-langchainWhat agents-langchain does
agents-langchain covers the main pieces of LangChain applications: model adapters for OpenAI, Anthropic, and Google, prompt chains, ReAct-style agents, tool execution, and conversation memory. It also walks through retrieval-augmented generation with document loading, embeddings, and a vector store.
The included Python examples show model calls, agent setup, multi-turn memory, and a RAG pipeline. The base install uses langchain with Python 3.10+; provider-specific examples add langchain-openai or langchain-anthropic. The RAG example uses langchain-community, langchain-chroma, and OpenAI embeddings.
The OpenAI RAG path requires langchain-openai and access to OpenAI, while the vector store example relies on Chroma. That dependency choice matters before you copy the pipeline into a project.
What it helps with
- build an agent that calls tools
- switch between OpenAI, Anthropic, and Google models
- keep conversation history across turns
- assemble a document retrieval pipeline
- return source documents with an answer
Example prompts for the agent
- Create a Python ReAct agent with tools for web search and calculations.
- Build a RAG pipeline that loads documents, splits them, and stores them in
Chroma. - Add conversation memory and keep the message history across requests.
How to install agents-langchain
1claude-code-templates
npx claude-code-templates@latest --skill ai-research/agents-langchain2Skills CLI (Vercel)
npx skills add davila7/claude-code-templates --skill agents-langchain -a claude-code3Manually: put the files in place
~/.claude/skills/agents-langchain/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/agents-langchain/
Manually: put the files in place
.agents/skills/agents-langchain/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/agents-langchain/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install davila7/claude-code-templates agents-langchain2Manually: put the files in place
.github/skills/agents-langchain/SKILL.mdPlatform CLI
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/ai-research/agents-langchainManually: put the files in place
.devin/skills/agents-langchain/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about agents-langchain
How do I install agents-langchain in Claude Code?
Run npx claude-code-templates@latest --skill ai-research/agents-langchain.
What does agents-langchain do?
It explains how to build LangChain applications with provider adapters, agents, chains, memory, tool calls, and RAG.
Which Python version does agents-langchain require?
The base langchain installation requires Python 3.10+.