langgraph-python-quickstart — Claude Code skill: setup guide
Scaffolds a minimal local LangGraph Python agent using the official quickstart. Useful when you need to test a Graph API agent in an isolated folder.
npx skills add langchain-ai/langchain-skills --skill langgraph-python-quickstart -a claude-codeWhat langgraph-python-quickstart does
The skill fetches the official LangGraph quickstart page directly via Docs MCP or HTTP instead of generating outdated code from memory. It builds everything inside a dedicated folder such as langgraph-agent/, keeping your current project directory untouched. The resulting setup implements a calculator agent using the Graph API without IPython graph visualization.
Model configuration relies on init_chat_model. When using anthropic:claude-sonnet-5, the skill omits temperature, top_p, and top_k because that model rejects those parameters. You can also supply other providers directly, such as openai:gpt-5.5 or google_genai:gemini-2.5-flash-lite.
The environment setup stays minimal on purpose. It only requires the model provider API key inside .env and skips optional tools like LangSmith or Tavily unless requested. Once it executes the initial math check and prints the result, it stops.
What it helps with
- scaffold a minimal LangGraph agent in an isolated directory
- build a Graph API calculator agent from live documentation
- configure chat models via
init_chat_modelwith valid parameters - verify a local agent run without extra tracing dependencies
Example prompts for the agent
- Scaffold a LangGraph agent in Python using anthropic:claude-sonnet-5.
- Set up a local langgraph-agent project following the official quickstart.
How to install langgraph-python-quickstart
1Skills CLI (Vercel)
npx skills add langchain-ai/langchain-skills --skill langgraph-python-quickstart -a claude-code2Manually: put the files in place
~/.claude/skills/langgraph-python-quickstart/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/langgraph-python-quickstart/
1Skills CLI (Vercel)
npx skills add langchain-ai/langchain-skills --skill langgraph-python-quickstart -a codex2Manually: put the files in place
.agents/skills/langgraph-python-quickstart/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add langchain-ai/langchain-skills --skill langgraph-python-quickstart -a cursor2Manually: put the files in place
.cursor/skills/langgraph-python-quickstart/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install langchain-ai/langchain-skills langgraph-python-quickstart2Manually: put the files in place
.github/skills/langgraph-python-quickstart/SKILL.md1Skills CLI (Vercel)
npx skills add langchain-ai/langchain-skills --skill langgraph-python-quickstart -a gemini-cli2Platform CLI
gemini skills install https://github.com/langchain-ai/langchain-skills --path config/skills/langgraph-python-quickstartManually: put the files in place
.devin/skills/langgraph-python-quickstart/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add langchain-ai/langchain-skills --skill langgraph-python-quickstart -a opencodeClaude.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 langgraph-python-quickstart
How do I install langgraph-python-quickstart in Claude Code?
Run npx skills add langchain-ai/langchain-skills --skill langgraph-python-quickstart -a claude-code.
What does langgraph-python-quickstart do?
It reads the live LangGraph quickstart docs, creates a clean subfolder, and builds a working calculator agent using the Graph API.
Which model providers are supported?
It works with any model accepted by init_chat_model, such as openai:gpt-5.5 or google_genai:gemini-2.5-flash-lite. If unsure, it defaults to anthropic:claude-sonnet-5.
Source text
SKILL.md · MIT
---
name: langgraph-python-quickstart
description: "Scaffold a minimal local LangGraph agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangGraph agent locally."
---
# LangGraph Python quickstart
Follow the live docs — do not invent an alternate API from memory:
**https://docs.langchain.com/oss/python/langgraph/quickstart**
Fetch that page (Docs MCP or HTTP) and implement what it shows (calculator / math agent with the Graph API). Prefer the Graph API path over the Functional API unless the user asks otherwise. Skip IPython graph visualization.
## Local setup constraints
Apply these on top of the quickstart (they keep setup minimal and model-agnostic):
1. **Ask** which provider/model to use. Showcase that LangGraph works with any LangChain chat model. Suggested prompt:
> Which model should this agent use? Pass a `provider:model` string — e.g. `openai:gpt-5.5`, `anthropic:claude-sonnet-5`, `google_genai:gemini-2.5-flash-lite`. Default if you're unsure: **`anthropic:claude-sonnet-5`**.
The docs often hardcode Anthropic — replace with `init_chat_model("<MODEL>")` (or equivalent) using their choice. If using Claude Sonnet 5+, omit `temperature` / `top_p` / `top_k` (unsupported).
2. Create a **new** directory (e.g. `langgraph-agent/`) and do all work there — do not pollute the open project.
3. Only secret: the provider API key in `.env` (gitignored). No LangSmith / Tavily unless they ask. Prefer they edit `.env` themselves — don't paste keys into chat.
4. Install packages from the quickstart plus the provider package for their model.
5. Run the example (e.g. “Add 3 and 4.”), show output, then stop. Point to `langgraph-fundamentals` for next steps. For a higher-level agent API, use LangChain `create_agent` instead.
© langchain-ai · MIT · langchain-ai/langchain-skills
