Agent Skills › langchain-ai/langchain-skills › langgraph-python-quickstart

langgraph-python-quickstart

GitHub

指导用户快速搭建本地 LangGraph Python Agent，遵循官方文档实现基础计算器功能。支持自定义模型提供商，隔离项目环境，仅配置必要 API Key，运行示例后停止并指引后续学习资源。

config/skills/langgraph-python-quickstart/SKILL.md langchain-ai/langchain-skills

触发场景

用户希望快速尝试或构建 LangGraph Agent 需要基于官方文档搭建最小化本地 LangGraph 环境

安装

npx skills add langchain-ai/langchain-skills --skill langgraph-python-quickstart -g -y

更多选项

非标准路径

npx skills add https://github.com/langchain-ai/langchain-skills/tree/main/config/skills/langgraph-python-quickstart -g -y

不安装直接使用

npx skills use langchain-ai/langchain-skills@langgraph-python-quickstart

指定 Agent (Claude Code)

npx skills add langchain-ai/langchain-skills --skill langgraph-python-quickstart -a claude-code -g -y

安装 repo 全部 skill

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

预览 repo 内 skill

npx skills add langchain-ai/langchain-skills --list

SKILL.md

Frontmatter

{
    "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):

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).
Create a new directory (e.g. langgraph-agent/) and do all work there — do not pollute the open project.
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.
Install packages from the quickstart plus the provider package for their model.
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.