Skip to main content
affpapa.org
RU EN
skill CX Codex

langchain-python-quickstart — Claude Code skill

Builds a minimal local LangChain agent in Python from the current quickstart. Use it to try an agent in a separate project directory.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add langchain-ai/langchain-skills --skill langchain-python-quickstart -a claude-code
Open on GitHub

What langchain-python-quickstart does

The skill checks the current LangChain Python quickstart through Docs MCP or HTTP, then builds the weather-agent example with create_agent. It asks for a provider and model in provider:model form, so the setup is not tied to one model service.

Work happens in a new directory such as langchain-agent/ rather than the open project. The skill creates a gitignored .env for the provider API key. Entering that key in .env yourself is the right call instead of posting it in chat.

When the base install needs more, it installs the package for the selected provider. It runs the example, shows its output, and stops. LangSmith and Tavily stay out unless you ask for them.

What it helps with

  • scaffold a local LangChain agent in Python
  • select a provider and model string
  • build the weather-agent example with create_agent
  • keep a provider API key in .env

Example prompts for the agent

  • Create a minimal local LangChain agent in a new directory.
  • Build the LangChain weather agent with anthropic:claude-sonnet-5.
  • Run the LangChain Python quickstart and show the output.

How to install langchain-python-quickstart

1Skills CLI (Vercel)

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

2Manually: put the files in place

~/.claude/skills/langchain-python-quickstart/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/langchain-python-quickstart/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about langchain-python-quickstart

How do I install langchain-python-quickstart in Claude Code?

Run npx skills add langchain-ai/langchain-skills --skill langchain-python-quickstart -a claude-code, then run npx skills add langchain-ai/langchain-skills --skill langchain-python-quickstart -a claude-code again. The skill file is at ~/.claude/skills/langchain-python-quickstart/SKILL.md.

What does langchain-python-quickstart do?

It scaffolds a minimal local LangChain agent in Python from the current official quickstart. The example uses a weather agent and create_agent.

What does the agent setup require?

Choose a provider and model using a provider:model string, then add that provider's API key to .env. The skill installs the provider package when the base LangChain install needs it.

Source text

SKILL.md · MIT 
---
name: langchain-python-quickstart
description: "Scaffold a minimal local LangChain agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent locally."
---

# LangChain Python quickstart

Follow the live docs — do not invent an alternate API from memory:

**https://docs.langchain.com/oss/python/langchain/quickstart**

Fetch that page (Docs MCP or HTTP) and implement what it shows (weather agent + `create_agent`).

## 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 LangChain is model-agnostic. 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`**.

   Swap the quickstart's model string for their choice (or the default).

2. Create a **new** directory (e.g. `langchain-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 the provider package needed for their model if the quickstart's base install isn't enough.

5. Run the example, show output, then stop. Point to `langchain-fundamentals` for next steps.

© langchain-ai · MIT · langchain-ai/langchain-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →
langchain-python official github A GitHub Copilot instruction file that steers the agent toward LangChain patterns: Runnable, LCEL, chat models, retrievers and vector stores. Useful when your Python code talks to LangChain. ★ 40,418repo stars langchain-development Mindrally Gives your agent a rulebook for LangChain and LangGraph work in Python: chain composition, agents, memory, RAG. Useful once a Python LLM project outgrows one file. CX Codex +1 681installs migrating-langchain-to-pydantic-ai pydantic A skill that moves Python apps off LangChain, LangGraph and Deep Agents onto Pydantic AI. Useful when you want to keep the behavior and drop the framework shape. CX Codex +1 314installs langchain-architecture Seth Hobson This skill helps design LangChain 1.x and LangGraph applications with agents, memory, state, and tool calls. Use it for multi-step LLM workflows. CX Codex 13,150installs dataverse-python-quickstart official github Generates Python examples for the Microsoft Dataverse SDK, including setup, CRUD, bulk requests, and paged queries. Use it when building a Dataverse integration in Python. 8,700installs n8n-code-tool czlonkowski A skill that teaches your agent to write JavaScript or Python for the n8n Custom Code Tool, the node an AI Agent calls, and to avoid its runtime traps. CX Codex +1 1,600installs

From the same set22

ecosystem-primer Guides framework selection across LangChain, LangGraph, and Deep Agents before writing code. Maps requirements to the right layer, env vars, and quickstarts. CX Codex +1 8,000installs eval-engineering A skill that walks you through agent eval design: it inspects your repo, writes a Task Spec, then builds and audits runnable tasks in Harbor. CX Codex +1 5,300installs langgraph-python-quickstart 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. CX Codex +1 5,200installs deepagents-python-quickstart Scaffolds a minimal Deep Agent in Python from the live LangChain quickstart: asks for a model, keeps work in a fresh folder, swaps Tavily for provider-native search. CX Codex +1 5,000installs langgraph-typescript-quickstart Scaffolds a minimal local LangGraph agent in TypeScript following official docs. Useful when testing graph architectures locally without polluting existing repositories. CX Codex +1 5,000installs deepagents-typescript-quickstart Scaffolds a minimal TypeScript Deep Agent from the official quickstart, swapping Tavily for the provider's built-in web search. CX Codex +1 4,900installs langchain-typescript-quickstart Builds a minimal LangChain agent in TypeScript following the official quickstart: a weather tool, createAgent, its own folder. Handy when you want to try LangChain locally. CX Codex +1 5,000installs langgraph-decision-models A skill that swaps LLM calls made only to extract a routing decision for typed questions that return probabilities. CX Codex +1 1,600installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor