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):

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).
Create a new directory (e.g. langchain-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 the provider package needed for their model if the quickstart's base install isn't enough.
Run the example, show output, then stop. Point to langchain-fundamentals for next steps.

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

72/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

78

Quality

68

Clarity

75

Completeness

62

Summary

This skill guides an agent to scaffold a minimal LangChain Python agent by following official documentation, implementing a weather agent example, and setting up a new isolated project directory with model-agnostic configuration. The agent fetches the live LangChain quickstart docs, asks the user for a model provider/choice, creates a new project directory, stores only the API key in a .env file, and runs the example.

Static Analysis Findings

1 finding

Patterns detected by deterministic static analysis before AI scoring. Hover over any finding code for detailed information and remediation guidance.

Credential Exposure

SEC-020Direct .env File Access2x in 1 file

Direct .env file access

SKILL.md.env2x

85% confidenceCWE-538: Sensitive Info in Externally-Accessible File

Detected Capabilities

fetch remote documentationcreate project directoryfile write (.env, Python scripts)shell execution (pip install, python)environment variable usageprompt user for configuration

Trigger Keywords

Phrases that agents use to match this skill to user intent.

langchain quick startsetup langchain agenttry langchain locallylangchain weather agenttest llm providers

Risk Signals

WARNING

SEC-020: Direct .env file access — .env file mentioned for storing provider API key

SKILL.md | Constraint 3

WARNING

User asked to provide API key for .env — potential for accidental credential exposure in chat history if agent pastes key

SKILL.md | Constraint 3 ('Prefer they edit .env themselves — don't paste keys into chat')

Referenced Domains

External domains referenced in skill content, detected by static analysis.

docs.langchain.com

Use Cases

Quickly prototype a LangChain agent locally without complex setup
Evaluate LangChain across different LLM providers (OpenAI, Anthropic, Google)
Learn LangChain basics through a working weather agent example
Test provider API keys and model compatibility in isolation
Set up a minimal Python agent project that can be extended with additional tools

Quality Notes

Positive: Skill explicitly discourages agent from pasting API keys into chat, recommending user self-edit of .env file
Positive: Clear scope boundaries — new isolated directory, model-agnostic, minimal setup
Positive: Directs agent to live official docs rather than hardcoding API patterns, reducing staleness
Positive: Constraint list is well-structured and actionable
Positive: Includes suggested user prompt with concrete examples of provider:model syntax
Negative: No error handling guidance — what should agent do if docs fetch fails, pip install fails, or model is unavailable?
Negative: Missing step-by-step walkthrough of implementation — agent must infer from docs alone
Negative: No mention of Python version requirements or virtual environment setup (venv), which could cause confusion
Negative: Constraint 4 (install provider package) is vague — no guidance on detecting which package is needed for each provider

Model: claude-haiku-4-5-20251001Analyzed: Oct 12, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

langchain-python-quickstart