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.

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

82/100

Grade

B

Good

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

Safety

85

Quality

80

Clarity

88

Completeness

76

Summary

This skill guides an agent to scaffold a minimal local LangGraph agent in Python by following the official quickstart documentation. It provides structured setup constraints (isolated directory, model selection, .env-based credentials) and directs the agent to implement a calculator example from the LangChain docs, then stop.

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

file writedirectory creationenvironment variable setuphttp requestcode generationpip installshell execution

Trigger Keywords

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

langgraph quickstartbuild python agentlanggraph calculator examplelocal agent setuplanggraph proof-of-concept

Risk Signals

WARNING

SEC-020: Direct .env file access documented as credential storage location

SKILL.md | Section 'Local setup constraints', item 3

INFO

External documentation link (docs.langchain.com) is the source of truth for implementation

SKILL.md | Line 5 and throughout

Referenced Domains

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

docs.langchain.com

Use Cases

Quick proof-of-concept LangGraph agent locally
Test LangGraph with different model providers
Learn LangGraph Graph API basics before advanced patterns
Verify LangChain model integration setup
Build a minimal agent for experimentation or demos

Quality Notes

Excellent scoping: isolated directory (langgraph-agent/) prevents project pollution
Strong credential hygiene: explicitly directs users to edit .env themselves, avoids pasting keys in chat
Clear model selection prompt with provider:model format and sensible default
Well-bounded scope: stops after running one example, points to next learning resource (langgraph-fundamentals)
Good constraints on dependencies: only installs quickstart packages + provider package
Mentions unsupported Claude Sonnet 5+ parameters (temperature, top_p, top_k), showing version awareness
References official docs as source of truth rather than hardcoding API — future-proofs against changes
Explicitly skips IPython visualization (scope reduction)
Includes rationale for setup decisions (model-agnostic, minimal, gitignored)
Minor: Could benefit from error handling guidance (e.g., import errors, API key validation) and success criteria definition

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.

langgraph-python-quickstart