LangGraph TypeScript quickstart

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

https://docs.langchain.com/oss/javascript/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 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 initChatModel("<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 createAgent instead.

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

76/100

Grade

B

Good

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

Safety

82

Quality

72

Clarity

78

Completeness

65

Summary

A skill that guides users through scaffolding a minimal LangGraph agent in TypeScript by following the official LangChain quickstart. It provides local setup constraints (new directory isolation, .env-based secrets, provider model selection) and walks the user through creating a simple calculator agent, then exits. The skill emphasizes following live documentation and keeping setup model-agnostic.

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 creationpackage installation (npm/yarn)code generationenvironment file handling (.env)external documentation fetchshell command execution

Trigger Keywords

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

langgraph quickstartbuild agent typescriptgraph api setupagent scaffoldingtry langgraph locallymath agent example

Risk Signals

INFO

Direct .env file access for API key storage

SKILL.md, Local setup constraints section 3

INFO

.env file referenced as location for provider API key

SKILL.md, instruction to prefer user self-edit of .env

Referenced Domains

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

docs.langchain.com

Use Cases

Quick prototyping of a LangGraph agent locally
Learning LangGraph fundamentals with a concrete example
Testing LangGraph with different AI providers (Anthropic, OpenAI, Google)
Building a minimal math agent to understand the Graph API
Setting up a local development environment for agent experimentation

Quality Notes

Positive: Clear scope boundaries — work isolated to new `langgraph-agent/` directory with no pollution of existing project
Positive: Explicit security guardrail — user asked to handle .env editing themselves (avoids pasting credentials in chat)
Positive: Practical provider selection flow with sensible default (Claude Sonnet 5)
Positive: References live documentation (docs.langchain.com) rather than inventing API from memory
Positive: Terminates early after first working example, pointing to next steps (langgraph-fundamentals)
Negative: No documented error handling for missing dependencies, API key failures, or network issues during doc fetch
Negative: No guidance on .gitignore validation or confirmation that .env is actually ignored
Negative: Limited edge case coverage (e.g., what if fetch of docs fails? what if model provider doesn't support initChatModel?)
Negative: Instructions assume `initChatModel()` exists and is the correct import — no fallback if API has changed

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-typescript-quickstart