Catalog
langchain-ai/langchain-typescript-quickstart

langchain-ai

langchain-typescript-quickstart

Scaffold a minimal local LangChain agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent locally.

v1.0LATEST
NewUpdated Oct 12, 2026

LangChain TypeScript quickstart

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

https://docs.langchain.com/oss/javascript/langchain/quickstart

Fetch that page (Docs MCP or HTTP) and implement what it shows (weather agent + createAgent). Requires Node 22+.

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.

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

75

Quality

68

Clarity

78

Completeness

65

Summary

A scaffolding skill that guides users through setting up a minimal LangChain TypeScript agent following the official quickstart. The skill emphasizes model-agnostic setup by asking users to specify their provider/model choice, creates an isolated project directory, and handles API credentials via `.env` files with explicit guidance to avoid pasting secrets in chat.

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

Detected Capabilities

file writedirectory creationhttp requestenvironment variable configurationshell execution (npm install, node)

Trigger Keywords

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

langchain setup typescriptscaffold langchain agentlangchain quickstart localtry langchain locallylangchain typescript starter

Risk Signals

WARNING

Direct .env file access for API keys

SKILL.md | constraint 3
INFO

Instruction to user to edit .env themselves with API credentials

SKILL.md | constraint 3

Referenced Domains

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

docs.langchain.com

Use Cases

  • .Quickly scaffold a LangChain TypeScript agent for local experimentation
  • Set up a model-agnostic agent with user-chosen LLM provider
  • Create an isolated LangChain project without polluting the current workspace
  • Follow official LangChain quickstart with practical local constraints
  • Build a weather agent example as a starting point for LangChain learning

Quality Notes

  • Positive: clear scope boundaries (isolated directory, no LangSmith/Tavily unless requested)
  • Positive: explicit guidance to avoid pasting secrets in chat (security-conscious)
  • Positive: model-agnostic approach encourages learning about provider flexibility
  • Positive: follows official quickstart as the source of truth (reduces drift)
  • Negative: no edge case coverage (missing Node 22+, network failures, invalid provider names)
  • Negative: minimal error handling guidance (what if npm install fails?)
  • Negative: truncated external link text (URL shown in docs but full guidance is on-site)
  • Negative: constraint 4 mentions provider package installation but no guidance on troubleshooting missing dependencies
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.

Use langchain-ai/langchain-typescript-quickstart in your dev environment

Command Palette

Search for a command to run...