Skills for Real Engineers. Straight from my .agents directory.
langchain-typescript-quickstart
Agent skill fromlangchain-ai/langchain-skills
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.
How to install langchain-typescript-quickstart
npx skills add langchain-ai/langchain-skills# or add only this skill to Claude Code: copy the folder
config/skills/langchain-typescript-quickstart/
# into
~/.claude/skills/langchain-typescript-quickstart/ (all projects)
.claude/skills/langchain-typescript-quickstart/ (one project)
1# LangChain TypeScript quickstart23Follow the live docs — do not invent an alternate API from memory:45**https://docs.langchain.com/oss/javascript/langchain/quickstart**67Fetch that page (Docs MCP or HTTP) and implement what it shows (weather agent + `createAgent`). Requires Node 22+.89## Local setup constraints1011Apply these on top of the quickstart (they keep setup minimal and model-agnostic):12131. **Ask** which provider/model to use. Showcase that LangChain is model-agnostic. Suggested prompt:1415 > 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`**.1617 Swap the quickstart's model string for their choice (or the default).18192. Create a **new** directory (e.g. `langchain-agent/`) and do all work there — do not pollute the open project.20213. 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.22234. Install the provider package needed for their model if the quickstart's base install isn't enough.24255. Run the example, show output, then stop. Point to `langchain-fundamentals` for next steps.
Excerpt shown under the repository's MIT license.
More skills in langchain-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
