From neatlogs
Use when adding neatlogs observability to a TypeScript/Node.js project that uses LangChain or LangGraph (depends on `@langchain/*` / `@langchain/langgraph`).
How this skill is triggered — by the user, by Claude, or both
Slash command
/neatlogs:neatlogs-ts-langchainThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This project uses LangChain (`@langchain/*`) or LangGraph (`@langchain/langgraph`). The `langchain` instrumentation auto-traces LLM calls, chains, agents, tools, and retrievers. Your job is minimal: init before the LangChain import, and add ONE `span({ kind:'WORKFLOW' })` on the user-facing entry.
This project uses LangChain (@langchain/*) or LangGraph (@langchain/langgraph). The langchain instrumentation auto-traces LLM calls, chains, agents, tools, and retrievers. Your job is minimal: init before the LangChain import, and add ONE span({ kind:'WORKFLOW' }) on the user-facing entry.
await init({ instrumentations: ['langchain'] }) BEFORE importing @langchain/*.import() the LangChain modules AFTER init.span({ kind:'WORKFLOW' }, fn) on the entry that runs the chain/graph/agent. Everything inside is auto-traced.llm.invoke() / .stream() → LLM spansreferences/1-install.mdreferences/2-add-init.mdreferences/3-set-env.mdreferences/4-add-workflow.mdreferences/5-lifecycle.mdawait init(...) MUST run BEFORE any @langchain/* import. Use dynamic import() AFTER init.instrumentations: ['langchain'] covers LangChain AND LangGraph. The langchain instrumentor also captures the underlying LLM (no separate provider key needed for chat models routed through LangChain).span({ kind:'WORKFLOW' }) on the user-facing entry that runs the chain/graph/agent.llm.invoke() with span()/trace() — they are auto-traced; manual wrapping duplicates.process.env.references/nextjs.md — REQUIRED if the project is a Next.js app, else the server 500s with Can't resolve 'crypto' and emits no traces.references/decorators-and-traces.mdreferences/prompt-templates.mdreferences/troubleshooting.mdnpx claudepluginhub neatlogs/skills --plugin neatlogs-tsProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.