context7-docs
About
The context7-docs skill fetches current, official documentation for frameworks and libraries to prevent hallucinations from stale training data. Use it when working with evolving tools like React, Next.js, or Vue to get accurate APIs and code examples. It activates via keywords like "use context7" or when discussing latest documentation.
Quick Install
Claude Code
Recommended/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/context7-docsCopy and paste this command in Claude Code to install this skill
Documentation
Context7 Documentation Fetching
This skill enables fetching up-to-date, version-specific documentation directly from official sources.
Problem Solved
LLMs have stale training data. When working with Next.js 15, React 19, or any library that evolved since the model's cutoff date, you get:
- Hallucinated APIs that don't exist
- Deprecated patterns
- Outdated code examples
When to Use
- Working with any framework/library (React, Next.js, Vue, Astro, Tailwind, etc.)
- Need current official documentation
- Want accurate code examples
- Encountering unfamiliar APIs
- Starting a new project with latest versions
How to Activate
Simply include "use context7" in your prompt:
use context7 でNext.js 15のApp Routerについて教えて
use context7 React 19の新機能を使ってコンポーネントを作って
Available Tools
1. resolve-library-id
Converts library name to Context7 ID.
Input: "next.js"
Output: "/vercel/next.js/v15.0.0"
2. get-library-docs
Fetches documentation chunks and code examples.
Parameters:
context7_id: Library ID from resolve-library-idtopic(optional): Specific topic to filtertokens(optional): Max tokens (default 5000)
Example Usage
Basic Documentation Fetch
User: use context7 でReact 19のuseActionStateの使い方を教えて
AI: [Calls resolve-library-id with "react"]
[Calls get-library-docs with topic "useActionState"]
[Returns current, accurate documentation]
Framework Setup
User: use context7 で最新のAstro 5プロジェクトをセットアップして
AI: [Fetches current Astro 5 documentation]
[Provides accurate setup commands and configuration]
Supported Libraries
Context7 supports documentation from major frameworks and libraries:
| Category | Libraries |
|---|---|
| Frontend | React, Vue, Svelte, Angular, Solid |
| Meta-frameworks | Next.js, Nuxt, Astro, Remix, SvelteKit |
| Styling | Tailwind CSS, CSS-in-JS libraries |
| State | Redux, Zustand, Jotai, Recoil |
| Testing | Jest, Vitest, Playwright, Cypress |
| Backend | Express, Fastify, Hono, tRPC |
| Database | Prisma, Drizzle, TypeORM |
| Build | Vite, esbuild, webpack, turbopack |
Best Practices
-
Always use for rapidly evolving frameworks
- Next.js (major updates frequently)
- React (new features in v19)
- Tailwind (v4 breaking changes)
-
Specify version when needed
use context7 Next.js 15.1の新機能 -
Combine with specific topics
use context7 Prismaのリレーション設定 -
Use for debugging
use context7 このエラーはReact 19で解決されてる?
Integration with TAISUN
Context7 is automatically available via MCP. No additional setup required.
When you include "use context7" or work with framework-specific tasks, the system will:
- Detect the library/framework
- Resolve the Context7 ID
- Fetch relevant documentation
- Provide accurate, current information
Source
GitHub Repository
Related Skills
content-collections
MetaThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
creating-opencode-plugins
MetaThis skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
langchain
MetaLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.
