context7-docs
について
context7-docsスキルは、フレームワークやライブラリの最新の公式ドキュメントを取得し、古いトレーニングデータによる誤った生成(ハルシネーション)を防ぎます。React、Next.js、Vueなどの進化の速いツールを扱う際に、正確なAPIやコード例を得るために使用してください。「use context7」などのキーワードや、最新のドキュメントについて議論する際に自動的に起動します。
クイックインストール
Claude Code
推奨/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/context7-docsこのコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします
ドキュメント
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- Outdated code examples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 リポジトリ
関連スキル
content-collections
メタThis 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
メタThis 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
テストThis 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.
polymarket
メタThis skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.
