使用方法
- 复制安装命令,在自己的智能体环境安装前先检查源码包。
- 从原始文档核对所需工具、凭据和支持的宿主。
- 说明输入材料与期望交付物,并对照来源检查输出。
npx skills add https://github.com/dcoon/agent-kit --skill context7开始前需了解
- 安装不包含模型订阅、API 额度或访问文件的权限。
- 仓库星数和安装量反映活跃情况,不等于独立质量或安全测试。
按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。
Guards
- Warn user if squeez tool and MCP aren't available. Do not install squeez unless approved.
- Read only. Never edit without approval.
<!-- context7 --> Use Context7 MCP to fetch current documentation whenever the user asks about a library, framework, SDK, API, CLI tool, or cloud service — even well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot. This includes API syntax, configuration, version migration, porting code between libraries, platforms, or SQL dialects, library-specific debugging, setup instructions, and CLI tool usage. Use even when you think you know the answer — your training data may not reflect recent changes. Prefer this over web search for library docs.
Do not use for: refactoring, debugging, or reviewing code that does not depend on a library or platform API, or general programming concepts.
Steps
- Always start with
resolve-library-idusing the library name and what to look up in the library's documentation, unless the user provides an exact library ID in/org/projectformat - Pick the best match (ID format:
/org/project) by: exact name match, description relevance, code snippet count, source reputation (High/Medium preferred), and benchmark score (higher is better). If results don't look right, try alternate names or queries (e.g., "next.js" not "nextjs", or rephrase the question). Use version-specific IDs when the user mentions a version query-docswith the selected library ID and what to look up in the library's documentation (not single words), scoped to a single concept. If the question spans multiple distinct concepts (e.g. routing and auth and caching), make a separatequery-docscall per concept with the same library ID, unless the question is about how the concepts interact — combined queries dilute ranking and return shallow results for each topic- Answer using the fetched docs
Library source code
If the query-code tool is available, use it when the docs do not answer an exact question: a signature or type, a default value, an option name, where an error message comes from, or how something works inside.
- Use a library ID that
resolve-library-idmarks with "Source code", usually the GitHub repository (e.g./colinhacks/zod)./websites/...and/llmstxt/...IDs have no source - Start with
grep(setfixed_stringsfor error messages) ordefinitionfor a symbol, thenreadthe file range in the result's "Next:" line - For a version, pass its git tag in
version(e.g.v3.24.2) - Most questions need 1 to 4
query-codecalls; stop at 6 - If it answers "being indexed", retry at most twice, then answer from
query-docs - Cite the file and line of the source you used
<!-- context7 -->