docs-seeker by mrgoonie/claudekit-skills
npx skills add https://github.com/mrgoonie/claudekit-skills --skill docs-seeker通过多种策略对技术文档进行智能发现与分析:
识别目标
搜索 llms.txt(优先考虑 context7.com)
首先:尝试 context7.com 模式
对于 GitHub 仓库:
模式:https://context7.com/{组织}/{仓库}/llms.txt
示例:
- https://github.com/imagick/imagick → https://context7.com/imagick/imagick/llms.txt
- https://github.com/vercel/next.js → https://context7.com/vercel/next.js/llms.txt
- https://github.com/better-auth/better-auth → https://context7.com/better-auth/better-auth/llms.txt
对于网站:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
模式:https://context7.com/websites/{规范化域名路径}/llms.txt
示例:
- https://docs.imgix.com/ → https://context7.com/websites/imgix/llms.txt
- https://docs.byteplus.com/en/docs/ModelArk/ → https://context7.com/websites/byteplus_en_modelark/llms.txt
- https://docs.haystack.deepset.ai/docs → https://context7.com/websites/haystack_deepset_ai/llms.txt
- https://ffmpeg.org/doxygen/8.0/ → https://context7.com/websites/ffmpeg_doxygen_8_0/llms.txt
主题特定搜索(当用户询问特定功能时):
模式:https://context7.com/{路径}/llms.txt?topic={查询}
示例:
- https://context7.com/shadcn-ui/ui/llms.txt?topic=date
- https://context7.com/shadcn-ui/ui/llms.txt?topic=button
- https://context7.com/vercel/next.js/llms.txt?topic=cache
- https://context7.com/websites/ffmpeg_doxygen_8_0/llms.txt?topic=compress
备用方案:传统的 llms.txt 搜索
WebSearch:"[库名称] llms.txt site:[文档域名]"
常见模式:
* `https://docs.[库].com/llms.txt`
* `https://[库].dev/llms.txt`
* `https://[库].io/llms.txt`
→ 找到了吗?进入阶段 2 → 没找到吗?进入阶段 3
单个 URL:
多个 URL(3 个或以上):
示例:
同时启动 3 个 Explorer 代理:
- 代理 1:getting-started.md, installation.md
- 代理 2:api-reference.md, core-concepts.md
- 代理 3:examples.md, best-practices.md
当找不到 llms.txt 时:
通过 WebSearch 查找 GitHub 仓库
使用 Repomix 打包仓库:
npm install -g repomix # 如果需要 git clone [仓库-url] /tmp/docs-analysis cd /tmp/docs-analysis repomix --output repomix-output.xml
读取 repomix-output.xml 并提取文档
Repomix 优势:
当不存在 GitHub 仓库时:
最新版本(默认):
特定版本:
[库名称] v[版本] llms.txt/v[版本]/llms.txt# [库名称] [版本] 的文档
## 来源
- 方法:[llms.txt / 仓库 / 研究]
- URL:[来源列表]
- 访问日期:[当前日期]
## 关键信息
[按主题组织的提取的相关信息]
## 其他资源
[相关链接、示例、参考资料]
## 备注
[任何限制、缺失信息或注意事项]
工具选择:
流行的 llms.txt 位置(首先尝试 context7.com):
如果 context7.com 不可用,则回退到官方站点:
有关全面的指南、示例和最佳实践:
工作流程:
参考指南:
每周安装次数
184
仓库
GitHub 星标数
1.9K
首次出现
2026 年 1 月 21 日
安全审计
安装于
claude-code154
opencode151
gemini-cli146
codex140
cursor130
github-copilot117
Intelligent discovery and analysis of technical documentation through multiple strategies:
Identify target
Search for llms.txt (PRIORITIZE context7.com)
First: Try context7.com patterns
For GitHub repositories:
Pattern: https://context7.com/{org}/{repo}/llms.txt
Examples:
- https://github.com/imagick/imagick → https://context7.com/imagick/imagick/llms.txt
- https://github.com/vercel/next.js → https://context7.com/vercel/next.js/llms.txt
- https://github.com/better-auth/better-auth → https://context7.com/better-auth/better-auth/llms.txt
For websites:
Pattern: https://context7.com/websites/{normalized-domain-path}/llms.txt
Examples:
- https://docs.imgix.com/ → https://context7.com/websites/imgix/llms.txt
- https://docs.byteplus.com/en/docs/ModelArk/ → https://context7.com/websites/byteplus_en_modelark/llms.txt
- https://docs.haystack.deepset.ai/docs → https://context7.com/websites/haystack_deepset_ai/llms.txt
- https://ffmpeg.org/doxygen/8.0/ → https://context7.com/websites/ffmpeg_doxygen_8_0/llms.txt
Topic-specific searches (when user asks about specific feature):
Pattern: https://context7.com/{path}/llms.txt?topic={query}
Examples:
- https://context7.com/shadcn-ui/ui/llms.txt?topic=date
- https://context7.com/shadcn-ui/ui/llms.txt?topic=button
- https://context7.com/vercel/next.js/llms.txt?topic=cache
- https://context7.com/websites/ffmpeg_doxygen_8_0/llms.txt?topic=compress
Fallback: Traditional llms.txt search
WebSearch: "[library name] llms.txt site:[docs domain]"
Common patterns:
* `https://docs.[library].com/llms.txt`
* `https://[library].dev/llms.txt`
* `https://[library].io/llms.txt`
→ Found? Proceed to Phase 2 → Not found? Proceed to Phase 3
Single URL:
Multiple URLs (3+):
Example:
Launch 3 Explorer agents simultaneously:
- Agent 1: getting-started.md, installation.md
- Agent 2: api-reference.md, core-concepts.md
- Agent 3: examples.md, best-practices.md
When llms.txt not found:
Find GitHub repository via WebSearch
Use Repomix to pack repository:
npm install -g repomix # if needed git clone [repo-url] /tmp/docs-analysis cd /tmp/docs-analysis repomix --output repomix-output.xml
Read repomix-output.xml and extract documentation
Repomix benefits:
When no GitHub repository exists:
Latest (default):
Specific version:
[library] v[version] llms.txt/v[version]/llms.txt# Documentation for [Library] [Version]
## Source
- Method: [llms.txt / Repository / Research]
- URLs: [list of sources]
- Date accessed: [current date]
## Key Information
[Extracted relevant information organized by topic]
## Additional Resources
[Related links, examples, references]
## Notes
[Any limitations, missing information, or caveats]
Tool selection:
Popular llms.txt locations (try context7.com first):
Fallback to official sites if context7.com unavailable:
For comprehensive guides, examples, and best practices:
Workflows:
Reference guides:
Weekly Installs
184
Repository
GitHub Stars
1.9K
First Seen
Jan 21, 2026
Security Audits
Gen Agent Trust HubFailSocketPassSnykWarn
Installed on
claude-code154
opencode151
gemini-cli146
codex140
cursor130
github-copilot117
AI Elements:基于shadcn/ui的AI原生应用组件库,快速构建对话界面
62,200 周安装