skill-builder
关于
The skill-builder automatically detects source types (like docs, repos, or PDFs) and converts them into AI-ready skills using Skill Seekers' tools. It is used to create, update, or sync skills from knowledge sources and can export them to vector databases. Developers should use it when they need to package documentation or other content for LLM consumption.
快速安装
Claude Code
推荐npx skills add yusufkaraaslan/Skill_Seekers -a claude-code/plugin add https://github.com/yusufkaraaslan/Skill_Seekersgit clone https://github.com/yusufkaraaslan/Skill_Seekers.git ~/.claude/skills/skill-builder在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Skill Builder
You have access to the Skill Seekers MCP server which provides 40 tools for converting knowledge sources into AI-ready skills.
When to Use This Skill
Use this skill when the user:
- Wants to create an AI skill from a documentation site, GitHub repo, PDF, video, or other source
- Needs to convert documentation into a format suitable for LLM consumption
- Wants to update or sync existing skills with their source documentation
- Needs to export skills to vector databases (Weaviate, Chroma, FAISS, Qdrant)
- Asks about scraping, converting, or packaging documentation for AI
Source Type Detection
Automatically detect the source type from user input:
| Input Pattern | Source Type | Tool to Use |
|---|---|---|
https://... (not GitHub/YouTube) | Documentation | scrape_docs |
owner/repo or github.com/... | GitHub | scrape_github |
*.pdf | scrape_pdf | |
| YouTube/Vimeo URL or video file | Video | scrape_video |
| Local directory path | Codebase | scrape_codebase |
*.ipynb, *.html, *.yaml (OpenAPI), *.adoc, *.pptx, *.rss, *.1-.8 | Various | scrape_generic |
| JSON config file | Unified | Use config with scrape_docs |
Recommended Workflow
- Detect source type from the user's input
- Generate or fetch config using
generate_configorfetch_configif needed - Estimate scope with
estimate_pagesfor documentation sites - Scrape the source using the appropriate scraping tool
- Enhance with
enhance_skillif the user wants AI-powered improvements - Package with
package_skillfor the target platform - Export to vector DB if requested using
export_to_*tools
Available MCP Tools
Config Management
generate_config— Generate a scraping config from a URLlist_configs— List available preset configsvalidate_config— Validate a config file
Scraping (use based on source type)
scrape_docs— Documentation sitesscrape_github— GitHub repositoriesscrape_pdf— PDF filesscrape_video— Video transcriptsscrape_codebase— Local code analysisscrape_generic— Jupyter, HTML, OpenAPI, AsciiDoc, PPTX, RSS, manpage, Confluence, Notion, chat
Post-processing
enhance_skill— AI-powered skill enhancementpackage_skill— Package for target platformupload_skill— Upload to platform APIinstall_skill— End-to-end install workflow
Advanced
detect_patterns— Design pattern detection in codeextract_test_examples— Extract usage examples from testsbuild_how_to_guides— Generate how-to guides from testssplit_config— Split large configs into focused skillsexport_to_weaviate,export_to_chroma,export_to_faiss,export_to_qdrant— Vector DB export
GitHub 仓库
常见问题
什么是 skill-builder Skill?
skill-builder 是一个 Claude Skill,作者为 yusufkaraaslan。Skill 将 Claude 按需加载的说明和资源打包,让 Claude 无需额外提示即可执行与 skill-builder 相关的任务。
如何安装 skill-builder?
使用本页的安装命令:将 skill-builder 作为插件添加到 Claude Code,或将其仓库克隆到 skills 目录,然后重启 Claude 以加载该 Skill。
skill-builder 属于哪个分类?
skill-builder 属于元分类。
skill-builder 可以免费使用吗?
可以。skill-builder 已收录在 AIMCP,可免费安装。
相关推荐技能
Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
