skill-builder

Convert documentation, repositories, PDFs, and videos into AI-ready skill packages.

9|6|Updated Aug 25, 2017
One-click install
npx skills add https://github.com/sergueik/springboot_study --skill skill-builder-sergueik
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-builder
Source: https://github.com/sergueik/springboot_study/tree/main/basic-skill-seekers/distribution/claude-plugin/skills/skill-builder
Command: npx skills add https://github.com/sergueik/springboot_study --skill skill-builder-sergueik

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires skill-seekers.

What problem does it solve? Turning scattered knowledge sources like documentation sites, GitHub repos, PDFs, and videos into structured AI skills requires manual scraping, formatting, and packaging. This Skill automates that entire pipeline through the Skill Seekers MCP server or its CLI fallback. ## Core Features & Use Cases - Automatic Source Detection: Identifies whether input is a documentation URL, GitHub repo, PDF, video, local codebase, or other format and routes it to the correct scraping tool. - End-to-End Skill Pipeline: Generates configs, scrapes content, enhances output with AI, and packages skills for platforms like Claude, Gemini, OpenAI, and LangChain. - Vector Database Export: Exports generated skills to Weaviate, Chroma, FAISS, or Qdrant for retrieval workflows. - Use Case: A developer wants to give their AI assistant deep knowledge of a framework. They provide the framework's documentation URL, and this Skill scrapes the site, builds a structured skill, and packages it for their platform. ## Quick Start Create a skill from the documentation at https://docs.example.com and package it for Claude.

Frequently Asked Questions about skill-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an AI skill from a documentation website?

Provide the documentation URL and the skill detects it as a documentation source, then uses the scrape_docs tool to crawl the site. After scraping, it can enhance the content and package the result into a distributable skill for your target platform.

What source types can Skill Seekers convert into skills?

Skill Seekers supports documentation sites, GitHub repositories, PDF files, video transcripts, local codebases, Jupyter notebooks, HTML, OpenAPI specs, AsciiDoc, PowerPoint, RSS feeds, man pages, Confluence, and Notion. The source type is detected automatically from your input.

What do I do if the Skill Seekers MCP tools are not available?

If tools like scrape_docs are missing, the MCP server is not connected. Install the package with pip install "skill-seekers[mcp]" and register the server, or use the CLI fallback by running skill-seekers create followed by your source.

Can I export a generated skill to a vector database?

Yes, the skill supports exporting generated content to Weaviate, Chroma, FAISS, and Qdrant using dedicated export tools. This is useful when you want retrieval-augmented access to the scraped knowledge rather than a packaged skill.

How do I build a skill from a GitHub repository?

Provide the repository in owner/repo format or as a github.com URL, and the skill routes it to the scrape_github tool. It can also detect design patterns and extract test examples from the repository to enrich the generated skill.