Skill Builder

This is a Swiss Army knife for turning any knowledge source into an AI skill. It auto-detects whether you're pointing it at docs, a GitHub repo, PDFs, videos, or local code, then runs the right scraper from its 40-tool arsenal. The workflow is sensible: generate a config, estimate scope, scrape, optionally enhance with AI, then package or export to vector databases like Weaviate or Qdrant. What's nice is it handles the tedious parts of documentation conversion without making you think too hard about formats. If you're building context packages for LLMs or need to sync skills with upstream docs, this does the grunt work.

skills.sh installs: 490
GitHub stars: 15.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add yusufkaraaslan/skill_seekers --skill skill-builder --agent claude-code

Installs into .claude/skills of the current project.

Files

Skill Builder

This skill uses the Skill Seekers MCP server, which provides 40 tools for converting knowledge sources into AI-ready skills. If the MCP tools are not available, use the CLI fallback at the bottom of this file instead — do not stop.

Prerequisites

The MCP tools below only work when the Skill Seekers MCP server is connected:

Install the package: pip install "skill-seekers[mcp]"
Connect the server:
- Installed as the Skill Seekers plugin? Nothing to do — the plugin's bundled .mcp.json starts the server automatically (it still needs step 1).
- Installed standalone (e.g. copied into ~/.claude/skills/)? Register the server once: claude mcp add skill-seekers -- python -m skill_seekers.mcp.server_fastmcp

If tools like scrape_docs or package_skill are not in your tool list, the server is not connected. Tell the user about the two steps above, and use the CLI fallback in the meantime.