Skill Builder

It detects whether you're pointing at a documentation site, GitHub repo, video, or PDF, then pulls the right scraping tool from a suite of 40. The workflow is straightforward: detect source type, generate a config, scrape, optionally enhance with AI, then package or export to vector databases like Weaviate or Chroma. What's nice is the automatic source detection, you just paste a URL or file path and it figures out the rest. Covers edge cases too, like Jupyter notebooks, OpenAPI specs, even manpages. Solid if you're building custom skills at scale.