Domains
Forms
Mechanism
Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.
When the user wants to deep-crawl a website, recursively scrape a whole site, build a RAG corpus / vector DB from docs, or convert a site to clean markdown/text.
scripts/).crawl_state.json and pages/ dir, then run BFS loop: navigate, wait stable, extract-page-content.py for clean text/markdown/HTML + metadata + outbound links.A directory of per-page records {url, crawl, metadata, text, markdown, html, outboundLinks} — LLM-ready corpus for RAG, chatbots, or training data.
Use Cases
A SaaS company wants to feed its public documentation into a support chatbot. The team provides the docs root URL; the skill crawls every in-scope page, strips nav/footer, and writes clean markdown per page. The resulting corpus is embedded into a vector store, giving the bot accurate answers from official docs without manual copy-paste, cutting onboarding time for the knowledge team.
An AI researcher needs a training corpus from a public knowledge base. Using the skill with depth and page limits, they recursively crawl the site, extract text/HTML with metadata (title, author, language), and persist per-page JSON. The clean, structured dataset is then used to fine-tune a model or evaluate retrieval, saving weeks of manual scraping and cleaning.
Skill Relationships
Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.
Tier 1 · These Skills Use Me
Tier 2 · Current Skill
Tier 3 · I Use These Skills
Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.
Skill File