This skill provides a general-purpose web scraping and crawling capability. It can fetch pages via HTTP, fall back to a headless browser for client-rendered sites, and return structured JSON containing extracted text, tables, and lists. Use it to extract article bodies, product data, or to monitor site changes programmatically. It supports batch URL processing and pagination handling for multi-page datasets.
Use this skill when you need dependable content extraction from static or JavaScript-heavy sites, to collect product information, scrape tables, or build datasets from public web pages. Prefer it for research, data-mining, monitoring site updates, and cases where you want well-structured JSON output. Respect site terms of service and rate limits.
Works with agent tooling that can run HTTP requests or control headless browsers (examples: Claude/Code-style agents, Cursor/Copilot integrations, or custom Node/Python runtimes).
This skill has not been reviewed by our automated audit pipeline yet.