This is a well-structured scraping toolkit built around Playwright's browser tools. It comes with Python utilities for validating URLs against robots.txt before you start, rate limiting helpers that enforce 1-3 second delays between requests, and processing scripts that convert your scraped JSON into CSV or Markdown. The documentation is thorough on the ethical side, covering exponential backoff for 429 responses and handling pagination patterns. You get extraction templates for common selectors and a clear workflow from URL validation through to export. If you're scraping multiple pages and want the guardrails built in rather than having to remember them yourself, this covers the boilerplate well.
npx skills add https://github.com/dawiddutoit/custom-claude --skill playwright-web-scraper