Crawl JavaScript-rendered websites and extract structured JSON or Markdown data.
npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-crawler
Please help me install this Agent Skill. Skill: mofa-crawler Source: https://github.com/mofa-org/mofa-skills/tree/main/_unpublished/mofa-crawler Command: npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-crawler
MOFA Crawler addresses the challenge of extracting data from modern, JavaScript-heavy websites by using Cloudflare's Browser Rendering API to fetch fully rendered pages and produce AI-structured outputs.
Provide a starting URL and run a crawl to obtain Markdown output by default.
High-intent search queries and answers about installing and using this skill.
Crawl JavaScript-rendered websites by fetching fully rendered pages via Cloudflare's Browser Rendering API, then output the extracted content into AI-ready JSON or Markdown formats by simply providing a starting URL.
Yes, you can build a RAG knowledge base by crawling dynamic marketing pages and knowledge bases, extracting the JavaScript-rendered content directly into Markdown formats ready for RAG ingestion.
The best way to crawl dynamic content for AI extraction is to fetch fully rendered pages via Cloudflare's Browser Rendering API, transforming JavaScript-heavy DOM structures into structured JSON or Markdown outputs.
Yes, the web scraping tool fulfills access controls, environment variable handling, and URL filtering to ensure robust error handling and reliable production use during dynamic content extraction.
Standard web scrapers fail on JavaScript-heavy sites because they cannot execute client-side scripts to render the DOM; using a Cloudflare browser rendering approach fetches the fully rendered page to capture dynamic content successfully.
Crawling JS-rendered pages yields AI-structured JSON and Markdown outputs by default, providing RAG-ready formats optimized for downstream content analysis and competitive research.
jscraikInitiate, monitor, and export website crawls via the Cloudflare Browser Rendering API.
karrtik159Build RAG systems with vector databases and semantic search.
UniquecreteExtract structured data from web pages using CSS schemas and crawling.
kevinnftExtract structured data from static HTML, JS-rendered pages, and hybrid sites.
