Extract content from modern websites and export clean Markdown documentation.
npx skills add https://github.com/northseadl/norix-skills --skill web-scraper-northseadl
Please help me install this Agent Skill. Skill: web-scraper Source: https://github.com/northseadl/norix-skills/tree/main/web-scraper Command: npx skills add https://github.com/northseadl/norix-skills --skill web-scraper-northseadl
Modern websites often rely on client-side rendering, making data extraction and documentation stale or incomplete. This skill automates content discovery, SPA rendering when needed, and clean Markdown export to accelerate knowledge capture.
Fetch a sample page and export the rendered content as Markdown.
High-intent search queries and answers about installing and using this skill.
To scrape JavaScript-rendered pages and export Markdown, the skill uses HTTP-first probing with a browser fallback to render dynamic SPA content, then converts the extracted data into clean Markdown documentation for analytics workflows.
Extracting OpenAPI or Swagger documentation into Markdown is handled by smart site discovery features that parse API specifications and export them as clean, organized Markdown files suitable for offline engineering reference.
Yes, this web scraper supports batch fetching with precision extraction, allowing you to crawl multiple pages and export the entire content as organized Markdown documentation for offline use.
The best way to automate content extraction from modern SPAs is using a smart discovery tool that probes HTTP first and falls back to browser rendering, ensuring dynamic content is fully captured before Markdown export.
Yes, leveraging the crawl4ai dependency, the skill performs smart site discovery using sitemaps, navigation structures, and breadth-first search to locate and extract content automatically.
vzcoInject ARC Probe into a running Windows x64 process via TCP port 9998.
joonlabConvert web page DOM content into Markdown files with YAML frontmatter.
QredenceFetch and inspect JavaScript-heavy web pages using a Daytona-enabled Playwright browser snapshot.
cameronraysmithConvert URLs to Markdown using trafilatura and shot-scraper.
