Download web pages and YouTube videos into Markdown or JSON.
npx skills add https://github.com/itda-skills/skills.pub --skill web-reader-itda-skills
Please help me install this Agent Skill. Skill: web-reader Source: https://github.com/itda-skills/skills.pub/tree/main/itda-work/skills/web-reader Command: npx skills add https://github.com/itda-skills/skills.pub --skill web-reader-itda-skills
This Skill streamlines the process of retrieving and converting web content and videos into clean, readable Markdown or JSON formats, reducing manual copying and formatting time.
Use the web-reader to fetch and convert the URL 'https://example.com/article' into Markdown for easy reading and note-taking.
High-intent search queries and answers about installing and using this skill.
To extract web content and convert HTML to Markdown, the Skill fetches web pages using requests and beautifulsoup4, then transforms the extracted HTML into structured Markdown format using markdownify for easy reading and note-taking.
Yes, you can scrape dynamic pages and JavaScript rendered SPA sites by utilizing Playwright integration, which executes client-side scripts to load dynamic content before extracting the fully rendered web page into Markdown.
To get YouTube transcripts and video captions, the Skill utilizes the youtube-transcript-api to fetch subtitles and metadata directly from video URLs, providing clean text outputs for review and analytics workflows.
You do not need Playwright installed for basic web content extraction, as requests and beautifulsoup4 handle static pages; Playwright is only required optionally to support JavaScript rendering for dynamic SPA sites.
The best way to automate downloading web pages and videos into Markdown is by using this Skill to fetch URLs, process dynamic content or YouTube transcripts, and output structured Markdown or JSON formats for knowledge assimilation.
Web scraping fails on dynamically rendered SPA sites when using only requests because it cannot execute JavaScript, requiring Playwright to render the dynamic content before successful extraction and conversion to Markdown.
pengfitCollects, processes, and synchronizes Rizhao City engineering material price data to Elasticsearch.
xcrrrExtract PDF text into structured JSON or Markdown and generate summaries.
jonnabioIndex and retrieve documents using semantic embeddings and metadata.
dglijin-ossAutomate browser navigation, form filling, screenshots, and data extraction.
