Extract clean markdown text from webpage URLs by removing noise.
npx skills add https://github.com/qq5855144/GitHubM --skill web-reader-qq5855144
Please help me install this Agent Skill. Skill: web-reader Source: https://github.com/qq5855144/GitHubM/tree/main/.skills/web-reader Command: npx skills add https://github.com/qq5855144/GitHubM --skill web-reader-qq5855144
This Skill removes the noise from web pages and converts a URL into clean, readable Markdown so you can analyze, summarize, translate, or reuse the content without distractions.
Use the web-reader skill to fetch the provided URL and return the cleaned Markdown content for analysis.
High-intent search queries and answers about installing and using this skill.
To extract clean markdown from a webpage URL, the web-reader fetches the provided link and removes navigation, ads, and scripts, returning only the readable article text for immediate analysis.
Parsing web content for AI summarization is best handled by stripping page noise and converting the main body into markdown, which provides a clean, structured text format that language models can easily process.
Yes, you can use selector-based filtering to target specific page analysis content, allowing you to extract only the relevant HTML sections and convert them into markdown or plain text.
Web content extraction supports SSE streaming to handle large articles, processing and returning page content progressively as it arrives instead of waiting for the entire fetch to complete.
When converting a URL to markdown, available output formats include plain text, HTML, markdown, and screenshots, providing flexibility for reading, translating, or analyzing shared links.
Markdown extraction includes unwanted navigation when standard noise filtering fails, requiring optional CSS selectors to isolate the main article body and effectively strip ads and scripts from the page.
doghelWangDetect and parse JSON, XML, Protobuf, SQLite, and raw binary files.
bahayonghangExtract text, entities, and relationships from images, PDFs, and charts.
eddmannRender dynamic web pages with Playwright to capture HTML, text, and screenshots.
devkeniParse Notion spec pages into structured implementation plans with linked tasks.
