Convert web pages into clean Markdown text using CLI tools.
npx skills add https://github.com/archibate/dotfiles-claude --skill read-url
Please help me install this Agent Skill. Skill: read-url Source: https://github.com/archibate/dotfiles-claude/tree/main/skills/read-url Command: npx skills add https://github.com/archibate/dotfiles-claude --skill read-url
Extract clean, readable text content (markdown) from any web page. Use this when reading articles, docs, GitHub READMEs, blog posts, social posts, or papers, or when the user says "read this page", "what does this link say", provides a URL to read, curl returns noisy HTML, or WebFetch returns truncated, summarized, or refused results.
Provide the cleaned Markdown text for the requested URL by fetching the page and stripping navigation, ads, and chrome.
High-intent search queries and answers about installing and using this skill.
To convert HTML to Markdown and extract clean text, the skill fetches the web page, removes navigation and ads, and outputs readable Markdown. It handles articles, docs, READMEs, and blogs automatically.
Extracting readable content from noisy HTML is handled by stripping chrome, ads, and navigation elements. The skill uses content extraction tools like defuddle and markdownify to produce clean Markdown instead of raw HTML.
Web content extraction for JS-rendered or anti-bot protected pages is supported through a fallback ladder. The skill routes requests to agent-browser or scrapling to bypass protection and retrieve the text.
Yes, you can read GitHub README files, research papers, social posts, and documentation. The versatile targeting extracts the main content and formats it as clean Markdown for consistent reading.
If WebFetch returns truncated or refused results, this skill fetches the page directly and applies HTML-to-Markdown conversion. It uses safe fallbacks to ensure complete text extraction from the target URL.
guyruSearch the web via DuckDuckGo HTML and output titles, URLs, and snippets.
u9401066Extract text, figures, and citations from PDFs into Markdown.
eddmannRender dynamic web pages with Playwright to capture HTML, text, and screenshots.
cxnaiveExtracts data from protected and dynamic websites via scrapling framework.
