read-url
CommunityExtract clean text from web pages instantly.
Authorarchibate
Version1.0.0
Installs0
System Documentation
What problem does it solve?
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.
Core Features & Use Cases
- Content extraction: Convert noisy HTML pages into clean, markdown-formatted text.
- Versatile targeting: Handles articles, docs, READMEs, blogs, social posts, and research papers.
- Fallback planning: If the page is JS-rendered or anti-bot protected, the skill routes to agent-browser or scrapling as needed.
Quick Start
Provide the cleaned Markdown text for the requested URL by fetching the page and stripping navigation, ads, and chrome.
Dependency Matrix
Required Modules
beautifulsoup4markdownify
Components
scriptsreferences
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: read-url Download link: https://github.com/archibate/dotfiles-claude/archive/main.zip#read-url Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.