web-reader

Extract clean Markdown with preserved links from dynamic and login-protected web pages.

Updated Feb 6, 2026

Search Tags:#markdown #web-scraping #content-extraction #web-reading #browser-rendering #defuddle

Ready to run

npx skills add https://github.com/glfruit/gorin-skills --skill web-reader-glfruit

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/glfruit/gorin-skills/tree/main/openclaw/web-reader
Command: npx skills add https://github.com/glfruit/gorin-skills --skill web-reader-glfruit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Reading and extracting content from diverse web pages—especially dynamic, login-protected, or JS-heavy sites—while preserving structure and links.

Core Features & Use Cases

Layered extraction pipeline (L1 defuddle/Scrapling, L2 browser rendering, L3 cleanup) to maximize success across a wide range of sites.
Supports login-required and JS-rendered pages, with deterministic fallbacks and domain-aware routing.
Outputs Markdown with original links and consistent formatting for downstream AI analysis or knowledge ingestion.

Quick Start

Ask it to read a web page and return the Markdown-ready content for downstream AI analysis.

Frequently Asked Questions about web-reader

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract clean Markdown from JavaScript-heavy web pages?▼

To extract clean Markdown from JavaScript-heavy web pages, a layered pipeline first attempts defuddle or Scrapling, then falls back to browser rendering, and finally cleans the content to preserve original links.

Can I read and extract content from login-protected pages?▼

Yes, you can read and extract content from login-protected pages. The extraction pipeline supports login-required sites using domain-aware routing and deterministic fallbacks to access and format the content.

What is the best way to scrape dynamic web content for downstream AI analysis?▼

The best way to scrape dynamic web content for AI analysis is using a three-layer strategy that handles JS rendering and outputs a clean Markdown body with preserved links for knowledge ingestion.

Why does web scraping fail on dynamic sites and how does browser rendering help?▼

Web scraping fails on dynamic sites when content requires JavaScript execution. Browser rendering resolves this by loading the page fully before applying content cleaning and Markdown extraction.

Does this content extraction tool work with sites that require explicit domain routing?▼

Yes, this content extraction tool works with sites requiring explicit domain routing. It applies deterministic fallbacks and domain-aware logic to successfully read and present web content.