web-reader

Convert web pages into clean Markdown text with headings and links.

Updated Jun 12, 2026
One-click install
npx skills add https://github.com/GGwujun/SigmX --skill web-reader-ggwujun
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/GGwujun/SigmX/tree/main/agent/src/skills/web-reader
Command: npx skills add https://github.com/GGwujun/SigmX --skill web-reader-ggwujun

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converts any URL into clean Markdown text by removing ads, navigation, styling, and other distractions, enabling quick reading and extraction of core content.

Core Features & Use Cases

  • Reads API documentation, technical articles, README pages, and blogs by converting the page to Markdown.
  • Removes clutter while preserving headings, links, and key structure for easy reuse.
  • Use Case: a data analyst wants to turn a GitHub README into a readable summary for a report.

Quick Start

Provide a URL to convert into clean Markdown text.

Frequently Asked Questions about web-reader

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

FAQPage Schema
How do I convert web pages to Markdown for API documentation and technical articles?

To convert web pages to Markdown, provide a URL to the skill, which removes ads and distractions while preserving headings and links. It returns a JSON object containing the title, url, content, and length for clean text extraction.

What is the best way to extract readable text from a GitHub README link?

The best way to extract readable text from a GitHub README link is URL conversion via an extraction pipeline that strips clutter. This preserves key structure and converts the page into clean Markdown text for quick reading.

Can I use link conversion to remove ads and navigation from blog posts?

Yes, you can use link conversion to remove ads, navigation, and styling from blog posts. The extraction pipeline preserves headings and links, returning a clean, structured Markdown output suitable for immediate reuse.

Does the text extraction pipeline return structured data or plain content?

The text extraction pipeline returns structured data rather than plain content. It outputs a JSON object that includes the page title, original url, clean Markdown content, and length, making it easy to parse downstream.

Why does my URL conversion output retain headings and links instead of plain text?

URL conversion retains headings and links instead of plain text because the extraction pipeline is designed to preserve key document structure. This ensures the resulting Markdown remains readable and structured for technical articles.