Web Clipper

Extract readable content from URLs and save it as Markdown files.

26|5|Updated Feb 19, 2026

Search Tags:#markdown #research #web scraping #content extraction #web #clipper

Ready to run

npx skills add https://github.com/kunwl123456/zeroclaw-skills-collection --skill web-clipper

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Web Clipper
Source: https://github.com/kunwl123456/zeroclaw-skills-collection/tree/main/web-clipper
Command: npx skills add https://github.com/kunwl123456/zeroclaw-skills-collection --skill web-clipper

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires axios, jsdom, @mozilla/readability, turndown, and includes scripts (resource) components.

What problem does it solve?

This Skill automates the process of extracting clean, readable content from web pages, saving users time and effort in manually copying and formatting information.

Core Features & Use Cases

Content Extraction: Removes ads, sidebars, and other clutter to get to the main article content.
Markdown Conversion: Converts HTML content into clean Markdown format.
Metadata Preservation: Saves the title, URL, date, and author of the clipped content.
Persistence: Stores clippings in a designated directory for easy access and future reference.
Use Case: A researcher needs to save several articles for a project. They can use the Web Clipper to quickly save each article as a well-formatted Markdown file, organized by date and title.

Quick Start

Use the web clipper skill to save the content from https://example.com/article.

Frequently Asked Questions about Web Clipper

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

FAQPage Schema

How do I extract readable content from a URL and save it as Markdown?▼

To extract readable content from a URL and save it as Markdown, the Web Clipper fetches HTML using axios, parses it with jsdom and @mozilla/readability to remove ads, and converts the result with turndown into a clean Markdown file.

Does web scraping with this approach remove ads and sidebars from HTML pages?▼

Yes, web scraping with this approach removes ads and sidebars from HTML pages by utilizing @mozilla/readability to isolate the primary article content before converting the HTML structure into Markdown format.

What metadata is preserved when converting web pages to Markdown files?▼

When converting web pages to Markdown files, the extraction preserves essential metadata including the original article title, source URL, publication date, and author information within the generated Markdown output for research and archiving purposes.

Can I use jsdom and turndown to automate web content extraction for research?▼

Yes, you can use jsdom and turndown to automate web content extraction for research, as these dependencies work together to fetch, parse, and convert HTML documents into well-formatted Markdown files stored in a designated directory.

What is the best way to archive web articles for offline documentation?▼

The best way to archive web articles for offline documentation is to automate the extraction of clean readable content from URLs, stripping away extraneous page elements and saving the formatted text as Markdown files for easy access and future reference.