defuddle

Extract clean Markdown from web pages using the Defuddle CLI.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Michael1Peng/watson --skill defuddle-michael1peng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/Michael1Peng/watson/tree/main/.agents/skills/defuddle
Command: npx skills add https://github.com/Michael1Peng/watson --skill defuddle-michael1peng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Defuddle provides a simple way to extract clean Markdown content from web pages, removing clutter, ads, and navigation to save tokens during reading or analysis. It helps to generate readable Markdown from any standard web page instead of fetching the raw HTML with noise.

Core Features & Use Cases

  • Extract clean, readable Markdown from standard web pages.
  • Remove navigation, ads, and clutter to minimize token usage.
  • Use it for online documentation, articles, blog posts, or other web content where a Markdown export is preferred.

Quick Start

Install Defuddle globally and run defuddle parse <url> --md to extract clean Markdown from a web page.

Frequently Asked Questions about defuddle

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

FAQPage Schema
How do I extract clean Markdown from a webpage to save tokens?

To extract clean Markdown from a webpage and save tokens, use a tool that removes navigation and ads. Defuddle processes standard web pages to output minimal, readable Markdown optimized for lower token usage.

What is the best way to convert online documentation into minimal Markdown?

The best way to convert online documentation into minimal Markdown is using a content extraction tool. Defuddle parses standard web pages and strips clutter, providing a clean Markdown export suitable for reading and analysis.

Do I need to install the Defuddle CLI to extract web content as Markdown?

Yes, you need to install the Defuddle CLI globally to extract web content as Markdown. Once installed, execute the parse command with the URL and the --md output option to generate the clean text.

Can I extract metadata along with the Markdown content from a web page?

Yes, you can extract metadata along with Markdown content from a web page. When running the Defuddle CLI parse command, use the optional -p metadata selectors to include specific metadata in your extraction output.

Does extracting readable Markdown from web pages work for blog posts and articles?

Extracting readable Markdown from web pages works effectively for blog posts and articles. Defuddle is designed to process standard web content, removing ads and navigation to deliver a minimal Markdown export.