defuddle

Extract clean Markdown content from web pages using Defuddle CLI.

6|1|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/kouko/monkey-skills --skill defuddle-kouko
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/kouko/monkey-skills/tree/main/obsidian/skills/defuddle
Command: npx skills add https://github.com/kouko/monkey-skills --skill defuddle-kouko

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract clutter from web pages by converting content into clean, readable Markdown, saving token usage and reducing noise.

Core Features & Use Cases

  • Removes navigation, ads, and clutter from standard web pages.
  • Outputs clean Markdown by default with --md; supports optional file output.
  • Ideal for turning articles, documentation, and blog posts into shareable notes with minimal noise.

Quick Start

Provide a URL to Defuddle to generate clean Markdown content.

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 content from a web page?

To extract clean Markdown content from a web page, you provide a URL to the Defuddle CLI, which parses the page and removes clutter like ads and navigation. This outputs readable Markdown text, reducing noise and saving token usage.

What is the best way to convert web articles into Markdown for token savings?

The best way to convert web articles into Markdown for token savings is using a content cleanup tool like Defuddle. It strips non-essential elements such as navigation and ads, outputting only the core readable text to minimize token consumption.

Can I save extracted Markdown content directly to a file?

Yes, you can save extracted Markdown content directly to a file. The Defuddle CLI supports the optional -o flag, allowing you to specify a file path for outputting the clean Markdown generated from the parsed URL.

Does Defuddle work with standard web pages and blog posts?

Yes, Defuddle works with standard web pages and blog posts. It is specifically designed to process standard articles and documentation, removing noise and clutter to produce clean Markdown suitable for reading or analysis.

Do I need any specific command line tools to parse URLs for Markdown output?

Yes, you need the Defuddle CLI to parse URLs for Markdown output. The extraction process relies on this command line interface to process web pages and generate clean text using the --md flag.

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

Yes, you can extract metadata along with the Markdown content from a web page. The Defuddle CLI supports the optional -p flag to include metadata when parsing URLs and generating clean Markdown output.