defuddle

Extract clean markdown content from web pages using the Defuddle CLI.

Updated Feb 28, 2026
One-click install
npx skills add https://github.com/raphaelmans/agent-skills --skill defuddle-raphaelmans
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/raphaelmans/agent-skills/tree/main/defuddle
Command: npx skills add https://github.com/raphaelmans/agent-skills --skill defuddle-raphaelmans

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract clean markdown content from web pages to save tokens and remove clutter, enabling efficient reading and analysis of online docs, articles, blogs, and standard web pages.

Core Features & Use Cases

  • Remove navigation, ads, and clutter from web pages to produce clean markdown.
  • Output formats include Markdown, JSON, and HTML with optional property extraction.
  • Use cases include reading documentation, extracting summaries, or preparing content for knowledge bases.

Quick Start

Parse a URL with the Defuddle CLI to generate clean markdown output for immediate reading.

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 web page while removing ads and navigation clutter?

Extract clean markdown from web pages by parsing the URL with the Defuddle CLI, which strips navigation, ads, and clutter to produce readable content suitable for reading or analysis.

Can I extract specific metadata from online documentation instead of the full article text?

Yes, you can extract specific metadata from online documentation by using the -p flags with the Defuddle CLI, allowing targeted property extraction alongside the standard markdown output.

What is the best way to save tokens when reading long online articles and blogs?

The best way to save tokens when reading online articles and blogs is converting the web content to clean markdown, removing unnecessary HTML elements and clutter that consume context window space.

Does extracting web content to markdown require installing any specific command line tools?

Yes, extracting web content to markdown requires the Defuddle CLI installed locally, as the Skill relies on this command line tool to parse URLs and generate the cleaned output formats.

What output formats are supported when parsing web page content for summarization?

Supported output formats for parsing web page content include Markdown, JSON, and HTML. Markdown is generated by default using the --md option, and content can also be saved directly to a file.

Why should I convert web content to markdown before summarization or knowledge base preparation?

Converting web content to markdown before summarization removes distracting clutter and standardizes the text format, making it significantly easier for downstream tools to parse and analyze the core information.