defuddle

Extract clean markdown content from web pages via Defuddle CLI.

Updated Jul 5, 2026
One-click install
npx skills add https://github.com/prince3626ezechiel-lang/ivoire-monade-palantir --skill defuddle-prince3626ezechiel-lang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/prince3626ezechiel-lang/ivoire-monade-palantir/tree/main/skills/defuddle
Command: npx skills add https://github.com/prince3626ezechiel-lang/ivoire-monade-palantir --skill defuddle-prince3626ezechiel-lang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Web pages are cluttered with ads and navigation that consume valuable tokens when accessed using standard APIs. Defuddle simplifies content retrieval by extracting the essential readable content.

Core Features & Use Cases

  • Content Extraction: Removes ads, navigation, and clutter to save tokens when fetching content.
  • Use Case: When analyzing a webpage, use Defuddle to obtain clean, markdown-formatted text, making it more efficient for token-constrained use cases like web scraping and information analysis.

Quick Start

To use the 'defuddle' skill, execute the command defuddle parse <url> --md and direct it to the web page URL you want to clean up.

Frequently Asked Questions about defuddle

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

FAQPage Schema
How do I extract clean readable content from web pages for token-efficient analysis?

To extract clean readable content from web pages, use the `defuddle parse <url> --md` command. It removes ads and navigation clutter, outputting concise markdown-formatted text to save tokens during web scraping and information analysis.

Why does extracting web page content save tokens compared to fetching standard HTML?

Extracting web page content saves tokens because standard HTML APIs fetch full pages cluttered with ads and navigation. Content extraction isolates essential readable text, significantly reducing token consumption for constrained use cases.

What is the best way to convert a standard web page into markdown format?

The best way to convert a standard web page into markdown format is using the `defuddle parse <url> --md` command. This specifically targets standard web pages and formats the extracted readable content as markdown.

Does content extraction work with URLs ending in .md?

Content extraction does not work with URLs ending in .md. The Defuddle CLI specifically targets standard web pages and avoids pre-formatted markdown URLs to distinguish from already clean content.

Can I control output format and extract metadata during web page parsing?

You can control output format and extract metadata during web page parsing by utilizing Defuddle CLI parsing commands and flags. These flags manage how the clean content is formatted and what metadata is retrieved.