defuddle

Extract clean Markdown content from web pages via the Defuddle CLI.

Updated Feb 11, 2016
One-click install
npx skills add https://github.com/Ehrax/dotfiles --skill defuddle-ehrax
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/Ehrax/dotfiles/tree/main/configs/agents/skills/defuddle
Command: npx skills add https://github.com/Ehrax/dotfiles --skill defuddle-ehrax

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Web pages are cluttered with ads, navigation, and noise that inflate content and token usage. Defuddle extracts clean Markdown content from standard web pages, making it easier to read, analyze, and store.

Core Features & Use Cases

  • Extract clean markdown content from web pages
  • Remove navigation, ads, and clutter to reduce token usage
  • Suitable for online documentation, articles, and blog posts to prepare content for AI consumption

Quick Start

Run defuddle parse <url> --md to extract clean Markdown content from the 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 web pages to reduce token usage?

To extract clean markdown from web pages and reduce token usage, you can use a content extraction tool that strips away navigation, ads, and clutter, leaving only the core text for AI consumption. This process produces concise markdown suitable for articles, blogs, and online documentation.

Does extracting web content to markdown remove ads and navigation clutter?

Yes, extracting web content to markdown removes ads and navigation clutter. Content extraction tools isolate the main textual content of a web page, filtering out sidebars and menus to deliver clean, readable markdown that significantly cuts down on unnecessary tokens.

What is the best way to convert online documentation into markdown for AI processing?

The best way to convert online documentation into markdown for AI processing is by using a CLI content extraction tool. These tools accept a URL as input and automatically parse the page, outputting clean markdown formatted specifically to minimize token usage during AI tasks.

Do I need to install a CLI tool to parse web pages into markdown?

Yes, you need to install a CLI tool to parse web pages into markdown. Command-line content extraction tools require local installation to process URLs and output clean text, ensuring you can efficiently convert web content directly from your terminal environment.

Can I get JSON or HTML output instead of markdown when extracting web content?

Yes, you can get JSON or HTML output instead of markdown when extracting web content. While markdown is the default format for token savings, content extraction CLI tools typically offer command flags that allow you to specify JSON or HTML as the output format.