skills.rest
breferrari
breferrariCOMMUNITY
Explore all skills by this author →
Website𝕏@brennoferrariGitHub

defuddle

Extract clean Markdown from web pages using Defuddle CLI.

4.3k|501|Updated Feb 28, 2026
Search Tags:#documentation#markdown#cli#web-content#content-extraction#web-pages#defuddle
One-click install
npx skills add https://github.com/breferrari/obsidian-mind --skill defuddle-breferrari
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/breferrari/obsidian-mind/tree/main/.claude/skills/defuddle
Command: npx skills add https://github.com/breferrari/obsidian-mind --skill defuddle-breferrari

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Defuddle provides a fast, deterministic way to convert web pages into clean Markdown, removing navigation, ads, and clutter so you can read or reuse content with reduced token usage.

Core Features & Use Cases

  • Extracts readable Markdown from standard web pages, blogs, and documentation.
  • Removes distractions such as navigation, ads, and sidebars to save tokens in downstream AI tasks.
  • Use Case: Quickly extract concise content from online articles for summaries or integration into notes.

Quick Start

Run the Defuddle CLI parse command on a URL to generate 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 text from web pages for Markdown documentation?▼

You can extract web page content into Markdown using the Defuddle CLI parse command on a URL. This removes clutter like ads and navigation, outputting clean text that significantly reduces token usage for AI processing.

What is the best way to convert web content to Markdown without ads and navigation?▼

Converting web content to Markdown without ads is done by running Defuddle CLI with the --md output flag. This deterministically strips sidebars and navigation, delivering clean Markdown text for articles and blogs.

Do I need Defuddle CLI installed to parse web pages into Markdown?▼

Yes, the Defuddle CLI must be installed on your system to parse web pages into Markdown. The Skill acts as a wrapper for the CLI, requiring it to execute parsing commands and generate clean text output.

Can I use custom options to tailor content extraction from web pages?▼

Yes, you can tailor content extraction from web pages by passing the -o and -p options to the Defuddle CLI. These flags allow you to customize the parsed Markdown output to fit your specific requirements.

Why convert online articles to Markdown before processing with AI?▼

Converting online articles to Markdown before AI processing reduces token usage by removing unnecessary page elements. This ensures downstream tasks like summarization receive concise, accessible text without clutter or distraction.

Related Skills

Explore More Software Engineering Skills→
WizarckWizarck

defuddle

Extract clean markdown from web pages via the Defuddle CLI.

Community
Intermediate
adiytharpansaadiytharpansa

news-aggregator

Aggregate news from multiple sources and generate concise article summaries.

Community
Intermediate
beauschwabbeauschwab

confluence

Convert Markdown to Confluence storage format and manage attachments.

Community
Advanced
mbastakismbastakis
5

crawl4ai

Crawl web pages with Python and extract structured data as Markdown or JSON.

Community
Intermediate