skills.rest
min-zou
min-zouCOMMUNITY
Explore all skills by this author →
GitHub

defuddle

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

Updated Aug 23, 2026
Search Tags:#markdown#content extraction#web page#token saving#defuddle
One-click install
npx skills add https://github.com/min-zou/obsidian-doc --skill defuddle-min-zou
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/min-zou/obsidian-doc/tree/main/format/areas/system/agent-skills/codex/defuddle
Command: npx skills add https://github.com/min-zou/obsidian-doc --skill defuddle-min-zou

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires defuddle, and includes scripts (resource) components.

What problem does it solve?

This Skill addresses the issue of extracting clean, readable markdown content from web pages, removing clutter and navigation to save tokens.

Core Features & Use Cases

  • Content Extraction: Extracts clean markdown content from web pages.
  • Prefer Over WebFetch: Use instead of WebFetch for standard web pages to save tokens.
  • Use Cases: Ideal for online documentation, articles, blog posts, or any standard web page. Not suitable for markdown files ending in .md.

Quick Start

Extract markdown content from a web page using Defuddle CLI:

defuddle parse <url> --md

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 to save tokens?▼

You can extract clean markdown from web pages by running the Defuddle CLI with the markdown output flag. This removes clutter and navigation, producing readable markdown ideal for online documentation and articles.

Why should I use Defuddle instead of WebFetch for extracting web content?▼

You should prefer Defuddle over WebFetch for standard web pages to save tokens. Defuddle eliminates page clutter and navigation elements, providing clean markdown content specifically optimized for articles and online documentation.

Do I need to install anything before extracting markdown from web pages?▼

Yes, you need to install the Defuddle CLI before extracting markdown from web pages. The extraction process requires the CLI environment and the markdown output flag to successfully parse URLs and generate clean content.

Can I use this markdown extraction method for all types of URLs?▼

No, this markdown extraction method is not suitable for all URLs. It is ideal for online documentation, articles, and blog posts, but you should not use it for direct markdown files ending in .md.

What is the best way to remove navigation and clutter from online articles?▼

The best way to remove navigation and clutter from online articles is using the Defuddle CLI to parse the web page. This extracts clean markdown content, eliminating unnecessary elements to save tokens.

Related Skills

Explore More Content & Communication Skills→
iwbc-mzkiwbc-mzk

defuddle

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

Community
Basic
sammcjsammcj
155

youtube-wisdom

Extract insights, quotes, and takeaways from YouTube transcripts into Markdown files.

Community
Intermediate
marktantongcomarktantongco

firecrawl-scrape

Extract HTML content from URLs and convert it to markdown.

Community
Advanced
Syedyasir001Syedyasir001

defuddle

Extract and clean markdown content from web pages.

Community
Basic