skills.rest
sonhaicoder
sonhaicoderCOMMUNITY
Explore all skills by this author →
GitHub

defuddle

Convert cluttered web pages into clean Markdown using Defuddle CLI.

Updated May 5, 2026
Search Tags:#markdown#readability#cli#web-scraping#web-content#content-extraction#defuddle
One-click install
npx skills add https://github.com/sonhaicoder/haiclaudeskill --skill defuddle-sonhaicoder
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/sonhaicoder/haiclaudeskill/tree/main/skills/obsidian-skills/skills/defuddle
Command: npx skills add https://github.com/sonhaicoder/haiclaudeskill --skill defuddle-sonhaicoder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Defuddle eliminates clutter from web pages by converting them into clean, readable markdown, reducing token usage and cognitive load when consuming online content.

Core Features & Use Cases

  • Convert standard web pages to markdown while preserving essential structure.
  • Remove navigation, ads, and distractions for focused reading.
  • Use case: extract clean docs, articles, or blog posts for quick summaries and archiving.

Quick Start

Run the Defuddle CLI to parse a URL and output Markdown using the --md flag.

Frequently Asked Questions about defuddle

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

FAQPage Schema
How do I convert web pages to markdown for easier reading?▼

You can convert web pages to markdown by running the Defuddle CLI with the --md flag. This removes clutter like navigation and ads, outputting clean markdown that preserves essential structure and reduces token usage.

Can I extract clean content from online documentation and articles?▼

Yes, you can extract clean content from online documentation, articles, and blogs. The tool removes distractions to provide focused reading output, making it suitable for archiving or generating quick summaries of standard web pages.

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

Yes, you need to install the Defuddle CLI globally using npm install -g defuddle. Once installed, you can parse URLs and output markdown directly from your command line environment.

What is the best way to reduce token usage when extracting web content?▼

The best way to reduce token usage when extracting web content is to convert it into clean markdown. This process strips away clutter and distractions, significantly lowering cognitive load and token consumption for online articles.

Does the web scraping output support formats other than markdown?▼

Yes, the web scraping output supports optional HTML or JSON formats in addition to markdown. You can use the CLI to parse URLs and specify your preferred output format alongside the standard markdown extraction.

What types of web pages are suitable for markdown extraction?▼

Markdown extraction is suitable for standard web pages such as online documentation, articles, and blogs. It effectively removes navigation and ads, preserving the essential structure for focused reading and archiving.

Related Skills

Explore More Content & Communication Skills→
WizarckWizarck

defuddle

Extract clean markdown from web pages via the Defuddle CLI.

Community
Intermediate
lisposterlisposter
1

baoyu-comic

Convert content into knowledge comics with storyboards, prompts, and PDFs.

Community
Advanced
otrebuotrebu
4

web-to-markdown

Batch-convert JavaScript-rendered web pages to a timestamped Markdown file.

Community
Advanced
hheydaroffhheydaroff

lightpanda-browser

Fetch web pages, evaluate JavaScript, and extract readable content as markdown.

Community
Basic