skills.rest
byrider
byriderOFFICIAL
Explore all skills by this author →
GitHub

defuddle

Clean web pages into readable markdown by removing ads and boilerplate.

Updated Jun 13, 2026
Search Tags:#markdown#content extraction#token optimization#wiki building#web content cleaning
One-click install
npx skills add https://github.com/byrider/claude-obsidian --skill defuddle-byrider
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/byrider/claude-obsidian/tree/main/skills/defuddle
Command: npx skills add https://github.com/byrider/claude-obsidian --skill defuddle-byrider

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the process of web content cleaning, removing ads, navigation, headers, footers, and boilerplate, resulting in clean, readable markdown that saves up to 60% of tokens.

Core Features & Use Cases

  • Web Page Cleaning: Extracts meaningful content from web pages while removing unnecessary elements.
  • Token Savings: Significantly reduces token usage for long articles, optimizing for cost-effective text processing.
  • Use Case: Before ingesting web content into a wiki, use Defuddle to clean a URL and save time and resources.

Quick Start

Run 'defuddle https://example.com/article' to clean a URL and save the output as markdown.

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 content for wiki building?▼

To extract clean markdown from web content, run a URL through the defuddle-cli to strip ads, navigation, and boilerplate, resulting in readable markdown optimized for personal knowledge management and wiki ingestion.

What is the best way to reduce token usage when processing long web articles?▼

The best way to reduce token usage when processing long web articles is to clean the web content first, removing headers, footers, and unnecessary elements to achieve 40-60% token savings before text processing.

Does defuddle-cli support cleaning boilerplate and ads from any URL?▼

Yes, defuddle-cli supports cleaning boilerplate and ads from any URL by extracting only the meaningful content and discarding navigation elements, which significantly optimizes text processing and reduces token usage.

Can I use markdown content extraction for personal knowledge management?▼

You can use markdown content extraction for personal knowledge management by running a web page URL through the cleaning script to remove unnecessary elements, providing clean markdown text ready for wiki building.

What are the limitations of using scripts for web content cleaning?▼

The primary limitation of using scripts for web content cleaning is that it relies on defuddle-cli to parse the provided URL, meaning it is designed specifically for text processing and token optimization rather than handling dynamic or interactive web elements.

Related Skills

Explore More Content & Communication Skills→
dotBeepsdotBeeps

defuddle

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

Community
Intermediate
juliuss1907juliuss1907

compile-agent

Compile raw content into structured wiki notes with tags.

Community
Advanced
CHENyiru3CHENyiru3

defuddle

Convert cluttered web pages into clean Markdown via the Defuddle CLI.

Community
Intermediate
wsxwj123wsxwj123
7

defuddle

Extract clean Markdown content from web pages using Defuddle CLI.

Community
Basic