defuddle

Extract clean markdown from web pages by removing navigation and ads.

3|3|Updated Apr 5, 2026
One-click install
npx skills add https://github.com/diegocamara89/ai-skills-hub --skill defuddle-diegocamara89
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/diegocamara89/ai-skills-hub/tree/main/all-skills/defuddle
Command: npx skills add https://github.com/diegocamara89/ai-skills-hub --skill defuddle-diegocamara89

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extracts clean, readable markdown from web pages by removing clutter, navigation, and ads to save tokens and improve processing efficiency.

Core Features & Use Cases

  • Removes page chrome (navigation bars, ads, sidebars) to produce concise markdown suitable for reading and analysis.
  • Supports multiple outputs: markdown by default, plus HTML or JSON representations with both HTML and markdown content.
  • Use Case: when you need a compact, distraction-free version of articles, documentation, or blog posts for summarization, offline reading, or QA.

Quick Start

Parse a URL to markdown with 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 extract clean markdown from a web page, use the parsing command to remove navigation, ads, and sidebars. This produces a distraction-free markdown version of web content, reducing token usage for efficient reading, summarization, or archival tasks.

How does web content extraction reduce token usage for LLM processing?

Web content extraction reduces token usage by stripping away page chrome like navigation bars and sidebars before generating markdown. This ensures only the core readable article is processed, increasing efficiency for summarization and analysis tasks.

Can I get JSON or HTML output instead of markdown when scraping articles?

Yes, you can get JSON or HTML output instead of markdown. The extraction process supports markdown by default and can generate HTML or JSON representations, which can include optional metadata like the page title and description.

What is the best way to remove ads and sidebars from web pages for offline reading?

The best way to remove ads and sidebars for offline reading is using a CLI extraction tool that filters out page clutter. It outputs concise markdown containing only the readable article text, making it ideal for distraction-free offline viewing.

Does this web scraping tool require any external dependencies to parse URLs?

No, this web scraping tool does not require external dependencies to parse URLs. It operates independently to extract readable markdown, HTML, or JSON from web pages without needing additional packages or component installations.