defuddle

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

118|26|Updated Apr 11, 2026
One-click install
npx skills add https://github.com/songzhuozhu/obsidian-llm-wiki --skill defuddle-songzhuozhu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/songzhuozhu/obsidian-llm-wiki/tree/main/.codex-en/skills/defuddle
Command: npx skills add https://github.com/songzhuozhu/obsidian-llm-wiki --skill defuddle-songzhuozhu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Web pages often include navigation, ads, and clutter that inflate token costs and obscure the actual content. Defuddle trims the noise and converts pages into clean Markdown for efficient reading and processing.

Core Features & Use Cases

  • Clean Markdown extraction: convert web pages to readable Markdown with navigation and clutter removed.
  • Token-efficient reading: reduces token usage for analysis, summarization, and archival workflows.
  • Use Case: extract documentation, blog posts, or articles for offline study or AI processing.

Quick Start

Run defuddle parse <url> --md to extract clean Markdown content from the target web page.

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, run the defuddle parse <url> --md command. This removes navigation and ads, outputting concise text for analysis or offline reading.

Why does extracting web content as Markdown reduce token costs?

Extracting web content as Markdown reduces token costs by stripping out ads and navigation clutter. Defuddle outputs only the readable text, minimizing wasted tokens during AI analysis.

Does Defuddle work with online documentation and blog posts?

Yes, Defuddle works with online documentation, blog posts, and standard articles. It trims page noise and converts the core content into readable Markdown for efficient processing.

Do I need to install Defuddle to use this content extraction feature?

Yes, you need to install the Defuddle CLI to use this content extraction feature. The capability relies on the local Defuddle command-line tool to parse URLs and generate Markdown.

Can I extract metadata along with Markdown from a web page?

Yes, you can extract metadata along with Markdown from a web page. Defuddle supports outputting clean Markdown by default and offers optional metadata extraction for your workflows.