defuddle 网页提取

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

1|Updated Jan 15, 2026
One-click install
npx skills add https://github.com/XIYBHK/claude-skills --skill defuddle-xiybhk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle 网页提取
Source: https://github.com/XIYBHK/claude-skills/tree/main/defuddle
Command: npx skills add https://github.com/XIYBHK/claude-skills --skill defuddle-xiybhk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Defuddle removes page chrome, ads, and navigation from standard web pages to produce clean, readable markdown, saving tokens and reading time.

Core Features & Use Cases

  • Generates concise, markdown-formatted content from articles, documentation, and blogs for quick reading or note-taking.
  • Prefer over WebFetch when you want minimal clutter and smaller output.
  • Useful in research or learning workflows to capture web content efficiently.

Quick Start

Provide a URL and run defuddle parse <url> --md to output clean markdown.

Frequently Asked Questions about defuddle 网页提取

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

FAQPage Schema
How do I extract clean markdown from a webpage for token-efficient reading?▼

To extract clean markdown from a webpage, you can use defuddle parse <url> --md to remove navigation, ads, and clutter, outputting concise, readable content for quick reading or integration.

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

Removing ads and navigation from online articles is best handled by content extraction tools that strip page chrome, producing clean, readable markdown that saves tokens and reading time.

Do I need to install defuddle globally to extract markdown content from web pages?▼

Yes, you need to install defuddle globally using npm install -g defuddle before you can run the command to extract markdown content from standard web pages.

When should I use defuddle instead of WebFetch for web content extraction?▼

You should use defuddle instead of WebFetch when you want minimal clutter and smaller output, as it specifically removes page chrome and ads to produce clean, markdown-formatted content.

Can I use defuddle to capture documentation and blogs for research workflows?▼

Yes, you can use defuddle to capture documentation, blogs, and online articles, generating concise markdown content efficiently for research or learning workflows and note-taking.

What are the limitations of extracting markdown from standard web pages?▼

The markdown extraction process is designed for standard web pages like articles and documentation; pages heavily reliant on dynamic JavaScript rendering may not parse correctly into clean markdown.