skills.rest
zjykzk
zjykzkCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

defuddle

Extract clean Markdown content from web pages by removing clutter and navigation.

Updated Feb 2, 2016
Search Tags:#markdown#readability#token-optimization#web-content#content-extraction#defuddle
One-click install
npx skills add https://github.com/zjykzk/blog --skill defuddle-zjykzk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/zjykzk/blog/tree/main/.agents/skills/defuddle
Command: npx skills add https://github.com/zjykzk/blog --skill defuddle-zjykzk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract clean Markdown content from web pages by removing clutter, ads, and navigation to save tokens and make reading easier.

Core Features & Use Cases

  • Remove page chrome (navigation, ads) to produce concise Markdown.
  • Output formats: Markdown by default; JSON with HTML and Markdown; or HTML when no flag is provided.
  • Use Case: Read online documentation, articles, or blog posts and save for offline analysis or summarization.

Quick Start

Provide a URL to parse and obtain clean Markdown content.

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 clean Markdown to save tokens?▼

To extract clean Markdown from web pages, you provide a URL to remove clutter and navigation. This produces concise text content, saving tokens for offline analysis or summarization.

Can I extract web content as JSON or HTML instead of Markdown?▼

Yes, you can extract web content as JSON containing both HTML and Markdown, or output raw HTML when no format flag is provided. Markdown is the default output format for token optimization.

Do I need to install Defuddle before extracting Markdown from web pages?▼

Yes, you need to have Defuddle installed to enable the web content extraction process. This prerequisite allows the tool to parse URLs and remove page chrome for generating concise Markdown outputs.

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

The best way to remove ads and navigation from online articles is using a content extraction tool that parses the page and outputs clean Markdown. This removes page chrome automatically, leaving only concise text.

Does web content extraction work for reading online documentation and blog posts?▼

Web content extraction works effectively for reading online documentation, articles, and blog posts. It removes non-essential page elements, delivering clean Markdown text suitable for saving and offline analysis.

Why does my extracted Markdown still contain navigation clutter from the web page?▼

If extracted Markdown contains navigation clutter, ensure you are using the default Markdown output format rather than the raw HTML option. The Markdown format specifically targets page chrome removal to produce concise text.

Related Skills

Explore More Content & Communication Skills→
zephyrwang6zephyrwang6
333

web-scraper

Fetch web page content and convert HTML to clean Markdown.

Community
Intermediate
CHENyiru3CHENyiru3

defuddle

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

Community
Intermediate
georgekhananaevgeorgekhananaev
27

token-formatter

Compress Markdown and text into token-efficient formats with Python scripts.

Community
Advanced
okwindsokwinds
50

headless-web-viewer

Render JavaScript-heavy webpages and extract visible text with Playwright.

Community
Intermediate