skills.rest
wyhlovecpp
wyhlovecppCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

defuddle

Extract readable web page content as markdown or JSON using defuddle-cli.

Updated Feb 22, 2026
Search Tags:#automation#markdown#web scraping#content extraction#web pages
One-click install
npx skills add https://github.com/wyhlovecpp/my-codex-settings --skill defuddle-wyhlovecpp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/wyhlovecpp/my-codex-settings/tree/main/skills/by-category/engineering-tools/llm-cli/defuddle
Command: npx skills add https://github.com/wyhlovecpp/my-codex-settings --skill defuddle-wyhlovecpp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires defuddle-cli.

What problem does it solve?

Manual copying and cleaning web page content is time-consuming and error-prone, especially when dealing with cluttered pages filled with ads and navigation.

Core Features & Use Cases

  • Content Extraction: Uses Defuddle CLI to parse web pages and produce clean, readable markdown content.
  • Versatile Output Formats: Supports markdown, HTML, JSON with embedded HTML/Markdown, and metadata extraction.
  • Use Case: Effortlessly gather readability-optimized content from multiple articles for research or note-taking projects.

Quick Start

Use the defuddle skill to extract and save the main content of a provided web URL 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 text from web pages for research without manual copying?▼

To extract clean text from web pages, this skill automates content extraction by parsing webpage HTML and stripping away ads and navigation clutter. It produces readability-optimized content, reducing the time and errors associated with manual copying.

Can I convert web page content to markdown or JSON formats?▼

Yes, you can convert web page content to markdown or JSON formats. The skill uses the defuddle-cli package to parse HTML and supports versatile output formats including markdown, HTML, and JSON with embedded HTML or markdown.

Does web scraping with defuddle-cli work well for cluttered articles filled with ads?▼

Web scraping with defuddle-cli works very well for cluttered articles. It specifically solves the problem of extracting readable content from web pages filled with ads and navigation, yielding clean markdown for your research projects.

What is the best way to automate content curation from multiple articles?▼

The best way to automate content curation from multiple articles is using this skill to parse webpage HTML and extract main content. It effortlessly gathers readability-optimized content, making it ideal for note-taking and research.

Do I need any specific packages to parse webpage HTML for data collection?▼

Yes, you need the defuddle-cli packages to parse webpage HTML for data collection. This dependency is required for the skill to extract readable content and convert it into markdown or JSON formats.

Are there limitations when extracting metadata from web pages using defuddle?▼

The metadata extraction is limited to parsing webpage HTML and converting it to markdown, JSON, or metadata formats. It is designed for readable content extraction and may not capture dynamically loaded data or complex interactive elements.

Related Skills

Explore More Content & Communication Skills→
JylhisJylhis
1

defuddle

Extract clean markdown from web pages using the Defuddle CLI.

Community
Basic
tan-yong-shengtan-yong-sheng
1

qmd

Index and query Markdown content locally with keyword and semantic search.

Community
Intermediate
christhz666christhz666

defuddle

Extract readable markdown content from web pages via Defuddle CLI.

Community
Basic
abdullah1854abdullah1854
1

crawl-cli

Crawl websites and extract content into Markdown, JSON, or text.

Community
Basic