skills.rest
enigmaicon-eng
enigmaicon-engCOMMUNITY
Explore all skills by this author →
GitHub

defuddle

Extracts main readable content from web pages into Markdown by removing navigation, ads, and clutter.

1|Updated May 16, 2026
Search Tags:#documentation#markdown#content extraction#token optimization#metadata extraction#web pages
One-click install
npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill defuddle-enigmaicon-eng
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/enigmaicon-eng/AI-Enterprise-OS/tree/main/examples/obsidian-skills/skills/defuddle
Command: npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill defuddle-enigmaicon-eng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Web pages often include navigation, ads, and other clutter that waste tokens and slow down summarization or analysis. Defuddle extracts only the main readable content so you can work with cleaner input.

Core Features & Use Cases

  • Clean markdown extraction: Converts standard web pages into readable Markdown with clutter removed.
  • Token-saving readability: Keeps the essential content for downstream tasks like summarization or research.
  • Use cases: Turn documentation pages, articles, and blog posts into clean content; extract specific metadata such as title, description, and domain.

Quick Start

Use Defuddle to parse a web page URL into markdown by running: 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 main content from web pages and convert it to markdown?▼

To extract main content from web pages and convert it to markdown, run a content extraction tool that removes navigation and ads. Defuddle parses standard HTML pages and outputs token-efficient readable text for documentation and articles.

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

Web page content extraction works for online documentation, articles, and blog posts. It removes clutter from standard HTML pages to provide clean text or metadata extraction, making it suitable for research and summarization tasks.

What is the best way to save tokens when processing web pages for analysis?▼

The best way to save tokens when processing web pages is to extract only the main readable content. Removing navigation and ads before analysis ensures clean input, reducing wasted tokens during downstream tasks like summarization.

Can I extract metadata like title and description from web pages?▼

You can extract metadata like title and description from web pages. Content extraction tools support property extraction flags alongside markdown output formatting, allowing you to capture specific metadata from standard HTML pages.

Can I use markdown files as input for web page content extraction?▼

No, you should avoid using markdown files as input for web page content extraction. The process is designed for standard HTML pages and requires running in markdown mode to parse URLs, not processing existing markdown files.

Related Skills

Explore More Content & Communication Skills→
JylhisJylhis
1

defuddle

Extract clean markdown from web pages using the Defuddle CLI.

Community
Basic
wwsunwwsun
1

defuddle

Extract clean markdown content and metadata from web pages using Defuddle CLI.

Community
Basic
hheydaroffhheydaroff

summarize

Convert web pages and documents to Markdown and generate concise summaries.

Community
Intermediate
wsxwj123wsxwj123
7

defuddle

Extract clean Markdown content from web pages using Defuddle CLI.

Community
Basic