skills.rest
XWIlluDelu
XWIlluDeluCOMMUNITY
Explore all skills by this author →
GitHub

defuddle

Extract clean markdown from web pages using Defuddle CLI.

Updated May 26, 2026
Search Tags:#markdown#web scraping#metadata#content extraction#token optimization#documentation analysis#defuddle
One-click install
npx skills add https://github.com/XWIlluDelu/agent-share --skill defuddle-xwilludelu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/XWIlluDelu/agent-share/tree/main/lib/defuddle
Command: npx skills add https://github.com/XWIlluDelu/agent-share --skill defuddle-xwilludelu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires defuddle.

What problem does it solve?

Web pages often include navigation, ads, and other clutter that bloats context and makes reading or analysis slower and more expensive.

Core Features & Use Cases

  • Clean markdown extraction: Convert a standard web page into readable markdown focused on the main content.
  • Token savings: Remove navigation and boilerplate so you send less irrelevant text to your model.
  • Metadata extraction: Pull specific fields like title, description, and domain when you only need key info.
  • Use case: You need to summarize an article; extracting the main content in markdown reduces noise and improves the quality of downstream analysis.

Quick Start

Run Defuddle to parse the page into markdown by providing the URL and using the --md flag.

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 web pages for content analysis?▼

To extract clean markdown from web pages, use the Defuddle CLI with the --md flag to strip navigation and ads, resulting in focused content that reduces token usage for downstream analysis.

What is the best way to remove web page clutter for token optimization?▼

The best way to remove web page clutter for token optimization is parsing standard HTML pages with the --md flag, which removes boilerplate and ads to send less irrelevant text to your model.

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

Yes, you can extract specific metadata fields like title and description from web pages by running the Defuddle CLI with the -p flag to pull key properties instead of full content.

Does defuddle work with standard HTML articles and blog posts?▼

Defuddle works with standard HTML pages including documentation, articles, blog posts, and general web content, converting the main readable text into markdown format.

When should I not use markdown extraction on a URL?▼

You should not use markdown extraction on URLs that already point directly to .md files, as the tool is designed to parse standard HTML pages into markdown output.

Why does web scraping output include so much irrelevant navigation text?▼

Web scraping output includes irrelevant navigation text because standard HTML pages contain boilerplate clutter; using the --md flag removes these elements to isolate the main content.

Related Skills

Explore More Content & Communication Skills→
xfs96192xfs96192

defuddle

Extract clean Markdown from web pages using the Defuddle CLI.

Community
Intermediate
ebrahim-saniebrahim-sani

web-reader

Convert web pages into clean Markdown text with JSON output.

Community
Basic
georgekhananaevgeorgekhananaev
27

token-formatter

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

Community
Advanced
akselikorhonen-siiliakselikorhonen-siili

html-to-md

Extract HTML content from web pages and convert it to Markdown.

Community
Basic