skills.rest
hviwen
hviwenCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

defuddle

Extract clean markdown content from web pages using the Defuddle CLI.

Updated Feb 2, 2026
Search Tags:#markdown#web scraping#content extraction#web fetch#token saving#defuddle
One-click install
npx skills add https://github.com/hviwen/mosaic-photo --skill defuddle
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/hviwen/mosaic-photo/tree/main/.claude/skills/defuddle
Command: npx skills add https://github.com/hviwen/mosaic-photo --skill defuddle

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the challenge of extracting clean, readable content from web pages, which often contain distracting advertisements, navigation menus, and other non-essential elements that consume valuable AI context tokens.

Core Features & Use Cases

  • Clutter Removal: Strips away website navigation, ads, and other extraneous content.
  • Token Efficiency: Significantly reduces the number of tokens required to process web content by focusing only on the main article or information.
  • Use Case: When a user provides a URL to an online article, blog post, or documentation, this Skill ensures that only the core content is fetched and processed, making AI analysis more efficient and cost-effective.

Quick Start

Use the defuddle skill to extract markdown content from the url https://example.com/article.

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 without ads and navigation clutter?▼

To extract clean markdown from web pages, this Skill uses the Defuddle CLI to strip away non-essential elements like ads and navigation menus. It processes online articles and documentation, returning only the core content to ensure token efficiency.

Why does fetching web content consume so many tokens when processing articles?▼

Fetching raw web content consumes excessive tokens because standard requests include website clutter like navigation menus and advertisements. This Skill solves token bloat by removing extraneous elements, ensuring only the main article text is processed.

What is the best way to save tokens when analyzing online blog posts?▼

The best way to save tokens when analyzing blog posts is to filter out non-essential website elements before processing. This Skill isolates the main content from URLs, significantly reducing the number of tokens required for AI analysis.

Can I use this web scraping skill for documentation sites?▼

Yes, you can use this web scraping skill for documentation sites. It is specifically designed to process online articles, documentation, and blog posts, extracting only the relevant core markdown content while ignoring distracting site layouts.

Does web content extraction work with any URL I provide?▼

Web content extraction works best when provided with URLs pointing to online articles, blog posts, or documentation. It fetches the page, removes website clutter, and extracts the main content as markdown for efficient AI processing.

Related Skills

Explore More Content & Communication Skills→
ittooittittooitt

defuddle

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

Community
Basic
kaifashraffkaifashraff

youtube-watcher

Fetch YouTube video transcripts using yt-dlp for summarization and content extraction.

Community
Intermediate
smilebank7smilebank7
2

Extract Materials

Extract text, tables, and equations from PDFs, PPTX, DOCX, and images into Markdown.

Community
Intermediate
OpenAEC-FoundationOpenAEC-Foundation
163

frappe-website-deploy

Deploy ERPNext/Frappe websites via REST API with Page Builder.

Official
Advanced