defuddle

Extract clean Markdown content from web pages using Defuddle.

Updated Mar 16, 2026
One-click install
npx skills add https://github.com/shihwesley/shihwesleys-harness --skill defuddle-shihwesley
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/shihwesley/shihwesleys-harness/tree/main/commands/defuddle
Command: npx skills add https://github.com/shihwesley/shihwesleys-harness --skill defuddle-shihwesley

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Defuddle extracts clean, markdown-ready content from standard web pages by removing navigation, ads, and clutter, helping you ingest readable text with lower token overhead.

Core Features & Use Cases

  • Clean extraction: Generate markdown-friendly content from articles, docs, tutorials, and blog posts.
  • Token optimization: Strip distractions to minimize token usage in AI workflows.
  • Metadata support: Retrieve and inspect basic metadata like title, domain, and description when needed.

Quick Start

Parse a given URL with Defuddle to generate clean Markdown output.

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 token-efficient AI ingestion?▼

Extracting clean markdown from web pages requires removing navigation, ads, and clutter to produce readable text. Defuddle parses standard URLs and outputs markdown-ready content, minimizing token overhead for AI workflows.

How do I scrape web content and remove ads without getting blocked by clutter?▼

Scraping web content and removing ads is done by parsing the target URL to strip away page clutter. Defuddle extracts clean text from articles and documentation, generating a compact markdown format output.

Do I need to install defuddle separately to extract web page content?▼

Yes, extracting web page content requires installing defuddle separately via npm. You must run npm install -g defuddle before using this Skill to parse URLs and generate markdown output.

Can I retrieve metadata like title and domain when parsing web articles?▼

Retrieving metadata like title and domain when parsing web articles is supported through optional query flags. Defuddle allows you to inspect basic page metadata using the -p title command option.

What's the best way to convert online tutorials and blog posts into readable text?▼

Converting online tutorials and blog posts into readable text is best handled by parsing the URL to strip distractions. Defuddle turns standard web pages into clean, markdown-ready content for summaries.