defuddle

Convert web pages into clean markdown with optional source metadata.

4|Updated Jan 29, 2026

Search Tags:#markdown #token-savings #noise-removal #cli-tools #defuddle #web-content-cleaning #web-article-ingestion

Ready to run

npx skills add https://github.com/danmestas/wardrobe --skill defuddle-danmestas

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/danmestas/wardrobe/tree/main/skills/defuddle
Command: npx skills add https://github.com/danmestas/wardrobe --skill defuddle-danmestas

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Removes ads, navigation, headers, and boilerplate from web pages to yield clean, readable markdown suitable for ingestion.

Core Features & Use Cases

Web-page cleaning: strips ads, banners, and unnecessary UI to produce article-focused markdown.
Ingestion-ready outputs: outputs clean markdown ready for wiki or knowledge bases, optionally preserving source metadata.
Token efficiency: reduces noise and token usage when ingesting content.

Quick Start

Run defuddle on a URL to extract clean article text for ingestion.

Frequently Asked Questions about defuddle

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert web pages to clean markdown for ingestion?▼

To convert web pages to clean markdown, you strip ads, navigation, and boilerplate to produce article-focused text. This removes noise and reduces token usage when ingesting content into knowledge bases.

What is the best way to remove web clutter before ingesting articles into a wiki?▼

The best way to remove web clutter is to process URLs through a content cleaning tool that strips banners and UI elements. It outputs readable markdown optionally preserving source metadata like the fetch date for archival.

Does web content cleaning work on documentation pages and blogs?▼

Web content cleaning works widely on news articles, blogs, and documentation pages. It removes unnecessary UI and banners to yield clean, readable markdown suitable for ingestion regardless of the source page type.

Can I include source URL metadata when extracting article text to markdown?▼

You can include a frontmatter header with the source URL and fetch date when extracting article text. This preserves archival metadata alongside the clean markdown output for ingestion into wikis or knowledge bases.

Why does ingesting raw web pages waste tokens?▼

Ingesting raw web pages wastes tokens because ads, navigation, and headers introduce noise. Removing this clutter yields article-focused markdown, significantly reducing token usage during content ingestion.