defuddle

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

Updated May 18, 2026
One-click install
npx skills add https://github.com/fts-pro/FTS-MMIS-AFRIKA --skill defuddle-fts-pro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/fts-pro/FTS-MMIS-AFRIKA/tree/main/.agent/skills/defuddle
Command: npx skills add https://github.com/fts-pro/FTS-MMIS-AFRIKA --skill defuddle-fts-pro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires defuddle.

What problem does it solve? Fetching web pages with standard tools returns raw HTML cluttered with navigation, ads, and boilerplate, wasting tokens and obscuring the actual content. This Skill uses the Defuddle CLI to strip clutter and return clean markdown from any URL. ## Core Features & Use Cases - Clean Markdown Extraction: Parse any web page into readable markdown with the --md flag, removing navigation and ads. - Metadata Retrieval: Extract specific properties like title, description, or domain with the -p flag. - Flexible Output Formats: Choose markdown, JSON, or HTML output, and save results directly to a file with -o. - Use Case: When a user shares a blog post or documentation URL to analyze, run defuddle parse <url> --md instead of WebFetch to get token-efficient, readable content. ## Quick Start Ask the AI to read and summarize the article at a given URL using defuddle instead of WebFetch.

Frequently Asked Questions about defuddle

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

FAQPage Schema
How do I extract markdown from a web page URL?▼

Run defuddle parse <url> --md to convert a web page into clean markdown. The CLI strips navigation, ads, and boilerplate, returning only the readable content. Add -o content.md to save the output to a file.

When should I use defuddle instead of WebFetch?▼

Use defuddle for standard web pages like articles, blog posts, and documentation where clutter removal saves tokens. Do not use it for URLs ending in .md, since those are already markdown and should be fetched directly with WebFetch.

How do I install the defuddle CLI?▼

Install defuddle globally with npm by running npm install -g defuddle. After installation, the defuddle command becomes available in your terminal for parsing URLs.

Can defuddle extract only the title or description of a page?▼

Yes, use the -p flag followed by a property name, such as defuddle parse <url> -p title, -p description, or -p domain. This returns just the requested metadata property instead of the full page content.

What output formats does defuddle support?▼

Defuddle supports three output formats: markdown via the --md flag, JSON containing both HTML and markdown via --json, and raw HTML when no flag is provided. Markdown is the recommended default for content analysis.