Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/kepano/obsidian-skills/llms.txt

Use this file to discover all available pages before exploring further.

The defuddle skill teaches AI coding assistants to use the Defuddle CLI to extract clean, readable content from web pages. Defuddle strips navigation bars, sidebars, ads, cookie banners, and other clutter from HTML pages, returning only the main article content. The output is significantly smaller than raw HTML, which reduces token usage when passing web content to a language model. Load this skill whenever the user provides a URL to read or analyze — for online documentation, articles, blog posts, or any standard web page. Prefer Defuddle over WebFetch for HTML pages; use WebFetch directly only for URLs that already return Markdown or plain text.

Installation

If Defuddle is not already installed, install it globally with npm:
npm install -g defuddle

Usage

Always use --md for Markdown output

The primary usage pattern. Fetches the URL, strips clutter, and outputs clean Markdown to stdout:
defuddle parse <url> --md

Save to file

Redirect the Markdown output directly to a file with -o:
defuddle parse <url> --md -o content.md

Extract metadata

Extract a specific metadata property from the page instead of the full content:
defuddle parse <url> -p title
defuddle parse <url> -p description
defuddle parse <url> -p domain

Output Formats

FlagFormat
--mdMarkdown (default choice)
--jsonJSON with both HTML and Markdown
(none)HTML
-p <name>Specific metadata property
Prefer Defuddle over WebFetch for standard web pages — HTML articles, documentation sites, and blogs. Defuddle removes clutter and nav elements that WebFetch would include, producing a much smaller and cleaner result that uses fewer tokens.
Do not use Defuddle for URLs ending in .md. Those URLs already return Markdown — use WebFetch directly to avoid unnecessary processing.

Build docs developers (and LLMs) love