About defuddle
defuddle is a CLI skill for extracting readable content and metadata from web pages. It offers Markdown, HTML, and JSON output, with options to save content or select metadata fields.
Key features
- 01Extract readable page content
- 02Output Markdown, HTML, or JSON
- 03Save Markdown to a file
- 04Select title, description, or domain
Use cases
- 01Extracting article text from a web page
- 02Saving page content as Markdown
- 03Retrieving selected page metadata
Install
Copy the command and run it in a terminal.
$
npx skills add https:/After installing, type/defuddlein Claude Code to confirm it loaded.
Details
From the project READMEDefuddle
Use Defuddle CLI to extract clean readable content from web pages. Prefer over WebFetch for standard web pages — it removes navigation, ads, and clutter, reducing token usage.
If not installed, use npx defuddle parse <url> --md. For repeated use,
npm install -g defuddle is also available.
Usage
Use --md for plain Markdown output:
defuddle parse <url> --md
Save to file:
defuddle parse <url> --md -o content.md
Extract specific metadata:
defuddle parse <url> -p title
defuddle parse <url> -p description
defuddle parse <url> -p domain
Output formats
| Flag | Format |
|---|---|
--md | Markdown (default choice) |
--json | JSON with metadata, HTML in content, and Markdown in contentMarkdown |
--json --md | JSON with metadata and Markdown in content; no separate contentMarkdown |
| (none) | HTML |
-p <name> | Specific metadata property |
Comments
Markdown supported