Score
8.5
/ 10
Installs
71K
Repo Stars
49.1K
Last Updated
18d ago
Quality Ratio
94%
Description
Verified
First Published
Feb 2026
Summary
The Defuddle agent skill extracts clean, relevant markdown content from standard web pages, reducing token usage for AI analysis by removing clutter. This agent skill is ideal for developers building AI agents that frequently need to analyze online documentation, articles, or blog posts without getting bogged down by extraneous UI elements. It is a widely adopted skill in the registry, noted as a skill with 66K installs. Instead of `WebFetch` for general web content, agents are instructed to use Defuddle CLI's `parse <url> --md` command. This ensures the agent receives focused content by stripping navigation, ads, and other irrelevant page elements before processing. The skill specifically warns against using it for URLs ending in `.md`, as those are already markdown and should be fetched directly.
Skill Definition
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: npm install -g defuddle
Usage
Always use --md for 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 both HTML and markdown |
| (none) | HTML |
-p <name> | Specific metadata property |