Defuddle
When you need to analyze web content without burning tokens on navigation menus and ads, this extracts clean markdown from any URL. It's essentially a smart web scraper that strips the clutter and gives you just the article content. Perfect for feeding documentation, blog posts, or news articles into Claude for analysis or summarization. The CLI tool handles the heavy lifting of content detection and cleanup, so you get readable markdown instead of messy HTML soup. Skip it for URLs that already end in .md since those don't need the extraction treatment.
- installs
- 74.8K
- GitHub stars
- 50.2K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add kepano/obsidian-skills --skill defuddle --agent claude-codeInstalls into .claude/skills of the current project.
Files
Defuddle
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 |
Sponsors
Details
- Repository
- github.com/kepano/obsidian-skills
- Categories
- Documentation, CLI & Terminal, Office & Documents
