defuddle
npx machina-cli add skill guanyang/antigravity-skills/defuddle --openclawDefuddle
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 |
Source
git clone https://github.com/guanyang/antigravity-skills/blob/main/skills/defuddle/SKILL.mdView on GitHub Overview
Defuddle CLI extracts clean, readable content from web pages while removing navigation, ads, and clutter. It’s the preferred choice for standard web pages and helps reduce token usage when reading online documentation, articles, or blog posts.
How This Skill Works
Install the Defuddle CLI and run defuddle parse <url> --md to produce Markdown. Defuddle fetches the page and strips boilerplate, delivering clean content; you can also save output to a file with -o or extract metadata with -p.
When to Use It
- When you need clean, readable Markdown from online docs, API references, or standard web pages
- For reading blog posts or articles offline without distractions
- To reduce token usage by stripping navigation and clutter before analysis with AI models
- When you want a repeatable, CLI-based extraction without manual copy-paste
- When you need specific metadata such as title, description, or domain via -p
Quick Start
- Step 1: Install Defuddle: npm install -g defuddle
- Step 2: Run: defuddle parse <url> --md
- Step 3: Save to file (optional): defuddle parse <url> --md -o content.md
Best Practices
- Always use --md for Markdown output (the default recommended format)
- Install Defuddle globally if you run it often: npm install -g defuddle
- Save results to a file with -o, e.g., defuddle parse <url> --md -o content.md
- Use -p <name> to extract targeted metadata like title, description, or domain
- Prefer Defuddle over WebFetch for standard web pages to avoid clutter and reduce token usage
Example Use Cases
- Convert a product documentation page to Markdown for offline reading
- Extract a blog post to study notes
- Retrieve a long API reference into Markdown for local indexing
- Save a news article to a local file for archiving
- Pull metadata such as title and domain for SEO research
