Skip to main content
skill CX Codex

defuddle · kepano — Claude Code skill: extract web pages as Markdown

This skill uses Defuddle CLI to turn web pages into readable Markdown. Use it when an agent needs page content without navigation or ads.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add kepano/obsidian-skills --skill defuddle -a claude-code
Open on GitHub

What defuddle does

The skill directs Claude Code to use Defuddle CLI to extract readable page content, preferring it to WebFetch for standard web pages. Defuddle removes navigation, ads, and other clutter. You can request Markdown or JSON containing both HTML and Markdown.

For Markdown, run defuddle parse <url> --md; add -o content.md to save the result to a file. The -p option returns a specific metadata property, such as title, description, or domain. The CLI must be installed first: run npm install -g defuddle.

What it helps with

  • Extract readable text from an HTML page
  • Save a page as a Markdown file
  • Fetch a page title, description, or domain

Example prompts for the agent

  • Extract this page as Markdown with defuddle parse <url> --md
  • Save the page content to content.md using defuddle parse <url> --md -o content.md
  • Get the page description with defuddle parse <url> -p description

How to install defuddle

1Skills CLI (Vercel)

npx skills add kepano/obsidian-skills --skill defuddle -a claude-code

2Manually: put the files in place

~/.claude/skills/defuddle/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/defuddle/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

From the same set3

Other versions of defuddle

Similar

Nearby in Browser and scraping

All skills for Browser and scraping →

Questions about defuddle

How do I install defuddle in Claude Code?

Run npx skills add kepano/obsidian-skills --skill defuddle -a claude-code. The skill file is at ~/.claude/skills/defuddle/SKILL.md.

What does defuddle do?

It uses Defuddle CLI to extract readable content from web pages and output it as Markdown. For standard pages, the skill recommends Defuddle over WebFetch.

Which output formats does Defuddle CLI support?

--md outputs Markdown, while --json returns JSON containing HTML and Markdown. With no format flag, the CLI outputs HTML; use -p to select a metadata property.

Source text

SKILL.md · MIT
---
name: defuddle
description: Extract clean Markdown from HTML pages with Defuddle CLI.
---

# 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:

```bash
defuddle parse <url> --md
```

Save to file:

```bash
defuddle parse <url> --md -o content.md
```

Extract specific metadata:

```bash
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 |

© kepano · MIT · kepano/obsidian-skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor