Back to search
defuddle-skill
SkillWorks with Claude CodeGitHub
Claude Code skill for defuddle - extract clean article content from web pages
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked today
Badge for your README
Markdown
[](/listings/joeseesun-defuddle-skill)HTML
<a href="/listings/joeseesun-defuddle-skill"><img src="/api/listings/joeseesun-defuddle-skill/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Option 1: npx (recommended)
npx defuddle-skill
This will: 1. Install `defuddle` CLI globally (if not already installed) 2. Copy the skill to `~/.claude/skills/defuddle/`
Option 2: Vercel Skills CLI
npx skills add joeseesun/defuddle-skill
Option 3: Manual
git clone https://github.com/joeseesun/defuddle-skill.git cd defuddle-skill bash install.sh
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 76 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- # defuddle-skill
- A [Claude Code](https://claude.ai/claude-code) skill that wraps [defuddle](https://github.com/kepano/defuddle) — extract clean article content from web pages, removing ads, sidebars, and clutter.
- ## Install
- ### Option 1: npx (recommended)
- ```bash
- npx defuddle-skill
- ```
- This will:
- 1. Install `defuddle` CLI globally (if not already installed)
- 2. Copy the skill to `~/.claude/skills/defuddle/`
- ### Option 2: Vercel Skills CLI
- ```bash
- npx skills add joeseesun/defuddle-skill
- ```
- ### Option 3: Manual
- ```bash
- git clone https://github.com/joeseesun/defuddle-skill.git
- cd defuddle-skill
- bash install.sh
- ```
- ## What it does
- Once installed, Claude Code can automatically extract clean content from any URL:
- - **Triggers**: "defuddle", "extract article", "clean this page", "get content from URL"
- - **Output**: Clean Markdown or JSON with metadata (title, author, date, word count)
- ## Usage examples
- Ask Claude Code:
- ```
- Extract the article from https://example.com/blog-post
- ```
- ```
- defuddle this page and give me the markdown: https://example.com/article
- ```
- ```
- Get the title and author from https://example.com/post
- ```
- ## CLI Reference
- The skill uses `defuddle` CLI under the hood:
- ```bash
- defuddle parse <url-or-file> [options]
- Options:
- -m, --markdown Convert to Markdown
- -j, --json Output as JSON with metadata
- -o, --output <file> Save to file
- -p, --property <name> Extract single field (title, author, published, etc.)
- --debug Verbose logging
- ```
- ## Credits
- - [defuddle](https://github.com/kepano/defuddle) by [@kepano](https://github.com/kepano) — the core extraction engine
- - Built for [Claude Code](https://claude.ai/claude-code) by Anthropic
- ## License
- MIT
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.