You know that moment when you're trying to read an article but the page is drowning in popups, sidebars, and newsletter prompts? This pulls the actual content out of any URL and gives you clean Markdown with metadata like title, author, and word count. The workflow is smart: it extracts everything, shows you a summary, asks where to save it once, then remembers your preference. Files get proper frontmatter and sensible names. It's basically Readability as a CLI tool that plays nice with Claude's file handling. Works great for blogs and news sites, though it'll struggle with JavaScript-heavy pages that need full browser rendering. If you're clipping articles or building a research library, this beats copying and pasting by hand.

skills.sh installs
1.3K
GitHub stars
112
last updated
Aug 21, 2026

Install

$ npx -y skills add joeseesun/defuddle-skill --skill defuddle --agent claude-code

Installs into .claude/skills of the current project.

Files

Defuddle - Web Content Extraction

Extract main article content from web pages, removing ads, sidebars, navigation, and other clutter. Output clean Markdown with metadata.

Prerequisites

Before first use, check if defuddle is installed:

command -v defuddle >/dev/null 2>&1 || npm install -g defuddle jsdom

Default Workflow

When user provides a URL, follow this workflow:

Step 1: Extract content as Markdown + JSON metadata

Always use both -m and -j flags to get markdown content with full metadata:

defuddle parse "<url>" -m -j

Step 2: Present a summary to the user

Show the user:

  • Title: from JSON title field
  • Author: from JSON author field
  • Source: domain
  • Word count: from JSON wordCount field
  • A brief preview (first 2-3 sentences)

Step 3: Ask where to save

If this is the first time using defuddle in this conversation, ask the user:

"Save to which directory? (e.g. ~/Documents, ~/Desktop, or a custom path)"

Remember the user's chosen directory for subsequent uses in the same conversation.

Step 4: Save as Markdown file

Write the file with frontmatter + full content:

Sponsors

Details

Repository
github.com/joeseesun/defuddle-skill
Category
Frontend Development
First seen
May 16, 2026
1cap-go avatarcapacitor-accessibilitycap-go/capgo-skillsAccessibility guide for Capacitor apps covering screen readers, semantic HTML, focus management, and WCAG compliance. Use this skill when users need to make the1.3Kskills.sh installs
2kostja94 avatarhero-generatorkostja94/marketing-skillsWhen the user wants to design, optimize, or audit hero sections (above-the-fold main visual area). Also use when the user mentions "hero," "hero section," "hero1.3Kskills.sh installs
3neolabhq avatartest-promptneolabhq/context-engineering-kitUse when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cyc1.3Kskills.sh installs
4jezweb avatargoogle-chat-messagesjezweb/claude-skillsSend Google Chat messages via incoming webhooks — text, rich cards (cardsV2), threaded replies. TypeScript types, card builder utility, widget reference inline.1.3Kskills.sh installs
5capawesome-team avatarcapawesome-cloudcapawesome-team/skillsGuides the agent through setting up and using Capawesome Cloud for Capacitor and Cordova apps. Covers three core workflows: (1) Native Builds — cloud builds for1.3Kskills.sh installs
6phaserjs avatarsprites-and-imagesphaserjs/phaserUse this skill when creating Sprites or Images in Phaser 4. Covers factory methods, texture/frame selection, position, scale, rotation, tint, flip, alpha, origi1.2Kskills.sh installs