Skill

Review

Audit score 70

defuddle

joeseesun/defuddle-skill

Extract clean article content from web pages, removing ads and clutter to get readable Markdown with metadata.

What is defuddle?

Defuddle extracts the main article content from web pages or local HTML files, stripping away ads, sidebars, navigation, and other noise. Use it when you need to convert web pages into clean, readable Markdown with structured metadata like title, author, and word count.

Extract article text from URLs or local HTML files with clutter removal
Output clean Markdown content with frontmatter metadata (title, author, publication date, word count)
Retrieve structured JSON metadata including title, author, description, domain, featured image, and parse time
Save extracted content to user-specified directories with sanitized filenames
Support single-property extraction for targeted data retrieval

How to install defuddle

npx skills add https://github.com/joeseesun/defuddle-skill --skill defuddle

Prerequisites

Node.js and npm installed
Install defuddle globally: npm install -g defuddle jsdom

Claude Code

Cursor

Windsurf

Cline

How to use defuddle

1.Run defuddle parse with both markdown and JSON flags: defuddle parse "<url>" -m -j
2.Review the extracted metadata (title, author, source, word count) and content preview
3.Specify a directory to save the file (e.g., ~/Documents, ~/Desktop)
4.Defuddle saves the file with frontmatter metadata and full Markdown content using the article title as the filename
5.Confirm the saved file path

Use cases

Good for

Save blog posts or news articles as clean Markdown files for offline reading or archiving
Extract article text from web pages to feed into downstream processing or analysis
Batch convert multiple web pages to structured Markdown with consistent metadata
Retrieve metadata (author, publication date, word count) from articles programmatically
Strip ads and navigation from documentation pages to focus on core content

Who it's for

Content researchers and archivists
Developers building content processing pipelines
Knowledge workers managing research materials
Documentation readers wanting clean offline copies

defuddle FAQ

What types of pages work best with defuddle?

Article-style pages like blogs, news sites, and documentation work best. JavaScript-heavy single-page applications and pages requiring browser rendering (e.g., WeChat articles) are not well-supported.

Can I extract a single piece of metadata instead of the full article?

Yes, use the -p or --property flag to extract a single field: defuddle parse "<url>" -p title (options: title, description, domain, author, published, wordCount, content).

How are filenames generated when saving?

Filenames are based on the article title with special characters replaced by spaces and whitespace trimmed. For example, an article titled 'The Shape of the Essay Field' becomes 'The Shape of the Essay Field.md'.

What metadata is included in the saved file?

Saved files include frontmatter with title, author, source URL, publication date, clipping date, and word count, followed by the full extracted Markdown content.

Does defuddle work with local HTML files?

Yes, you can pass a local file path instead of a URL to defuddle parse.

Full instructions (SKILL.md)

Source of truth, from joeseesun/defuddle-skill.

name: defuddle description: Extract clean article content from web pages or local HTML files. Removes clutter (ads, sidebars, nav) and returns readable content with metadata. trigger: Use when user wants to extract/clean web page content, strip clutter from HTML, get article text from a URL, or convert web pages to clean markdown. Triggers include "defuddle", "extract article", "clean this page", "get content from URL", "strip clutter", "web extract".

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:

---
title: {title}
author: {author}
source: {url}
date: {published or "Unknown"}
clipped: {today's date YYYY-MM-DD}
wordCount: {wordCount}
---

# {title}

{markdown content}

File naming: Use the article title as filename, sanitized for filesystem:

Replace special characters with spaces
Trim whitespace
Example: The Shape of the Essay Field.md

Step 5: Confirm to user

Tell the user the file path where it was saved.

CLI Reference

defuddle parse <source> [options]

Arguments:

<source> — URL (https://...) or local HTML file path

Options:

Flag	Description
`-m, --markdown`	Convert content to Markdown
`-j, --json`	Output as JSON with full metadata
`-o, --output <file>`	Write to file instead of stdout
`-p, --property <name>`	Extract single property (title, description, domain, author, published, wordCount, content)
`--debug`	Verbose logging

JSON Response Fields

When using -j, the response includes:

title — Article title
author — Author name
published — Publication date
description — Meta description
content — Extracted Markdown (when -m used)
domain — Source domain
favicon — Favicon URL
image — Featured image URL
site — Site name
wordCount — Word count
parseTime — Processing time in ms

Notes

Requires Node.js and npm
jsdom is required as a peer dependency
Works best with article-style pages (blogs, news, documentation)
Not designed for SPAs or JavaScript-heavy pages (e.g. WeChat articles need browser rendering)