skills.rest
mofa-org
mofa-orgOFFICIAL
Explore all skills by this author →
WebsiteGitHub

mofa-defuddle

Extract clean article content from web pages into Markdown or JSON.

11|12|Updated Feb 28, 2026
Search Tags:#markdown#readability#json#web-scraping#article-extraction#web-content-extraction#defuddle
One-click install
npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-defuddle
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mofa-defuddle
Source: https://github.com/mofa-org/mofa-skills/tree/main/_unpublished/mofa-defuddle
Command: npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-defuddle

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract clean article content from cluttered web pages by converting messy HTML into readable Markdown or structured data, saving time and reducing manual editing.

Core Features & Use Cases

  • Extracts article text from any web page into clean Markdown or JSON with metadata
  • Outputs can be saved to files for archiving or further processing
  • Useful for researchers, content teams, and knowledge workers who curate web content

Quick Start

Provide a URL to a webpage and choose the output format to immediately obtain clean Markdown or JSON.

Frequently Asked Questions about mofa-defuddle

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract article content from a web page into Markdown?▼

To extract article content into Markdown, provide a URL to the webpage and choose the Markdown output format. The tool cleans cluttered HTML and returns readable, ads-free text suitable for immediate use.

Can I get structured JSON with metadata when scraping web content?▼

Yes, you can extract web content into structured JSON with optional metadata. By selecting the JSON output format, the tool converts messy HTML pages into structured data for content curation and archival workflows.

Do I need Node.js and npx to run web content extraction?▼

Yes, Node.js and npx are required to install and run the defuddle package for web content extraction. This environment provides the runtime needed to process URLs and output clean Markdown or JSON.

What's the best way to remove ads and clutter from web pages for research?▼

The best way to remove ads and clutter is using a dedicated article extraction tool that parses HTML and isolates main content. This yields clean, readable text outputs that save manual editing time for researchers.

Does web content extraction work for content curation and archival workflows?▼

Web content extraction works well for content curation and archival workflows. It extracts article text from any URL into clean Markdown or JSON files, which can be saved for further processing or long-term storage.

Related Skills

Explore More Content & Communication Skills→
caoronglincaoronglin
2

markdownify-mcp

Convert web pages, PDFs, Office documents, images, and audio into Markdown format.

Community
Intermediate
carterwayneskhizeinecarterwayneskhizeine
19

ocr-and-documents

Extract text and structured content from PDFs and scanned documents.

Community
Intermediate
marktantongcomarktantongco

firecrawl-scrape

Extract HTML content from URLs and convert it to markdown.

Community
Advanced
AradotsoAradotso
7

kindly-web-search-mcp-server

Searches web and extracts full pages to structured Markdown for AI coding workflows.

Official
Advanced