web-content-extractor

Extract main article content from webpages as Markdown using Defuddle with Jina AI fallback.

361|58|Updated Mar 1, 2026
One-click install
npx skills add https://github.com/OpenMinis/MinisSkills --skill web-content-extractor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-content-extractor
Source: https://github.com/OpenMinis/MinisSkills/tree/main/web-content-extractor
Command: npx skills add https://github.com/OpenMinis/MinisSkills --skill web-content-extractor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Cleanly extract the main article content from a webpage by removing ads, navigation, and clutter, yielding a usable Markdown body for reading, clipping, or summarization.

Core Features & Use Cases

  • Primary extraction via Defuddle to fetch clean Markdown from a URL.
  • Fallback extraction via Jina AI Reader when Defuddle fails.
  • Output ready for reading, summarization, or archiving, with preserved formatting when possible.

Quick Start

Paste a webpage URL into the assistant and have it return the main article content as Markdown.

Frequently Asked Questions about web-content-extractor

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

FAQPage Schema
How do I extract main article content from a webpage as clean Markdown?

To extract main article content as clean Markdown, paste a webpage URL into the assistant. It queries Defuddle to remove ads and clutter, yielding a readable Markdown body, and falls back to Jina AI Reader on error.

What is the best way to get readable Markdown from news posts and long-form web articles?

The best way to get readable Markdown from long-form web articles is using an extractor that removes navigation and ads. This Skill queries Defuddle for clean output and uses Jina AI as a fallback.

Does web content extraction work when Defuddle fails to fetch the article?

Web content extraction works when Defuddle fails by automatically falling back to the Jina AI Reader. This ensures you still get a clean Markdown version of the article even if the primary method encounters an error.

Can I use extracted Markdown for summarization and archiving?

You can use extracted Markdown for summarization and archiving because the output is a clean body with preserved formatting. This makes it ready for reading, clipping, or feeding into summarization tools.

Why does my webpage extraction include ads and navigation clutter?

Webpage extraction might include clutter if the primary fetch method fails to isolate the main article. This Skill specifically addresses that by querying Defuddle and falling back to Jina AI to yield a clean Markdown body.