web-content-extractor

Extract clean main content from webpage URLs as Markdown using Defuddle or Jina AI reader services.

1|Updated Jun 20, 2026

Search Tags:#markdown #web scraping #content extraction #curl #defuddle #jina ai #article reader

Ready to run

npx skills add https://github.com/riipandi/minis-skills --skill web-content-extractor-riipandi

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: web-content-extractor
Source: https://github.com/riipandi/minis-skills/tree/main/web-content-extractor
Command: npx skills add https://github.com/riipandi/minis-skills --skill web-content-extractor-riipandi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Webpages are cluttered with ads, navigation menus, and boilerplate that make it hard to read or reuse the actual article content. This Skill converts any webpage URL into clean Markdown containing only the main body text. ## Core Features & Use Cases - Clean Content Extraction: Fetches a webpage through the Defuddle service to strip ads, navigation, and clutter, returning only the main article as Markdown. - Automatic Fallback: Switches to the Jina AI reader service (r.jina.ai) when Defuddle fails or returns an error. - Use Case: A user finds a long blog post and wants to save it as a readable Markdown note without sidebars and popups. The Skill fetches the URL through the extraction service and returns clean Markdown ready to save or summarize. ## Quick Start Extract the main article content from https://example.com/some-article and give it to me as clean 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 the main article text from a webpage URL?▼

Prepend https://defuddle.md/ to the target URL and fetch it with curl, for example curl -sL "https://defuddle.md/https://example.com/article". The response is clean Markdown containing only the main content without ads or navigation.

What is the difference between Defuddle and Jina AI reader for webpage extraction?▼

Defuddle (defuddle.md) is the primary extraction service used by default, while Jina AI reader (r.jina.ai) serves as the fallback. Both convert webpages to clean Markdown by prepending their service URL to the target URL.

What should I do if webpage content extraction fails or returns empty?▼

Switch from Defuddle to the Jina AI reader fallback by fetching https://r.jina.ai/ prepended to the target URL. Also verify the target URL includes the https:// protocol and is quoted in the curl command.

Does the extracted webpage content come in Markdown format?▼

Yes, both Defuddle and Jina AI reader return the extracted main content in Markdown format. You can present it directly, save it to a file, or use it to answer questions about the page.

Why does my curl command fail on URLs with special characters?▼

URLs containing characters like & or ? get misinterpreted by the shell if unquoted. Always enclose the full fetch URL in double quotes inside the curl command to prevent shell interpretation.