defuddle

Extract clean Markdown from web pages using Defuddle CLI.

Updated Mar 27, 2026

Search Tags:#markdown #cli #token-optimization #web-scraping #web-content #content-extraction #defuddle

Ready to run

npx skills add https://github.com/EmaRimoldi/Claude-scholar-extended --skill defuddle-emarimoldi

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/EmaRimoldi/Claude-scholar-extended/tree/main/skills/defuddle
Command: npx skills add https://github.com/EmaRimoldi/Claude-scholar-extended --skill defuddle-emarimoldi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Web pages often include clutter like navigation, ads, and sidebars that inflate content size and waste tokens. Defuddle CLI outputs clean, readable Markdown from web pages, making it easier to read or analyze content with minimal noise.

Core Features & Use Cases

Extract clean Markdown from standard web pages (documentation, articles, blog posts) by removing navigation and clutter.
Supports quick extraction of metadata and plain content to save tokens for downstream analysis.
Use cases include reading online references, preparing summaries, or feeding clean content into AI workflows.

Quick Start

Parse a URL and generate clean Markdown content with Defuddle.

Frequently Asked Questions about defuddle

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

FAQPage Schema

How do I extract clean Markdown from a web page to reduce token usage?▼

You can extract clean Markdown from a web page to reduce token usage by running the Defuddle CLI tool, which strips away navigation, ads, and sidebars to output only readable content. This minimizes clutter for downstream AI workflows.

Do I need npm to install Defuddle for web content extraction?▼

Yes, you need npm to install Defuddle for web content extraction. The tool is installed via the npm package manager, after which you can parse URLs using the command line interface to output clean Markdown, JSON, or HTML formats.

What is the best way to scrape online articles without ads and navigation clutter?▼

The best way to scrape online articles without ads and navigation clutter is using a content extraction CLI like Defuddle. It specifically targets standard pages such as blogs and documentation, removing noise and outputting plain Markdown to save tokens.

Can I output extracted web content as JSON or HTML instead of Markdown?▼

Yes, you can output extracted web content as JSON or HTML instead of Markdown. Defuddle CLI supports multiple output formats, allowing you to choose the structure that best fits your content analysis or data processing pipeline.

How do I parse a URL with Defuddle to get Markdown content?▼

To parse a URL with Defuddle and get Markdown content, run the command defuddle parse <url> --md in your terminal. This processes the web page and returns clean, readable Markdown text by removing sidebars and ads.

When should I not use a CLI web scraper for content extraction?▼

You should not use a CLI web scraper for content extraction if your target page relies heavily on dynamic JavaScript rendering, as Defuddle is designed for standard online documentation, articles, and blogs where static content extraction is sufficient.