skills.rest
virahitvin8
virahitvin8COMMUNITY
Explore all skills by this author →
GitHub

defuddle

Extract clean markdown content from web pages using the Defuddle CLI.

2|Updated May 30, 2026
Search Tags:#markdown#cli#web scraping#content extraction#web pages#token reduction#defuddle
One-click install
npx skills add https://github.com/virahitvin8/crafty-gis --skill defuddle-virahitvin8
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/virahitvin8/crafty-gis/tree/main/GIT_STAR/assignment-generator/antigravity-skills-main/antigravity-skills-main/skills/defuddle
Command: npx skills add https://github.com/virahitvin8/crafty-gis --skill defuddle-virahitvin8

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires defuddle.

What problem does it solve? Fetching web pages with standard tools returns cluttered HTML full of navigation, ads, and boilerplate, wasting tokens and obscuring the actual content you need to read or analyze. ## Core Features & Use Cases - Clean Content Extraction: Parse any standard web page into readable markdown with clutter, navigation, and ads removed. - Metadata Retrieval: Pull specific properties like title, description, or domain directly from a URL. - Flexible Output Formats: Choose markdown, JSON, or raw HTML output depending on your downstream workflow. - Use Case: When a user shares a link to a blog post or documentation page, run defuddle parse <url> --md to get a token-efficient markdown version for summarization or analysis. ## Quick Start Ask the assistant to read and summarize the article at a given URL using defuddle instead of a standard web fetch.

Frequently Asked Questions about defuddle

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

FAQPage Schema
How do I convert a web page to clean markdown from the command line?▼

Run defuddle parse <url> --md to extract the main content of a web page as markdown. The CLI strips navigation, ads, and boilerplate, producing a compact document suitable for reading or feeding to an LLM.

When should I use Defuddle instead of a standard web fetch tool?▼

Use Defuddle for standard web pages like articles, blog posts, and documentation where clutter inflates token usage. Do not use it for URLs ending in .md, since those are already markdown and can be fetched directly.

How do I install the Defuddle CLI?▼

Install it globally with npm by running npm install -g defuddle. After installation, the defuddle command becomes available in your terminal for parsing URLs.

Can Defuddle extract only the title or description of a page?▼

Yes, use the -p flag followed by a property name, such as defuddle parse <url> -p title or -p description. This returns just that metadata field without the full page content.

What output formats does Defuddle support?▼

Defuddle supports markdown via --md, JSON containing both HTML and markdown via --json, and raw HTML when no flag is given. Markdown is the recommended default for token-efficient reading.

Related Skills

Explore More Content & Communication Skills→
TeamWiseFlowTeamWiseFlow
8.4k

rss-reader

Convert RSS/Atom feed URLs into markdown lists of recent entries.

Official
Intermediate
lordkinglordking

web-article-collector

Extract article content from public webpages and save Markdown notes.

Community
Advanced
NousResearchNousResearch
239.1k

blocked-page-recovery

Recover blocked, paywalled, or WAF-protected web pages from third-party archives.

Official
Advanced
istota-projectistota-project
10

browse

Fetch JavaScript-rendered pages and extract content via CSS selectors.

Official
Advanced