Extract clean markdown content from web pages using the Defuddle CLI.
npx skills add https://github.com/gtbauke/bj-utils --skill defuddle-gtbauke
Please help me install this Agent Skill. Skill: defuddle Source: https://github.com/gtbauke/bj-utils/tree/main/.agent/skills/defuddle Command: npx skills add https://github.com/gtbauke/bj-utils --skill defuddle-gtbauke
defuddle parse <url> --md. - Metadata Retrieval: Pull specific page properties like title, description, or domain with the -p flag. - Flexible Output Formats: Choose markdown, JSON (with both HTML and markdown), or raw HTML output. - Use Case: When a user shares a blog post or documentation URL to summarize, run Defuddle instead of WebFetch to get a compact markdown version that consumes far fewer tokens. ## Quick Start Ask the AI to extract the content of a given URL as markdown using Defuddle, for example by saying "use defuddle to read this article" followed by the link.High-intent search queries and answers about installing and using this skill.
Run defuddle parse followed by the URL and the --md flag to get markdown output. Add -o content.md to save the result directly to a file instead of printing it.
Defuddle is preferred for standard web pages because it strips navigation, ads, and clutter, producing cleaner markdown with lower token usage. WebFetch remains an option for non-standard cases.
Install Defuddle globally with npm by running npm install -g defuddle. After installation, the defuddle command becomes available in your terminal for parsing URLs.
Yes, use the -p flag followed by a property name, such as defuddle parse <url> -p title, -p description, or -p domain, to retrieve a single metadata property.
Defuddle supports markdown via --md, JSON containing both HTML and markdown via --json, and raw HTML when no flag is given. The -p flag returns a specific metadata property instead.
TeamWiseFlowConvert RSS/Atom feed URLs into markdown lists of recent entries.
lordkingExtract article content from public webpages and save Markdown notes.
zjp1997720Clip web articles into local Markdown with frontmatter and original URLs.
appautomatonConverts HTML or live web pages into structured Markdown with metadata and link inventories.