Extract clean markdown content from web pages using the Defuddle CLI.
npx skills add https://github.com/adrianasiam19/ATLAS --skill defuddle-adrianasiam19
Please help me install this Agent Skill. Skill: defuddle Source: https://github.com/adrianasiam19/ATLAS/tree/main/.agent/skills/defuddle Command: npx skills add https://github.com/adrianasiam19/ATLAS --skill defuddle-adrianasiam19
defuddle parse <url> --md to strip clutter and output readable markdown from any standard web page. - Metadata Retrieval: Pull specific properties like title, description, or domain with the -p flag. - Flexible Output Formats: Choose markdown, JSON, or HTML output, and save results directly to a file with -o. - Use Case: When a user shares a blog post or documentation URL to summarize, use Defuddle instead of WebFetch to get a compact, token-efficient version of the page content. ## Quick Start Use the defuddle skill to extract the article content from this URL as markdown and summarize it for me.High-intent search queries and answers about installing and using this skill.
Run `defuddle parse <url> --md` in the terminal. The Defuddle CLI removes navigation, ads, and boilerplate, returning only the readable article content as markdown. Add `-o content.md` to save the output to a file.
Use Defuddle for standard web pages like articles, blog posts, and documentation, since it strips clutter and reduces token usage. For URLs ending in .md, use WebFetch directly because the content is already markdown.
Install it globally with npm by running `npm install -g defuddle`. Node.js must be available on your system before installation.
Yes, use the `-p` flag with a property name, such as `defuddle parse <url> -p title`, `-p description`, or `-p domain`, to retrieve specific metadata fields from a page.
Defuddle supports markdown via `--md`, JSON containing both HTML and markdown via `--json`, and plain HTML when no flag is given. Markdown is the recommended default for content analysis.
TeamWiseFlowConvert RSS/Atom feed URLs into markdown lists of recent entries.
drewid74Archive websites into a searchable personal knowledge base with full-text search.
OldCoderIsMeExtract structured metadata from article URLs or content.
eddmannRender dynamic web pages with Playwright to capture HTML, text, and screenshots.