Extracts clean markdown content from web pages via URL.
npx skills add https://github.com/kirakuiin/note --skill defuddle-kirakuiin
Please help me install this Agent Skill. Skill: defuddle Source: https://github.com/kirakuiin/note/tree/main/Obsidian%20Vault/9-Meta/Skills/defuddle Command: npx skills add https://github.com/kirakuiin/note --skill defuddle-kirakuiin
Extracts clean markdown content from web pages, removing navigation, ads, and clutter to save time and tokens when reading or analyzing online content.
Run defuddle parse <url> --md to extract a clean markdown version of the page.
High-intent search queries and answers about installing and using this skill.
To extract clean markdown from a web page, run the defuddle parse command with your target URL and the --md flag. This strips navigation and ads, outputting readable markdown text for quick reading or knowledge capture.
Yes, you can extract web page metadata alongside markdown content by passing the -p flag. This provides optional metadata output while converting standard articles and documentation into clean markdown format.
Markdown is the default output format for extracted web content, but HTML and JSON are also supported as alternative formats. Use the --md flag to explicitly request markdown output for articles and blogs.
Yes, defuddle must be installed locally before you can parse web pages. Once installed, you can run defuddle parse <url> --md to extract clean markdown from documentation, tutorials, and articles.
Extracting web pages to markdown removes navigation, ads, and clutter, saving time and tokens when reading or analyzing online content. This produces clean text ideal for drafting notes or feeding into knowledge bases.
Defuddle applies to standard articles, documentation, and blogs accessible via URL. It is optimized for extracting clean markdown from these standard web pages rather than complex web applications.
dotBeepsExtract clean markdown content from web pages using the Defuddle CLI.
amychina12Standardize raw academic paper data into analysis-ready datasets with Python codebooks.
zzafergokConvert Markdown documents to HTML using marked.js, pandoc, gomarkdown, or static site generators.
tusososExtract clean article text from URLs and save it as plain text.
