Extract clean Markdown from web pages using the Defuddle CLI.
npx skills add https://github.com/xfs96192/claude-config --skill defuddle-xfs96192
Please help me install this Agent Skill. Skill: defuddle Source: https://github.com/xfs96192/claude-config/tree/main/skills/defuddle Command: npx skills add https://github.com/xfs96192/claude-config --skill defuddle-xfs96192
Defuddle helps you extract clean, readable Markdown from web pages by stripping navigation, ads, and other clutter, reducing token usage when reading or analyzing online content.
Parse a web page URL and return the clean Markdown content with navigation removed.
High-intent search queries and answers about installing and using this skill.
You can extract clean Markdown from a web page by using the Defuddle CLI to parse the URL, which strips away navigation and ads to reduce token usage for reading and analyzing online content.
Extracting clean Markdown from web pages with heavy navigation is the best way to reduce token usage and improve readability, preferring this approach over standard web fetching for cluttered documentation and articles.
Yes, you can extract specific metadata like title, description, and domain from a URL using the Defuddle CLI, which offers targeted metadata extraction capabilities alongside its default Markdown output.
Yes, the webpage extractor supports outputting HTML or JSON as alternative formats, allowing you to parse URLs and retrieve web content in the format that best suits your analysis workflow.
Markdown content extraction is suitable for standard web pages including documentation, articles, and blogs, where concise content is needed and removing clutter helps reduce token usage during analysis.
Yes, you need the Defuddle CLI installed to parse URLs and output Markdown by default, as it serves as the core engine for removing clutter and extracting readable content from web pages.
berrzebbSummarize or extract text from URLs, files, YouTube videos, and podcasts via CLI.
swarm-ai-researchGenerate and validate an Atom feed from Markdown articles.
appautomatonConverts HTML or live web pages into structured Markdown with metadata and link inventories.
woosulExtract clean markdown content and metadata from web pages using Defuddle CLI.
