Extract clean markdown from web pages using the Defuddle CLI.
npx skills add https://github.com/Nero-kk/claude-agent-skills --skill defuddle-nero-kk
Please help me install this Agent Skill. Skill: defuddle Source: https://github.com/Nero-kk/claude-agent-skills/tree/main/claude-skills/defuddle Command: npx skills add https://github.com/Nero-kk/claude-agent-skills --skill defuddle-nero-kk
Defuddle removes site navigation, ads, and clutter from standard web pages so you get concise, readable markdown suitable for analysis, summarization, or archival without wasting tokens on irrelevant content.
Ask the skill to parse the target article URL and return the page as markdown using defuddle's markdown output mode.
High-intent search queries and answers about installing and using this skill.
Extract clean markdown from web pages by providing a URL to parse cluttered HTML into concise text. This removes site navigation and ads, returning readable markdown suitable for analysis, summarization, or archival without wasting tokens on irrelevant content.
Yes, web scraping can extract specific metadata fields such as title, description, and domain. It optionally outputs JSON for richer downstream processing, allowing structured content ingestion into knowledge bases or content pipelines.
Yes, extracting clean markdown from online documentation requires the Defuddle CLI installed. You use its markdown output mode to parse target URLs and receive readable text, provided the URL does not already end with .md.
Removing ads and navigation from blog posts is best handled by parsing the URL to strip cluttered HTML. This produces concise, readable markdown optimized for token efficiency, making it ideal for ingesting web content into LLM prompts.
No, content extraction does not apply to URLs that already end with .md. It is designed specifically to parse standard online articles, documentation pages, and blogs with cluttered HTML and convert them into clean markdown.
prince3626ezechiel-langExtract clean markdown content from web pages via Defuddle CLI.
Mathews-TomConvert files and URLs to Markdown using MarkItDown with OCR and transcription.
CodingHeaderExtract web page content into markdown, JSON, or text outputs.
otrebuBatch-convert JavaScript-rendered web pages to a timestamped Markdown file.
