Extract clean Markdown content from web pages using Defuddle CLI.
npx skills add https://github.com/triodelab/agenci --skill defuddle-triodelab
Please help me install this Agent Skill. Skill: defuddle Source: https://github.com/triodelab/agenci/tree/main/.claude/obsidian-skills-main/skills/defuddle Command: npx skills add https://github.com/triodelab/agenci --skill defuddle-triodelab
Defuddle converts cluttered web pages into clean, readable Markdown by stripping navigation, ads, and extraneous content, helping reduce token usage when reading online documentation, articles, or blogs. It is preferred over WebFetch for standard pages and should not be used for URLs ending in .md.
Run defuddle parse <url> --md to obtain a clean Markdown version of the page.
High-intent search queries and answers about installing and using this skill.
To extract clean markdown from web pages, use the Defuddle CLI to strip navigation and ads. Run the command defuddle parse <url> --md to obtain a token-saving markdown version of the page.
Yes, you can extract web page metadata by applying the -p option to the defuddle parse command. This returns common metadata such as title, description, and domain for quick indexing and summaries.
The best way to reduce token usage when reading online articles is converting them to clean markdown. Defuddle removes clutter and extraneous content from web pages, minimizing token consumption for standard pages.
You should prefer Defuddle over WebFetch for standard web pages to minimize token consumption. Defuddle specifically strips navigation and ads to provide a cleaner markdown output for articles and online documents.
You should not use web content extraction for markdown conversion on URLs ending in .md. Defuddle is designed for standard web pages, articles, and online documents rather than existing markdown files.
Yes, the Defuddle CLI must be installed locally to extract markdown content from web pages. The workflow relies on running the defuddle parse command with the --md flag for standard web pages.
xotongExtract clean, clutter-free Markdown from web pages via Defuddle CLI.
jackspaceConvert PDFs, DOCX, PPTX, XLSX, HTML, EPUB, CSV, JSON, and images into Markdown.
caoqiubozhangchenqin2Extract clean Markdown content from URLs using fallback services.
JKHeadleyFetch clean readable web content from URLs via llms.txt and markdown fallback.
