obsidian-defuddle

Extract clean Markdown content from web pages using Defuddle CLI.

Updated Sep 23, 2026

Search Tags:#markdown #cli #web scraping #obsidian #content extraction #html parsing #defuddle

One-click install

npx skills add https://github.com/ehadziabdic/WAgents --skill obsidian-defuddle-ehadziabdic

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: obsidian-defuddle
Source: https://github.com/ehadziabdic/WAgents/tree/main/opencode/skills/obsidian-defuddle
Command: npx skills add https://github.com/ehadziabdic/WAgents --skill obsidian-defuddle-ehadziabdic

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires defuddle.

What problem does it solve? Fetching web pages with standard tools returns raw HTML cluttered with navigation, ads, and boilerplate, wasting tokens and obscuring the actual content. This Skill uses the Defuddle CLI to strip that clutter and return clean, readable Markdown. ## Core Features & Use Cases - Clean Markdown Extraction: Parse any URL into readable Markdown with the `--md` flag, removing navigation, ads, and clutter. - Metadata Extraction: Pull specific properties like title, description, or domain with the `-p` flag. - Flexible Output Formats: Choose Markdown, JSON (with both HTML and markdown), or raw HTML output. - Use Case: When researching a topic, run `defuddle parse <url> --md -o content.md` to save a clean article copy for notes or further AI processing instead of pasting noisy HTML. ## Quick Start Ask the AI to extract the readable content of a given article URL as Markdown using defuddle and save it to a file.

Frequently Asked Questions about obsidian-defuddle

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert a web page to clean Markdown?▼

Run defuddle parse <url> --md to extract the readable content of a web page as Markdown. Add -o content.md to save the output directly to a file.

How to extract metadata like title or description from a URL?▼

Use the -p flag with defuddle parse, for example defuddle parse <url> -p title or -p description. Supported properties include title, description, and domain.

How do I install the Defuddle CLI?▼

Install Defuddle globally with npm by running npm install -g defuddle. After installation, the defuddle command is available in your terminal.

When should I use Defuddle instead of WebFetch?▼

Prefer Defuddle for standard web pages because it removes navigation, ads, and clutter, reducing token usage. Raw fetching may still be needed for non-standard pages or when full HTML structure is required.

What output formats does Defuddle support?▼

Defuddle supports Markdown via --md, JSON containing both HTML and markdown via --json, raw HTML with no flag, and single metadata properties via -p <name>.