SkillHub GitHub

Skills kepano/obsidian-skills

defuddle

Use it when
the agent needs to read a web page and you'd rather it skipped the menus, ads and clutter
It does
runs the Defuddle command-line tool on a URL to pull out the page's main content
You get
the page as clean Markdown, in the chat or saved to a file, or just its title, description or domain
Needs
the defuddle CLI, installed with npm
Unlike
the other skills in its repo, which are for the Obsidian notes app, this one is only about reading web pages

TLDR

It tells the agent to prefer the Defuddle CLI over its built-in web fetch for standard web pages, because Defuddle strips navigation, ads and other clutter, which saves tokens. The agent runs defuddle parse with --md to get Markdown, can save the result to a file with -o, and can pull out a single property such as the page's title, description or domain. JSON output with both the HTML and the Markdown is also available. If the tool is missing, it installs it with npm.

Summarizes the skill at 3ccff53.

npx skills add https://github.com/kepano/obsidian-skills --skill defuddle
Installs
69,204 on skills.sh, Sep 21, 2026
Repo stars
48,653 kepano/obsidian-skills
First seen
Feb 11, 2026 on skills.sh
Weekly installs
1.1K
-67% over 8 weeks · week to Sep 21
Weekly values
Week toInstalls
Aug 33,492
Aug 103,876
Aug 173,646
Aug 244,249
Aug 312,839
Sep 71,238
Sep 14996
Sep 211,147
Category

Drive browsers, scrape pages and search the web.

Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.

Type

Operates a CLI, API, app or bundled script to get something done.

Effect

Adds no side effects of its own. It shapes how the agent thinks, writes or reviews. Guidelines and routers are always effect:none, even when the task they support edits code.

Needs

A specific command-line tool or desktop app must be installed, such as gh, agent-browser, LibreOffice, Obsidian or a vendor CLI.

Publisher

A verified publisher on its registry (skills.sh, ClawHub or Tencent SkillHub), or the company or maintainer behind the product the skill operates.

Topics
Stack

SKILL.md

From kepano/obsidian-skills at 3ccff53. Checked daily, last changed Oct 20, 2026.

Frontmatter
name: defuddle
description: Extract clean Markdown from HTML pages with Defuddle CLI.

Defuddle

Use Defuddle CLI to extract clean readable content from web pages. Prefer over WebFetch for standard web pages — it removes navigation, ads, and clutter, reducing token usage.

If not installed: npm install -g defuddle

Usage

Always use --md for markdown output:

defuddle parse <url> --md

Save to file:

defuddle parse <url> --md -o content.md

Extract specific metadata:

defuddle parse <url> -p title
defuddle parse <url> -p description
defuddle parse <url> -p domain

Output formats

Flag Format
--md Markdown (default choice)
--json JSON with both HTML and markdown
(none) HTML
-p <name> Specific metadata property