skills.rest
aokazaki-olp
aokazaki-olpCOMMUNITY
Explore all skills by this author →
GitHub

defuddle

Extract clean markdown content from web pages using the Defuddle CLI.

Updated May 17, 2026
Search Tags:#markdown#cli#web scraping#content extraction#web pages#html parsing#defuddle
One-click install
npx skills add https://github.com/aokazaki-olp/electron-prototype --skill defuddle-aokazaki-olp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: defuddle
Source: https://github.com/aokazaki-olp/electron-prototype/tree/main/.agents/skills/defuddle
Command: npx skills add https://github.com/aokazaki-olp/electron-prototype --skill defuddle-aokazaki-olp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires defuddle.

What problem does it solve? Fetching web pages with standard tools returns raw HTML full of navigation, ads, and clutter, wasting tokens and making content hard to read. This Skill uses the Defuddle CLI to strip away the noise and return clean markdown from any standard web page. ## Core Features & Use Cases - Clean Markdown Extraction: Parse any URL into readable markdown with the --md flag, removing navigation and ads. - Metadata Retrieval: 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 a user shares a blog post or documentation URL to analyze, run defuddle parse <url> --md instead of WebFetch to get token-efficient, clutter-free content. ## Quick Start Ask the AI to extract the content of a given URL as clean markdown using defuddle, for example: "Use defuddle to read this article and summarize it."

Frequently Asked Questions about defuddle

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

FAQPage Schema
How do I extract markdown from a web page with defuddle?▼

Run `defuddle parse <url> --md` to get clean markdown output. To save the result directly to a file, add the output flag: `defuddle parse <url> --md -o content.md`.

When should I use defuddle instead of WebFetch?▼

Use defuddle for standard web pages like articles, blog posts, and documentation, since it removes navigation and ads to reduce token usage. For URLs ending in .md, use WebFetch directly because the content is already markdown.

How do I install the defuddle CLI?▼

Install defuddle globally via npm with `npm install -g defuddle`. Once installed, the `defuddle parse` command is available from any terminal session.

Can defuddle extract only the title or description of a page?▼

Yes, use the `-p` flag to extract a specific metadata property, such as `defuddle parse <url> -p title`, `-p description`, or `-p domain`, without fetching the full page content.

What output formats does defuddle support?▼

Defuddle supports markdown via `--md`, JSON containing both HTML and markdown via `--json`, and raw HTML when no flag is given. Markdown is the recommended default for readability and token efficiency.

Related Skills

Explore More Software Engineering Skills→
TeamWiseFlowTeamWiseFlow
8.4k

rss-reader

Convert RSS/Atom feed URLs into markdown lists of recent entries.

Official
Intermediate
lc0rplc0rp

qmd

Search local Markdown notes using BM25 keyword indexing.

Community
Intermediate
Arbab1308Arbab1308

geo-fundamentals

Audit public content for structured data, authorship, and freshness.

Community
Intermediate
vm0-aivm0-ai
76

browserless

Execute Puppeteer and Playwright scripts in the cloud via REST endpoints.

Official
Intermediate