skills.rest
evolution-foundation
evolution-foundationOFFICIAL
Explore all skills by this author →
WebsiteGitHub

obs-defuddle

Extract clean markdown content and metadata from web pages using Defuddle CLI.

520|175|Updated Apr 8, 2026
Search Tags:#documentation#token optimization#content summarization#defuddle#markdown extraction#web page parsing
One-click install
npx skills add https://github.com/evolution-foundation/evo-nexus --skill obs-defuddle-evolution-foundation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: obs-defuddle
Source: https://github.com/evolution-foundation/evo-nexus/tree/main/.claude/skills/obs-defuddle
Command: npx skills add https://github.com/evolution-foundation/evo-nexus --skill obs-defuddle-evolution-foundation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Web pages often include navigation, ads, and boilerplate that waste context window space and make it harder for an AI to find the information you actually care about.

Core Features & Use Cases

  • Clean markdown extraction: Converts a page into readable markdown by removing clutter such as menus and irrelevant layout content.
  • Token-efficient context: Produces a tighter text representation suitable for analysis, summarization, and Q&A.
  • Metadata targeting: Extracts specific fields like title, description, or domain when you only need that information.
  • Use case: When you share an online article or documentation URL, use this skill to extract the main content so your agent can summarize it without ingesting navigation and sidebar noise.

Quick Start

Use the obs-defuddle skill to extract clean markdown from a documentation or article URL.

Frequently Asked Questions about obs-defuddle

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

FAQPage Schema
How do I extract clean markdown from a web page for AI analysis?▼

You can extract clean markdown from a web page by removing navigation, ads, and boilerplate. This produces a smaller, token-saving text representation suitable for AI context analysis and summarization.

How do I remove ads and navigation clutter from article URLs before summarization?▼

To remove ads and navigation clutter from article URLs, parse the page to extract only the main content. This discards sidebar noise and layout elements, yielding a tighter text representation for token-efficient AI ingestion.

Can I extract only the title and description metadata from a web page?▼

Yes, you can extract targeted metadata fields like title, description, and domain from a web page. This allows you to retrieve only the specific information you need without parsing the entire page content.

Does this web page parsing tool work with markdown file URLs?▼

No, this web page parsing tool does not work with markdown file URLs. It is designed to extract content from standard web pages, online documentation, articles, and blog posts while avoiding direct markdown file links.

Why does my AI context window fill up when reading online documentation?▼

Your AI context window fills up because online documentation includes navigation, ads, and boilerplate. Extracting the clean markdown content removes this clutter, saving tokens and making it easier for the AI to find relevant information.

Related Skills

Explore More Content & Communication Skills→
zephyrwang6zephyrwang6
333

web-scraper

Fetch web page content and convert HTML to clean Markdown.

Community
Intermediate
officechbusinessservices-creatorofficechbusinessservices-creator

defuddle

Convert noisy web pages into clean Markdown content via Defuddle CLI.

Community
Intermediate
Syedyasir001Syedyasir001

defuddle

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

Community
Basic
zakarooozakarooo

web-reader

Extract web page content and metadata via the page_reader function.

Community
Intermediate