PurposeExtracts clean markdown from web pages via Defuddle CLI, removing clutter to save tokens. Method: run `defuddle parse <url> --md`. Value: clean readable content for analysis, lower token cost than WebFetch.

Domains

Others

Forms

Cli Manual
Required Tools
defuddle
Languages
nodejs
Package Manager
npm
Skill Composition
  • SKILL.md100.0%

Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger

When a user provides a URL of a standard web page (not ending in .md) to read or analyze, such as docs, articles, or blog posts.

Mechanism

  • Run defuddle parse <url> --md via CLI to strip navigation/ads and output clean markdown
  • Support saving to file with -o and extracting metadata via -p
  • Installs globally via npm install -g defuddle if missing

Result

Clean markdown content with reduced tokens, ready for analysis or storage, instead of noisy WebFetch output.