Index of every page on this site: llms.txt
All skills
Run it yourself

Extract clean Markdown from HTML pages with Defuddle CLI.

Use this Skill: https://skilld.dev/gh/obsidianmd/obsidian-skills/defuddle

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈17 tokens for metadata: the name and description. ≈217 when used: this file.

How this Skill uses context

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈68 characters, or 0.9%.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Defuddle

Use Defuddle CLI when the user wants clean Markdown extracted from a web page. It removes navigation, ads, and other page clutter.

Check availability with defuddle --help. If it is missing, explain the dependency and offer installation with npm install -g defuddle. Do not claim extraction succeeded if the tool is unavailable or returns an error.

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

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning7d3 checks · Risk SAFE
  • Gen Agent Trust Hub8d

    This skill uses the Defuddle CLI to extract Markdown content from web pages. It is generally safe but carries a low-risk surface for indirect prompt injection since it processes content from external URLs.

  • Socket7d

    No alerts

  • Snyk8d

    Risk: MEDIUM · 1 issue

Signed by skilld at b110b2f. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 12 hours ago.

Activeupdated 2 weeks ago

README badge

README badge for obsidianmd/obsidian-skills/defuddle

Extracts clean markdown from web pages using Defuddle CLI, removing navigation and ads to reduce token usage. Use this skill instead of WebFetch when analyzing URLs to articles, documentation, or blog posts — not for .md files, which WebFetch handles directly.

Generated from the current SKILL.md.

When should I use Defuddle instead of WebFetch?
Use Defuddle for standard web pages, online documentation, articles, and blog posts where you want to remove navigation, ads, and clutter. Use WebFetch only for URLs ending in .md, which are already markdown.
What output format should I use?
Always use the `--md` flag to get markdown output, which is the primary use case for this skill.
Does Defuddle reduce token usage compared to fetching raw HTML?
Yes. By removing navigation, ads, and other clutter, Defuddle produces cleaner markdown output that uses fewer tokens than fetching the full HTML page.
Can I extract specific metadata like title or domain?
Yes. Use the `-p` flag with property names like `title`, `description`, or `domain` to extract specific metadata from a page.

Generated from the current SKILL.md. These answers refresh after source changes.