playbooks

home / skills / bahayonghang / my-claude-code-settings / defuddle

defuddle skill

/content/skills/obsidian-skills/defuddle

This skill extracts clean markdown content from web pages using Defuddle, reducing clutter and token usage for reading and analysis.

npx playbooks add skill bahayonghang/my-claude-code-settings --skill defuddle

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
1.0 KB
---
name: defuddle
description: Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.
---

# 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-cli`

## Usage

Always use `--md` for markdown output:

```bash
defuddle parse <url> --md
```

Save to file:

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

Extract specific metadata:

```bash
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 |

Overview

This skill integrates the Defuddle CLI to extract clean, focused markdown content from standard web pages. It removes navigation, ads, and layout clutter so you get the article body and useful metadata while saving tokens. Use it whenever you need readable markdown or compact HTML/JSON for downstream analysis or summarization.

How this skill works

The skill runs Defuddle CLI commands against a provided URL and requests markdown output by default. It can save output to a file, return JSON that includes both HTML and markdown, or extract specific metadata properties like title, description, or domain. The result is minimal, readable content optimized for processing by language models.

When to use it

  • User provides a URL for an article, blog post, or documentation page.
  • You need a compact markdown version of a web page to reduce token usage.
  • Preparing content for summarization, indexing, or citation extraction.
  • When navigation, ads, or sidebar content would confuse parsing or analysis.

Best practices

  • Always request markdown output (use --md) for the cleanest, model-friendly text.
  • Save a local copy when you need repeatable access or provenance (use -o filename).
  • Extract metadata (-p title, -p description, -p domain) to help with citations and context.
  • Prefer this skill over raw web fetch for standard readable pages; use WebFetch only for nonstandard sites or APIs.
  • Validate results on complex pages—Defuddle handles most but may miss highly dynamic content.

Example use cases

  • Convert a technical blog post URL to markdown before summarizing or translating.
  • Strip navigation and ads from documentation pages for training data preparation.
  • Extract title and description metadata for automatic citation generation.
  • Save cleaned article markdown to a file for offline review or content pipelines.

FAQ

Do I need to install anything to use this skill?

Yes. Defuddle CLI must be installed (npm install -g defuddle-cli) on the host that runs the skill.

What output format should I pick?

Use --md for markdown by default. Use --json if you need both HTML and markdown or structured fields.