agent data_extraction skill risk: low

Defuddle CLI Markdown Web Extractor

Instructs to use Defuddle CLI with the --md flag to extract clean markdown from web page URLs, including installation command, usage examples for parsing and metadata, output forma…

External action: medium

SKILL 1 file

SKILL.md

Download

---
name: antigravity-awesome-skills-defuddle-966c741a
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.

## When to Use
- Use when the user provides a normal webpage URL to read, summarize, or analyze.
- Prefer it over noisy page-fetch approaches when token efficiency matters.
- Use for docs, articles, blog posts, and similar public web content.

If not installed: `npm install -g defuddle`

## 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 |

## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

REQUIRED CONTEXT

webpage URL

OPTIONAL CONTEXT

output file path
metadata property name

ROLES & RULES

Prefer it over noisy page-fetch approaches when token efficiency matters.
Always use `--md` for markdown output
Use this skill only when the task clearly matches the scope described above.
Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

EXPECTED OUTPUT

Format

markdown

Constraints

always use --md flag
remove navigation, ads, and clutter

SUCCESS CRITERIA

Use when the user provides a normal webpage URL to read, summarize, or analyze.
Use for docs, articles, blog posts, and similar public web content.

EXAMPLES

Includes multiple bash command examples for Defuddle CLI usage plus a table of output format flags.

CAVEATS

Missing context

How the extracted content should be used downstream (e.g., passed to another tool)
Error-handling instructions when Defuddle fails or returns unexpected output

Ambiguities

'normal webpage URL' and 'standard web page' are somewhat vague without explicit criteria
The prompt name contains an opaque hash that is not explained

QUALITY

OVERALL: 0.82
CLARITY: 0.82
SPECIFICITY: 0.78
REUSABILITY: 0.88
COMPLETENESS: 0.80

IMPROVEMENT SUGGESTIONS

Replace vague phrases with concrete inclusion/exclusion criteria for page types
Add a short 'Example' section showing a sample user URL and the resulting markdown snippet

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.