agent tool_use skill risk: low

Defuddle CLI Web Content Extractor

Instructs to use Defuddle CLI to extract clean markdown from web page URLs instead of WebFetch, including installation steps, command examples with flags, output format table, and…

External action: medium

SKILL 1 file

SKILL.md

Download

---
name: antigravity-awesome-skills-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.

## 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.

INPUTS

<url> REQUIRED: target web page URL to parse

REQUIRED CONTEXT

web page URL

OPTIONAL CONTEXT

output file path
metadata property name

ROLES & RULES

Prefer over WebFetch for standard web pages
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
prefer over WebFetch for standard web pages

SUCCESS CRITERIA

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

FAILURE MODES

Use outside the described scope for web pages
Treat output as substitute for validation or expert review

EXAMPLES

Includes several bash command examples for defuddle parse plus a table of output format flags

CAVEATS

Dependencies

Defuddle CLI (npm install -g defuddle if not installed)

Missing context

How the extracted content should be processed or returned to the user
Environment assumptions (npm availability, OS)

QUALITY

OVERALL: 0.80
CLARITY: 0.85
SPECIFICITY: 0.80
REUSABILITY: 0.75
COMPLETENESS: 0.78

IMPROVEMENT SUGGESTIONS

Add a short example showing how the markdown output is typically used downstream
Clarify what constitutes a 'standard web page' vs. edge cases that should fall back to WebFetch

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.