Skip to content
Back to skills

748 Quality Bar 6e74e4d9

ASecurity

To transform **Antigravity Awesome Skills** from a collection of scripts into a trusted platform, every skill must meet a specific standard of quality and safety.

  • 9 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 11, 2026
toolsrustgobashreacttestinggit

Security analysis

A100/100

Scanned October 11, 2026

npx -y skills add tools-only/X-Skills --skill 748-quality_bar_6e74e4d9 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of 748 Quality Bar 6e74e4d9?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for 748 Quality Bar 6e74e4d9
[![Security: A β€” Skills Directory](https://www.skillsdirectory.com/api/skills/tools-only-748-quality-bar-6e74e4d9/badge)](https://www.skillsdirectory.com/skills/tools-only-748-quality-bar-6e74e4d9)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

SKILL.md
# πŸ† Quality Bar & Validation Standards

To transform **Antigravity Awesome Skills** from a collection of scripts into a trusted platform, every skill must meet a specific standard of quality and safety.

## The "Validated" Badge βœ…

A skill earns the "Validated" badge only if it passes these **5 automated checks**:

### 1. Metadata Integrity

The `SKILL.md` frontmatter must be valid YAML and contain:

- `name`: Kebab-case, matches folder name.
- `description`: Under 200 chars, clear value prop.
- `risk`: One of `[none, safe, critical, offensive]`.
- `source`: URL to original source (or "self" if original).

### 2. Clear Triggers ("When to use")

The skill MUST have a section explicitly stating when to trigger it.

- **Good**: "Use when the user asks to debug a React component."
- **Bad**: "This skill helps you with code."
Accepted headings: `## When to Use`, `## Use this skill when`, `## When to Use This Skill`.

### 3. Safety & Risk Classification

Every skill must declare its risk level:

- 🟒 **none**: Pure text/reasoning (e.g., Brainstorming).
- πŸ”΅ **safe**: Reads files, runs safe commands (e.g., Linter).
- 🟠 **critical**: Modifies state, deletes files, pushes to prod (e.g., Git Push).
- πŸ”΄ **offensive**: Pentesting/Red Team tools. **MUST** have "Authorized Use Only" warning.

### 4. Copy-Pasteable Examples

At least one code block or interaction example that a user (or agent) can immediately use.

### 5. Explicit Limitations

A list of known edge cases or things the skill _cannot_ do.

- _Example_: "Does not work on Windows without WSL."

---

## Support Levels

We also categorize skills by who maintains them:

| Level         | Badge | Meaning                                             |
| :------------ | :---- | :-------------------------------------------------- |
| **Official**  | 🟣    | Maintained by the core team. High reliability.      |
| **Community** | βšͺ    | Contributed by the ecosystem. Best effort support.  |
| **Verified**  | ✨    | Community skill that has passed deep manual review. |

---

## How to Validate Your Skill

The canonical validator is `scripts/validate_skills.py`. Run `npm run validate` (or `npm run validate:strict`) before submitting a PR:

```bash
npm run validate       # soft mode (warnings only)
npm run validate:strict  # strict mode (CI uses this)
```

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.