Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Skill Validator

ASecurity

Use for 100-point QA validation of all skills + auto-fix + report.

5 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agentspythongobashgit

Works with

cli

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add openamer/openamer --skill skill-validator --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Skill Validator?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Skill Validator
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/openamer-skill-validator/badge)](https://www.skillsdirectory.com/skills/openamer-skill-validator)

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

Download with Pro
Files
SKILL.md
---
name: skill-validator
description: 'Use for 100-point QA validation of all skills + auto-fix + report.'
version: 1.0.0
author: OpenAmer Agent
license: MIT
tags:
  - validation
  - quality
  - skills
  - qa
  - report
  - auto-fix
platforms: [linux, macos, windows]
metadata:
  openamer:
    tags: [validation, quality, skills, QA, report, auto-fix, cron]
    related_skills: [auto-env-checker, smart-cron-scheduler]
---

# Skill Validator

Automatisierte 100-Punkte-Qualitätsprüfung für alle OpenAmer Skills.
Validiert Frontmatter, Description-Qualität, Body-Struktur, Cross-Refs und CLI-Commands.

## Overview

Der Skill Validator prüft alle 659 SKILL.md Dateien gegen 5 Kategorien:

| Kategorie | Punkte | Beschreibung |
|-----------|--------|--------------|
| Frontmatter | 30 | name, description, version, tags, platforms, metadata.openamer |
| Description | 15 | ≤57 Zeichen, Trigger-Wort, sinnvolle Länge |
| Body-Struktur | 25 | Sections (Overview, Usage, etc.), Code-Blöcke, Tabellen |
| Cross-Refs | 15 | related_skills existieren, Selbstverweise, keine broken Links |
| Commands/CLI | 15 | openamer-Befehle, bash-Blöcke, Exit-Codes, Setup-Befehle |

## When to Use

- **Täglich**: `--all --json` für kontinuierliche Qualitätsüberwachung
- **Nach Skill-Importen**: `--all --fix` um neue Skills automatisch zu korrigieren
- **Vor Releases**: `--all --html` für visuellen Qualitätsbericht
- **Bei Problemen**: `--skill <name>` für gezielte Einzelprüfung
- **Fokus**: `--best` (Top 10) oder `--worst` (Bottom 10) für schnelle Übersicht

## Installation

Das Skript liegt unter `scripts/skill-validator.py` und wird direkt ausgeführt:

```bash
# Prüfen ob vorhanden
python scripts/skill-validator.py --version 2>/dev/null || echo "Script bereit"
```

Keine zusätzlichen Dependencies erforderlich (nur Python 3.10+ Standardbibliothek).

## Usage

### Alle Skills prüfen

```bash
python scripts/skill-validator.py --all
```

### Einzelnen Skill prüfen

```bash
python scripts/skill-validator.py --skill github-pr-workflow --verbose
```

### Auto-Fix

```bash
python scripts/skill-validator.py --all --fix
```
Korrigiert automatisch:
- Fehlendes Frontmatter → minimales Frontmatter hinzufügen
- Fehlende `metadata.openamer` → leeren Block hinzufügen
- Fehlende `platforms` → `[linux, macos, windows]`
- Fehlende `version` → `1.0.0`

### JSON-Report

```bash
python scripts/skill-validator.py --all --json --output logs/skill-validator-report.json
```

### HTML-Report

```bash
python scripts/skill-validator.py --all --html --output logs/skill-validator-report.html
```

Generiert ein interaktives Dashboard mit:
- Notenverteilung (A+ bis F)
- Kategorien-Balkendiagramme
- Beste/Schlechteste Skills
- Top-Probleme
- Vollständige Liste aller Skills mit Einzelscores

### Best/Worst

```bash
# Top 10 beste Skills
python scripts/skill-validator.py --best

# Top 10 schlechteste (mit Problemen)
python scripts/skill-validator.py --worst --verbose
```

## Verification

Nach der Installation prüfen:

```bash
# Kurztest mit Einzel-Skill
python scripts/skill-validator.py --skill auto-env-checker
# Erwartet: Score zwischen 30-70, gültiges Frontmatter

# JSON-Ausgabe testen
python scripts/skill-validator.py --skill plan --json | python3 -c "import sys,json; d=json.load(sys.stdin); print(f'OK: Score={d[\"skill_results\"][0][\"score\"]}')"

# HTML-Report testen
python scripts/skill-validator.py --skill plan --html --output /tmp/test-report.html
# Erwartet: report.html existiert und ist > 10KB
```

## Troubleshooting

| Problem | Ursache | Lösung |
|---------|---------|--------|
| "Kein gültiges YAML-Frontmatter" | SKILL.md hat kein --- Block | `--fix` verwenden oder manuell hinzufügen |
| Alle Skills zeigen 0 Punkte | Frontmatter-Parser Problem | Pfad zu skills/ prüfen |
| HTML-Report leer | Fehler in der HTML-Generierung | `--json` stattdessen nutzen |
| Exit-Code 127 | 127+ Skills mit Note F | Normal bei vielen importierten Skills; keine Sorge |
| Langsame Ausführung (659 Skills) | Erwartet, ~60-90 Sekunden | Mit `--json --output` für schnelle Speicherung |

## Pitfalls

- **Frontmatter wichtig**: Ohne gültiges Frontmatter gibt es 0 Punkte — immer `--fix` nach Import neuer Skills
- **metadata.openamer**: Wird nur erkannt wenn korrekt eingerückt (2 Spaces pro Level)
- **Große Reports**: Der JSON-Report aller Skills ist ~12 MB — HTML-Dashboard ist besser lesbar
- **False Positives**: Importierte NVIDIA Skills haben oft fehlende Sections (erwartet)
- **Exit-Code**: Wird auf 127 gecappt da OS-Limit für Exit-Codes

Attribution

openameropenamer
View sourceSee grades on GitHubMore from openamer →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →