Skill Evaluator

About

Provides a systematic framework for auditing Claude Code skills, ensuring they meet professional standards and official Anthropic guidelines. By analyzing eight critical dimensions—ranging from size and structure to anti-pattern detection and prompt engineering quality—it generates detailed reports with prioritized, actionable suggestions. This tool is essential for developers who want to refine their custom capabilities, maintain consistency across a plugin library, and optimize skill performance for maximum AI reliability.

Key Features

• Multi-dimensional analysis across size, scope, and structure
• Detection of common anti-patterns and prompt engineering flaws
• 0 GitHub stars
• Evaluation of example quality and realistic pattern demonstration
• Generation of comprehensive reports with prioritized improvements
• Compliance checking against official Anthropic best practices

Use Cases

• Auditing custom Claude Code skills before publication or internal distribution
• Refining prompt engineering quality for more reliable skill execution
• Standardizing skill structure and documentation across a development team