Skill Evaluator
Evaluates the quality of agent skills using a comprehensive, rubric-based assessment.
The source repository doesn't declare a license. Check its terms before reusing the code.
Key features
- Comprehensive rubric-based evaluation across four dimensions: Clarity, Completeness, Examples, and Focus.
- Quantitative scoring system with defined quality thresholds (e.g., Excellent, Strong, Adequate).
- Generates a standardized evaluation report with scores, detailed observations, and analysis.
- Produces prioritized, actionable recommendations to guide skill improvement.
- Includes best practices and checklists to ensure objective and thorough assessments.
Use cases
- Evaluate a new skill's quality and readiness before deployment.
- Assess an existing skill's effectiveness to identify improvement opportunities.
- Ensure skills adhere to team-wide quality standards and best practices.
FAQ
What is the primary function of the Skill Evaluator?
The Skill Evaluator provides a structured, rubric-based framework to assess the quality of other Claude Code Skills. It generates a quantitative score and a detailed report with actionable recommendations for improvement.
When should I use this skill?
Use this skill when you need to objectively evaluate a new skill before deployment, assess an existing skill's effectiveness, identify specific improvement opportunities, or ensure your skills meet consistent quality standards.
What core capabilities does the Skill Evaluator provide?
It offers a comprehensive evaluation across four dimensions (Clarity, Completeness, Examples, Focus), a quantitative scoring system with quality thresholds, standardized report generation, and prioritized, actionable recommendations to guide improvements.
How does this skill improve my development workflow?
It standardizes the quality assurance process for skills. By providing a consistent rubric and actionable feedback, it helps you and your team build higher-quality, more reliable, and more effective AI agent capabilities faster.
Related skills
OpenCode Skill Tester
Verifies and validates the full suite of OpenCode Agent Skills plugin tools, scripts, and file access APIs.
Security Testing27012 ptsSkill Evaluator
Evaluates agent skills against Anthropic's official best practices to ensure optimal structure, naming, and content organization.
Security Testing6812 ptsTest Skill
Validates the execution of PostToolUse hooks to ensure proper skill invocation and system integration.
Security Testing312 pts