This skill provides a comprehensive quality assurance framework designed to eliminate bias and prevent test gaming by establishing a rigorous, independent verification pattern. It validates code across five distinct layers: rules-based linting, functional test execution, visual UI validation, system-level integration, and final quality scoring using an LLM-as-judge pattern. With a mandatory score threshold of 90/100, it ensures that code is not just functional, but also secure, maintainable, and fully ready for production deployment.
Características Principales
015-Layer Verification Pyramid ranging from automated rules to quality scoring
02Independent verification pattern to prevent implementation bias
030 GitHub stars
04Integrated security scanning (SAST) and accessibility validation
05Objective 0-100 scoring with a strict 90+ production threshold
06LLM-as-judge and Agent-as-a-Judge evaluation patterns
