Can I call the judge skill directly?

No, the judge skill is designed to be invoked automatically by the cookoff or omakase-off processes during the evaluation phase.

What are the five scoring criteria?

The criteria are Fitness for Purpose, Justified Complexity, Readability, Robustness & Scale, and Maintainability.

How does the 'Fitness Gate' work?

If there is a score difference of 2 or more in the Fitness category between implementations, the one with the higher fitness wins immediately.

What is the difference between a Cookoff and an Omakase evaluation?

A Cookoff compares different implementations of the same design, while an Omakase evaluation compares entirely different approaches or designs.

What happens if an implementation gets a score of 1 in any category?

Any criterion scoring a 1 triggers a 'Critical Flaw' gate, which automatically eliminates that implementation from the selection process.

Code Implementation Judge

Name: Code Implementation Judge
Author: 2389-research

by2389-research

•

Seguridad y Pruebas

Evaluates and scores multiple code implementations using a standardized five-criteria framework to identify optimal software solutions.

Acerca de

The Judge skill provides a rigorous, objective methodology for comparing different code implementations or architectural approaches within Claude Code. By systematically assessing fitness for purpose, complexity, readability, robustness, and maintainability, it eliminates subjective bias and ensures that chosen solutions meet high production standards. This skill is essential for 'cookoffs' and 'omakase' workflows where multiple variants of a solution must be weighed against each other using hard gates and feasibility checks.

Características Principales

Automated 'Hard Gate' checks to disqualify flawed implementations
Structured winner selection with transparent rationale and trade-offs
Standardized 5-criteria scoring framework for objective evaluation
Deep feasibility analysis covering O(n) complexity and memory usage
8 GitHub stars
Side-by-side scorecard generation for rapid implementation comparison

Casos de Uso

Evaluating different architectural designs for scalability and robustness
Standardizing code review criteria for AI-generated implementation variants
Comparing multiple coding patterns to solve the same functional requirement

Acerca de

Características Principales

Automated 'Hard Gate' checks to disqualify flawed implementations
Structured winner selection with transparent rationale and trade-offs
Standardized 5-criteria scoring framework for objective evaluation
Deep feasibility analysis covering O(n) complexity and memory usage
8 GitHub stars
Side-by-side scorecard generation for rapid implementation comparison

Casos de Uso

Evaluating different architectural designs for scalability and robustness
Standardizing code review criteria for AI-generated implementation variants
Comparing multiple coding patterns to solve the same functional requirement