judge-model-evaluator

Official

Automated code quality scoring (ICE + Code Judge)

AuthorZTE-AICloud
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Evaluating AI-generated code for quality is time-consuming and inconsistent; this skill provides a structured, automated assessment using ICE Score and Code Judge metrics to standardize feedback.

Core Features & Use Cases

  • ICE Score Evaluation: measures functional correctness and usefulness
  • Code Judge Assessment: identifies inconsistencies in code implementation
  • Reference Comparison: enhanced accuracy when reference code is provided
  • Standardized Metrics: consistent scoring from 0-4 across ICE components and a normalization to a final score
  • Flexible Integration: suitable for CI/CD pipelines, code reviews, and automated QA

Quick Start

Provide the generated code and optional reference code to receive ICE Score and Code Judge results.

Dependency Matrix

Required Modules

requestsjinja2loguru

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: judge-model-evaluator
Download link: https://github.com/ZTE-AICloud/Co-OmniSpec/archive/main.zip#judge-model-evaluator

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.