evaluator

Score implementations against a Sprint Contract and produce PASS/FAIL verdicts.

1|Updated Mar 23, 2026
One-click install
npx skills add https://github.com/RaNDoM6913/claude-code-superkit --skill evaluator-random6913
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: evaluator
Source: https://github.com/RaNDoM6913/claude-code-superkit/tree/main/packages/codex/skills/evaluator
Command: npx skills add https://github.com/RaNDoM6913/claude-code-superkit --skill evaluator-random6913

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Calibrates QA by scoring implementations against a Sprint Contract and providing structured critique to guide iterative improvements.

Core Features & Use Cases

  • Read the Sprint Contract, changed files, and prior evaluation inputs to compute objective scores.
  • Apply the evaluation protocol to assess testability, execute checks, and deliver a PASS/FAIL verdict with a calibrated score.
  • Generate structured reports, including trends, remediation guidance, and actionable feedback for iteration.

Quick Start

Run the evaluator with the Sprint Contract and the list of changed files to generate a structured critique and decision report.

Frequently Asked Questions about evaluator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate code against a Sprint Contract to generate a QA score?

To evaluate code against a Sprint Contract, load the contract and audit inputs to identify criteria, then process changed files and run checks to produce a PASS/FAIL verdict with a calibrated score.

What is a Sprint Contract in code review and QA testing?

A Sprint Contract in code review defines the evaluation criteria used to score implementations, ensuring QA testing objectively measures changed files against expected project standards and remediation guidance.

How do I run an automated code critique on changed files?

Run the evaluator with your Sprint Contract and list of changed files to generate a structured critique, executing checks that deliver a decision report with actionable feedback for iteration.

Can I use previous evaluation results to calibrate QA scoring for new sprints?

Yes, you can calibrate QA scoring by providing previous evaluation inputs alongside the Sprint Contract and changed files, allowing the evaluator to compute objective scores and track remediation trends.

What's the best way to generate structured reports for code review remediation?

The best way to generate structured code review reports is to apply an evaluation protocol that assesses testability and executes checks, yielding a verdict, score, and actionable remediation guidance.

Why does my code review evaluation return a FAIL verdict despite passing local tests?

A code review evaluation returns a FAIL verdict when changed files are calibrated against the Sprint Contract criteria and fail specific testability checks, requiring iteration based on the generated remediation guidance.