rate

Compute a probabilistic codebase rating using parallel raters and adversaries.

Updated Feb 1, 2026
One-click install
npx skills add https://github.com/HECStore/cj-store --skill rate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rate
Source: https://github.com/HECStore/cj-store/tree/main/.claude/skills/rate
Command: npx skills add https://github.com/HECStore/cj-store --skill rate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a structured, probabilistic assessment of a codebase or project by orchestrating multiple raters and adversaries to produce a final rating, helping teams gauge quality quickly.

Core Features & Use Cases

  • Parallel multi-agent evaluation: spawns N raters to sample diverse aspects of the repository and produce individual ratings.
  • Adversarial refinement: for each rater, K subagents generate adjusted reports that challenge the original assessment.
  • Improve mode: optional flag that collects actionable improvements from subagents and includes them in the final synthesis.
  • Final synthesis: aggregates surviving ratings into a single mean rating and provides a concise synthesis of strengths and gaps.

Quick Start

Invoke /rate in chat to obtain a probabilistic rating for your codebase.

Frequently Asked Questions about rate

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

FAQPage Schema
How do I get a probabilistic quality rating for my codebase?

To get an AI codebase review, invoke the /rate command in chat. The system uses parallel raters and adversaries to sample repository aspects and compute a final probabilistic quality rating.

How does adversarial AI review work for project quality assessments?

Adversarial AI review works by spawning K subagents per rater to generate adjusted reports that challenge original assessments. Surviving ratings aggregate into a final mean rating with a concise synthesis of strengths and gaps.

Can I get actionable improvements during a codebase assessment?

Yes, you can get actionable improvements during a codebase assessment by using the optional improve flag. This mode collects suggested improvements from subagents and includes them directly in the final synthesis.

Does this multi-rater codebase rating support different programming languages?

Yes, the multi-rater codebase rating supports different programming languages and tooling. It applies to project reviews and repo quality judgments across diverse languages by sampling repository aspects.

What is the best way to evaluate repository quality for a project review?

The best way to evaluate repository quality is using a probabilistic rating system with N raters and K adversaries per rater. This approach challenges initial assessments to produce a synthesized mean rating.