cross-model-peer-review

Official

Get a robust second opinion on model outputs.

Authorm2ai-portfolio
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Cross-model peer review solves the problem of unreliable self-assessment by using a second model to validate outputs.

Core Features & Use Cases

  • Structured rubric (4-6 dimensions) for evaluating outputs (factual accuracy, logical coherence, completeness, calibration, internal consistency).
  • Phase-driven workflow: define target, build rubric, construct reviewer prompt, run review, delta analysis, and reporting.
  • Use case: validate a complex analysis produced by Model A by having Model B critically review it before deployment.

Quick Start

Run a cross-model peer review on the latest output using the defined rubric to generate an evaluation report.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: cross-model-peer-review
Download link: https://github.com/m2ai-portfolio/m2ai-skills-pack/archive/main.zip#cross-model-peer-review

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 510,000+ vetted skills library on demand.