Which AI models are used in the review process?

The orchestrator coordinates Claude Code for architecture, Codex for logic, Gemini for performance, and Factory.ai Droid for security and maintainability.

Does it support iterative improvements?

Yes, the skill runs multiple cycles, applying fixes and re-reviewing the code until the improvement delta falls below a specific threshold or a max iteration limit is reached.

How does the skill handle conflicting AI suggestions?

A master orchestrator agent uses a priority scoring algorithm that weighs agreement levels, severity, and implementation complexity to resolve contradictions.

What are the prerequisites for using this skill?

You need API keys for the respective AI services and the corresponding CLI tools (Codex, Gemini, Droid) configured within your environment.

Can this skill automatically fix my code?

Yes, high-consensus changes (agreed upon by 3 or more AI models) can be automatically applied, while lower-confidence issues are flagged for manual review.

Multi-AI Code Review Orchestrator

Name: Multi-AI Code Review Orchestrator
Author: dev-jelly

bydev-jelly

협업 도구

Orchestrates multiple AI models to perform comprehensive, cross-validated code reviews with automated improvement cycles.

소개

This skill transforms Claude into a master orchestrator that coordinates multiple AI engines—including Claude Code, Codex, Gemini, and Factory.ai Droid—to analyze code from diverse perspectives such as architecture, logic, performance, and security. It goes beyond simple analysis by aggregating multi-model feedback, resolving conflicting suggestions through a priority scoring system, and iteratively applying improvements until the code meets high-quality benchmarks, ensuring production-ready results with minimal manual intervention.

주요 기능

Comprehensive multi-perspective quality and audit reports
Multi-model orchestration using Claude, Codex, Gemini, and Droid
Iterative improvement cycles with automated validation
Intelligent conflict detection and automated resolution logic
Priority-based scoring for severity and consensus ranking
0 GitHub stars

사용 사례

Automating the identification and resolution of complex logic bugs and performance bottlenecks
Performing deep architectural and security audits on critical modules before production
Executing pre-commit reviews to ensure high-consensus quality standards across the team

소개

주요 기능

Comprehensive multi-perspective quality and audit reports
Multi-model orchestration using Claude, Codex, Gemini, and Droid
Iterative improvement cycles with automated validation
Intelligent conflict detection and automated resolution logic
Priority-based scoring for severity and consensus ranking
0 GitHub stars

사용 사례

Automating the identification and resolution of complex logic bugs and performance bottlenecks
Performing deep architectural and security audits on critical modules before production
Executing pre-commit reviews to ensure high-consensus quality standards across the team