multi-llm-review

Review code concurrently with multiple AI models and MCP tools.

10|Updated Mar 31, 2026

Search Tags:#code review #security audit #AI models #bug detection #parallel review

Ready to run

npx skills add https://github.com/verivus-oss/llm-cli-gateway --skill multi-llm-review-verivus-oss

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: multi-llm-review
Source: https://github.com/verivus-oss/llm-cli-gateway/tree/main/.agents/skills/multi-llm-review
Command: npx skills add https://github.com/verivus-oss/llm-cli-gateway --skill multi-llm-review-verivus-oss

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill solves the problem of comprehensive code review by leveraging multiple AI models simultaneously, providing a diverse set of perspectives and expertise to ensure quality, security, and correctness in code changes.

Core Features & Use Cases

Parallel Reviews: Conducts code reviews in parallel using Claude, Codex, Gemini, Grok, and Mistral Vibe.
Quality Analysis: Identifies architecture, design, quality, and documentation gaps.
Bug Finding: Detects logic bugs, off-by-one errors, and missing error handling.
Security Audit: Identifies security issues such as injection, auth bypasses, and data leaks.
Use Case: For a critical code change, use this Skill to get multiple perspectives on the changes before merging.

Quick Start

Use the multi-llm-review skill to review the changes in the 'feature-branch' with the 'pull-request-123'.

Frequently Asked Questions about multi-llm-review

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

FAQPage Schema

How do I run a parallel code review using multiple AI models?▼

To run a parallel code review, you can use this skill to concurrently analyze code changes across Claude, Codex, Gemini, Grok, and Mistral Vibe models to enhance quality, security, and correctness.

Can I perform a security audit and bug detection at the same time?▼

Yes, you can perform a security audit and bug detection simultaneously, as the parallel review identifies injection risks, auth bypasses, logic bugs, and missing error handling across multiple AI models.

Does this parallel AI review work with my existing MCP tools?▼

Yes, the parallel AI review uses MCP tools for execution and verification, requiring access to Claude, Codex, Gemini, Grok, and Mistral Vibe models to function properly.

What is the best way to review critical code changes before merging?▼

The best way to review critical code changes is leveraging multiple AI models simultaneously, which provides diverse perspectives on architecture, design, security, and correctness before merging.

Do I need access to all five AI models to run a concurrent code review?▼

Yes, running a concurrent code review requires access to Claude, Codex, Gemini, Grok, and Mistral Vibe models to provide the diverse set of perspectives needed for comprehensive analysis.

Why use multiple AI models for code review instead of a single model?▼

Using multiple AI models for code review solves the problem of limited perspective by leveraging diverse expertise concurrently, ensuring higher quality, security, and correctness in code changes.