Multi Model Review Router

What it does

The Multi-Model Review Router is a sophisticated orchestration layer that enables your AI agent to delegate specialized tasks to external models and tools. It acts as a safety-first "dispatcher" for high-stakes scenarios such as adversarial code reviews, multi-model consensus, and long-context repository analysis.

Why use this skill

Prompting an AI yourself often leads to "hallucination loops" where the agent validates its own mistakes. This skill breaks that cycle by enforcing independent verification. It provides a structured framework for:

• Adversarial Validation: Explicitly seeking flaws in a proposed plan or code change.
• Rescue Operations: Automatically triggering a second opinion after repeated task failures.
• Specialized Routing: Sending video, audio, or massive repositories to the specific models (like Gemini or local LLMs) best equipped to handle them.

Supported Scenarios

The skill is designed to integrate with external tools in your environment, including CLI-based reviewers, MCP servers, and secondary APIs. It produces an adjudicated report that combines raw findings from external tools with a final decision-making summary.