cross-review

Automate code reviews by spawning subagents with specified models.

Updated Apr 1, 2026
One-click install
npx skills add https://github.com/aarushlohit/TheRocketProject --skill cross-review-aarushlohit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cross-review
Source: https://github.com/aarushlohit/TheRocketProject/tree/main/rocket/external/shokunin/.pack/skills/cross-review
Command: npx skills add https://github.com/aarushlohit/TheRocketProject --skill cross-review-aarushlohit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates code reviews by delegating to subagents with specific models, reducing the time and effort spent on manual code inspections.

Core Features & Use Cases

  • Model-Specific Reviews: Utilize different models for specialized review tasks like security analysis, architectural review, and code generation.
  • Custom Review Requests: Allow users to specify models for their code reviews.
  • Contextual Review: Gather context from conversation history and related files to ensure comprehensive reviews.
  • Direct Output: Provide subagent review results directly without alterations.

Quick Start

Use the cross-review skill with a specific model, e.g., "review with gemini".

Frequently Asked Questions about cross-review

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

FAQPage Schema
How do I automate code reviews for security and architecture?

Automated code review delegates to subagents with specified models, extracting conversation context and code diffs to provide specialized security analysis and architectural reviews directly.

Can I use different models for specialized code review tasks?

Model-specific reviews utilize different models for specialized tasks, allowing you to spawn subagents for security analysis, architectural review, and code generation.

How does automated code review handle conversation context and code diffs?

Automated code review handles code diffs by extracting context from conversation history and related files, passing this information to subagents to ensure comprehensive and contextual reviews.

What is the best way to request a custom model for code generation review?

Custom review requests allow you to specify models for code generation reviews, spawning subagents that output review results directly without alterations.

Are code review subagents suitable for large architectural changes?

Code review subagents gather context from conversation history and related files, making them suitable for analyzing architectural changes and providing specialized architectural reviews.

Does automated code review alter the output from subagents?

Automated code review provides direct output, delivering subagent review results directly without alterations to ensure the specialized model's analysis remains unchanged.