gemini

Analyze large codebases and architectural plans via the Gemini CLI.

Updated Jul 24, 2026
One-click install
npx skills add https://github.com/imMamdouhaboammar/kaku-chatgpt-harness --skill gemini-immamdouhaboammar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini
Source: https://github.com/imMamdouhaboammar/kaku-chatgpt-harness/tree/main/.agents/skills/gemini
Command: npx skills add https://github.com/imMamdouhaboammar/kaku-chatgpt-harness --skill gemini-immamdouhaboammar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the challenge of analyzing massive codebases and complex architectural plans that exceed standard context windows, providing state-of-the-art reasoning for software engineering tasks.

Core Features & Use Cases

  • Massive Context Processing: Analyze entire repositories or documentation sets up to 1M tokens.
  • Intelligent Model Selection: Choose between flagship reasoning models like Gemini 3 Pro or speed-optimized flash models.
  • Automated Safety: Includes built-in background execution safety, timeout management, and approval mode controls to prevent hung processes.

Quick Start

Use the gemini skill to perform a comprehensive security and quality review of the current codebase using the Gemini 3 Pro model.

Frequently Asked Questions about gemini

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

FAQPage Schema
How do I analyze a massive codebase that exceeds standard context windows?

You can analyze a massive codebase by using an intelligent interface for the Gemini CLI to process up to 1M tokens. This approach enables large-scale code analysis and complex reasoning for software engineering tasks that exceed standard context limitations.

Can I run automated code reviews in the background without hanging the process?

Yes, you can run automated code reviews in the background safely. The system includes built-in background execution safety, timeout management, and configurable approval mode controls to prevent hung processes during large-scale analysis.

What is the best way to perform an architectural review of an entire repository?

The best way to perform an architectural review of an entire repository is using a high-context AI analysis tool. It allows you to process entire repositories and provides state-of-the-art reasoning for complex software engineering tasks.

Does the Gemini CLI interface support both interactive and background execution modes?

Yes, the Gemini CLI interface supports both interactive and background execution modes. It includes configurable approval policies to ensure safe automated workflows during complex reasoning and multi-file pattern recognition tasks.

How do I choose between flagship reasoning models and speed-optimized flash models?

You can choose between flagship reasoning models like Gemini 3 Pro and speed-optimized flash models based on your task requirements. Intelligent model selection allows you to balance in-depth architectural reviews against faster code analysis needs.