# Gemini AI (Patched)

> Use this tool when you need to integrate AI models into your workflow, requiring features like intelligent quota management, structured brainstorming, and code testing with sandbox execution. It solves problems related to AI model compatibility, response formatting, and safe code testing, providing inputs like brainstorming prompts and code snippets, and outputs like formatted responses and test results. Ideal for use cases involving AI-driven idea generation, content creation, and automation, with a user-friendly interface through the Gemini CLI.

Canonical page: https://skillsregistry.net/skills/glitterkill-gemini-patched  
JSON: https://api.skillsregistry.net/v1/skills/glitterkill-gemini-patched

## Description

A patched MCP server that integrates with Google's Gemini AI models through the Gemini CLI, featuring Windows compatibility fixes and intelligent quota management with automatic fallback from gemini-2.5-pro to gemini-2.5-flash when limits are exceeded. Provides specialized tools including a structured brainstorming framework with multiple methodologies (SCAMPER, design thinking, lateral thinking), a changeMode system that formats Gemini responses into Claude-compatible edit instructions with chunking for large responses, and sandbox execution capabilities for safe code testing.

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/glitterkill-gemini-patched)
- **Repository:** <https://github.com/glitterkill/gemini-mcp-tool-patched>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "glitterkill-gemini-patched"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/glitterkill-gemini-patched` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/glitterkill-gemini-patched/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt