Back to Details

gemini

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Gemini CLI Integration

Gemini CLI 集成

Overview

概述

Execute Gemini CLI commands with support for multiple models and flexible prompt input. Integrates Google's Gemini AI models into Claude Code workflows.
执行支持多模型和灵活提示输入的Gemini CLI命令。将Google的Gemini AI模型集成到Claude Code工作流中。

When to Use

适用场景

  • Complex reasoning tasks requiring advanced AI capabilities
  • Code generation and analysis with Gemini models
  • Tasks requiring Google's latest AI technology
  • Alternative perspective on code problems
  • 需要高级AI能力的复杂推理任务
  • 使用Gemini模型进行代码生成与分析
  • 需要Google最新AI技术的任务
  • 从不同视角解决代码问题

Usage

使用方法

Mandatory: Run via uv with fixed timeout 7200000ms (foreground):
bash
uv run ~/.claude/skills/gemini/scripts/gemini.py "<prompt>" [working_dir]
Optional (direct execution or using Python):
bash
~/.claude/skills/gemini/scripts/gemini.py "<prompt>" [working_dir]
强制要求：通过uv运行，固定超时时间7200000毫秒（前台执行）：
bash
uv run ~/.claude/skills/gemini/scripts/gemini.py "<prompt>" [working_dir]
可选方式（直接执行或使用Python）：
bash
~/.claude/skills/gemini/scripts/gemini.py "<prompt>" [working_dir]

or

or

python3 ~/.claude/skills/gemini/scripts/gemini.py "<prompt>" [working_dir]
undefined
python3 ~/.claude/skills/gemini/scripts/gemini.py "<prompt>" [working_dir]
undefined

Environment Variables

环境变量

  • GEMINI_MODEL: Configure model (default: 
    gemini-3-pro-preview
    )
    • Example: 
      export GEMINI_MODEL=gemini-3
  • GEMINI_MODEL：配置使用的模型（默认值：
    gemini-3-pro-preview
    ）
    • 示例：
      export GEMINI_MODEL=gemini-3

Timeout Control

超时控制

  • Fixed: 7200000 milliseconds (2 hours), immutable
  • Bash tool: Always set 
    timeout: 7200000
    for double protection
  • 固定值：7200000毫秒（2小时），不可修改
  • Bash工具：始终设置
    timeout: 7200000
    以实现双重保护

Parameters

参数

  • prompt
    (required): Task prompt or question
  • working_dir
    (optional): Working directory (default: current directory)
  • prompt
    （必填）：任务提示或问题
  • working_dir
    （可选）：工作目录（默认值：当前目录）

Return Format

返回格式

Plain text output from Gemini:
text
Model response text here...
Error format (stderr):
text
ERROR: Error message
Gemini输出的纯文本内容：
text
Model response text here...
错误格式（标准错误输出）：
text
ERROR: Error message

Invocation Pattern

调用方式

When calling via Bash tool, always include the timeout parameter:
yaml
Bash tool parameters:
- command: uv run ~/.claude/skills/gemini/scripts/gemini.py "<prompt>"
- timeout: 7200000
- description: <brief description of the task>
Alternatives:
yaml
undefined
通过Bash工具调用时，务必包含超时参数：
yaml
Bash tool parameters:
- command: uv run ~/.claude/skills/gemini/scripts/gemini.py "<prompt>"
- timeout: 7200000
- description: <brief description of the task>
其他替代方式：
yaml
undefined

Direct execution (simplest)

直接执行（最简方式）

  • command: ~/.claude/skills/gemini/scripts/gemini.py "<prompt>"
  • command: ~/.claude/skills/gemini/scripts/gemini.py "<prompt>"

Using python3

使用python3

  • command: python3 ~/.claude/skills/gemini/scripts/gemini.py "<prompt>"
undefined
  • command: python3 ~/.claude/skills/gemini/scripts/gemini.py "<prompt>"
undefined

Examples

示例

Basic query:
bash
uv run ~/.claude/skills/gemini/scripts/gemini.py "explain quantum computing"
基础查询：
bash
uv run ~/.claude/skills/gemini/scripts/gemini.py "explain quantum computing"

timeout: 7200000

timeout: 7200000


**Code analysis:**

```bash
uv run ~/.claude/skills/gemini/scripts/gemini.py "review this code for security issues: $(cat app.py)"

**代码分析：**

```bash
uv run ~/.claude/skills/gemini/scripts/gemini.py "review this code for security issues: $(cat app.py)"

timeout: 7200000

timeout: 7200000


**With specific working directory:**

```bash
uv run ~/.claude/skills/gemini/scripts/gemini.py "analyze project structure" "/path/to/project"

**指定工作目录：**

```bash
uv run ~/.claude/skills/gemini/scripts/gemini.py "analyze project structure" "/path/to/project"

timeout: 7200000

timeout: 7200000


**Using python3 directly (alternative):**

```bash
python3 ~/.claude/skills/gemini/scripts/gemini.py "your prompt here"

**直接使用python3（替代方式）：**

```bash
python3 ~/.claude/skills/gemini/scripts/gemini.py "your prompt here"

Notes

注意事项

  • Recommended: Use 
    uv run
    for automatic Python environment management (requires uv installed)
  • Alternative: Direct execution 
    ./gemini.py
    (uses system Python via shebang)
  • Python implementation using standard library (zero dependencies)
  • Cross-platform compatible (Windows/macOS/Linux)
  • PEP 723 compliant (inline script metadata)
  • Requires Gemini CLI installed and authenticated
  • Supports all Gemini model variants (configure via 
    GEMINI_MODEL
    environment variable)
  • Output is streamed directly from Gemini CLI
  • 推荐方式：使用
    uv run
    进行自动Python环境管理（需提前安装uv）
  • 替代方式：直接执行
    ./gemini.py
    （通过shebang使用系统Python）
  • Python实现基于标准库（零依赖）
  • 跨平台兼容（Windows/macOS/Linux）
  • 符合PEP 723规范（内联脚本元数据）
  • 需提前安装并认证Gemini CLI
  • 支持所有Gemini模型变体（通过
    GEMINI_MODEL
    环境变量配置）
  • 输出直接从Gemini CLI流式传输