gemini
Execute Gemini CLI for AI-powered code analysis and generation. Use when you need to leverage Google's Gemini models for complex reasoning tasks.
When & Why to Use This Skill
The Gemini CLI skill empowers Claude with the ability to invoke Google's Gemini models directly within its workflow. This integration facilitates high-level code analysis, complex reasoning, and multi-model cross-validation, allowing developers to leverage the unique strengths of Google's AI for intricate programming tasks and architectural decision-making.
Use Cases
- Cross-Model Code Review: Use Gemini to provide an alternative perspective or a 'second opinion' on complex code logic and security vulnerabilities to ensure higher code quality.
- Complex Reasoning & Problem Solving: Leverage Gemini's specific reasoning capabilities for tasks that require deep contextual understanding or specialized logic beyond standard model outputs.
- Advanced Code Generation: Utilize specific Gemini model variants (like Gemini 1.5 Pro) to generate boilerplate, refactor legacy code, or design system architectures using Google's latest AI technology.
- Automated Technical Documentation: Analyze large codebases via the CLI to automatically generate comprehensive documentation, README files, and technical explanations.
| name | gemini |
|---|---|
| description | Execute Gemini CLI for AI-powered code analysis and generation. Use when you need to leverage Google's Gemini models for complex reasoning tasks. |
Gemini CLI Integration
Overview
Execute Gemini CLI commands with support for multiple models and flexible prompt input. Integrates Google's Gemini AI models into Claude Code workflows.
When to Use
- 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
Usage
Mandatory: Run via uv with fixed timeout 7200000ms (foreground):
uv run ~/.claude/skills/gemini/scripts/gemini.py "<prompt>" [working_dir]
Optional (direct execution or using Python):
~/.claude/skills/gemini/scripts/gemini.py "<prompt>" [working_dir]
# or
python3 ~/.claude/skills/gemini/scripts/gemini.py "<prompt>" [working_dir]
Environment Variables
- GEMINI_MODEL: Configure model (default:
gemini-3-pro-preview)- Example:
export GEMINI_MODEL=gemini-3
- Example:
Timeout Control
- Fixed: 7200000 milliseconds (2 hours), immutable
- Bash tool: Always set
timeout: 7200000for double protection
Parameters
prompt(required): Task prompt or questionworking_dir(optional): Working directory (default: current directory)
Return Format
Plain text output from Gemini:
Model response text here...
Error format (stderr):
ERROR: Error message
Invocation Pattern
When calling via Bash tool, always include the timeout parameter:
Bash tool parameters:
- command: uv run ~/.claude/skills/gemini/scripts/gemini.py "<prompt>"
- timeout: 7200000
- description: <brief description of the task>
Alternatives:
# Direct execution (simplest)
- command: ~/.claude/skills/gemini/scripts/gemini.py "<prompt>"
# Using python3
- command: python3 ~/.claude/skills/gemini/scripts/gemini.py "<prompt>"
Examples
Basic query:
uv run ~/.claude/skills/gemini/scripts/gemini.py "explain quantum computing"
# timeout: 7200000
Code analysis:
uv run ~/.claude/skills/gemini/scripts/gemini.py "review this code for security issues: $(cat app.py)"
# timeout: 7200000
With specific working directory:
uv run ~/.claude/skills/gemini/scripts/gemini.py "analyze project structure" "/path/to/project"
# timeout: 7200000
Using python3 directly (alternative):
python3 ~/.claude/skills/gemini/scripts/gemini.py "your prompt here"
Notes
- Recommended: Use
uv runfor 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_MODELenvironment variable) - Output is streamed directly from Gemini CLI