Gemini Cli

Authentication Model:

This tool uses your Gemini API Key passed as an environment variable:

GEMINI_API_KEY=<your-key> gemini <command>

Key Points:

• ✅ Official Google tool (not third-party)
• ✅ Credentials stored as environment variable (not in tool)
• ✅ You control scope: set env var only when needed
• ✅ No persistent credential storage in ~/.gemini/ directory
• ✅ Direct calls to Gemini API endpoints (googleapis.com)

What This Skill Does:

• ✅ Queries your codebase and documents with Gemini models
• ✅ Generates code/apps from images and PDFs
• ✅ Runs automated workflows using AI
• ✅ Provides interactive debugging and code review
• ❌ Does NOT store credentials
• ❌ Does NOT cache sensitive data
• ❌ Does NOT modify your system beyond running commands

Requirements

Binaries (required):

• gemini — Gemini CLI tool (installed via npm)
• node — Node.js 20.0.0+ (usually pre-installed)

Credentials (environment variable):

• GEMINI_API_KEY — Your Gemini API key from Google AI Studio or Google Cloud

System Requirements:

• macOS 15+, Windows 11 24H2+, or Ubuntu 20.04+
• 4GB+ RAM (casual usage), 16GB+ (power usage with large codebases)
• Internet connection required

Optional:

• bash, zsh, or PowerShell — Any modern shell

Installation & Setup

1. Check Installation

Gemini CLI is usually pre-installed:

gemini --version

If not installed:

npm install -g @google/gemini-cli
# OR
brew install gemini-cli

2. Set API Key (One-time per session)

export GEMINI_API_KEY="<your-api-key>"

Or use it inline:

GEMINI_API_KEY="<your-api-key>" gemini <command>

To find your API key:

• Go to https://aistudio.google.com/app/apikey
• Create or copy your API key
• Store securely (don't commit to git)

3. Verify Installation

gemini --version
gemini --help

Quick Start

Interactive Shell (Ask Gemini Questions)

gemini chat

Then type your questions about code, architecture, debugging, etc.

Query a Codebase

gemini code --prompt "What does this function do?" <file-or-directory>

Generate from Image

gemini create --from-image ./screenshot.png --prompt "Create a React component from this design"

Generate from PDF

gemini create --from-pdf ./document.pdf --prompt "Create an API spec based on this document"

Automate a Workflow

gemini workflow --steps "1) analyze code, 2) identify issues, 3) suggest fixes"

Get Help

gemini --help
gemini <command> --help

Common Commands

Interactive

gemini chat                    # Start interactive chat
gemini chat --context ./src    # Chat with codebase context

Code Analysis

gemini code --prompt "analyze" ./file.js
gemini code --explain ./function.ts
gemini code --review ./pull_request.patch

Code Generation

gemini create --from-image ./design.png
gemini create --from-pdf ./spec.pdf
gemini create --template react --prompt "counter app"

Batch Operations

gemini batch --input ./tasks.json --output ./results.json

Configuration

• API Key: Set via GEMINI_API_KEY environment variable
• Temp Storage: Uses system temp directory (auto-cleaned)
• No persistent config: Unlike mirocli, Gemini CLI doesn't store auth locally

To persist API key across sessions (optional):

Add to your ~/.bashrc, ~/.zshrc, or equivalent:

export GEMINI_API_KEY="<your-key>"

⚠️ Security warning: Only do this if your shell profile is secure and not synced to public repos.

Global Options

--version              # Show version
--help                # Show help
--verbose             # Verbose output
--api-key <key>       # Pass API key directly (overrides env var)
--model <model>       # Specify Gemini model (default: gemini-2.5-pro)

Help & Documentation

gemini --help                  # Global help
gemini <command> --help        # Command-specific help

Official Docs: https://geminicli.com/docs

Tips & Tricks

1. Use with your codebase:

   cd /path/to/your/project
   gemini chat --context ./src
   

2. Chain commands:

   gemini code --review ./changes.patch | tee review.txt
   

3. Batch process files:

   for file in src/*.js; do
     gemini code --explain "$file" > "docs/${file}.md"
   done
   

4. Store prompts in files:

   cat prompt.txt | gemini chat
   

When to Use Gemini CLI vs Other Tools

Status & Next Steps

✅ Installation: Pre-installed (v0.28.2)

✅ Configuration: Ready to use with GEMINI_API_KEY environment variable

✅ Authentication: Set env var before use (no interactive steps needed)

Testing: Run gemini --help to verify installation

Usage: Set API key and start using:

export GEMINI_API_KEY="your-key-here"
gemini chat

Setup Date: 2026-03-14
Status: Ready (no authentication required — env var based)