What is Gemini CLI used for?

Interact with Google's Gemini CLI locally to run queries, compare with Claude, or delegate tasks to Gemini.

How can I get JSON output?

Use the -o json option with your query to get structured JSON results.

How do I analyze a file with Gemini CLI?

Pipe the file contents into Gemini with a prompt, e.g., cat file.txt | gemini \"Analyze this\".

Gemini Cli

npx machina-cli add skill hackermanishackerman/claude-skills-vault/gemini-cli --openclaw

Files (1)

SKILL.md

1.4 KB

Gemini CLI

Interact w/ Google's Gemini CLI locally. Run queries, get responses, compare outputs.

Prerequisites

Gemini CLI must be installed & configured:

Install: https://github.com/google-gemini/gemini-cli
Auth: Run gemini & sign in w/ Google account
Verify: gemini --version

When to Use

User asks to "run/ask/use gemini"
Compare Claude vs Gemini responses
Get second AI opinion
Delegate task to Gemini

Usage

# One-shot query
gemini "Your prompt"

# Specific model
gemini -m gemini-3-pro-preview "prompt"

# JSON output
gemini -o json "prompt"

# YOLO mode (auto-approve)
gemini -y "prompt"

# File analysis
cat file.txt | gemini "Analyze this"

Comparison Workflow

Provide Claude's response first
Run same query via Gemini CLI
Present both for comparison

CLI Options

Flag	Desc
`-m`	Model (gemini-3-pro)
`-o`	Output: text/json/stream-json
`-y`	Auto-approve (YOLO)
`-d`	Debug mode
`-s`	Sandbox mode
`-r`	Resume session
`-i`	Interactive after prompt

Best Practices

Quote prompts w/ double quotes
Use -o json for parsing
Pipe files for context
Specify model for specific capabilities

Source

git clone https://github.com/hackermanishackerman/claude-skills-vault/blob/main/.claude/skills/gemini-cli/SKILL.mdView on GitHub

Overview

Gemini CLI lets you run AI queries against Google's Gemini from your terminal. It supports one-shot prompts, model specification, JSON output, YOLO mode, and file analysis, enabling quick comparisons with Claude and easy task delegation.

How This Skill Works

Install Gemini CLI, authenticate with your Google account, and verify the tool with gemini --version. Then you can run prompts directly (gemini "prompt"), specify a model (-m), request JSON output (-o json), enable auto-approve (-y), or pipe data for analysis (e.g., cat file.txt | gemini "Analyze this"). A common workflow is to present Claude's response first, then run the same query via Gemini CLI for side-by-side comparison.

When to Use It

User asks to run/ask/use Gemini from the terminal.
You need to compare Claude vs Gemini responses.
You want a second AI opinion or alternative perspective.
You want to delegate a task to Gemini.
You need to analyze a file or long text with context from a prompt (file analysis).

Quick Start

Step 1: Install Gemini CLI and authenticate (install; run gemini; sign in; verify with gemini --version).
Step 2: Run a basic query (gemini \"Your prompt\" or gemini -m gemini-3-pro-preview \"prompt\").
Step 3: Get structured output or analyze files (gemini -o json \"prompt\" or cat file.txt | gemini \"Analyze this\").

Best Practices

Quote prompts with double quotes.
Use -o json for predictable parsing.
Pipe files for context when analyzing content.
Specify model with -m for targeted capabilities.
Compare outputs with Claude when possible to validate results.

Example Use Cases

One-shot query: gemini \"Your prompt\"
Specific model: gemini -m gemini-3-pro-preview \"prompt\"
JSON output: gemini -o json \"prompt\"
YOLO mode: gemini -y \"prompt\"
File analysis: cat file.txt | gemini \"Analyze this\"

Frequently Asked Questions

Add this skill to your agents