Mastering Gemini Cli Agentic Skill

Mastering Gemini CLI Skill

Build headless automation and agentic workflows with Google's Gemini CLI.

Overview

This skill provides comprehensive guidance for using Google's Gemini CLI in headless and agentic scenarios. It covers:

• Approval Modes: Understanding default, auto_edit, and yolo modes
• File Permission Model: Explicit consent and visibility patterns
• Tool Selection: When to use Edit vs WriteFile vs RunShell
• smartEdit Configuration: Solving the "0 occurrences found" reliability crisis
• GEMINI.md Context Files: Project-specific agent instructions
• settings.json Hierarchy: Configuration precedence
• MCP Server Integration: Extending agents to external services
• Session Persistence: Multi-step workflows with --resume

Quick Start

# Basic headless invocation
gemini -p "Refactor auth.js to use async/await" --approval-mode auto_edit

# Pipe input for context
git diff --staged | gemini -p "Generate semantic commit message"

# JSON output for scripts
gemini -p "List TODOs in src/" --output-format json --include-directories src

When to Use This Skill

Use when:

• Building CI/CD pipelines with Gemini
• Debugging "0 occurrences found" edit failures
• Configuring --approval-mode for automation
• Creating long-running agents with --resume
• Integrating external services via Model Context Protocol

Installing with Skilz (Universal Installer)

The recommended way to install this skill across different AI coding agents is using the **skilz** universal installer.

Install Skilz

pip install skilz

This skill supports [Agent Skill Standard](https://agentskills.io/) which means it supports 14 plus coding agents including Claude Code, OpenAI Codex, Cursor and Gemini.

Git URL Options

You can use either `-g` or `--git` with HTTPS or SSH URLs:

# HTTPS URL
skilz install -g https://github.com/SpillwaveSolutions/mastering-gemini-cli-agentic-skill

# SSH URL
skilz install --git git@g