### Gemma Setup without Auto-Start

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/core/gemma-setup.md

Perform the Gemma setup, including downloading binaries and models, but prevent the LiteRT server from starting automatically afterward.

```bash
gemini gemma setup --no-start
```

--------------------------------

### Gemma Setup Skipping Model Download

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/core/gemma-setup.md

Run the Gemma setup command to install only the necessary binaries, skipping the download of the ~1GB Gemma model.

```bash
gemini gemma setup --skip-model
```

--------------------------------

### Run Full Gemma Setup

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/core/gemma-setup.md

Execute this command to download the runtime, pull the Gemma model, configure settings, and start the local server. You will be prompted to accept the Gemma Terms of Use.

```bash
gemini gemma setup
```

--------------------------------

### Install a Skill using Gemini CLI

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/using-agent-skills.md

Install a skill from a remote repository URL or a local `.skill` package. By default, it installs to the user profile; use `--scope workspace` for project-specific installation.

```bash
gemini skills install https://github.com/user/my-awesome-skill
```

--------------------------------

### SKILL.md Frontmatter Example

Source: https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/skills/builtin/skill-creator/SKILL.md

Demonstrates the required YAML frontmatter for a SKILL.md file, specifying the skill's name and a concise description for Gemini CLI to determine its usage.

```yaml
name: "skill-name"
description: "A concise description of what this skill does and when it should be used."
```

--------------------------------

### Gemma Setup with Force Re-download

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/core/gemma-setup.md

Execute the Gemma setup command and force a complete re-download of all components, including the runtime and model.

```bash
gemini gemma setup --force
```

--------------------------------

### Install a Skill

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/skills.md

Install a skill from a Git repository or a local directory using the `gemini skills install` command. Use the `--consent` flag to bypass the security confirmation prompt.

```bash
# Install a skill from a Git repository or local directory.
# Use --consent to skip the security confirmation prompt.
gemini skills install https://github.com/user/repo.git --consent
```

--------------------------------

### Skill Structure Example

Source: https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/skills/builtin/skill-creator/SKILL.md

Illustrates the required and optional file structure for a Gemini CLI skill, including the SKILL.md file and bundled resources like scripts, references, and assets.

```tree
skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter metadata (required)
│   │   ├── name: (required)
│   │   └── description: (required)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code (Node.js/Python/Bash/etc.)
    ├── references/       - Documentation intended to be loaded into context as needed
    └── assets/           - Files used in output (templates, icons, fonts, etc.)
```

--------------------------------

### Model Configuration Example

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/reference/configuration.md

Example of configuring different models with specific actions and state transitions. This includes settings for 'flash-lite', 'gemini-2.5-flash', and 'gemini-2.5-pro' models.

```json
{
          "model": "flash-lite",
          "actions": {
            "terminal": "silent",
            "transient": "silent",
            "not_found": "silent",
            "unknown": "silent"
          },
          "stateTransitions": {
            "terminal": "terminal",
            "transient": "terminal",
            "not_found": "terminal",
            "unknown": "terminal"
          }
        },
        {
          "model": "gemini-2.5-flash",
          "actions": {
            "terminal": "silent",
            "transient": "silent",
            "not_found": "silent",
            "unknown": "silent"
          },
          "stateTransitions": {
            "terminal": "terminal",
            "transient": "terminal",
            "not_found": "terminal",
            "unknown": "terminal"
          }
        },
        {
          "model": "gemini-2.5-pro",
          "isLastResort": true,
          "actions": {
            "terminal": "silent",
            "transient": "silent",
            "not_found": "silent",
            "unknown": "silent"
          },
          "stateTransitions": {
            "terminal": "terminal",
            "transient": "terminal",
            "not_found": "terminal",
            "unknown": "terminal"
          }
        }
```

--------------------------------

### Run React DevTools

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/CONTRIBUTING.md

Launch the installed React DevTools. After starting the Gemini CLI in development mode, this tool will connect to it for UI debugging.

```bash
react-devtools
```

--------------------------------

### Install an extension using gemini CLI

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/extensions/reference.md

Install an extension by providing its GitHub repository URL or a local file path. Ensure `git` is installed for GitHub sources. Updates require running `gemini extensions update`.

```bash
gemini extensions install <source> [--ref <ref>] [--auto-update] [--pre-release] [--consent] [--skip-settings]
```

--------------------------------

### Install Extension from Git URL

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/cli-reference.md

Installs an extension from a Git repository. Supports installation from a specific branch, tag, or commit using the --ref flag.

```bash
gemini extensions install https://github.com/user/my-extension
```

```bash
gemini extensions install https://github.com/user/my-extension --ref develop
```

--------------------------------

### Install Dependencies and Build Project

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/resources/troubleshooting.md

If encountering MODULE_NOT_FOUND or import errors, run these commands to ensure dependencies are installed and the project is built.

```bash
npm install
```

```bash
npm run build
```

```bash
npm run start
```

--------------------------------

### Install Dependencies

Source: https://github.com/google-gemini/gemini-cli/blob/main/GEMINI.md

Installs all project dependencies using npm.

```bash
npm install
```

--------------------------------

### Install and Run React DevTools

Source: https://github.com/google-gemini/gemini-cli/blob/main/CONTRIBUTING.md

Commands to install or execute React DevTools version 6.

```bash
npm install -g react-devtools@6
react-devtools
```

```bash
npx react-devtools@6
```

--------------------------------

### Install skill from source

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/cli-reference.md

Install a new agent skill from a specified source, which can be a Git repository URL, a local path, or a file.

```bash
gemini skills install https://github.com/u/repo
```

--------------------------------

### Quick Install Gemini CLI with npx

Source: https://github.com/google-gemini/gemini-cli/blob/main/README.md

Run the Gemini CLI instantly without installation using npx.

```bash
# Using npx (no installation required)
npx @google/gemini-cli
```

--------------------------------

### Install Extension Dependencies

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/extensions/writing-extensions.md

Before linking your extension, navigate to its directory and install its Node.js dependencies using npm.

```bash
cd my-first-extension
npm install
```

--------------------------------

### Install Gemini CLI IDE Companion Extension

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/ide-integration/index.md

Run this command within Gemini CLI to manually install the IDE companion extension if you previously dismissed the prompt or prefer manual installation.

```bash
/ide install
```

--------------------------------

### Start LiteRT-LM Runtime (MacOS)

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/core/local-model-routing.md

Start the LiteRT-LM runtime on MacOS, specifying the port for the Gemma model.

```bash
./lit.macos_arm64 serve --port=9379 --verbose
```

--------------------------------

### Install Eleven Labs Extension

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/changelogs/index.md

Install the Eleven Labs Gemini CLI extension to manage audio play tracks.

```bash
gemini extensions install https://github.com/elevenlabs/elevenlabs-mcp
```

--------------------------------

### Install Data Commons Gemini CLI Extension

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/changelogs/index.md

Install the Data Commons Gemini CLI extension to query open-source statistical data. Requires a Data Commons API key and uv installed.

```bash
gemini extensions install https://github.com/gemini-cli-extensions/datacommons
```

--------------------------------

### Start Genkit Telemetry Server

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/local-development.md

Run this command to start the Genkit telemetry server for viewing traces in the Genkit Developer UI.

```bash
npm run telemetry -- --target=genkit
```

--------------------------------

### List Installed Extensions

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/cli-reference.md

Displays a list of all extensions currently installed in the Gemini CLI.

```bash
gemini extensions list
```

--------------------------------

### Install Monday.com Extension

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/changelogs/index.md

Install the Monday.com extension to analyze sprints and update task boards. This command registers the extension with the Gemini CLI.

```bash
gemini extensions install https://github.com/mondaycom/mcp
```

--------------------------------

### Start Gemma Server

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/core/gemma-setup.md

Manually start the LiteRT server for local model routing. It typically auto-starts on CLI launch.

```bash
gemini gemma start
```

--------------------------------

### Start Telemetry Collector for Google Cloud

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/local-development.md

Run this command to start a local OpenTelemetry collector that forwards telemetry data to Google Cloud Trace.

```bash
npm run telemetry -- --target=gcp
```

--------------------------------

### Install Redis Extension

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/changelogs/index.md

Install the Redis extension to manage and search data in Redis using natural language.

```bash
gemini extensions install https://github.com/redis/mcp-redis
```

--------------------------------

### Install Gemini CLI with npm

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/get-started/installation.mdx

Install the Gemini CLI globally using npm. This is a common method for Node.js packages.

```bash
npm install -g @google/gemini-cli
```

--------------------------------

### Gemma Setup with Custom Port

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/core/gemma-setup.md

Configure the Gemma setup process to use a specific network port for the LiteRT server.

```bash
gemini gemma setup --port 8080
```

--------------------------------

### Install Gemini CLI Extension

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/changelogs/index.md

Use this command to install a Gemini CLI extension from a GitHub URL or a local folder path.

```bash
gemini extensions install <github url|folder path>
```

--------------------------------

### Install Hugging Face Extension

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/changelogs/index.md

Install the Hugging Face extension to access the Hugging Face hub. This command registers the extension with the Gemini CLI.

```bash
gemini extensions install https://github.com/huggingface/hf-mcp-server
```

--------------------------------

### Initialize Gemini CLI Skill

Source: https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/skills/builtin/skill-creator/SKILL.md

Initializes a new Gemini CLI skill by creating a template directory with essential files and subdirectories. This script automates the setup process for new skills, ensuring a consistent and efficient starting point. It requires the skill name and an output path for the new skill.

```bash
node <path-to-skill-creator>/scripts/init_skill.cjs <skill-name> --path <output-directory>
```

--------------------------------

### Install Gemini CLI Skill

Source: https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/skills/builtin/skill-creator/SKILL.md

Installs a packaged Gemini CLI skill. Skills can be installed either locally within the current workspace or at the user level. After installation, the user must manually reload the CLI for the new skill to become active.

```bash
gemini skills install <path/to/skill-name.skill> --scope workspace
```

```bash
gemini skills install <path/to/skill-name.skill> --scope user
```

--------------------------------

### User Settings Configuration Example

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/enterprise.md

Allows users to define their preferred UI theme, custom MCP servers, and additional context directories.

```json
{
  "ui": {
    "theme": "user-preferred-dark-theme"
  },
  "mcpServers": {
    "corp-server": {
      "command": "/usr/local/bin/corp-server-dev"
    },
    "user-tool": {
      "command": "npm start --prefix ~/tools/my-tool"
    }
  },
  "context": {
    "includeDirectories": ["~/gemini-context"]
  }
}
```

--------------------------------

### PDF Rotation Script Example (Node.js)

Source: https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/skills/builtin/skill-creator/SKILL.md

An example of an executable script for a PDF rotation task, intended to be placed in the 'scripts/' directory of a skill. It should output LLM-friendly stdout.

```javascript
// scripts/rotate_pdf.cjs
// Example script for PDF rotation
// Ensure output is LLM-friendly stdout

const fs = require('fs');
const path = require('path');

async function rotatePdf(filePath, degrees) {
    // Placeholder for actual PDF rotation logic
    console.log(`Simulating rotation of ${filePath} by ${degrees} degrees.`);
    // In a real scenario, you would use a library like 'pdf-lib' or 'sharp'
    // and handle file operations.

    // Example success output:
    console.log(`Success: PDF rotated. Processed file: ${path.basename(filePath)}`);
    // Example failure output:
    // console.error(`Error: Failed to rotate PDF. Reason: ...`);
    return true;
}

// Example usage (replace with actual argument parsing)
const args = process.argv.slice(2);
if (args.length < 2) {
    console.error('Usage: node rotate_pdf.cjs <file_path> <degrees>');
    process.exit(1);
}

const filePath = args[0];
const degrees = parseInt(args[1], 10);

if (isNaN(degrees)) {
    console.error('Error: Degrees must be a number.');
    process.exit(1);
}

rotatePdf(filePath, degrees).catch(err => {
    console.error(`Unhandled error during PDF rotation: ${err.message}`);
    process.exit(1);
});

```

--------------------------------

### Display MCP Server Status

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/tools/mcp-server.md

Run the /mcp command to get a comprehensive overview of your MCP server setup, including server lists, connection status, and available tools.

```bash
/mcp
```

--------------------------------

### MCP Server Implementation (`example.js`)

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/extensions/writing-extensions.md

This JavaScript file defines the behavior of your extension's MCP server, registering tools and handling requests using the `@modelcontextprotocol/sdk`.

```javascript
/**
 * @license
 * Copyright 2025 Google LLC
 * SPDX-License-Identifier: Apache-2.0
 */

import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
import { z } from 'zod';

const server = new McpServer({
  name: 'prompt-server',
  version: '1.0.0',
});

// Registers a new tool named 'fetch_posts'
server.registerTool(
  'fetch_posts',
  {
    description: 'Fetches a list of posts from a public API.',
    inputSchema: z.object({}).shape,
  },
  async () => {
    const apiResponse = await fetch(
      'https://jsonplaceholder.typicode.com/posts',
    );
    const posts = await apiResponse.json();
    const response = { posts: posts.slice(0, 5) };
    return {
      content: [
        {
          type: 'text',
          text: JSON.stringify(response),
        },
      ],
    };
  },
);

const transport = new StdioServerTransport();
await server.connect(transport);
```

--------------------------------

### Start a complex task in Plan Mode

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/tutorials/plan-mode-steering.md

Initiate a task in Plan Mode to begin the research phase for a new implementation. This command sets up the structured environment for guided development.

```bash
/plan I want to implement a new notification service using Redis.
```

--------------------------------

### Start New Project with Gemini CLI

Source: https://github.com/google-gemini/gemini-cli/blob/main/README.md

Demonstrates starting a new project and using Gemini CLI to generate code for a Discord bot based on a provided FAQ file.

```bash
cd new-project/
gemini
> Write me a Discord bot that answers questions using a FAQ.md file I will provide
```

--------------------------------

### Build All Project Components

Source: https://github.com/google-gemini/gemini-cli/blob/main/GEMINI.md

Builds all packages, the sandbox, and the VS Code companion.

```bash
npm run build:all
```

--------------------------------

### Workspace Settings Configuration Example

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/enterprise.md

Enables project-specific configurations for UI theme, MCP servers, and context directories.

```json
{
  "ui": {
    "theme": "project-specific-light-theme"
  },
  "mcpServers": {
    "project-tool": {
      "command": "npm start"
    }
  },
  "context": {
    "includeDirectories": ["./project-context"]
  }
}
```

--------------------------------

### Specify the Gemini model to use

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/reference/configuration.md

Select the Gemini model for the session with the `--model` or `-m` flag. This example shows how to pass the model name when starting the CLI via npm.

```bash
npm start -- --model gemini-3-pro-preview
```

--------------------------------

### Launch Antigravity CLI

Source: https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/skills/builtin/antigravity-support/SKILL.md

Run this command in any project or workspace directory to start the Antigravity CLI. The first launch will guide you through workspace trust verification, theme configuration, and rendering modes.

```bash
agy
```

--------------------------------

### Text Input Question Example

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/tools/ask-user.md

Shows how to set up a free-form text input question using the ask_user tool. A placeholder can be provided for user guidance.

```json
{
  "questions": [
    {
      "header": "Project Name",
      "question": "What is the name of your new project?",
      "type": "text",
      "placeholder": "for example, my-awesome-app"
    }
  ]
}
```

--------------------------------

### Final Merged Configuration Example

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/enterprise.md

Illustrates the resulting configuration after applying the precedence rules and merging settings from system defaults, user, workspace, and system overrides.

```json
{
  "ui": {
    "theme": "system-enforced-theme"
  },
  "mcpServers": {
    "corp-server": {
      "command": "/usr/local/bin/corp-server-prod"
    },
    "user-tool": {
      "command": "npm start --prefix ~/tools/my-tool"
    },
    "project-tool": {
      "command": "npm start"
    }
  },
  "context": {
    "includeDirectories": [
      "/etc/gemini-cli/common-context",
      "~/gemini-context",
      "./project-context",
      "/etc/gemini-cli/global-context"
    ]
  }
}
```

--------------------------------

### System Defaults Configuration Example

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/enterprise.md

Defines the baseline configuration for Gemini CLI, including UI theme and default context directories.

```json
{
  "ui": {
    "theme": "default-corporate-theme"
  },
  "context": {
    "includeDirectories": ["/etc/gemini-cli/common-context"]
  }
}
```

--------------------------------

### Link Gemini CLI Extension

Source: https://github.com/google-gemini/gemini-cli/blob/main/packages/cli/src/commands/extensions/examples/policies/README.md

This command links the policy engine extension to your local Gemini CLI installation. After running this command, you need to restart your Gemini CLI session for the changes to take effect.

```bash
gemini extensions link packages/cli/src/commands/extensions/examples/policies
```

--------------------------------

### Approve and start implementation

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/tutorials/plan-mode-steering.md

Confirm the generated plan is satisfactory and initiate the implementation phase. This signals the agent to proceed with executing the refined plan.

```bash
"Looks perfect. Let's start the implementation."
```

--------------------------------

### Node.js Script for Assistant Initialization

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/hooks/writing-hooks.md

This Node.js script initializes the Gemini assistant by logging a message to stderr and outputting a JSON object to stdout containing a system message. This script is intended to be used as a hook during the session start.

```javascript
#!/usr/bin/env node
// Initialize DB or resources
console.error('Initializing assistant...');

// Output to user
console.log(
  JSON.stringify({
    systemMessage: '🧠 Smart Assistant Loaded',
  }),
);

```

--------------------------------

### Verify Antigravity CLI Installation

Source: https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/skills/builtin/antigravity-support/SKILL.md

Use this command to check the installed version of Antigravity CLI after installation.

```bash
agy --version
```

--------------------------------

### Example Custom Theme File

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/themes.md

A sample `my-theme.json` file demonstrating the structure for defining custom theme properties like colors for background, text, borders, and status indicators.

```json
{
  "name": "Gruvbox Dark",
  "type": "custom",
  "background": {
    "primary": "#282828",
    "diff": {
      "added": "#2b3312",
      "removed": "#341212"
    }
  },
  "text": {
    "primary": "#ebdbb2",
    "secondary": "#a89984",
    "link": "#83a598",
    "accent": "#d3869b"
  },
  "border": {
    "default": "#3c3836",
    "focused": "#458588"
  },
  "status": {
    "success": "#b8bb26",
    "warning": "#fabd2f",
    "error": "#fb4934"
  },
  "ui": {
    "comment": "#928374",
    "symbol": "#8ec07c",
    "gradient": ["#cc241d", "#d65d0e", "#d79921"]
  }
}
```

--------------------------------

### Verify Gemini CLI Installation

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/sandbox.md

Verify that the Gemini CLI has been installed correctly by checking its version. This confirms the installation was successful.

```bash
gemini --version
```

--------------------------------

### Start Gemini CLI

Source: https://github.com/google-gemini/gemini-cli/blob/main/README.md

Initiates the Gemini CLI. For users with a paid Code Assist License, ensure your Google Cloud Project is set.

```bash
gemini
```

```bash
# Set your Google Cloud Project
export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"
gemini
```

--------------------------------

### Install Latest Stable Gemini CLI

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/changelogs/latest.md

Install the latest stable version of Gemini CLI using npm. This is the recommended installation method for most users.

```bash
npm install -g @google/gemini-cli
```

--------------------------------

### Yes/No Question Example

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/tools/ask-user.md

Illustrates configuring a simple Yes/No confirmation question for the ask_user tool. This is useful for straightforward user approvals.

```json
{
  "questions": [
    {
      "header": "Deploy",
      "question": "Do you want to deploy the application now?",
      "type": "yesno"
    }
  ]
}
```

--------------------------------

### Example settings.json Configuration

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/reference/configuration.md

This JSON file demonstrates the nested structure for configuring the Gemini CLI, including options for general settings, UI, tools, servers, telemetry, model, and context.

```json
{
  "general": {
    "vimMode": true,
    "preferredEditor": "code",
    "sessionRetention": {
      "enabled": true,
      "maxAge": "30d",
      "maxCount": 100
    }
  },
  "ui": {
    "theme": "GitHub",
    "hideBanner": true,
    "hideTips": false,
    "customWittyPhrases": [
      "You forget a thousand things every day. Make sure this is one of ’em",
      "Connecting to AGI"
    ]
  },
  "tools": {
    "sandbox": "docker",
    "discoveryCommand": "bin/get_tools",
    "callCommand": "bin/call_tool",
    "exclude": ["write_file"]
  },
  "mcpServers": {
    "mainServer": {
      "command": "bin/mcp_server.py"
    },
    "anotherServer": {
      "command": "node",
      "args": ["mcp_server.js", "--verbose"]
    }
  },
  "telemetry": {
    "enabled": true,
    "target": "local",
    "otlpEndpoint": "http://localhost:4317",
    "logPrompts": true
  },
  "privacy": {
    "usageStatisticsEnabled": true
  },
  "model": {
    "name": "gemini-1.5-pro-latest",
    "maxSessionTurns": 10,
    "summarizeToolOutput": {
      "run_shell_command": {
        "tokenBudget": 100
      }
    }
  },
  "context": {
    "fileName": ["CONTEXT.md", "GEMINI.md"],
    "includeDirectories": ["path/to/dir1", "~/path/to/dir2", "../path/to/dir3"],
    "loadFromIncludeDirectories": true,
    "fileFiltering": {
      "respectGitIgnore": false
    }
  },
  "advanced": {
    "excludedEnvVars": ["DEBUG", "DEBUG_MODE", "NODE_ENV"]
  }
}
```

--------------------------------

### Install Gemini CLI Stable Release

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/get-started/installation.mdx

Installs the latest stable version of the Gemini CLI. This is the recommended version for most users. Omitting the tag also installs the latest stable release.

```bash
npm install -g @google/gemini-cli
```

```bash
npm install -g @google/gemini-cli@latest
```

--------------------------------

### Install Gemini CLI with Anaconda

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/get-started/installation.mdx

Install Gemini CLI within a Conda environment, which is useful for managing dependencies in restricted environments. This involves creating and activating an environment, then installing Node.js and the CLI.

```bash
conda create -y -n gemini_env -c conda-forge nodejs
conda activate gemini_env

npm install -g @google/gemini-cli
```

--------------------------------

### Verify Gemini CLI Version

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/release-confidence.md

After installation, verify the installed version of the Gemini CLI.

```bash
gemini --version
```

--------------------------------

### Basic import usage

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/reference/memport.md

Example of importing files into a main GEMINI.md document.

```markdown
# My GEMINI.md

Welcome to my project!

@./get-started.md

## Features

@./features/overview.md
```

--------------------------------

### Example MCP Server Status Output

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/tools/mcp-server.md

This is an example of the output you can expect when running the /mcp command, showing details for multiple MCP servers and the overall discovery state.

```text
MCP Servers Status:

📡 pythonTools (CONNECTED)
  Command: python -m my_mcp_server --port 8080
  Working Directory: ./mcp-servers/python
  Timeout: 15000ms
  Tools: calculate_sum, file_analyzer, data_processor

🔌 nodeServer (DISCONNECTED)
  Command: node dist/server.js --verbose
  Error: Connection refused

🐳 dockerizedServer (CONNECTED)
  Command: docker run -i --rm -e API_KEY my-mcp-server:latest
  Tools: mcp_dockerizedServer_docker_deploy, mcp_dockerizedServer_docker_status

Discovery State: COMPLETED
```

--------------------------------

### Install React DevTools Globally

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/CONTRIBUTING.md

Install React DevTools version 6 globally to debug the CLI's React-based UI. Ensure you install version 6 to match the CLI's react-devtools-core.

```bash
npm install -g react-devtools@6
```

--------------------------------

### Install Gemini CLI with Anaconda

Source: https://github.com/google-gemini/gemini-cli/blob/main/README.md

Install the Gemini CLI within a Conda environment for restricted environments. This involves creating and activating a new environment with Node.js, then installing the CLI globally via npm.

```bash
# Create and activate a new environment
conda create -y -n gemini_env -c conda-forge nodejs
conda activate gemini_env

# Install Gemini CLI globally via npm (inside the environment)
npm install -g @google/gemini-cli
```

--------------------------------

### Import tree structure visualization

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/reference/memport.md

Example output showing the hierarchy of imported files.

```text
Memory Files
 L project: GEMINI.md
            L a.md
              L b.md
                L c.md
              L d.md
                L e.md
                  L f.md
            L included.md
```

--------------------------------

### Install Antigravity CLI on Windows

Source: https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/skills/builtin/antigravity-support/SKILL.md

Execute this PowerShell command to install the Antigravity CLI on Windows environments.

```powershell
irm https://antigravity.google/cli/install.ps1 | iex
```

--------------------------------

### Uninstall gemini-cli installed with MacPorts

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/resources/uninstall.md

If you installed the CLI globally using MacPorts, use this command to remove it.

```bash
sudo port uninstall gemini-cli
```

--------------------------------

### Uninstall gemini-cli installed with Homebrew

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/resources/uninstall.md

If you installed the CLI globally using Homebrew, use this command to remove it.

```bash
brew uninstall gemini-cli
```

--------------------------------

### Initialize a New Skill with Gemini CLI

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/creating-skills.md

Use this script to automate the initialization of a new skill. Specify the skill name and the directory where it should be created.

```bash
node scripts/init_skill.cjs <name> --path <dir>
```

--------------------------------

### Install Gemini CLI with MacPorts

Source: https://github.com/google-gemini/gemini-cli/blob/main/docs/get-started/installation.mdx

Install the Gemini CLI globally using MacPorts on macOS systems.

```bash
sudo port install gemini-cli
```