Looker Agent Skills

[!NOTE] Currently in beta (pre-v1.0), and may see breaking changes until the first stable release (v1.0).

This repository provides a set of agent skills to interact with Looker. These skills can be used with various AI agents, including Antigravity, Claude Code and Codex, to explore data, manage dashboards, and develop LookML using natural language prompts.

[!IMPORTANT] We Want Your Feedback! Please share your thoughts with us by filling out our feedback form. Your input is invaluable and helps us improve the project for everyone.

Table of Contents

• Why Use Looker Agent Skills?
• Prerequisites
• Getting Started
  • Configuration
  • Installation & Usage
    • Antigravity
    • Claude Code
    • Codex
• Installing using open agent skills tool
• Installing via a compatible Agent Plugins client
• Usage Examples
• Supported Skills
• Troubleshooting

Why Use Looker Agent Skills?

• Seamless Workflow: Integrates seamlessly into your AI agent's environment. No need to constantly switch contexts for common Looker tasks.
• Natural Language Queries: Stop wrestling with complex UI or LookML. Explore data and create content by describing what you want in plain English.
• Full Lifecycle Control: Manage your Looker environment, from exploring models to creating dashboards and authoring LookML.
• Accelerate Development: Speed up LookML development by asking your agent to generate or update files based on your requirements.

Prerequisites

Before you begin, ensure you have the following:

• One of these AI agents installed
  • Antigravity
    • Antigravity CLI version v1.6.0 or higher
    • Antigravity 2.0 version v2.0.0 or higher.
  • Claude Code version v2.1.94 or higher.
  • Codex v0.117.0 or higher.
• A Looker instance and API credentials (Client ID and Client Secret).

Getting Started

Configuration

Please keep these env vars handy during the installation process:

• LOOKER_BASE_URL: The base URL of your Looker instance.
• LOOKER_CLIENT_ID: The Looker API client ID.
• LOOKER_CLIENT_SECRET: The Looker API client secret.
• LOOKER_VERIFY_SSL: (Optional) Whether to verify SSL certificates. Defaults to true.
• LOOKER_SHOW_HIDDEN_MODELS: (Optional) Whether to show models that are hidden in the UI. Defaults to true.
• LOOKER_SHOW_HIDDEN_EXPLORES: (Optional) Whether to show explores that are hidden in the UI. Defaults to true.
• LOOKER_SHOW_HIDDEN_FIELDS: (Optional) Whether to show fields that are hidden in the UI. Defaults to true.

Installation & Usage

To start interacting with Looker, install the skills for your preferred AI agent, then launch the agent and use natural language to ask questions or perform tasks.

For the latest version, check the releases page.

git clone --branch 0.3.10 https://github.com/gemini-cli-extensions/looker.git

cp -R looker/skills/* ~/.gemini/antigravity/skills/

git clone --branch 0.3.10 https://github.com/gemini-cli-extensions/looker.git

agy plugin install https://github.com/gemini-cli-extensions/looker

claude

/plugin install looker@claude-plugins-official

codex plugin marketplace add GoogleCloudPlatform/data-agent-kit

codex plugin add looker@data-agent-kit

codex plugin marketplace upgrade data-agent-kit

Installing using open agent skills tool

You can install skills using the npx skills command.

1. Install the skills:

Run the following command in your terminal to automatically download and register the skills:

npx skills add https://github.com/gemini-cli-extensions/looker/tree/0.3.10

For detailed info check out the Skills npm package.

2. Set env vars: Set your environment vars as described in the configuration section.

Installing via a compatible Agent Plugins client

This repository is a valid Agent Plugins (v1) plugin. Any Agent Plugins–compatible client can install it directly using its own built-in plugin command — no extra tooling required — by pointing at this repository:

https://github.com/gemini-cli-extensions/looker

Beyond harnesses covered by the native install above, compatible clients include VS Code, Cursor, GitHub Copilot, and Kiro. See your agent's documentation for its exact install command.

Set env vars: Set your environment vars as described in the configuration section.

Usage Examples

Interact with Looker using natural language:

• Explore Data:
  • "Show me the top 10 products by sales in the last month."
  • "What is the average order value by region?"
• Manage Content:
  • "Create a new dashboard titled 'Executive Overview' with tiles for revenue and user growth."
  • "Find all dashboards related to 'Marketing' and list their tiles."
• Develop LookML:
  • "Create a new view for the 'users' table in the 'e-commerce' project."
  • "Add a new measure 'total_revenue' to the 'orders' view."

Supported Skills

The following skills are available in this repository:

• Looker - These skills are designed for data discovery and business intelligence.
• Looker Development - These skills are built for LookML developers, data engineers, and administrators who manage the backbone of Looker.

Troubleshooting

Use the debug mode of your agent (e.g., gemini --debug) to enable debugging.

Common issues:

• "✖ Error during discovery for server: MCP error -32000: Connection closed": The database connection has not been established. Ensure your configuration is set via environment variables.
• "✖ MCP ERROR: Error: spawn /Users/USER/.gemini/extensions/cloud-sql-sqlserver/toolbox ENOENT": The Toolbox binary did not download correctly. Ensure you are using Gemini CLI v0.6.0+.
• "cannot execute binary file": The Toolbox binary did not download correctly. Ensure the correct binary for your OS/Architecture has been downloaded. See Installing the server for more information.