google-agents-cli

Automate AI agent creation, evaluation, and deployment for Gemini Enterprise.

4|Updated May 16, 2026

Search Tags:#deployment #rag #evaluation #adk #cloud run #gemini enterprise #agents-cli

Ready to run

npx skills add https://github.com/Aradotso/devtools-skills --skill google-agents-cli

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: google-agents-cli
Source: https://github.com/Aradotso/devtools-skills/tree/main/skills/google-agents-cli
Command: npx skills add https://github.com/Aradotso/devtools-skills --skill google-agents-cli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Building AI agents for Google Cloud’s Gemini Enterprise environment is difficult to set up correctly from scaffolding through deployment, especially when you also need evaluation and observability.

Core Features & Use Cases

Scaffold ADK agent projects: Generate an opinionated project structure for agents-cli/ADK with common best practices.
Run and test agents locally: Execute prompts, stream outputs, install dependencies, and lint to speed iteration.
Evaluate agent quality: Run evalsets, compare results, and apply custom metrics (including LLM-as-judge patterns).
Deploy to Google Cloud: Provision infrastructure and deploy to targets such as Cloud Run, with environment config and CI/CD templates.
Publish to Gemini Enterprise: Register agent metadata so it can run within Gemini Enterprise workflows.

Quick Start

Install and scaffold a new agent project named my-agent by running uvx google-agents-cli setup.

Frequently Asked Questions about google-agents-cli

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build and deploy Gemini agents for Google Cloud end-to-end?▼

You can build and deploy Gemini agents by scaffolding an ADK project, running local evaluations, and using agents-cli to provision infrastructure and publish directly to Gemini Enterprise.

What is the best way to evaluate AI agents before deploying to Cloud Run?▼

Evaluating AI agents requires running evalsets locally, comparing results, and applying custom metrics like LLM-as-judge patterns, which this tool automates to validate agent quality before Cloud Run deployment.

Do I need to set up Google authentication to deploy agents to Gemini Enterprise?▼

Yes, deploying agents to Gemini Enterprise requires Google authentication configured via agents-cli login or by setting a GOOGLE_API_KEY environment variable for API access.

Can I use RAG datastore connectivity with my ADK agent project?▼

Yes, you can configure optional RAG datastore connectivity when setting up your ADK agent project to support retrieval-augmented generation use cases within Gemini Enterprise.

How does scaffolding a new agents-cli project work?▼

Scaffolding a new agents-cli project generates an opinionated directory structure with common best practices, which you initialize by running the uvx google-agents-cli setup command.

What are the limitations of deploying ADK agents to Gemini Enterprise?▼

Deployment requires specific prerequisites including the agents-cli toolchain, proper Google authentication, and configured deployment targets, limiting use to provisioned Google Cloud infrastructure like Cloud Run.