Set up Google's agents-cli and find the right workflow for building AI agents. Connects requirements planning, project creation, implementation, evaluation, deployment, publishing, and monitoring through specialized skills for the Gemini Enterprise Agent Platform.
Onboarding entrypoint for agents-cli in Agent Platform. It should be used when the user wants to "create a new agent", "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent", "evaluate an agent", "deploy an agent", "publish an agent", "monitor an agent", or needs the ADK (Agent Development Kit) development lifecycle.
Review the instructions the agent will receive before you install.
[!TIP] One-Time Setup: To install the CLI and enable all 7 specialized development skills in your coding agent, run the setup command:
uvx google-agents-cli setupAlternatively, to install only the expert skills and let the agent handle execution:
npx skills add google/agents-cli
This skill serves as the entrypoint for agents-cli — Google's toolkit for building, evaluating, and deploying AI agents on the Gemini Enterprise Agent Platform.
Use this skill to perform the initial setup and identify the correct specialized workflows for your task.
After running the setup, the following specialized skills become available and will activate automatically based on your requests. Use this table to identify which skill to load for your current phase:
| Phase | Specialized Skill | Purpose / When to Load |
|---|---|---|
| 0 — Understand | google-agents-cli-workflow | Clarify intent. Define the agent spec in .agents-cli-spec.md before coding. |
| 1 — Study | google-agents-cli-workflow | Leverage samples. Study existing agent samples (e.g., ambient-expense) before scaffolding. |
| 2 — Scaffold | google-agents-cli-scaffold | Create/Enhance. Initialize the project structure, CI/CD, and infrastructure templates. |
| 3 — Build | google-agents-cli-adk-code | Implement. Write agent logic, tools, callbacks, and manage state using ADK APIs. |
| 4 — Evaluate | google-agents-cli-eval | Validate Quality. Run systematic evaluations (LLM-as-judge). |
| 5 — Deploy | google-agents-cli-deploy | Go Production. Deploy to Agent Runtime (Vertex AI), Cloud Run, or GKE. |
| 6 — Publish | google-agents-cli-publish | Register. Make your agent available as a tool in Gemini Enterprise. |
| 7 — Observe | google-agents-cli-observability | Monitor. Set up Cloud Trace, prompt-response logging, and BigQuery analytics. |
Below are the primary commands you will use throughout the development lifecycle:
| Command | Description |
|---|---|
agents-cli setup | Install the CLI and configure skills in your coding agent. |
agents-cli scaffold <name> | Create a new agent project from a template. |
agents-cli eval run | Run the agent and grade the traces in a single step (generate + grade). |
agents-cli deploy | Deploy your agent to Google Cloud (Agent Runtime, Cloud Run, GKE). |
agents-cli publish gemini-enterprise | Register your deployed agent with Gemini Enterprise. |
For the full list of available commands and global options, run agents-cli --help.
Follow this sequence to initiate the development workflow:
uvx or npx command in the [!TIP] box above
to install the CLI and enable the specialized skills in your environment.agents-cli info to confirm the installation
and view the active project configuration..agents-cli-spec.md before writing any code.Report bugs or improvements at Google Agents CLI Issues.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Create Terraform files that define alerts for AI agent latency, errors, token use, safety, security, and response quality. Check telemetry and existing policies first, then validate the generated configuration. Quality alerts require Vertex AI.
Deploy Model Garden models to Agent Platform endpoints, the addresses used for model requests. Check supported hardware and estimated hourly costs, inspect deployment progress, test predictions, and remove deployed resources after use.
Manages Agent Platform endpoints, the stable URLs used to serve online model predictions. It supports listing, inspecting, creating, updating, and deleting endpoints, plus troubleshooting permission errors, quota limits, and resources that are busy.
Evaluate AI models and agents on Google Cloud using test datasets and scoring criteria. Generate simulated user scenarios, analyze failures, and compare results across changes to guide improvements to prompts and code.
Call Gemini and OpenMaaS models such as Llama, DeepSeek, and Qwen through Google Cloud Agent Platform. Prepare authentication and SDK code, run prompts, configure connection endpoints, and troubleshoot common request errors.
Guides migration from Google AI Studio’s Gemini API to Gemini Enterprise Agent Platform on Google Cloud, covering billing, access permissions, authentication, and connection settings for SDKs and supported agent tools.