google/skills · Apache-2.0

google-agents-cli-onboarding

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.

agents cloud stable

Google Agents CLI Onboarding

> [!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 setup
>

> Alternatively, to install only the expert skills and let the agent handle

> execution:

> npx skills add google/agents-cli
>

Overview

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.

The Agent Development Lifecycle

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.

Key CLI Commands

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`.*

Next Steps

Follow this sequence to initiate the development workflow:

Execute Setup: Run the uvx or npx command in the [!TIP] box above

to install the CLI and enable the specialized skills in your environment.

Verify Installation: Run agents-cli info to confirm the installation

and view the active project configuration.

Initiate Phase 0: Ask the user for their core requirements (agent

purpose, external tools, deployment target) and document them in

.agents-cli-spec.md before writing any code.

Reporting Issues

Report bugs or improvements at Google Agents CLI Issues.

Supporting Links

Google Agents CLI Documentation

Provenance

Authored by Google LLC in google/skills. The content is mirrored here under its upstream license.

agent-platform-alert-configuration Configures best-practice alerting policies for AI agents using OpenTelemetry (OTel) metrics, generating output as Terraform (.tf) configuration files. Use when analyzing, writing, or deploying alerting policies to monitor agent latency, error rates, token usage, and quality metrics. Don't use for standard infrastructure monitoring unrelated to AI agents, or when the agent is not instrumented with OpenTelemetry (for Reliability, Cost, Safety, Security alerts). NOTE: Reliability, Cost, Safety, and Security alerts use generic OTel metrics and work across runtimes (such as Cloud Run, Vertex AI). Quality alerts rely on Vertex AI Online Monitors and are strictly bound to Vertex AI deployments. google/skills Apache-2.0 agent-platform-deploy Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up resources by undeploying models and deleting endpoints. Use when asked to actively deploy a model, list the Model Garden CATALOG of available models, check if a specific model is deployable (`gcloud ai model-garden models list-deployment-config`), query deployment cost, troubleshoot deployment errors (like quota limits), or undeploy/clean up endpoints. Also use when copying and deploying a 1P Tuned Model. Don't use for pure listing/discovery questions of the form "is X deployed?", "list my endpoints", or "which regions have models running?" — for those use `agent-platform-endpoint-management`. Don't use for public Vertex AI deployments (use the `vertex-deploy` skill) or for running model evaluations (use the `agent-platform-eval-flywheel` skill). google/skills Apache-2.0 agent-platform-endpoint-management Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model evaluations. google/skills Apache-2.0 agent-platform-eval-flywheel Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on Agent Platform eval methodology — including dataset schema, LLM-as-judge scoring, and common failure causes. For fine-tuning, use agent-platform-tuning. For general production deployment, use agent-platform-deploy. google/skills Apache-2.0 agent-platform-inference Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when asked to perform inference, ask a model a question, run a test prompt, execute chat completions, or generate code for calling Gemini or OpenMaaS models, authenticate with GenAI SDK, OpenAI SDK, or legacy Agent Platform SDK, configure base URLs and global/regional endpoints, or troubleshoot 429 Resource Exhausted (DSQ), 400 User Validation, or 404 Not Found errors. Don't use for deploying models to endpoints or for running model evaluations. google/skills Apache-2.0