Google Agents Cli Onboarding

by google55b4e13eba6dNo licenseListed Oct 8, 2026Updated Oct 8, 2026

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.

FeaturedInstructions onlyAI & AgentsDevOps & Cloud
AI-generated overview

Entrypoint skill that guides setup of Google's agents-cli and routes agent development tasks to specialized lifecycle skills.

What it does
This skill acts as the onboarding entrypoint for agents-cli, Google's toolkit for building, evaluating, and deploying AI agents on the Gemini Enterprise Agent Platform. It explains the one-time setup commands, presents a table mapping eight development phases to specialized skills, and lists key CLI commands. It produces guidance and a documented agent spec rather than code or files.
When to use it
Use it when a user wants to create, develop, run, debug, test, evaluate, deploy, publish, or monitor an agent using ADK and agents-cli. It is meant for the initial setup and orientation step before loading a specialized workflow skill.
Requirements
Requires the agents-cli tooling, installed via uvx or npx, and network access to fetch it. Google Cloud access is implied for later deployment phases. The skill ships no scripts; it is instructions only.

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:

bash
uvx google-agents-cli setup

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

bash
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:

PhaseSpecialized SkillPurpose / When to Load
0 — Understandgoogle-agents-cli-workflowClarify intent. Define the agent spec in .agents-cli-spec.md before coding.
1 — Studygoogle-agents-cli-workflowLeverage samples. Study existing agent samples (e.g., ambient-expense) before scaffolding.
2 — Scaffoldgoogle-agents-cli-scaffoldCreate/Enhance. Initialize the project structure, CI/CD, and infrastructure templates.
3 — Buildgoogle-agents-cli-adk-codeImplement. Write agent logic, tools, callbacks, and manage state using ADK APIs.
4 — Evaluategoogle-agents-cli-evalValidate Quality. Run systematic evaluations (LLM-as-judge).
5 — Deploygoogle-agents-cli-deployGo Production. Deploy to Agent Runtime (Vertex AI), Cloud Run, or GKE.
6 — Publishgoogle-agents-cli-publishRegister. Make your agent available as a tool in Gemini Enterprise.
7 — Observegoogle-agents-cli-observabilityMonitor. 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:

CommandDescription
agents-cli setupInstall the CLI and configure skills in your coding agent.
agents-cli scaffold <name>Create a new agent project from a template.
agents-cli eval runRun the agent and grade the traces in a single step (generate + grade).
agents-cli deployDeploy your agent to Google Cloud (Agent Runtime, Cloud Run, GKE).
agents-cli publish gemini-enterpriseRegister 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:

  1. 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.
  2. Verify Installation: Run agents-cli info to confirm the installation and view the active project configuration.
  3. 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

Source and attribution

Source:google/skillsinskills/cloud/google-agents-cli-onboardingat commit55b4e13

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

More from google/skills

Google Cloud Solution N Tier Serverless Web App

google

Featured

Guides design and Terraform implementation of secure n-tier serverless web apps on Google Cloud.

DevOps & CloudOct 8, 2026

Google Cloud Solution Hybrid Search Alloydb

google

Featured

Discovers requirements and generates architectural, design, and deployment guidance for dynamic hybrid search systems by combining semantic search and keyword search. Optimized for AlloyDB hybrid search use cases in Google Cloud. Use when users need vector search combined with structured SQL filtering, faceted attributes, semantic reranking, in-database AI validation, or serverless hosting across transactional relational databases, analytical data warehouses, or managed database engines. DON'T use this skill for simple keyword-only search, or when a standalone non-relational vector database is required.

Awaiting classificationOct 8, 2026

Google Cloud Solution Architecture

google

Featured

Interactively discovers requirements and designs holistic, multi-product system architectures, solution blueprints, and deployment recommendations for complex workloads on Google Cloud. Use when designing end-to-end cloud solutions, selecting and integrating Google Cloud services, generating architecture diagrams, or conducting requirements discovery for new cloud workloads or migrations. Don't use for single-product tasks (use product-specific skills), initial onboarding or authentication (use google-cloud-recipe-*), Well-Architected Framework reviews or audits (use google-cloud-waf-*), or workloads covered by specialized solution skills.

Awaiting classificationOct 8, 2026

Google Cloud Solution Agentic Ai Data Science Workflow

google

Featured

Designs a tailored multi-product agentic data science architecture on Google Cloud that incorporates opinionated best practices. Use when architecting multi-product solutions for agent-based data analytics or ML workloads. Don't use for simple queries, non-agentic pipelines, general cloud reviews, or writing agent code.

Awaiting classificationOct 8, 2026

Google Cloud Solution Agentic Ai Borderless Data Lakehouse

google

Featured

Discovers requirements and designs a borderless open data lakehouse using Lakehouse for Apache Iceberg and BigQuery data agents. Use when architecting multi-cloud storage infrastructure (Cloud Storage, AWS S3, Azure Blob), establishing ingestion and AI serving subsystems, configuring Cross-Cloud Interconnect, or deploying Gemini Enterprise Agent Platform and BigQuery data agents. Don't use for single-cloud data warehouses, or when the focus is on Knowledge Catalog metadata governance and Spark-driven IDE analytics workflows (use google-cloud-solution-agentic-analytics-spark-knowledge-catalog instead).

Awaiting classificationOct 8, 2026

Google Cloud Solution Agentic Ai Bidirectional Streaming

google

Featured

Guides agents to interactively discover customer requirements for live, bidirectional multi-agent AI systems that process continuous streams of multimodal data for real-time technical guidance and safety monitoring. Generates a custom Google Cloud solution that uses opinionated best practices and architecture guidance. Use when users need agentic assistance to design and create a multi-product solution in the cloud for live bidirectional multimodal streaming workloads. Don't use for simple text-based chat applications or workloads without real-time streaming requirements.

Awaiting classificationOct 8, 2026