google-agents-cli-onboarding

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

[!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

[!提示] 一次性设置：如需安装CLI并在你的编码Agent中启用全部7项专业开发技能，请运行以下设置命令：
bash
uvx google-agents-cli setup
或者，若仅需安装专家技能并让Agent处理执行流程：
bash
npx skills add google/agents-cli

Overview

概述

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.

本技能是agents-cli的入口——agents-cli是谷歌推出的工具包，用于在Gemini Enterprise Agent Platform上构建、评估和部署AI Agent。

使用本技能完成初始设置，并为你的任务确定合适的专业工作流。

The Agent Development Lifecycle

Agent开发生命周期

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.

运行设置后，以下专业技能将可用，并会根据你的请求自动激活。使用下表确定当前阶段应加载的技能：

阶段	专业技能	用途/加载时机
0 — 需求梳理	`google-agents-cli-workflow`	明确意图：在编码前，在 `.agents-cli-spec.md` 中定义Agent规格。
1 — 参考学习	`google-agents-cli-workflow`	参考示例：在搭建项目前，学习现有Agent示例（如 `ambient-expense` ）。
2 — 项目搭建	`google-agents-cli-scaffold`	创建/优化：初始化项目结构、CI/CD和基础设施模板。
3 — 开发构建	`google-agents-cli-adk-code`	功能实现：使用ADK API编写Agent逻辑、工具、回调函数并管理状态。
4 — 质量评估	`google-agents-cli-eval`	验证质量：运行系统性评估（LLM作为评判者）。
5 — 部署上线	`google-agents-cli-deploy`	投入生产：部署至Agent Runtime（Vertex AI）、Cloud Run或GKE。
6 — 发布注册	`google-agents-cli-publish`	注册生效：让你的Agent在Gemini Enterprise中作为工具可用。
7 — 监控观测	`google-agents-cli-observability`	监控运维：设置Cloud Trace、提示-响应日志记录和BigQuery分析。

Key CLI Commands

核心CLI命令

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
.

以下是开发生命周期中会用到的主要命令：

命令	描述
`agents-cli setup`	安装CLI并在你的编码Agent中配置技能。
`agents-cli scaffold <name>`	从模板创建新的Agent项目。
`agents-cli eval run`	运行Agent并一步完成轨迹评分（生成+评分）。
`agents-cli deploy`	将Agent部署至谷歌云（Agent Runtime、Cloud Run、GKE）。
`agents-cli publish gemini-enterprise`	将已部署的Agent注册到Gemini Enterprise。

如需查看完整命令列表和全局选项，请运行
agents-cli --help
。

Next Steps

后续步骤

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.

按照以下流程启动开发工作流：

执行设置：运行上方[!提示]框中的
```
uvx
```
或
```
npx
```
命令，安装CLI并在你的环境中启用专业技能。
验证安装：运行
```
agents-cli info
```
确认安装完成，并查看当前项目配置。
启动阶段0：询问用户核心需求（Agent用途、外部工具、部署目标），并在编写代码前将其记录在
```
.agents-cli-spec.md
```
中。