Google Agents Cli Onboarding

作者 google55b4e13eba6d無授權條款21K 個星標收錄於 2026年10月8日更新於 2026年10月8日儲存庫今天更新

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.

精選僅含說明AI & AgentsDevOps & Cloud
AI 產生的概覽

引導安裝 Google agents-cli,並將代理程式開發工作導向各專用生命週期技能的入口技能。

功能
這個技能是 agents-cli 的入門入口,agents-cli 是 Google 用來在 Gemini Enterprise Agent Platform 上建置、評估及部署 AI 代理程式的工具組。它說明一次性安裝指令,提供將八個開發階段對應到專用技能的表格,並列出主要 CLI 指令。它產出的是指引與記錄下來的代理程式規格,而非程式碼或檔案。
適用情境
當使用者想使用 ADK 與 agents-cli 建立、開發、執行、偵錯、測試、評估、部署、發布或監控代理程式時使用。它適用於載入專用工作流程技能之前的初始安裝與入門階段。
執行需求
需要 agents-cli 工具,透過 uvx 或 npx 安裝,並需要網路存取以下載。後續部署階段隱含需要 Google Cloud 存取權。這個技能不隨附指令碼,僅為說明性內容。

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

來源與署名

來源:google/skills位於skills/cloud/google-agents-cli-onboarding提交55b4e13

授權條款: 無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架

更多來自 google/skills 的技能

Dpop Adoption

google

精選

指導為 Google OAuth 平台實作 OAuth 2.0 DPoP(RFC 9449)傳送方約束的更新權杖。

Security21K今天更新

Finding Google Skills

google

精選

Google platform decision and setup guidance, loaded on demand from Google's skill catalog. Use when a developer is choosing or setting up part of their stack, such as where to run a service, a database, storage, messaging, authentication, analytics, ads, or AI model serving, and a Google product is a reasonable candidate - whether or not a vendor is named - or when a request names a Google product or API. Brings in the matching Google skill so the answer can weigh Google options, their trade-offs, and when they are not the right fit. Skip when the stack is already settled on another provider and no Google product is named, or the task involves no platform choice.

待分類21K今天更新

Spanner Basics

google

精選

指導 Google Cloud Spanner 的執行個體與資料庫管理、結構定義設計、查詢與效能診斷。

Data & Analytics21K今天更新

Secops Triage

google

精選

引導 SOC 分析師對 Google SecOps 安全警示進行分診,從調查到結案或升級。

Security21K今天更新

Secops Investigate

google

精選

指導 SOC 分析師在 Google SecOps 中使用 UDM 查詢與時間軸進行深入的安全事件與實體調查。

Security21K今天更新

Secops Hunt

google

精選

指導在 Google SecOps 中使用 UDM 查詢、IoC 回溯、普遍性與異常分析進行主動威脅狩獵。

Security21K今天更新