Back to Details

adk-agent-builder

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

ADK Agent Builder

ADK Agent构建工具

Build production-ready agents with Google’s Agent Development Kit (ADK): scaffolding, tool wiring, orchestration patterns, testing, and optional deployment to Vertex AI Agent Engine.
使用Google的Agent Development Kit（ADK）构建可用于生产环境的Agent：包括脚手架搭建、工具连接、编排模式、测试，以及可选的部署至Vertex AI Agent Engine的功能。

Overview

概述

  • Creates a minimal, production-oriented ADK scaffold (agent entrypoint, tool registry, config, and tests).
  • Supports single-agent ReAct-style workflows and multi-agent orchestration (Sequential/Parallel/Loop).
  • Produces a validation checklist suitable for CI (lint/tests/smoke prompts) and optional Agent Engine deployment verification.
  • 创建面向生产环境的极简ADK脚手架（Agent入口、工具注册表、配置文件和测试用例）。
  • 支持单Agent的ReAct风格工作流和多Agent编排（顺序/并行/循环模式）。
  • 生成适用于CI的验证清单（代码检查/测试/冒烟提示），以及可选的Agent Engine部署验证步骤。

Prerequisites

前置条件

  • Python runtime compatible with your project (often Python 3.10+)
  • google-adk
    installed and importable
  • If deploying: access to a Google Cloud project with Vertex AI enabled and permissions to deploy Agent Engine runtimes
  • Secrets available via environment variables or a secret manager (never hardcoded)
  • 与项目兼容的Python运行时环境（通常为Python 3.10+）
  • 已安装并可导入
    google-adk
  • 若需部署：拥有启用Vertex AI的Google Cloud项目访问权限，以及部署Agent Engine运行时的权限
  • 机密信息通过环境变量或机密管理器获取（切勿硬编码）

Instructions

操作步骤

  1. Confirm scope: local-only agent scaffold vs Vertex AI Agent Engine deployment.
  2. Choose an architecture:
    • Single agent (ReAct) for adaptive tool-driven tasks
    • Multi-agent system (specialists + orchestrator) for complex, multi-step workflows
  3. Define the tool surface (built-in ADK tools + any custom tools you need) and required credentials.
  4. Scaffold the project: 
    • src/agents/
      , 
      src/tools/
      , 
      tests/
      , and a dependency file (
      pyproject.toml
      or 
      requirements.txt
      )
  5. Implement the minimum viable agent and a smoke test prompt; add regression tests for tool failures.
  6. If deploying, produce an 
    adk deploy ...
    command and a post-deploy validation checklist (AgentCard/task endpoints, permissions, logs).
  1. 确认范围：仅本地Agent脚手架 或 部署至Vertex AI Agent Engine。
  2. 选择架构：
    • 单Agent（ReAct）：适用于自适应工具驱动型任务
    • 多Agent系统（专家Agent + 编排器）：适用于复杂的多步骤工作流
  3. 定义工具范围（ADK内置工具 + 所需的任何自定义工具）及必要的凭证。
  4. 搭建项目脚手架：
    • 生成
      src/agents/
      、
      src/tools/
      、
      tests/
      目录，以及依赖文件（
      pyproject.toml
      或
      requirements.txt
      ）
  5. 实现最小可行Agent和冒烟测试提示；添加针对工具故障的回归测试。
  6. 若需部署，生成
    adk deploy ...
    命令以及部署后验证清单（AgentCard/任务端点、权限、日志）。

Output

输出内容

  • A repo-ready ADK scaffold (files and directories) plus starter agent code
  • Tool stubs and wiring points (where to add new tools safely)
  • A test + validation plan (unit tests and a minimal smoke prompt)
  • Optional: deployment commands and verification steps for Agent Engine
  • 可直接用于仓库的ADK脚手架（文件和目录）及初始Agent代码
  • 工具存根和安全添加新工具的连接点
  • 测试与验证计划（单元测试和最小冒烟提示）
  • 可选：Agent Engine的部署命令和验证步骤

Error Handling

错误处理

  • Dependency/runtime issues: provide pinned install commands and validate imports.
  • Auth/permission failures: identify the missing role/API and propose least-privilege fixes.
  • Tool failures/rate limits: add retries/backoff guidance and a regression test to prevent recurrence.
  • 依赖/运行时问题：提供固定版本的安装命令并验证导入情况。
  • 认证/权限失败：识别缺失的角色/API，并建议最小权限原则的修复方案。
  • 工具故障/速率限制：添加重试/退避策略指导，并编写回归测试以防止问题复发。

Examples

示例

Example: Scaffold a single ReAct agent
  • Request: “Create an ADK agent that summarizes PRs and proposes test updates.”
  • Result: agent entrypoint + tool registry + a smoke test command for local verification.
Example: Multi-agent orchestrator
  • Request: “Build a supervisor + deployer + verifier team and deploy to Agent Engine.”
  • Result: orchestrator skeleton, per-agent responsibilities, and 
    adk deploy ...
    + post-deploy health checks.
示例：搭建单ReAct Agent脚手架
  • 请求：“创建一个能总结PR并提出测试更新建议的ADK Agent。”
  • 结果：Agent入口 + 工具注册表 + 用于本地验证的冒烟测试命令。
示例：多Agent编排器
  • 请求：“构建一个包含监督者、部署者、验证者的Agent团队，并部署至Agent Engine。”
  • 结果：编排器框架、各Agent职责，以及
    adk deploy ...
    命令 + 部署后健康检查步骤。

Resources

资源

  • Full detailed guide (kept for reference): 
    {baseDir}/references/SKILL.full.md
  • Repo standards (source of truth): 
    • 000-docs/6767-a-SPEC-DR-STND-claude-code-plugins-standard.md
    • 000-docs/6767-b-SPEC-DR-STND-claude-skills-standard.md
  • ADK / Agent Engine docs: https://cloud.google.com/vertex-ai/docs/agent-engine
  • 完整详细指南（供参考）：
    {baseDir}/references/SKILL.full.md
  • 仓库标准（权威来源）： 
    • 000-docs/6767-a-SPEC-DR-STND-claude-code-plugins-standard.md
    • 000-docs/6767-b-SPEC-DR-STND-claude-skills-standard.md
  • ADK / Agent Engine文档：https://cloud.google.com/vertex-ai/docs/agent-engine