adk-infra-expert
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseAdk Infra Expert
Adk Infra 专家
Overview
概述
Provision production-grade Vertex AI ADK infrastructure with Terraform: secure networking, least-privilege IAM, Agent Engine runtime, Code Execution sandbox defaults, and Memory Bank configuration. Use this skill to generate/validate Terraform modules and a deployment checklist that matches enterprise security constraints (including VPC Service Controls when required).
使用Terraform预置生产级别的Vertex AI ADK基础设施:包括安全网络、最小权限IAM、Agent Engine运行时、代码执行沙箱默认配置以及Memory Bank配置。使用此技能可生成/验证符合企业安全约束的Terraform模块和部署清单(包括必要时的VPC服务控制)。
Prerequisites
前提条件
Before using this skill, ensure:
- Google Cloud project with billing enabled
- Terraform 1.0+ installed
- gcloud CLI authenticated with appropriate permissions
- Vertex AI API enabled in target project
- VPC Service Controls access policy created (for enterprise)
- Understanding of Agent Engine architecture and requirements
使用此技能前,请确保:
- 已启用计费的Google Cloud项目
- 已安装Terraform 1.0+
- gcloud CLI已通过具备适当权限的账号认证
- 目标项目中已启用Vertex AI API
- 已创建VPC服务控制访问策略(面向企业用户)
- 了解Agent Engine的架构和需求
Instructions
操作步骤
- Initialize Terraform: Set up backend for remote state storage
- Configure Variables: Define project_id, region, agent configuration
- Provision VPC: Create network infrastructure with Private Service Connect
- Set Up IAM: Create service accounts with least privilege roles
- Deploy Agent Engine: Configure runtime with code execution and memory bank
- Enable VPC-SC: Apply service perimeter for data exfiltration protection
- Configure Monitoring: Set up Cloud Monitoring dashboards and alerts
- Validate Deployment: Test agent endpoint and verify all components
- 初始化Terraform:设置远程状态存储的后端
- 配置变量:定义project_id、区域、Agent配置
- 预置VPC:使用Private Service Connect创建网络基础设施
- 配置IAM:创建具备最小权限角色的服务账号
- 部署Agent Engine:配置带有代码执行和Memory Bank的运行时
- 启用VPC-SC:应用服务边界以防止数据泄露
- 配置监控:设置Cloud Monitoring仪表板和告警
- 验证部署:测试Agent端点并验证所有组件
Output
输出
- Configuration files or code changes applied to the project
- Validation report confirming correct implementation
- Summary of changes made and their rationale
See Terraform implementation details for output format specifications.
- 应用到项目的配置文件或代码变更
- 确认正确实施的验证报告
- 所做变更及其理由的摘要
有关输出格式规范,请参阅Terraform实现细节。
Error Handling
错误处理
See for comprehensive error handling.
${CLAUDE_SKILL_DIR}/references/errors.md有关全面的错误处理,请参阅${CLAUDE_SKILL_DIR}/references/errors.md。
Examples
示例
See for detailed examples.
${CLAUDE_SKILL_DIR}/references/examples.md有关详细示例,请参阅${CLAUDE_SKILL_DIR}/references/examples.md。
Resources
资源
- Agent Engine: https://cloud.google.com/vertex-ai/generative-ai/docs/agent-engine/overview
- VPC-SC: https://cloud.google.com/vpc-service-controls/docs
- Terraform Google Provider: https://registry.terraform.io/providers/hashicorp/google/latest
- ADK Terraform examples in ${CLAUDE_SKILL_DIR}/examples/
- Agent Engine:https://cloud.google.com/vertex-ai/generative-ai/docs/agent-engine/overview
- VPC-SC:https://cloud.google.com/vpc-service-controls/docs
- Terraform Google Provider:https://registry.terraform.io/providers/hashicorp/google/latest
- ADK Terraform示例:${CLAUDE_SKILL_DIR}/examples/