mcpField
A
adk-infra-expert

adk-infra-expert

github.com/jeremylongshoreCloud & DevOps2.9k37 installsUpdated 2d ago
Repository

About adk-infra-expert

adk-infra-expert is a skill for generating and validating Terraform infrastructure for Vertex AI ADK deployments. It helps teams apply security controls and produce a deployment checklist and validation report.

Key features

  1. 01Terraform module generation and validation
  2. 02Secure VPC and Private Service Connect setup
  3. 03Least-privilege IAM configuration
  4. 04Agent Engine, Code Execution, and Memory Bank setup
  5. 05VPC Service Controls and monitoring
  6. 06Deployment validation and checklist

Use cases

  1. 01Provisioning infrastructure for a Vertex AI ADK agent
  2. 02Applying enterprise network and IAM constraints
  3. 03Reviewing deployment components and configuration

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace --skill adk-infra-expert

After installing, type/adk-infra-expertin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
ARD.md
errors.md
examples.md
implementation.md
PRD.md
scripts/
init-terraform.sh

Details

From the project README

Adk Infra Expert

Overview

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).

Prerequisites

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

Instructions

  1. Initialize Terraform: Set up backend for remote state storage
  2. Configure Variables: Define project_id, region, agent configuration
  3. Provision VPC: Create network infrastructure with Private Service Connect
  4. Set Up IAM: Create service accounts with least privilege roles
  5. Deploy Agent Engine: Configure runtime with code execution and memory bank
  6. Enable VPC-SC: Apply service perimeter for data exfiltration protection
  7. Configure Monitoring: Set up Cloud Monitoring dashboards and alerts
  8. Validate Deployment: Test agent endpoint and verify all components

Output

  • 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.

Error Handling

See ${CLAUDE_SKILL_DIR}/references/errors.md for comprehensive error handling.

Examples

See ${CLAUDE_SKILL_DIR}/references/examples.md for detailed examples.

Resources

Comments

Markdown supported