adk-deployment-specialist
Deploy and orchestrate Vertex AI ADK agents using A2A protocol. Manages AgentCard discovery, task submission, Code Execution Sandbox, and Memory Bank. Use when asked to "deploy ADK agent" or "orchestrate agents".
When & Why to Use This Skill
The Adk Deployment Specialist is a professional-grade Claude skill designed to streamline the deployment and orchestration of Vertex AI ADK agents. It leverages the A2A (Agent-to-Agent) protocol to manage complex multi-agent workflows, including AgentCard discovery, task submission, and stateful conversation management via Memory Banks. By automating the integration with Google Cloud's Vertex AI Agent Engine, it enables developers to build, test, and scale production-ready AI agent architectures with built-in security and observability.
Use Cases
- Multi-Agent System Orchestration: Designing and deploying complex AI workflows that require multiple agents to collaborate using sequential, parallel, or loop patterns.
- Automated Cloud Deployment: Streamlining the deployment of AI agents to Vertex AI Agent Engine runtimes, including the configuration of AgentCard endpoints and A2A interfaces.
- Secure Code Execution: Utilizing the Code Execution Sandbox for safe GCP operations and infrastructure-as-code tasks within an agentic framework.
- Stateful AI Interactions: Implementing long-term memory and context retention across distributed agent systems using the integrated Memory Bank feature.
- Enterprise CI/CD Integration: Incorporating AI agent deployment into DevOps pipelines with support for Workload Identity Federation and automated endpoint verification.
| name | adk-deployment-specialist |
|---|---|
| description | | |
| allowed-tools | Read, Write, Edit, Grep, Glob, Bash(cmd:*) |
| version | 1.0.0 |
| author | Jeremy Longshore <jeremy@intentsolutions.io> |
| license | MIT |
Adk Deployment Specialist
Overview
Expert in building and deploying production multi-agent systems using Google's Agent Development Kit (ADK). Handles agent orchestration (Sequential, Parallel, Loop), A2A protocol communication, Code Execution Sandbox for GCP operations, Memory Bank for stateful conversations, and deployment to Vertex AI Agent Engine.
Prerequisites
- A Google Cloud project with Vertex AI enabled (and permissions to deploy Agent Engine runtimes)
- ADK installed (and pinned to the project’s supported version)
- A clear agent contract: tools required, orchestration pattern, and deployment target (local vs Agent Engine)
- A plan for secrets/credentials (OIDC/WIF where possible; never commit long-lived keys)
Instructions
- Confirm the desired architecture (single agent vs multi-agent) and orchestration pattern (Sequential/Parallel/Loop).
- Define the AgentCard + A2A interfaces (inputs/outputs, task submission, and status polling expectations).
- Implement the agent(s) with the minimum required tool surface (Code Execution Sandbox and/or Memory Bank as needed).
- Test locally with representative prompts and failure cases, then add smoke tests for deployment verification.
- Deploy to Vertex AI Agent Engine and validate the generated endpoints (
/.well-known/agent-card, task send/status APIs). - Add observability: logs, dashboards, and retry/backoff behavior for transient failures.
Output
- Agent source files (or patches) ready for deployment
- Deployment commands/config (e.g.,
adk deployinvocation + required flags) - A verification checklist for Agent Engine endpoints (AgentCard + task APIs) and security posture
Error Handling
See {baseDir}/references/errors.md for comprehensive error handling.
Examples
See {baseDir}/references/examples.md for detailed examples.
Resources
- ADK docs: https://cloud.google.com/vertex-ai/docs/agent-engine
- Workload Identity (CI/CD): https://cloud.google.com/iam/docs/workload-identity-federation
- A2A / AgentCard patterns: see
000-docs/6767-a-SPEC-DR-STND-claude-code-plugins-standard.md