agent_engine_terraform_deployer

Name: agent_engine_terraform_deployer
Author: VeerMuchandi

15stars1forks

How to install agent_engine_terraform_deployer?

veermuchandi/rad-skills/agent_engine_terraform_deployer

$npx -y skills add VeerMuchandi/rad-skills --skill agent_engine_terraform_deployer

Installs into the current project.

Summary

Deploys ADK agents to Vertex AI Agent Engine using the standard Terraform pattern.

Files · 1

View on GitHub

SKILL.md

1	# Agent Engine Terraform Deployer Skill
2
3	This skill helps you deploy your Agent Development Kit (ADK) agent to Vertex AI Agent Engine using a robust, self-contained Terraform pattern. It implements the "Golden Project Structure" and automated packaging logic recommended by the ADK team.
4
5	## Official References
6	- Module Source: [github.com/GoogleCloudPlatform/cloud-foundation-fabric/modules/agent-engine](https://github.com/GoogleCloudPlatform/cloud-foundation-fabric/tree/master/modules/agent-engine)
7	- Documentation: [Agent Engine Module README](https://github.com/GoogleCloudPlatform/cloud-foundation-fabric/blob/master/modules/agent-engine/README.md)
8
9	## Capabilities
10	- Intelligent Preparation: Intelligently scans and updates `.ae_ignore`, `requirements.txt`, and `.env` for deployment readiness.
11	- Initialize Deployment: Sets up a `deploy/` directory with the golden `main.tf` template.
12	- Support for Multiple Sources:
13	- Local Source: Deploys from your local machine (ideal for dev).
14	- GitHub Source: Deploys directly from a GitHub repository (ideal for CI/CD).
15	- Auto-Packaging: Automatically packages your agent code, excluding bulky files.
16	- Non-Intrusive Wrapping: Dynamically generates an `app.py` wrapper during deployment.
17
18	## Prerequisites
19	- Terraform Version:
20	- Minimum: `v1.12.2`
21	- Recommended: `v1.14.4`
22	- [Download Terraform](https://releases.hashicorp.com/terraform/) if needed.
23	- GCP Project: Access to a Google Cloud Project with billing enabled.
24	- Permissions:
25	- `roles/aiplatform.user`
26	- `roles/storage.objectViewer`
27	- `roles/serviceusage.serviceUsageConsumer`
28	- `roles/cloudtrace.agent`
29
30	## 1. Golden Project Structure
31	Always separate your deployment logic from your agent code. This prevents Terraform from accidentally zipping up its own bulky provider binaries.
32
33	```text
34	my_project/
35	├── .ae_ignore # Patterns to exclude (caching, env files, etc.)
36	├── my_agent_package/ # YOUR AGENT FOLDER (must have __init__.py)
37	│ ├── agent.py # Root agent logic
38	│ ├── requirements.txt # Dependencies
39	│ └── ...
40	└── deploy/ # DEDICATED DEPLOYMENT FOLDER
41	└── main.tf # Self-contained Terraform logic
42	```
43
44	## 2. Configuration Reference
45
46	### Environment Variables (.env)
47	Ensure your agent's `.env` includes the following for proper observability:
48	```bash
49	# Enables agent traces and logs (excludes prompts/responses)
50	GOOGLE_CLOUD_AGENT_ENGINE_ENABLE_TELEMETRY=true
51
52	# Enables logging of input prompts and output responses
53	OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=true
54	```
55
56	### Dependencies (requirements.txt)
57	Your agent's `requirements.txt` MUST include:
58	```text
59	google-cloud-aiplatform[agent_engines,adk]
60	```
61
62	## 3. Workflow
63
64	### Step 0: Intelligent Agent Preparation (Automated)
65	Instead of manually creating files, run the provided helper script. It will intelligently scan your agent directory and generate/update `.ae_ignore`, `requirements.txt`, and `.env` with the correct configurations.
66
67	```bash
68	# Run the preparation script pointing to your agent directory (replace /path/to/your/agent)
69	python3 scripts/prepare_agent.py /path/to/your/agent
70	```
71
72	This script will:
73	1. Exclude Junk: Add robust exclusions to `.ae_ignore` (git, venve, terraform, `.zip`, `.pkl`, etc.).
74	2. Ensure Dependencies: Add `google-cloud-aiplatform[agent_engines,adk]` to `requirements.txt` if missing.
75	3. Enable Telemetry: Inject observability env vars into `.env` if not present.
76
77	### Option A: Local Deployment (Development)
78	Use this when you have the code on your machine.
79
80	1. Initialize:
81	```bash
82	mkdir -p deploy
83	# Copy templates/main_local.tf to deploy/main.tf
84	```
85	2. Configure (`deploy/terraform.tfvars`):
86	```hcl
87	project_id = "your-project-id"
88	region = "us-central1"
89	agent_engine_name = "epp-telecom-concierge"
90	agent_folder_name = "epp_telecom_concierge"
91	```
92	3. Deploy:
93	```bash
94	cd deploy && terraform init && terraform apply
95	```
96
97	### Option B: GitHub Deployment (CI/CD)
98	Use this to deploy code from a remote repository.
99
100	1. Initialize:
101	```bash
102	mkdir -p deploy
103	# Copy templates/main_github.tf to deploy/main.tf
104	```
105	2. Configure (`deploy/terraform.tfvars`):
106	```hcl
107	project_id = "your-project-id"
108	region = "us-central1"
109	agent_engine_name = "epp-telecom-concierge"
110	github_repo = "username/repo"
111	github_branch = "main"
112	agent_package_name = "epp_telecom_concierge"
113	```
114	3. Deploy:
115	```bash
116	cd deploy && terraform init && terraform apply
117	```
118
119	## 4. Critical Learnings & Troubleshooting
120
121	### A. The "ResourceExhausted" (256MB) Limit
122	The Issue: Terraform's `inline_source`

People who liked this also viewed

6 picks

Type

microsoft-foundryDeploy, evaluate, fine-tune, and manage Foundry agents end-to-end with azd: hosted agent scaffold/run/deploy, prompt agent create, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffoSkillsJul 2026476k1.3k
azure-deployExecute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application SkillsJul 2026472k1.3k
azure-preparePrepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wSkillsJul 2026471k1.3k
azure-validate--- name: azure-validate description: "Pre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity pSkillsJul 2026471k1.3k
azure-aigatewayConfigure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbSkillsJul 2026470k1.3k
azure-hosted-copilot-sdkOfficial agent plugin providing skills and MCP server configurations for Azure scenarios.SkillsJul 2026424k1.3k

agent_engine_terraform_deployer

15stars1forks

View on GitHub

How to install agent_engine_terraform_deployer?

veermuchandi/rad-skills/agent_engine_terraform_deployer

$npx -y skills add VeerMuchandi/rad-skills --skill agent_engine_terraform_deployer

Installs into the current project.

Summary

Deploys ADK agents to Vertex AI Agent Engine using the standard Terraform pattern.

Files · 1

View on GitHub

SKILL.md

1	# Agent Engine Terraform Deployer Skill
2
3	This skill helps you deploy your Agent Development Kit (ADK) agent to Vertex AI Agent Engine using a robust, self-contained Terraform pattern. It implements the "Golden Project Structure" and automated packaging logic recommended by the ADK team.
4
5	## Official References
6	- Module Source: [github.com/GoogleCloudPlatform/cloud-foundation-fabric/modules/agent-engine](https://github.com/GoogleCloudPlatform/cloud-foundation-fabric/tree/master/modules/agent-engine)
7	- Documentation: [Agent Engine Module README](https://github.com/GoogleCloudPlatform/cloud-foundation-fabric/blob/master/modules/agent-engine/README.md)
8
9	## Capabilities
10	- Intelligent Preparation: Intelligently scans and updates `.ae_ignore`, `requirements.txt`, and `.env` for deployment readiness.
11	- Initialize Deployment: Sets up a `deploy/` directory with the golden `main.tf` template.
12	- Support for Multiple Sources:
13	- Local Source: Deploys from your local machine (ideal for dev).
14	- GitHub Source: Deploys directly from a GitHub repository (ideal for CI/CD).
15	- Auto-Packaging: Automatically packages your agent code, excluding bulky files.
16	- Non-Intrusive Wrapping: Dynamically generates an `app.py` wrapper during deployment.
17
18	## Prerequisites
19	- Terraform Version:
20	- Minimum: `v1.12.2`
21	- Recommended: `v1.14.4`
22	- [Download Terraform](https://releases.hashicorp.com/terraform/) if needed.
23	- GCP Project: Access to a Google Cloud Project with billing enabled.
24	- Permissions:
25	- `roles/aiplatform.user`
26	- `roles/storage.objectViewer`
27	- `roles/serviceusage.serviceUsageConsumer`
28	- `roles/cloudtrace.agent`
29
30	## 1. Golden Project Structure
31	Always separate your deployment logic from your agent code. This prevents Terraform from accidentally zipping up its own bulky provider binaries.
32
33	```text
34	my_project/
35	├── .ae_ignore # Patterns to exclude (caching, env files, etc.)
36	├── my_agent_package/ # YOUR AGENT FOLDER (must have __init__.py)
37	│ ├── agent.py # Root agent logic
38	│ ├── requirements.txt # Dependencies
39	│ └── ...
40	└── deploy/ # DEDICATED DEPLOYMENT FOLDER
41	└── main.tf # Self-contained Terraform logic
42	```
43
44	## 2. Configuration Reference
45
46	### Environment Variables (.env)
47	Ensure your agent's `.env` includes the following for proper observability:
48	```bash
49	# Enables agent traces and logs (excludes prompts/responses)
50	GOOGLE_CLOUD_AGENT_ENGINE_ENABLE_TELEMETRY=true
51
52	# Enables logging of input prompts and output responses
53	OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=true
54	```
55
56	### Dependencies (requirements.txt)
57	Your agent's `requirements.txt` MUST include:
58	```text
59	google-cloud-aiplatform[agent_engines,adk]
60	```
61
62	## 3. Workflow
63
64	### Step 0: Intelligent Agent Preparation (Automated)
65	Instead of manually creating files, run the provided helper script. It will intelligently scan your agent directory and generate/update `.ae_ignore`, `requirements.txt`, and `.env` with the correct configurations.
66
67	```bash
68	# Run the preparation script pointing to your agent directory (replace /path/to/your/agent)
69	python3 scripts/prepare_agent.py /path/to/your/agent
70	```
71
72	This script will:
73	1. Exclude Junk: Add robust exclusions to `.ae_ignore` (git, venve, terraform, `.zip`, `.pkl`, etc.).
74	2. Ensure Dependencies: Add `google-cloud-aiplatform[agent_engines,adk]` to `requirements.txt` if missing.
75	3. Enable Telemetry: Inject observability env vars into `.env` if not present.
76
77	### Option A: Local Deployment (Development)
78	Use this when you have the code on your machine.
79
80	1. Initialize:
81	```bash
82	mkdir -p deploy
83	# Copy templates/main_local.tf to deploy/main.tf
84	```
85	2. Configure (`deploy/terraform.tfvars`):
86	```hcl
87	project_id = "your-project-id"
88	region = "us-central1"
89	agent_engine_name = "epp-telecom-concierge"
90	agent_folder_name = "epp_telecom_concierge"
91	```
92	3. Deploy:
93	```bash
94	cd deploy && terraform init && terraform apply
95	```
96
97	### Option B: GitHub Deployment (CI/CD)
98	Use this to deploy code from a remote repository.
99
100	1. Initialize:
101	```bash
102	mkdir -p deploy
103	# Copy templates/main_github.tf to deploy/main.tf
104	```
105	2. Configure (`deploy/terraform.tfvars`):
106	```hcl
107	project_id = "your-project-id"
108	region = "us-central1"
109	agent_engine_name = "epp-telecom-concierge"
110	github_repo = "username/repo"
111	github_branch = "main"
112	agent_package_name = "epp_telecom_concierge"
113	```
114	3. Deploy:
115	```bash
116	cd deploy && terraform init && terraform apply
117	```
118
119	## 4. Critical Learnings & Troubleshooting
120
121	### A. The "ResourceExhausted" (256MB) Limit
122	The Issue: Terraform's `inline_source`

People who liked this also viewed

6 picks

Type