Provision Vertex AI infrastructure with Terraform (endpoints, deployed models, vector search indices, pipelines) with production guardrails: encryption, autoscaling, IAM least privilege, and operational validation steps. Use this skill to generate a minimal working Terraform baseline and iterate toward enterprise-ready deployments.
Prerequisites
Before using this skill, ensure:
Google Cloud project with Vertex AI API enabled
Terraform 1.0+ installed
gcloud CLI authenticated with appropriate permissions
Understanding of Vertex AI services and ML models
KMS keys created for encryption (if required)
GCS buckets for model artifacts and embeddings
Instructions
Define AI Services: Identify required Vertex AI components (endpoints, vector search, pipelines)
Configure Terraform: Set up backend and define project variables
Provision Endpoints: Deploy Gemini or custom model endpoints with auto-scaling
Set Up Vector Search: Create indices for embeddings with appropriate dimensions
Configure Encryption: Apply KMS encryption to endpoints and data
Implement Monitoring: Set up Cloud Monitoring for model performance
Apply IAM Policies: Grant least privilege access to AI services
Validate Deployment: Test endpoints and verify model availability
Output
Configuration files or code changes applied to the project
Terraform examples in ${CLAUDE_SKILL_DIR}/vertex-examples/
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: jeremylongshore-claude-code-plugins-plus-skills-vertex-infra3description: Vertex Infra Expert4---5# Vertex Infra Expert67## Overview89Provision Vertex AI infrastructure with Terraform (endpoints, deployed models, vector search indices, pipelines) with production guardrails: encryption, autoscaling, IAM least privilege, and operational validation steps. Use this skill to generate a minimal working Terraform baseline and iterate toward enterprise-ready deployments.1011## Prerequisites1213Before using this skill, ensure:14- Google Cloud project with Vertex AI API enabled15- Terraform 1.0+ installed16- gcloud CLI authenticated with appropriate permissions17- Understanding of Vertex AI services and ML models18- KMS keys created for encryption (if required)19- GCS buckets for model artifacts and embeddings2021## Instructions22231. **Define AI Services**: Identify required Vertex AI components (endpoints, vector search, pipelines)242. **Configure Terraform**: Set up backend and define project variables253. **Provision Endpoints**: Deploy Gemini or custom model endpoints with auto-scaling264. **Set Up Vector Search**: Create indices for embeddings with appropriate dimensions275. **Configure Encryption**: Apply KMS encryption to endpoints and data286. **Implement Monitoring**: Set up Cloud Monitoring for model performance297. **Apply IAM Policies**: Grant least privilege access to AI services308. **Validate Deployment**: Test endpoints and verify model availability3132## Output333435- Configuration files or code changes applied to the project36- Validation report confirming correct implementation37- Summary of changes made and their rationale3839See [Terraform implementation details](${CLAUDE_SKILL_DIR}/references/implementation.md) for output format specifications.4041## Error Handling4243See `${CLAUDE_SKILL_DIR}/references/errors.md` for comprehensive error handling.4445## Examples4647See `${CLAUDE_SKILL_DIR}/references/examples.md` for detailed examples.4849## Resources5051- Vertex AI Terraform: https://registry.terraform.io/providers/hashicorp/google/latest/docs/resources/vertex_ai_endpoint52- Vertex AI documentation: https://cloud.google.com/vertex-ai/docs53- Model Garden: https://cloud.google.com/model-garden54- Vector Search guide: https://cloud.google.com/vertex-ai/docs/vector-search55- Terraform examples in ${CLAUDE_SKILL_DIR}/vertex-examples/5657---58> Converted and distributed by [TomeVault](https://tomevault.io/claim/jeremylongshore) — claim your Tome and manage your conversions.59<!-- tomevault:4.0:skill_md:2026-04-11 -->
Run npx skillmds@latest add tomevault-io/jeremylongshore-claude-code-plugins-plus-skills-vertex-infra in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Vertex Infra Expert It is listed under DevOps & Infra on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.