vertex-infra-expert

Execute use when provisioning Vertex AI infrastructure with Terraform. Trigger with phrases like "vertex ai terraform", "deploy gemini terraform", "model garden infrastructure", "vertex ai endpoints terraform", or "vector search terraform". Provisions Model Garden models, Gemini endpoints, vector search indices, ML pipelines, and production AI services with encryption and auto-scaling.

1.06x

Quality

71%

Does it follow best practices?

Impact

88%

1.06x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/devops/jeremy-vertex-terraform/skills/vertex-infra-expert/SKILL.md

Evaluation results

74%

Deploy Gemini Pro Endpoint for Internal Analytics Chatbot

Gemini endpoint with encryption and IAM

Criteria

Without context

With context

Terraform backend block

Project variables defined

100%

Auto-scaling configuration

20%

70%

KMS encryption on endpoint

100%

KMS IAM binding

100%

Least-privilege IAM roles

100%

GCS bucket reference

API enable command

30%

Validation report file

100%

Changes summary with rationale

100%

Without context: $0.2479 · 1m 17s · 13 turns · 15 in / 4,029 out tokens

With context: $0.6657 · 2m 39s · 36 turns · 591 in / 8,873 out tokens

96%

Vector Search Infrastructure for E-Commerce Product Recommendations

Vector search index with embeddings and monitoring

Criteria

Without context

With context

Embedding dimensions specified

100%

GCS bucket for embeddings

100%

GCS IAM permissions

100%

KMS encryption on index

100%

cloudkms IAM binding

100%

Least-privilege IAM roles

100%

Cloud Monitoring configured

100%

Terraform variables defined

50%

Smoke test script

100%

Validation report

100%

Without context: $0.7536 · 4m 26s · 27 turns · 34 in / 14,009 out tokens

With context: $0.8572 · 3m 34s · 39 turns · 813 in / 12,515 out tokens

96%

Production-Ready AI Search Platform on Vertex AI

Full production stack with monitoring and validation

Criteria

Without context

With context

Multiple resource types

100%

Auto-scaling on deployed model

100%

KMS encryption present

100%

cloudkms IAM role granted

100%

Least-privilege roles only

100%

Cloud Monitoring resource

100%

API enable command

100%

Smoke test queries endpoint

100%

Smoke test checks index build

100%

Validation report with rationale

100%

Terraform backend and variables

50%

Without context: $0.6737 · 3m 43s · 27 turns · 33 in / 12,842 out tokens

With context: $0.8680 · 3m 31s · 38 turns · 303 in / 12,967 out tokens

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 454476c

Evaluated: 9 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Deploy Gemini Pro Endpoint for Internal Analytics Chatbot Vector Search Infrastructure for E-Commerce Product Recommendations Production-Ready AI Search Platform on Vertex AI

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.