CtrlK
BlogDocsLog inGet started
Tessl Logo

vertex-infra-expert

Terraform infrastructure specialist for Vertex AI services and Gemini deployments. Provisions Model Garden, endpoints, vector search, pipelines, and enterprise AI infrastructure. Triggers: "vertex ai terraform", "gemini deployment terraform", "model garden infrastructure", "vertex ai endpoints"

72

1.56x
Quality

60%

Does it follow best practices?

Impact

100%

1.56x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./backups/skills-batch-20251204-000554/plugins/devops/jeremy-vertex-terraform/skills/vertex-infra-expert/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

47%

Deploy Production Gemini Model Endpoint on Vertex AI

Gemini endpoint Terraform provisioning

Criteria
Without context
With context

Endpoint resource type

100%

100%

Deployed model resource type

0%

100%

Gemini model path

0%

100%

KMS encryption block

100%

100%

Dedicated resources block

100%

100%

Dedicated min replicas

100%

100%

Dedicated max replicas

0%

100%

Machine type

100%

100%

Automatic resources block

0%

100%

Auto min replicas

0%

100%

Auto max replicas

0%

100%

Region variable

100%

100%

100%

12%

Provision Vertex AI Vector Search Index for Semantic Document Retrieval

Vector Search index Terraform configuration

Criteria
Without context
With context

Index resource type

100%

100%

GCS contents_delta_uri

0%

100%

Embedding dimensions

100%

100%

Approximate neighbors count

100%

100%

Distance measure type

100%

100%

Tree AH algorithm

100%

100%

Leaf node embedding count

100%

100%

Leaf nodes search percent

100%

100%

Region variable

100%

100%

100%

48%

Build Terraform Infrastructure for an Enterprise RAG Application on Vertex AI

Full Vertex AI RAG infrastructure

Criteria
Without context
With context

Endpoint resource type

100%

100%

Deployed model resource type

0%

100%

Vector index resource type

100%

100%

Gemini model path

0%

100%

KMS encryption

100%

100%

Machine type

0%

100%

Dedicated max replicas

0%

100%

Auto max replicas

0%

100%

GCS index URI

0%

100%

Embedding dimensions

100%

100%

Distance measure type

100%

100%

ANN algorithm config

50%

100%

Region variable

100%

100%

Repository
jeremylongshore/claude-code-plugins-plus-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

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.