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

What This Skill Does

Expert in provisioning Vertex AI infrastructure including Model Garden, Gemini endpoints, vector search, ML pipelines, and production AI services.

When This Skill Activates

Triggers: "vertex ai terraform", "deploy gemini terraform", "model garden infrastructure", "vertex ai endpoints terraform", "vector search terraform"

Core Terraform Modules

Gemini Model Endpoint

resource "google_vertex_ai_endpoint" "gemini_endpoint" {
  name         = "gemini-25-flash-endpoint"
  display_name = "Gemini 2.5 Flash Production"
  location     = var.region

  encryption_spec {
    kms_key_name = google_kms_crypto_key.vertex_key.id
  }
}

resource "google_vertex_ai_deployed_model" "gemini_deployment" {
  endpoint = google_vertex_ai_endpoint.gemini_endpoint.id
  model    = "publishers/google/models/gemini-2.5-flash"

  dedicated_resources {
    min_replica_count      = 1
    max_replica_count      = 10
    machine_spec {
      machine_type = "n1-standard-4"
    }
  }

  automatic_resources {
    min_replica_count = 1
    max_replica_count = 5
  }
}

Vector Search Index

resource "google_vertex_ai_index" "embeddings_index" {
  display_name = "production-embeddings"
  location     = var.region

  metadata {
    contents_delta_uri = "gs://${google_storage_bucket.embeddings.name}/index"
    config {
      dimensions                  = 768
      approximate_neighbors_count = 150
      distance_measure_type       = "DOT_PRODUCT_DISTANCE"

      algorithm_config {
        tree_ah_config {
          leaf_node_embedding_count    = 1000
          leaf_nodes_to_search_percent = 10
        }
      }
    }
  }
}

Tool Permissions

Read, Write, Edit, Grep, Glob, Bash - AI infrastructure provisioning

References

  • Vertex AI Terraform: https://registry.terraform.io/providers/hashicorp/google/latest/docs/resources/vertex_ai_endpoint
Repository
jeremylongshore/claude-code-plugins-plus-skills
Commit

c8a915c

Last updated
Created

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.

Claim skill