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.
61
53%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/devops/jeremy-vertex-terraform/skills/vertex-infra-expert/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its scope at the intersection of Vertex AI and Terraform, lists concrete provisioning actions, and provides explicit trigger phrases. The only minor issue is the awkward opening 'Execute use when' which appears to be a grammatical error, but it doesn't materially impact the description's effectiveness for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Provisions Model Garden models, Gemini endpoints, vector search indices, ML pipelines, and production AI services with encryption and auto-scaling.' | 3 / 3 |
Completeness | Clearly answers both what ('Provisions Model Garden models, Gemini endpoints, vector search indices, ML pipelines, and production AI services') and when ('use when provisioning Vertex AI infrastructure with Terraform') with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'vertex ai terraform', 'deploy gemini terraform', 'model garden infrastructure', 'vertex ai endpoints terraform', 'vector search terraform'. These cover multiple natural variations of how users would phrase requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining Vertex AI specifically with Terraform infrastructure provisioning. The trigger terms are specific enough (e.g., 'vertex ai terraform', 'model garden infrastructure') to avoid conflicts with general Terraform or general AI skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a table of contents with no actionable content. It lacks any Terraform HCL code, specific resource configurations, or concrete commands — everything is deferred to referenced files that don't exist in the bundle. The instructions read like a project plan rather than executable guidance, making this skill nearly useless for actually provisioning Vertex AI infrastructure.
Suggestions
Add at least one complete, executable Terraform HCL example for a core use case (e.g., a Vertex AI endpoint with a deployed model) directly in the SKILL.md body.
Replace the abstract instruction steps with concrete commands: include `terraform init`, `terraform plan`, `terraform apply` with validation checkpoints and error recovery loops between steps.
Remove the prerequisites section (Claude knows what Terraform and gcloud are) and replace it with a minimal provider configuration block that's copy-paste ready.
Either provide the referenced bundle files (errors.md, examples.md, implementation.md) or inline the critical content — currently all substantive guidance is deferred to non-existent files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is padded with unnecessary context Claude already knows (prerequisites like 'Terraform 1.0+ installed', 'gcloud CLI authenticated'), explains obvious concepts ('Identify required Vertex AI components'), and the instructions are high-level descriptions rather than efficient, actionable content. The overview restates what the description already conveys. | 1 / 3 |
Actionability | There is no executable Terraform code, no concrete HCL snippets, no specific resource configurations, and no copy-paste ready commands. The instructions are entirely abstract ('Configure Terraform', 'Provision Endpoints', 'Set Up Vector Search') with no concrete implementation details whatsoever. | 1 / 3 |
Workflow Clarity | While steps are numbered, they are vague descriptions rather than a clear workflow. There are no validation checkpoints between steps, no feedback loops for error recovery, and the 'Validate Deployment' step at the end lacks any specific commands or criteria. For infrastructure provisioning (a destructive/batch operation), the absence of terraform plan/apply validation steps is a significant gap. | 1 / 3 |
Progressive Disclosure | The skill does reference external files (implementation.md, errors.md, examples.md) with clear signaling, which is good structure. However, since no bundle files are provided, all the actual useful content appears to be deferred to non-existent references, leaving the SKILL.md itself as an empty shell with no substantive content to work with. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3a2d27d
- Reviewed
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.