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.
77
Quality
71%
Does it follow best practices?
Impact
88%
1.06xAverage score across 3 eval scenarios
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 excels across all dimensions. It provides specific capabilities (Model Garden models, Gemini endpoints, vector search indices), explicit trigger phrases that users would naturally say, and clear guidance on when to use the skill. The combination of Vertex AI and Terraform creates a distinct niche that minimizes conflict risk with other skills.
| 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 various Vertex AI components) and when ('use when provisioning Vertex AI infrastructure with Terraform' plus explicit trigger phrases). Has explicit 'Use when' and 'Trigger with phrases' guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'vertex ai terraform', 'deploy gemini terraform', 'model garden infrastructure', 'vertex ai endpoints terraform', 'vector search terraform' - these are specific phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche combining Vertex AI + Terraform. The specific trigger phrases like 'vertex ai terraform' and 'model garden infrastructure' are unlikely to conflict with generic Terraform or generic AI skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has good structural organization with appropriate progressive disclosure to reference files, but critically lacks actionable content. The instructions are abstract descriptions rather than concrete Terraform code or commands, making it difficult for Claude to execute without consulting the referenced files for all substantive guidance.
Suggestions
Add at least one complete, executable Terraform code block showing a minimal Vertex AI endpoint configuration that can be copy-pasted and modified
Include explicit validation steps with actual commands (e.g., 'terraform plan -out=tfplan', 'terraform show tfplan' for review, then 'terraform apply tfplan')
Replace abstract instructions like 'Configure Terraform' with specific commands and configuration snippets
Add a concrete example of the expected output format inline rather than only referencing implementation.md
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary explanation (e.g., 'Use this skill to generate a minimal working Terraform baseline'). The prerequisites section explains things Claude would know to check, and the instructions are high-level without adding unique value. | 2 / 3 |
Actionability | The skill provides only vague, abstract guidance with no concrete Terraform code, commands, or executable examples. Instructions like 'Configure Terraform' and 'Provision Endpoints' describe rather than instruct, offering no copy-paste ready content. | 1 / 3 |
Workflow Clarity | Steps are listed in sequence but lack validation checkpoints and feedback loops. For infrastructure provisioning (a potentially destructive operation), there's no explicit 'terraform plan' review step or validation before apply. The 'Validate Deployment' step is vague. | 2 / 3 |
Progressive Disclosure | Good structure with clear overview and well-signaled one-level-deep references to implementation.md, errors.md, and examples.md. Content is appropriately split between the main skill and reference files. | 3 / 3 |
Total | 8 / 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
454476c
- 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.