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.
55
63%
Does it follow best practices?
Impact
—
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 niche at the intersection of Vertex AI and Terraform. It provides specific concrete actions, explicit trigger phrases, and clear 'when to use' guidance. The only minor issue is the slightly 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, production AI services) and 'when' (explicit trigger phrases and 'use when provisioning Vertex AI infrastructure with Terraform'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually 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 domain-specific enough (e.g., 'model garden infrastructure', 'vector search terraform') to be unlikely to conflict with generic Terraform or generic AI skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a high-level outline that lacks any concrete, executable content. It reads more like a table of contents than an actionable skill — no Terraform resource blocks, no CLI commands, no example configurations are provided inline. All substantive content is deferred to referenced files that don't exist in the bundle, making the skill effectively non-functional.
Suggestions
Add at least one complete, executable Terraform resource block inline (e.g., a google_vertex_ai_endpoint with auto-scaling and KMS encryption) so Claude has a concrete starting template.
Include specific terraform and gcloud commands for validation steps (e.g., 'terraform validate', 'terraform plan', 'gcloud ai endpoints describe') as explicit checkpoints in the workflow.
Either provide the referenced bundle files (errors.md, examples.md, implementation.md) or inline the critical content — currently the skill delegates everything to nonexistent files.
Remove the Prerequisites section or reduce it to a single line; Claude doesn't need to be told what Terraform or gcloud CLI are.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary padding like the Prerequisites section (Claude knows what gcloud CLI is and what Terraform requires) and the vague 'Understanding of Vertex AI services and ML models' bullet. The overview also restates what the instructions cover. However, it's not egregiously verbose. | 2 / 3 |
Actionability | The instructions are entirely abstract and descriptive — 'Define AI Services', 'Configure Terraform', 'Provision Endpoints' — with zero concrete code, Terraform resource blocks, commands, or executable examples. Everything actionable is deferred to referenced files that don't exist in the bundle. | 1 / 3 |
Workflow Clarity | Steps are listed in a logical sequence and step 8 mentions validation, but there are no explicit validation checkpoints between steps, no feedback loops for error recovery, and no concrete commands for verification. For infrastructure provisioning (a destructive/batch operation), the lack of inline validation gates is a notable gap. | 2 / 3 |
Progressive Disclosure | The skill references multiple external files (implementation.md, errors.md, examples.md, vertex-examples/) but none of these bundle files exist. The main SKILL.md contains almost no substantive content itself — it's essentially an empty shell pointing to nonexistent references, making the progressive disclosure structure hollow rather than functional. | 1 / 3 |
Total | 6 / 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
69c73e9
- 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.