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.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/devops/jeremy-vertex-terraform/skills/vertex-infra-expert/SKILL.md

Quality

Content

35%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured as an overview and points to real reference files, but it lacks executable code or validation checkpoints in the main workflow, and navigation is prose-only with one broken reference path. Concrete guidance lives almost entirely in the referenced files rather than in SKILL.md itself.

Suggestions

Add at least one minimal executable HCL snippet or the init-terraform.sh invocation in SKILL.md so Claude has copy-paste-ready guidance without opening references.

Insert an explicit validation checkpoint into the Instructions workflow (e.g. 'Run terraform init && terraform validate && terraform plan; fix and re-run until clean') to satisfy the feedback-loop requirement for batch/infra operations.

Convert prose references to clickable markdown links (e.g. [errors.md](references/errors.md)) and remove or correct the non-existent '${CLAUDE_SKILL_DIR}/vertex-examples/' Resource entry.

Dimension	Reasoning	Score
Conciseness	The body is reasonably lean for a single-domain skill, but the Instructions section restates high-level steps Claude already knows ('Define AI Services', 'Configure Terraform') without adding Terraform specifics, leaning toward the 'could be tightened' anchor.	2 / 3
Actionability	The SKILL.md body contains no executable code or commands; it only describes steps ('Provision Endpoints', 'Configure Encryption') and defers all concrete HCL/commands to external reference files, matching the 'describes rather than instructs' anchor.	1 / 3
Workflow Clarity	Steps are listed in a clear 1-8 sequence, but there are no explicit validation checkpoints (e.g. terraform validate/plan) within the workflow; the rubric caps batch/infra operations at 2 when validation feedback loops are absent from the body.	2 / 3
Progressive Disclosure	The body signals one-level-deep references (errors.md, examples.md, implementation.md all exist), but links are prose-only ('See ${CLAUDE_SKILL_DIR}/references/...') rather than clickable markdown, and the referenced 'vertex-examples/' path in Resources does not exist as a bundle file, so organization could be better.	2 / 3
	Total	7 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly states what the skill does and when to use it, with concrete capability actions and natural trigger phrases tied to a specific Vertex AI + Terraform niche. Uses third-person 'Provisions' verb form with no voice violation.

Dimension	Reasoning	Score
Specificity	Lists multiple 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	Explicitly answers both 'what' (provisions Vertex AI infrastructure components) and 'when' ('Use when...' with explicit trigger phrases).	3 / 3
Trigger Term Quality	Good coverage of natural trigger phrases users would say: 'vertex ai terraform', 'deploy gemini terraform', 'model garden infrastructure', 'vertex ai endpoints terraform', 'vector search terraform'.	3 / 3
Distinctiveness Conflict Risk	Clear niche (Vertex AI + Terraform) with distinct, specific triggers unlikely to overlap with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/devops/jeremy-vertex-terraform/skills/vertex-infra-expert/SKILL.md
Commit: 399d94c

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.