CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

57

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

35%

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

The body works as a slim overview with real one-level-deep references, but it is not itself actionable — concrete code lives only in the references, validation is implicit, and one cited path is broken. Tightening instructions and fixing navigation would lift it substantially.

Suggestions

Add at least one inline, copy-paste-ready HCL snippet or a terraform init/plan/apply command sequence in the body so the skill is actionable without first opening a reference file.

Replace the final 'Validate Deployment' step with an explicit checkpoint (e.g., run 'terraform validate' / a predict smoke-test) and a fix-and-retry loop, given infrastructure applies are batch/destructive operations.

Fix navigation: give 'implementation details' an explicit ${CLAUDE_SKILL_DIR}/references/implementation.md path and either create the cited vertex-examples/ directory or remove the broken reference.

DimensionReasoningScore

Conciseness

The body is largely lean and avoids re-explaining concepts Claude knows, but the generic Prerequisites list and abstract one-line step descriptions ('Define AI Services: Identify required Vertex AI components') add little that the references don't already provide.

2 / 3

Actionability

The body contains no executable code or commands — every concrete HCL/bash snippet is deferred to reference files — and the Instructions describe rather than instruct ('Configure Terraform: Set up backend and define project variables'), matching the vague/abstract anchor.

1 / 3

Workflow Clarity

Eight steps are listed and sequenced, but validation is only a vague final step ('Validate Deployment: Test endpoints and verify model availability') with no explicit checkpoint or fix-retry feedback loop, which caps clarity at 2 for batch/infra operations.

2 / 3

Progressive Disclosure

References exist one level deep (errors.md, examples.md, implementation.md are real files), but navigation is inconsistent: 'Terraform implementation details' is not given an explicit path, and the Resources section points to a vertex-examples/ directory that does not exist.

2 / 3

Total

7

/

12

Passed

Description

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.

The description is specific, complete, and distinctive, with explicit trigger guidance and natural keyword coverage. It is a strong, well-scoped skill description.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions/resources — 'Model Garden models, Gemini endpoints, vector search indices, ML pipelines, and production AI services with encryption and auto-scaling' — matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

It answers both 'what' (provisions endpoints, indices, pipelines) and 'when' via an explicit 'Execute use when provisioning...' clause plus 'Trigger with phrases like...', satisfying the explicit-trigger requirement.

3 / 3

Trigger Term Quality

Explicit trigger phrases such as 'vertex ai terraform', 'deploy gemini terraform', 'model garden infrastructure', 'vertex ai endpoints terraform', and 'vector search terraform' give good coverage of natural terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The Vertex-AI-with-Terraform niche and its dedicated trigger phrases are clearly distinguishable and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.