CtrlK
BlogDocsLog inGet started
Tessl Logo

validator-expert

Validate production readiness of Vertex AI Agent Engine deployments across security, monitoring, performance, compliance, and best practices. Generates weighted scores (0-100%) with actionable remediation plans. Use when asked to validate a deployment, run a production readiness check, audit security posture, or verify compliance for Vertex AI agents. Trigger with "validate deployment", "production readiness", "security audit", "compliance check", "is this agent ready for prod", "check my ADK agent", "review before deploy", or "production readiness check". Make sure to use this skill whenever validating ADK agents for Agent Engine.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 with executable commands, a clean error-handling table, worked examples, and effective progressive disclosure into real reference files. Its main weakness is the absence of explicit per-step validation/feedback checkpoints in the batch validation workflow, which caps workflow clarity.

Suggestions

Insert explicit validation checkpoints into the numbered workflow (e.g., 'Verify IAM access before running suites; if a check errors, fix permissions and re-run that suite') to add fix-and-retry feedback loops for the batch operation.

Tighten conciseness by removing duplicated category weights (stated in both Overview and Output) and trimming prerequisite detail Claude can derive, keeping only the non-obvious role/IAM specifics.

Move the long per-check bullet lists for each suite into the referenced checklists and keep the body as a brief pointer, reinforcing the progressive-disclosure split.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete SDK/REST calls and a compact error table, but includes some padding Claude already knows (e.g. elaborating prerequisite role lists and restating category weights both in the Overview and Output). It is tighter than the verbose anchor at 1 but not the lean 'every token earns its place' anchor at 3.

2 / 3

Actionability

Provides fully executable specifics: 'vertexai.Client().agent_engines.get(name)', a concrete REST URL, role strings like 'roles/aiplatform.expressUser', TTL ranges, and a scoring formula. This matches the 'copy-paste ready / fully executable' anchor rather than the pseudocode anchor at 2.

3 / 3

Workflow Clarity

A clear numbered 7-step sequence is present, but the batch validation workflow lacks explicit per-step validation checkpoints or fix-and-retry feedback loops (it defers all validation to the referenced checklists and a final score). Per the rubric's feedback_loops note for batch operations, missing explicit validate->fix->retry loops caps this at 2 rather than the explicit-checkpoint anchor at 3.

2 / 3

Progressive Disclosure

The body is an overview that signals one-level-deep references to three real files (security-checklist.md, monitoring-checklist.md, performance-compliance-checklist.md, all present in references/) with weights noted, plus an external-docs section. This matches the 'clear overview with well-signaled one-level-deep references' anchor rather than the inline-wall-of-text anchor at 2.

3 / 3

Total

10

/

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 is concrete, trigger-rich, and complete, explicitly covering both what the skill does and when to use it within a well-scoped Vertex AI Agent Engine niche. Minor padding and a formatting oddity (newlines inside the YAML string) slightly reduce polish but not the scored dimensions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'Validate production readiness', 'generates weighted scores (0-100%) with actionable remediation plans', 'audit security posture', 'verify compliance'. Names the specific target (Vertex AI Agent Engine deployments), so it reaches the 'multiple specific concrete actions' anchor rather than the partial-domain anchor at 2.

3 / 3

Completeness

Explicitly answers what ('Validate production readiness ... Generates weighted scores ... remediation plans') and when ('Use when asked to validate a deployment, run a production readiness check...'). Both clauses are present and explicit, hitting the top anchor; it is not the score-2 case where 'when' is only implied.

3 / 3

Trigger Term Quality

Provides broad natural-language coverage users would say: 'validate deployment', 'production readiness', 'security audit', 'compliance check', 'is this agent ready for prod', 'check my ADK agent', 'review before deploy'. These are natural phrasings, not just technical jargon, matching the 'good coverage' anchor; the trailing 'Make sure to use this skill whenever validating ADK agents' is mildly repetitive but does not lower it below 3.

3 / 3

Distinctiveness Conflict Risk

Scoped to a clear niche (Vertex AI Agent Engine / ADK agents) with distinct triggers unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor rather than the 'could overlap with similar skills' anchor at 2.

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.