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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

62%

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

The body is a well-sequenced, mostly-lean audit overview that delegates detail to real checklist files, but it is held back by redundancy in the scoring breakdown, no copy-paste executable checks, and an orphaned validate-production.sh script that is never referenced.

Suggestions

Reference scripts/validate-production.sh (e.g., in Instructions or Resources) so the bundled executable check has a navigation entry and actionability improves.

De-duplicate the category/weight breakdown: state the 30/20/25/15/10 weights once (Overview) and have the Output section reference rather than re-list them.

Add a concrete inline example check with a runnable command or short code block so guidance is copy-paste ready rather than only API/role names.

Dimension	Reasoning	Score
Conciseness	Information-dense and free of concept-explanation fluff, but the five categories and their point weights are stated twice (Overview and Output) and the narrative Examples add illustrative padding that could be trimmed. Not level 3 because redundancy means not every token earns its place; not level 1 because it assumes Claude's competence throughout.	2 / 3
Actionability	Names concrete specifics — 'vertexai.Client().agent_engines.get(name)', the REST endpoint, exact IAM roles, TLS 1.3, sandbox TTL '7-14 days' — but stops short of copy-paste executable checks and, notably, never references the bundled scripts/validate-production.sh that would provide them. Not level 3 (no ready-to-run code, available script orphaned); not level 1 (specific APIs/roles are given).	2 / 3
Workflow Clarity	A clear 7-step sequence (retrieve config → run each validation suite → calculate weighted scores → prioritized remediation), each suite yielding pass/fail with per-category checklists referenced, plus an Error Handling table for recovery. This is a read-only audit so the destructive-op feedback-loop cap does not apply.	3 / 3
Progressive Disclosure	The three reference checklists are linked one level deep and clearly signaled in Resources, and all referenced files exist; however the bundled scripts/validate-production.sh is never linked from the body, leaving an orphaned bundle file with no navigation entry. Not level 3 because bundle navigation is incomplete; not level 1 because the signaled references are well-structured.	2 / 3
	Total	9 / 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, trigger-rich, and fully answers what-and-when in third person with a distinct Vertex AI Agent Engine niche. It is somewhat verbose (categories and trigger lists are long), but no dimension is weak enough to drop below 3.

Dimension	Reasoning	Score
Specificity	Lists concrete actions across a named domain: 'Validate production readiness of Vertex AI Agent Engine deployments', 'Generates weighted scores (0-100%) with actionable remediation plans', spanning security, monitoring, performance, compliance, and best practices.	3 / 3
Completeness	Explicitly answers both what ('Validate production readiness... Generates weighted scores... remediation plans') and when ('Use when asked to validate a deployment... Trigger with...').	3 / 3
Trigger Term Quality	Abundant natural trigger phrases a user would actually say: 'validate deployment', 'production readiness', 'security audit', 'compliance check', 'is this agent ready for prod', 'check my ADK agent', 'review before deploy'.	3 / 3
Distinctiveness Conflict Risk	Clear niche — Vertex AI Agent Engine / ADK agents — with deployment-specific triggers unlikely to collide with generic security or doc 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
Commit: 2cafb23

Reviewed: 2 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.