vertex-engine-inspector

Inspect and validate Vertex AI Agent Engine deployments including Code Execution Sandbox, Memory Bank, A2A protocol compliance, and security posture. Generates production readiness scores. Use when asked to inspect, validate, or audit an Agent Engine deployment. Trigger with "inspect agent engine", "validate agent engine deployment", "check agent engine config", "audit agent engine security", "agent engine readiness check", "vertex engine health", or "reasoning engine status".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

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

The body is concise and well-structured with clean progressive disclosure to real reference files, but it stops short of copy-paste-ready execution by omitting executable code/command blocks and inline validation checkpoints. Actionability and workflow clarity are the weakest dimensions.

Suggestions

Add at least one concrete, runnable code block or command snippet in the body (e.g., the Python SDK connect call or a curl probe for the A2A AgentCard endpoint) so guidance is copy-paste ready rather than abstract.

Reference and link the bundled scripts (check-security.py, inspect-agent.sh) from the Instructions so existing executable tooling is discoverable instead of orphaned.

Insert explicit validation checkpoints into the 10-step sequence (e.g., 'Confirm agent metadata is accessible before parsing runtime config') to create inline feedback loops rather than deferring all recovery to the error table.

Dimension	Reasoning	Score
Conciseness	The body is lean: a 10-step numbered process with specific SDK calls, endpoints, and thresholds, and an 'Important' note about the absent gcloud surface that is genuinely non-obvious. It does not re-explain concepts Claude already knows.	3 / 3
Actionability	Instructions name concrete SDK calls (client.agent_engines.get(name=...)) and specific thresholds (TTL 7-14 days, error rate < 5%, min 100 memories), but the main body contains no executable code/commands; the bundled scripts (check-security.py, inspect-agent.sh) are never shown or linked, leaving key details implicit.	2 / 3
Workflow Clarity	A clear 10-step sequence is present, but it lacks explicit validate/checkpoint steps within the flow; recovery guidance lives only in the separate error-handling table rather than inline feedback loops, so checkpoints are implicit.	2 / 3
Progressive Disclosure	Clear overview with well-signaled one-level-deep references (inspection-workflow.md, inspection-categories.md, example-inspection-report.md, errors.md), all of which exist as real files, keeping the SKILL.md body appropriately light.	3 / 3
	Total	10 / 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 well-crafted: it states concrete capabilities, provides explicit 'Use when' guidance, and lists seven natural trigger phrases tied to a distinct Vertex AI Agent Engine niche. No vague fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and sub-targets: 'Inspect and validate Vertex AI Agent Engine deployments including Code Execution Sandbox, Memory Bank, A2A protocol compliance, and security posture' and 'Generates production readiness scores'.	3 / 3
Completeness	Explicitly answers both what (inspect/validate deployments across named categories, generate readiness scores) and when via a 'Use when asked to inspect, validate, or audit an Agent Engine deployment' clause plus triggers.	3 / 3
Trigger Term Quality	Seven natural trigger phrases a user would say ('inspect agent engine', 'validate agent engine deployment', 'check agent engine config', 'audit agent engine security', 'agent engine readiness check', 'vertex engine health', 'reasoning engine status'), giving good coverage.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Vertex AI Agent Engine deployments) with distinct, domain-specific triggers unlikely to fire for unrelated 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: about 2 hours 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.