vertex-engine-inspector

tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill vertex-engine-inspector

Execute 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 agent engine" or "validate depl... Trigger with relevant phrases based on skill purpose.

51%

Overall

Validation — 81%

Implementation — 22%

Activation — 68%

SKILL.md

Review

Evals

Validation

81%

Warnings & errors only

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata' field is not a dictionary	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Implementation

22%

This skill is a hollow template with no actual content. Despite describing complex functionality (Vertex AI Agent Engine inspection, Code Execution Sandbox validation, A2A protocol compliance, security posture assessment), the body contains only generic placeholder text that could apply to any skill. Claude would have no idea how to actually perform any of the described inspections.

Suggestions

Add concrete, executable code or commands for inspecting Vertex AI Agent Engine deployments (e.g., gcloud commands, API calls, or Python SDK usage)

Define specific validation steps for each component mentioned in the description: Code Execution Sandbox, Memory Bank, A2A protocol compliance, and security posture

Include a clear workflow with validation checkpoints showing how to generate production readiness scores and what thresholds indicate pass/fail

Provide at least one concrete example showing input parameters and expected output format for the inspection results

Dimension	Reasoning	Score
Conciseness	The content is brief but wastes tokens on generic boilerplate ('This skill provides automated assistance...') that adds no value. It's not verbose, but every line is filler rather than substance.	2 / 3
Actionability	Completely vague with no concrete guidance. Instructions like 'Invoke this skill when trigger conditions are met' and 'Provide necessary context' give Claude nothing executable—no code, no commands, no specific steps for inspecting Vertex AI Agent Engine.	1 / 3
Workflow Clarity	The 4-step 'instructions' are generic placeholders with no actual workflow. For a skill involving deployment validation, security posture checks, and production readiness scoring, there are no validation checkpoints, no specific inspection steps, and no feedback loops.	1 / 3
Progressive Disclosure	References to external files (errors.md, examples.md) exist and are one level deep, but the main content is so empty that the structure is meaningless. The overview provides no useful quick-start content before pointing elsewhere.	2 / 3
	Total	6 / 12 Passed

Activation

68%

The description demonstrates strong specificity with concrete Vertex AI Agent Engine capabilities and generates a clear niche. However, it suffers from truncation and includes placeholder text ('Trigger with relevant phrases based on skill purpose') that provides no value, undermining the trigger term quality and completeness.

Suggestions

Complete the truncated 'Use when...' clause with full trigger phrases like 'validate deployment', 'check agent readiness', 'audit agent security'

Remove the placeholder text 'Trigger with relevant phrases based on skill purpose' and replace with actual natural language triggers users would say

Add common variations users might use: 'agent inspection', 'deployment validation', 'production readiness check', 'Vertex AI audit'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'inspect and validate Vertex AI Agent Engine deployments', 'Code Execution Sandbox', 'Memory Bank', 'A2A protocol compliance', 'security posture', and 'Generates production readiness scores'.	3 / 3
Completeness	The 'what' is well-covered with specific capabilities, and there's a partial 'Use when...' clause, but it's truncated ('validate depl...') and ends with unhelpful placeholder text rather than complete trigger guidance.	2 / 3
Trigger Term Quality	Includes some relevant keywords like 'inspect agent engine', 'validate depl...' (truncated), and domain-specific terms, but the description is cut off and ends with generic placeholder text 'Trigger with relevant phrases based on skill purpose' which provides no actual trigger terms.	2 / 3
Distinctiveness Conflict Risk	Highly specific to Vertex AI Agent Engine with distinct technical domain (A2A protocol, Memory Bank, Code Execution Sandbox) making it unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Reviewed

17 days ago

Table of Contents

Validation Implementation Activation

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.