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

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/ai-ml/jeremy-vertex-engine/skills/vertex-engine-inspector/SKILL.md

Quality

Content

50%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 a clear 10-step inspection sequence, concrete thresholds, and a useful error table, but it lacks executable code, inter-step validation checkpoints, and leaves several bundle files orphaned. Tightening version pins and wiring in the bundled scripts would raise it notably.

Suggestions

Add explicit validation checkpoints between inspection steps (e.g., 'Confirm agent metadata is reachable before probing A2A endpoints') and reference the phased inspection-workflow.md sequence as a validate-then-proceed loop.

Wire the bundled scripts into the workflow with executable invocations (e.g., 'bash ${CLAUDE_SKILL_DIR}/scripts/inspect-agent.sh <project-id> <agent-engine-id>') and link examples.md, ARD.md, and PRD.md from the body so no bundle file is orphaned.

Move version/model pinning ('>=1.120.0', 'Gemini 2.5 Pro/Flash') into a prerequisites or compatibility note framed as current-as-of, or a dedicated section, to keep the main flow evergreen.

Dimension	Reasoning	Score
Conciseness	Mostly lean and action-dense, but includes time-sensitive pinning ('google-cloud-aiplatform[agent_engines]>=1.120.0', 'Gemini 2.5 Pro/Flash') and a 'Familiarity with ... concepts' prerequisite that ages and over-explains; per the rubric, bare version/model numbers outside a deprecated section penalize conciseness.	2 / 3
Actionability	Gives concrete SDK methods, endpoints ('/.well-known/agent-card', 'POST /v1/tasks:send'), and thresholds (error rate <5%, TTL 7-14 days, min 100 memories), but provides no complete executable code blocks and never wires in the bundled scripts (check-security.py, inspect-agent.sh), leaving guidance short of copy-paste ready.	2 / 3
Workflow Clarity	The 10 numbered inspection steps are clearly sequenced and an error-handling table exists, but there are no explicit validation checkpoints or feedback loops between steps (e.g., 'verify metadata before probing A2A'); checkpoints are only implicit.	2 / 3
Progressive Disclosure	The four referenced files (inspection-workflow.md, inspection-categories.md, example-inspection-report.md, errors.md) are well-signaled and one level deep, but three reference files (ARD.md, PRD.md, examples.md) and both scripts are orphaned — never linked from the body, creating discoverability gaps.	2 / 3
	Total	8 / 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 specific, complete, and rich in natural trigger terms with a clear 'Use when' clause and a distinct Vertex AI Agent Engine niche. It is among the strongest examples in the rubric.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Inspect and validate Vertex AI Agent Engine deployments including Code Execution Sandbox, Memory Bank, A2A protocol compliance, and security posture. Generates production readiness scores' — naming specific sub-capabilities rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Inspect and validate ... Generates production readiness scores') and when ('Use when asked to inspect, validate, or audit an Agent Engine deployment'), with an explicit 'Use when' clause.	3 / 3
Trigger Term Quality	Provides broad natural-language triggers users would actually 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'.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Vertex AI Agent Engine) 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
Path: plugins/ai-ml/jeremy-vertex-engine/skills/vertex-engine-inspector/SKILL.md
Commit: 0540a62

Reviewed: 1 day 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.