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 recommendations. Use when asked to "validate deploymen... Trigger with phrases like 'validate', 'check', or 'verify'.
Install with Tessl CLI
npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill validator-expertActivation
60%The description demonstrates strong specificity with concrete capabilities (security, monitoring, performance validation with weighted scores), but suffers from truncation and overly generic trigger terms. The 'Use when' clause is incomplete and the trigger phrases lack domain specificity, which could cause conflicts with other validation-related skills.
Suggestions
Complete the truncated 'Use when' clause and include domain-specific triggers like 'Vertex AI deployment', 'Agent Engine validation', 'GCP agent readiness'
Add natural user phrases that combine the action with the domain: 'check my Vertex AI agent', 'verify Agent Engine deployment', 'production readiness for GCP agents'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Validate production readiness', 'across security, monitoring, performance, compliance, and best practices', 'Generates weighted scores (0-100%) with actionable recommendations'. | 3 / 3 |
Completeness | The 'what' is well-covered (validate deployments, generate scores), but the 'when' clause is truncated ('validate deploymen...') and the trigger guidance is generic ('validate', 'check', 'verify') without connecting to the specific Vertex AI domain. | 2 / 3 |
Trigger Term Quality | Includes some natural trigger terms ('validate', 'check', 'verify') but the description is truncated and missing domain-specific terms users might say like 'Vertex AI', 'Agent Engine', 'deployment review', or 'production ready'. | 2 / 3 |
Distinctiveness Conflict Risk | The Vertex AI Agent Engine focus provides some distinctiveness, but generic triggers like 'validate', 'check', 'verify' could easily conflict with other validation or deployment skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
7%This skill is largely boilerplate with minimal actionable content. It provides a checklist of validation items but lacks any concrete implementation guidance - no commands, scripts, or specific steps to actually perform the validations. The duplicate 'Overview' sections and generic placeholder content (Examples, Error Handling) suggest this was auto-generated without meaningful customization.
Suggestions
Replace the checklist with executable validation commands (e.g., 'gcloud projects get-iam-policy $PROJECT_ID | grep -E "roles/aiplatform"' for IAM validation)
Add a clear numbered workflow: 1) Run security checks, 2) Validate monitoring, 3) Check performance configs, with specific commands for each step
Remove all generic boilerplate sections (Prerequisites, Instructions, Output, Error Handling, Examples) that contain no skill-specific content
Include example output showing what a passing vs failing validation looks like, with the weighted scoring mentioned in the description
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Contains significant redundancy with repeated 'This skill provides automated assistance' phrases, generic boilerplate sections (Prerequisites, Instructions, Output, Error Handling, Examples) that add no value, and explains obvious concepts Claude already knows. | 1 / 3 |
Actionability | Provides only a checklist of items to validate without any concrete code, commands, or executable guidance on HOW to perform these validations. No gcloud commands, no Python scripts, no specific file paths to check. | 1 / 3 |
Workflow Clarity | No clear sequence for performing validations, no validation checkpoints, no feedback loops for error recovery. The checklist format doesn't explain the order of operations or what to do when checks fail. | 1 / 3 |
Progressive Disclosure | Has some structure with categorized sections (Security, Monitoring, Performance, Compliance) and includes one external reference link, but the content is poorly organized with duplicate overview sections and generic boilerplate that should be removed entirely. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
81%| 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 | |
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.