validator-expert
About
This skill validates Vertex AI Agent Engine deployments for production readiness across security, monitoring, performance, and compliance. It generates weighted scores (0-100%) with actionable recommendations and activates when asked to "validate deployment" or check "production readiness." Use it for comprehensive pre-deployment audits and best practice checks.
Quick Install
Claude Code
Recommended/plugin add https://github.com/jeremylongshore/claude-code-plugins-plusgit clone https://github.com/jeremylongshore/claude-code-plugins-plus.git ~/.claude/skills/validator-expertCopy and paste this command in Claude Code to install this skill
Documentation
What This Skill Does
Production validator for Vertex AI deployments. Performs comprehensive checks on security, compliance, monitoring, performance, and best practices before approving production deployment.
When This Skill Activates
Triggers: "validate deployment", "production readiness", "security audit vertex ai", "check compliance", "validate adk agent"
Validation Checklist
Security Validation
- ✅ IAM roles follow least privilege
- ✅ VPC Service Controls enabled
- ✅ Encryption at rest configured
- ✅ No hardcoded secrets
- ✅ Service accounts properly configured
- ✅ Model Armor enabled (for ADK)
Monitoring Validation
- ✅ Cloud Monitoring dashboards configured
- ✅ Alerting policies set
- ✅ Token usage tracking enabled
- ✅ Error rate monitoring active
- ✅ Latency SLOs defined
Performance Validation
- ✅ Auto-scaling configured
- ✅ Resource limits appropriate
- ✅ Caching strategy implemented
- ✅ Code Execution sandbox TTL set
- ✅ Memory Bank retention configured
Compliance Validation
- ✅ Audit logging enabled
- ✅ Data residency requirements met
- ✅ Privacy policies implemented
- ✅ Backup/disaster recovery configured
Tool Permissions
Read, Grep, Glob, Bash - Read-only analysis for security
References
- Vertex AI Security: https://cloud.google.com/vertex-ai/docs/security
GitHub Repository
Related Skills
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
llamaguard
OtherLlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.
langchain
MetaLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.