googlecloudplatform
31 verified skills5,724 total stars
go-project-setup
Standardized setup for new Go (Golang) projects and services. Activate to ensure clean, idiomatic project structures (Standard Layout) and implement production-ready patterns (graceful shutdown, package separation) from day one.
development260
gcp-agent-eval-engine-runner
Boilerplate for a production evaluation runner that performs parallel inference, captures reasoning traces via SSE, and integrates with the Vertex AI Gen AI Evaluation service.
devops260
gcp-agent-eval-metric-configurator
Provides templates for configuring Vertex AI Gen AI Evaluation metrics like GROUNDING, TOOL_USE_QUALITY, and ResponseMatch for specific agent domains.
tools260
gcp-agent-golden-dataset-builder
Assists developers in collecting and structuring a library of diverse examples ("Golden Dataset") required for data-driven evaluation, including tool trajectories.
tools260
gcp-agent-safety-gatekeeper
Implements the "Defense-in-Depth" integration pattern in Python (intercepting prompts, parsing filter results).
development260
adk-memory-bank-initializer
Helps developers implement the long-term memory layer by providing the boilerplate code for the VertexAiMemoryBankService and the save_session_to_memory_callback.
development260
gcp-agent-sdp-template-factory
Standardizes the creation of Sensitive Data Protection (DLP) templates for PII and credential redaction.
devops260
latest-software-version
Real-time source of truth for software and model versions. Activate when adding dependencies, installing packages, or identifying Gemini model names. Bypasses internal knowledge cutoffs by querying live registries (NPM, PyPI, Go Proxy) and official documentation.
development260
cloud-run-agent-architect
Automates the generation of Terraform files for a secure Cloud Run deployment of an AI agent.
devops260
gcp-agent-model-armor-shield
Configures Model Armor security policies (Prompt Injection, Jailbreak, RAI filters).
testing260
video-description
Generates optimized descriptions for video platforms from transcripts and supplementary material. Use when the user asks for a video description or provides a transcript for video preparation.
content-media260
gke-ai-troubleshooting-jobset-interruption
Systematically diagnose GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads. Identifies preemption events, maintenance interruptions, bad host VMs, unhealthy pods, and coordinator worker failures.
data-ai158
gke-ai-troubleshooting-tpu-connection-failure-vbar-oom
Diagnose and prevent `vbar_control_agent` segfaults and OOMs caused by race conditions during TPU device resets and frequent metrics collection (e.g. every 3s). Use when TPU slice initialization fails or `vbar_control_agent` crashes on TPU v6e nodes.
development148
gke-ai-troubleshooting-skill-creation-guide
Expert instructions for building high-quality GKE troubleshooting skills. Codifies Step 0 context rules, zero-hallucination signatures, and explicit LQL/PromQL query requirements.
development148
gke-productionize
Assists in preparing applications and clusters on GKE for production.
tools148
gke-app-onboarding
Workflows for containerizing and deploying applications to GKE for the first time.
devops148
gke-workload-security
Workflows for auditing and hardening the security of GKE workloads.
testing142
gke-cost-analysis
Answer natural language questions about GKE-related costs by leveraging BigQuery export and cost allocation data.
data-ai141
gke-storage
Guidance on managing storage in Google Kubernetes Engine (GKE) clusters.
development141
gke-reliability
Workflows for ensuring high availability and reliability of GKE workloads.
data-ai141
gke-multi-tenancy
Guidance on implementing multi-tenancy and governance in Google Kubernetes Engine (GKE) clusters.
development141
gke-cluster-lifecycle
Guidance on managing the lifecycle and upgrades of Google Kubernetes Engine (GKE) clusters.
development141
gke-compute-class-creator
Guide for creating GKE ComputeClass resources. Use this skill when users want to define custom node configurations, autoscaling priorities, or hardware requirements (e.g., Spot VMs, GPUs, specific machine families) for their GKE workloads.
testing141
gke-inference-quickstart
Deploy optimized AI/ML inference workloads on GKE using Google's Inference Quickstart (GIQ). Covers model discovery, manifest generation, and deployment using native MCP tools and CLI.
tools141
gke-networking-edge
Workflows for configuring edge networking, ingress, and security on GKE.
testing141
gke-workload-scaling
Specific workflows for scaling GKE workloads using HPA and VPA, as well as best practices for autoscaling configuration.
testing141
gke-observability
Workflows for setting up and auditing observability (logging, monitoring, tracing) on GKE.
testing141
gke-cost-optimization
Guidance on optimizing costs for Google Kubernetes Engine (GKE) clusters.
development141
gke-cluster-creator
Guides the user through creating GKE clusters using pre-defined templates (Standard, Autopilot, GPU/AI).
documentation141
gke-backup-dr
Workflows for configuring Backup for GKE and disaster recovery.
tools140
custom-golden-image-discovery
Expert at discovering golden base images for GKE custom nodes using technical specs or context clues.
development140