Skill

gcp-expert

Google Cloud Platform expertise from Google engineers. Master GCP services, GKE, BigQuery, Vertex AI, and cloud-native architecture. Use when working with Google Cloud services, deploying to GCP, or designing GCP architectures. Learn from the company that runs Google Search, YouTube, and Gmail on their own infrastructure.

npx claudepluginhub duylinhdang1998/claude-template-agent --plugin vfm-agent-company

Tool Access

This skill uses the workspace's default tool permissions.

Preview

**Experts**: Emily Rodriguez (Google AI, 10 years), Alex Kim (Google SRE, 11 years)

Supporting Assets

references/ai-ml.mdreferences/compute.mdreferences/data.mdreferences/databases.mdreferences/messaging.md

SKILL.md

Similar Skills

skill-lookup

159.9k

Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.

prompts.chat

prompt-lookup

159.9k

Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.

prompts.chat

next-compile

139.2k

Checks Next.js compilation errors using a running Turbopack dev server after code edits. Fixes actionable issues before reporting complete. Replaces `next build`.

1 file

vercel-next-js-2

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitApr 16, 2026

Actions

View Source View Plugin View on GitHub View README

GCP Expert - Google Cloud Platform Mastery

Experts: Emily Rodriguez (Google AI, 10 years), Alex Kim (Google SRE, 11 years) Level: 10/10 - Google's own cloud platform

Overview

Google Cloud Platform from Google engineers - the infrastructure powering Search, YouTube, Gmail, Maps. This is cloud expertise from the source.

When to Use GCP Services

Compute needs:

Containers/Kubernetes → GKE (see references/compute.md)
Serverless containers → Cloud Run (see references/compute.md)
VMs → Compute Engine (see references/compute.md)

Data & Analytics:

Data warehouse → BigQuery (see references/data.md)
Streaming pipelines → Dataflow (see references/data.md)

Databases:

Relational → Cloud SQL or Cloud Spanner (see references/databases.md)
NoSQL → Firestore (see references/databases.md)

AI & ML:

Machine learning → Vertex AI (see references/ai-ml.md)

Messaging:

Pub/Sub, event-driven → See references/messaging.md

Core Workflow

Design: Choose appropriate services for requirements
Provision: Use Terraform or gcloud CLI
Deploy: GKE for containers, Cloud Run for serverless
Monitor: Cloud Monitoring + Cloud Logging
Optimize: Cost optimization + performance tuning

Best Practices

Security

IAM: Least privilege access
VPC Service Controls: Perimeter security
Secret Manager: Never hardcode secrets
Workload Identity: For GKE pods

Cost Optimization

Committed Use Discounts: Save 57% on VMs
Preemptible VMs: Save 80% for batch jobs
BigQuery slots: Reserve for predictable costs

Reliability

Multi-region for critical services
Health checks on all services
Auto-scaling for traffic spikes

Monitoring

Cloud Monitoring: Metrics + alerts
Cloud Logging: Centralized logs
Cloud Trace: Distributed tracing

Google's Production Scale

GCP powers:

Google Search: 8.5 billion searches/day
YouTube: 2 billion users, 1 billion hours/day
Gmail: 1.8 billion users
Google Maps: 1 billion users

Related Skills

kubernetes-expert - GKE foundation
deep-learning - Vertex AI ML
sre-practices - Google SRE on GCP

Last Updated: 2026-02-03 Experts: Emily Rodriguez, Alex Kim (Google, 10-11 years each)