스킬 찾기

Prepare trained machine learning models for production with deployment, monitoring, and retraining workflows. Build RAG systems that retrieve documents for answers, and integrate language model APIs with retries, fallback providers, and cost tracking.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deploying a trained model to production
• Setting up model monitoring and retraining workflows
• Building a RAG pipeline for document-based answers

Plan controlled failure experiments to uncover system weaknesses. Define normal operating metrics, estimate affected users and reliability risk, set abort and recovery conditions, and turn experiment results into a structured review with follow-up actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a controlled failure experiment
• Estimating affected users and reliability risk
• Planning a team failure response exercise

Audit environment files and repository contents for possible credential leaks, then prioritize findings by severity. Plan credential replacement, improve configuration examples, and establish checks in development and delivery pipelines to reduce accidental exposure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking configuration files before a commit
• Planning credential replacement after a leak
• Keeping environment examples safe for new contributors

Find the right skill among 37 advanced engineering options for architecture, development, automation, and operations. The index maps tasks to individual skills, helping you choose which instructions to load for a specific job.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding a skill for agent or RAG design
• Choosing database design and query optimization skills
• Finding deployment automation and monitoring skills

Review cloud permissions, public storage access, network rules, and infrastructure definitions for security gaps. The skill helps identify risky configurations, rank findings by severity, and suggest narrower permissions, with fuller coverage for AWS than Azure or GCP.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing cloud settings before deployment
• Finding excessive permissions and privilege escalation paths
• Checking public storage and exposed ports

Create CI/CD configurations, which automate build, test, and deployment steps, alongside Terraform infrastructure templates and Kubernetes deployment files. Generate health-check and rollback instructions to review before applying changes to cloud infrastructure or application environments.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up GitHub Actions or CircleCI pipelines
• Creating Terraform modules for AWS, GCP, or Azure
• Preparing blue/green or rolling deployments

Assess startup engineering operations across delivery, hiring, team structure, and production practices. Use delivery metrics, hiring conversion rates, and staffing data to identify bottlenecks, estimate candidate needs, and plan management roles and operational improvements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find where development work waits before release
• Estimate candidate volume needed for hiring goals
• Review team structure and manager hiring needs

Guide releases of Happy's CLI, mobile app, web app, and server. Choose versions and release channels, follow build and test checks, publish through the designated services, and verify the resulting packages or app updates.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Publishing a stable or beta CLI release
• Delivering preview or production mobile updates
• Building native apps and submitting to stores

Develop time-series and event-data solutions with TimescaleDB, an extension for PostgreSQL. The skill provides organized references for installation, time-based tables, ongoing aggregate calculations, compression, and performance troubleshooting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learn how to install and use TimescaleDB
• Design tables for time-series and event data
• Implement time-bucket and continuous aggregates

Diagnose GKE TPU slice creation failures caused by shared nodes. Check slice status, partition labels, and monitoring data to identify conflicting resource groups, then provide resolution steps for the user to apply.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating node overlap behind SliceCreationFailed
• Finding slices that share nodes across partition shapes
• Checking whether resource conflicts existed at incident time

Diagnose GKE TPU node pool creation or expansion failures despite reserved capacity. Trace which virtual machines and unhealthy node pools occupy reservation slots, check automatic repair settings, and provide remediation steps for the user to apply.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate TPU capacity errors despite a reservation
• Identify node pools occupying reserved TPU capacity
• Check automatic repair settings on unhealthy TPU nodes

Diagnose GKE TPU virtual machines that remain in repair by checking instance status, host events, and automatic repair history. Understand the impact on grouped TPU nodes and identify recovery steps for the user to apply.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating TPU VMs that remain in REPAIRING
• Assessing how a failed node affects a TPU slice
• Checking automatic repair history and failure reasons

Diagnose GKE TPU slice creation failures and pending JobSets caused by unstable managed instance groups, the underlying VM groups. Read-only checks examine logs, instance status, upgrades, and repairs to identify causes and suggest user-applied fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating TPU SliceCreationFailed errors
• Checking whether pending JobSets relate to MIG instability
• Tracing stalled node pool upgrades or repairs

Investigate stalled TPU training across multiple slices on GKE using hang reports, logs, and latency metrics. Separate compilation inconsistencies and data input stalls from hardware or network faults, and identify the relevant nodes for further investigation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating HANG_DETECTED logs during TPU training
• Separating input stalls from hardware faults
• Mapping reported faulty instances to GKE nodes

Investigate slow TPU training on GKE by comparing diagnostic events with one-minute monitoring metrics. Separate memory or CPU bottlenecks from hardware and network issues, and identify the appropriate next steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating slower TPU training without pod crashes
• Checking PERFORMANCE_DEGRADATION events
• Separating resource bottlenecks from infrastructure issues

Diagnose unresponsive GKE GPU or TPU nodes and pods stuck terminating through read-only checks of node status, logs, serial output, and repair history. Receive documented recovery guidance to apply yourself.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate nodes stuck in NodeStatusUnknown
• Find kernel panic or hardware failure evidence
• Check node auto-repair settings and failures

Guides migration of existing AI inference workloads to self-hosted GKE, Google’s managed Kubernetes service. Covers requirements, GPU sizing, deployment configuration, model storage, validation, and traffic cutover using gcloud and kubectl.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Migrating an existing Cloud Run AI service to GKE
• Planning a self-hosted replacement for Gemini API inference
• Sizing GPUs and preparing deployment configuration

Design an enterprise search system that answers questions using retrieved company content, an approach called RAG. Gather requirements and produce architecture diagrams, deployment guidance, and validation plans using GKE, AlloyDB, and open models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing conversational search for internal documents
• Planning RAG with a vector-enabled SQL database
• Hosting open models on GKE

Guides authentication and access permissions for Google Cloud users and applications. It helps choose credentials for local development, production services, or external clouds, with guidance on short-lived credentials and avoiding downloaded service account keys.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up credentials for local Python development
• Configure Cloud Run access to Cloud SQL
• Connect workloads on AWS or Azure to Google Cloud

Investigate failed workflows and tasks in Managed Service for Apache Airflow. The skill compares remote logs, task states, and source code to explain failures, show supporting evidence, and recommend specific code or configuration fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a failed DAG run
• Diagnosing task timeouts and queue delays
• Checking service errors against DAG code

Diagnoses applications that fail to start or repeatedly crash on GKE, Google's managed Kubernetes service. It examines logs, events, memory use, image pulls, and connectivity, then proposes configuration patches or commands without applying live changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate repeated container restarts
• Diagnose memory exhaustion
• Find causes of image pull or scheduling failures

Guides an application’s first deployment to GKE, Google’s managed Kubernetes service. Covers application assessment, container creation, image storage, deployment configuration, security settings, health checks, and verification that the application is running.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deploying an existing application to GKE for the first time
• Creating a Dockerfile and registering a container image
• Preparing deployment configuration with health checks

Investigate interruptions affecting GPU and TPU workloads on GKE using maintenance labels, monitoring queries, logs, and node scheduling restrictions. The skill helps determine whether host maintenance caused a disruption and recommends workload protection measures when maintenance is confirmed or expected.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating unexpected GPU or TPU workload interruptions
• Checking upcoming host maintenance on GKE nodes
• Tracking maintenance interruptions with PromQL

Assess whether a GKE cluster or application is ready for production. Coordinates specialist skills to review scaling, security, reliability, monitoring, recovery, costs, and maintenance, then reports domain status, a weighted readiness score, and remediation priorities.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review a GKE application before its production launch
• Assess production readiness across an entire cluster
• Prioritize fixes using domain status and a readiness score