查找技能

Review Google Cloud operations and develop guidance for monitoring, incident response, resource sizing, and automated deployments. Use framework-based questions and checklists to identify gaps in production readiness and plan ongoing operational improvements.

中文简介正在准备中。当前显示英语简介。

• Reviewing production readiness
• Planning monitoring and logging
• Improving incident response procedures

Helps choose and tune Cloud Storage FUSE mounts, which expose bucket objects through file paths. It covers cache sizing, training performance, checkpoint write safety, and cost diagnosis on GKE, Compute Engine, and Cloud Run.

中文简介正在准备中。当前显示英语简介。

• Access training data through file paths
• Choose between FUSE, native reads, and shared file systems
• Check checkpoint and concurrent write safety

Create and connect to managed MySQL, PostgreSQL, or SQL Server databases on Google Cloud. This skill guides instance setup, database creation, access permissions, and connection steps, with references for backups, security, and Terraform configuration.

中文简介正在准备中。当前显示英语简介。

• Create a PostgreSQL database on Google Cloud
• Connect to a database through Cloud SQL Auth Proxy
• Review database permissions and backup options

Create and manage custom Agent resources on Gemini Enterprise Agent Platform before running conversations. Prepare REST requests to configure instructions, attach files and skills, connect tools, track creation progress, and retrieve, update, or delete agents.

中文简介正在准备中。当前显示英语简介。

• Create an Agent with task-specific instructions
• Attach files and skills from Cloud Storage or Skill Registry
• Configure connections to external MCP tools

Answers questions about GKE spending using BigQuery billing exports and live cluster metrics. It breaks down costs by project, namespace, or workload and compares requested computing resources with actual usage to investigate cost increases.

中文简介正在准备中。当前显示英语简介。

• Comparing GKE costs across projects
• Finding the most expensive namespace or workload
• Investigating a sudden increase in cluster costs

Investigate crashes, out-of-memory errors, and device initialization failures on GKE TPU v6e nodes. The skill checks logs and custom metrics collection for conflicting operations, then guides temporary mitigation by disabling an identified collector.

中文简介正在准备中。当前显示英语简介。

• Investigate vbar_control_agent crashes and memory exhaustion
• Check tpu-device-plugin metrics checksum errors
• Inspect conflicts with custom TPU metrics collectors

Plan and configure GKE cluster networks, including private nodes, IP address ranges, DNS, and outbound connectivity. Use the guidance to set up VPC-native networking and Dataplane V2, which provides built-in network policy enforcement.

中文简介正在准备中。当前显示英语简介。

• Designing a private GKE cluster network
• Planning IP ranges for Pods, Services, and nodes
• Configuring outbound access with a static source IP

Build Gemini API integrations on Google Cloud’s Agent Platform using the Google Gen AI SDK. Get guidance on authentication, text and media processing, structured JSON responses, function calls, caching, batch processing, and real-time voice or video interactions.

中文简介正在准备中。当前显示英语简介。

• Adding Gemini to enterprise applications
• Processing images, audio, and documents
• Generating JSON in a specified format

Reserve remote Android devices on Google's Developer Device Platform and connect through ADB, Android's device control tool. Check session status and expiration, extend usage time, or cancel sessions and release resources.

中文简介正在准备中。当前显示英语简介。

• Find and reserve a remote Android device
• Connect to a reserved device through ADB
• Check session status and expiration

Create and validate Terraform alerts for GKE using PromQL, a monitoring query language. Cover response times, errors, traffic, memory usage, and cluster health, with checks for alert timing, duplicate signals, and metric ingestion costs.

中文简介正在准备中。当前显示英语简介。

• Create alerts for GKE service latency and errors
• Detect frequent container restarts and unhealthy nodes
• Review existing Terraform alert configurations

Configure Backup for GKE to protect Kubernetes configurations and persistent data. Set backup schedules, retention periods, and customer-managed encryption keys, then prepare restore plans with explicit policies for handling existing resources.

中文简介正在准备中。当前显示英语简介。

• Setting scheduled backups and retention periods
• Backing up persistent data and Secrets
• Encrypting backups with customer-managed keys

Configure GKE logging, metrics collection, dashboards, and alerts with Cloud Logging, Cloud Monitoring, and managed Prometheus. Diagnose missing measurements, collection failures, permission errors, and alert rule problems to identify appropriate configuration changes.

中文简介正在准备中。当前显示英语简介。

• Setting up GKE logging and metrics collection
• Investigating missing Prometheus metrics
• Planning dashboards and alerts for cluster health

Diagnose why GKE Pods cannot authenticate to Google Cloud APIs. Inspect cluster settings, service account bindings, resource permissions, and metadata server health, then provide evidence and concrete fixes for a human to apply.

中文简介正在准备中。当前显示英语简介。

• Investigate Pod authentication failures and 403 errors
• Check Kubernetes service account identity bindings
• Diagnose metadata server connectivity problems

Audit and strengthen security for applications running on GKE. Configure pod traffic restrictions, sandbox isolation, namespace security standards, and Secret Manager volume mounts to protect workloads at the application and namespace level.

中文简介正在准备中。当前显示英语简介。

• Auditing GKE security settings
• Restricting communication within a namespace
• Isolating risky pods and applying security standards

Diagnose interrupted or repeatedly restarting AI training jobs managed by JobSet on GKE. Correlate restart metrics, node events, host health, and worker logs to distinguish Spot VM preemptions, infrastructure failures, and application crashes, then recommend responses.

中文简介正在准备中。当前显示英语简介。

• Investigating repeated JobSet restarts
• Checking whether Spot VM preemptions interrupted training
• Tracing recurring failures to a physical host

Prepare and run Google Cloud CLI commands with syntax checks, explicit project and location settings, and focused output. Guides agents through change previews and authorization requirements for destructive operations and sensitive infrastructure changes.

中文简介正在准备中。当前显示英语简介。

• Check command syntax and flags before execution
• List cloud resources with only the fields needed
• Review infrastructure changes before running commands

Trace where BigQuery and Cloud Storage data comes from and where it goes. The skill summarizes table or column lineage, meaning data origins and movement, in a readable Markdown report to support data quality investigations.

中文简介正在准备中。当前显示英语简介。

• Investigating data origins during a quality issue
• Summarizing data sources and destinations
• Tracing the flow of a specific column

Reduce Google Kubernetes Engine costs by adjusting CPU and memory requests, setting resource quotas, and choosing Spot VMs or committed use discounts. Match spending decisions to steady usage, variable demand, and workloads that tolerate interruptions.

中文简介正在准备中。当前显示英语简介。

• Reduce excessive CPU and memory requests
• Set resource quotas for teams sharing a cluster
• Move interruption-tolerant batch jobs to Spot VMs

Assess how changes, failures, or paused updates to a BigQuery table or view affect downstream assets. Trace data lineage, the relationships showing where data flows, and summarize dependent tables, dashboards, and processes with direct and indirect impacts.

中文简介正在准备中。当前显示英语简介。

• Assess downstream effects of a table failure
• Check dependencies before changing or deleting a view
• Evaluate the impact of pausing data updates

Convert Snowflake dbt SQL models to BigQuery through a bulk migration workflow. Preserve Jinja template logic while adapting configuration, explicit type conversions, JSON access, and deduplication patterns, with translated files saved in their directory structure.

中文简介正在准备中。当前显示英语简介。

• Migrating Snowflake dbt models to BigQuery in bulk
• Preserving dbt references and incremental processing logic
• Adapting JSON, array, and STRUCT access during migration

Set up a managed Kubernetes environment on Google Cloud, from choosing Autopilot or Standard to creating a GKE cluster, obtaining kubectl connection credentials, and deploying workloads. Includes guidance on private clusters and resource requests.

中文简介正在准备中。当前显示英语简介。

• Choosing between Autopilot and Standard
• Creating a private GKE cluster
• Obtaining kubectl credentials for a cluster

Prepare to fine-tune open models or Gemini models on Agent Platform. Check the environment, convert and validate training data, choose supported models and settings, and estimate tuning costs for open models.

中文简介正在准备中。当前显示英语简介。

• Checking whether an Agent Platform tuning environment is ready
• Converting and validating training datasets
• Choosing models and training settings for a task

Manages Agent Platform endpoints, the stable URLs used to serve online model predictions. It supports listing, inspecting, creating, updating, and deleting endpoints, plus troubleshooting permission errors, quota limits, and resources that are busy.

中文简介正在准备中。当前显示英语简介。

• Listing endpoints and checking their configuration
• Creating an endpoint before model deployment
• Updating endpoint display names or labels

Configure Cloud Logging within one Google Cloud project. Set storage locations, retention periods, routing rules, and viewing permissions; create metrics from logs; and adjust stored volume through exclusions or sampling, which retains only a portion of entries.

中文简介正在准备中。当前显示英语简介。

• Set regional log storage and retention periods
• Restrict access to sensitive logs
• Count specific errors with logs-based metrics