基础设施与 DevOps技能

Design and create custom cloud controls and frameworks for Google Cloud data boundary requirements that existing resources cannot meet. Receive prepared configuration fields for manual setup, or approve creation through the agent.

中文简介正在准备中。当前显示英语简介。

• Designing controls for requirements existing frameworks cannot meet
• Preparing configuration fields for the Google Cloud console
• Creating a framework that groups newly authored controls

Match Google Cloud data residency and access requirements to available data boundary frameworks and cloud controls. Compare ranked recommendations in a table, see requirement gaps, and receive deployment guidance with built-in frameworks prioritized.

中文简介正在准备中。当前显示英语简介。

• Finding frameworks for data residency requirements
• Comparing framework coverage and major requirement gaps
• Planning deployment for existing or new projects

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.

中文简介正在准备中。当前显示英语简介。

• 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.

中文简介正在准备中。当前显示英语简介。

• 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 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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

Creates Terraform configuration for Google Cloud Monitoring notification channels, including email, Slack, and Pub/Sub, and attaches channels to existing alert policies. It also checks Pub/Sub topic compatibility and publishing permissions when inspecting the cloud environment.

中文简介正在准备中。当前显示英语简介。

• Configuring email or Slack alert notifications
• Adding notification channels to existing alert policies
• Checking Pub/Sub topic compatibility and publishing permissions

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

Investigate slow or failing requests in Google Cloud using Cloud Trace. Filter traces by duration or error status, inspect spans representing individual operations, and retrieve related Cloud Logging entries to investigate bottlenecks and exceptions.

中文简介正在准备中。当前显示英语简介。

• Find requests exceeding a latency threshold
• Inspect operation hierarchies within a trace
• Investigate failures using related application logs

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.

中文简介正在准备中。当前显示英语简介。

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

Finds and loads relevant Google skills for choosing or setting up services, databases, storage, authentication, and other platform components. It supplies guidance for comparing Google options, understanding trade-offs, and recognizing when another choice fits better.

中文简介正在准备中。当前显示英语简介。

• Compare platforms for running a service
• Find guidance for database or authentication setup
• Locate a skill for a named Google product or API

Inspect Google Cloud Filestore usage and free space, then propose capacity increases or decreases based on configured thresholds and storage tier limits. Apply resizing after confirmation to address low space or reduce excess capacity.

中文简介正在准备中。当前显示英语简介。

• Check free space across Filestore instances
• Increase capacity when storage is running low
• Reduce excess capacity on eligible storage tiers

Adapt Airflow workflow definitions for newer versions in Google Cloud's managed service. The skill guides checks for incompatible code and dependencies, explains required changes, and supports requested deployment and verification for Airflow 2.11.1 or Airflow 3.

中文简介正在准备中。当前显示英语简介。

• Migrate workflow definitions to Airflow 2.11.1
• Review code changes needed for Airflow 3
• Replace removed operators and outdated dependencies

Inspect and manage Google Cloud IAM policies that grant roles or explicitly deny permissions. The skill prepares policy changes for user approval, supports organization, folder, project, and supported resource scopes, and verifies the resulting policy after execution.

中文简介正在准备中。当前显示英语简介。

• Reviewing existing allow and deny policies
• Adding or removing role bindings for specific identities
• Creating or updating organization, folder, or project deny policies

Browse and search files on Google Cloud Filestore, read selected log lines, and inspect permissions and timestamps. Uses a Cloud Run bridge or an existing virtual machine without requiring local NFS client packages or root access.

中文简介正在准备中。当前显示英语简介。

• Explore the folder structure of a Filestore share
• Find backup files by filename pattern
• Search remote logs for errors and read selected lines

Evaluate Google Cloud workloads and develop reliability recommendations covering user experience goals, redundancy, monitoring, and recovery. The skill applies the Google Cloud Well-Architected Framework to help identify gaps and plan improvements suited to business requirements.

中文简介正在准备中。当前显示英语简介。

• Reviewing a Google Cloud architecture for reliability gaps
• Setting reliability targets based on user experience
• Planning redundancy and behavior during partial failures

Set up an organization-wide Google Cloud foundation with 17 baseline security policies, environment folders and projects, billing links, and centralized audit logging and monitoring. Check the resulting setup against a defined validation checklist.

中文简介正在准备中。当前显示英语简介。

• Set up the initial foundation for a Google Cloud organization
• Organize production, non-production, and development resources
• Apply baseline security policies across an organization

Diagnose Google Cloud Filestore mount failures by checking client access rules, network firewalls, and audit logs. Distinguish permission errors from connection timeouts, then provide a structured report and remediation commands that require confirmation before execution.

中文简介正在准备中。当前显示英语简介。

• Investigating a Filestore mount that hangs or fails
• Diagnosing access-denied errors from a GKE workload
• Checking client permissions and VPC firewall rules

Design a Google Cloud system that combines multiple services, starting with a discussion of business and technical requirements. The skill produces service recommendations, architecture diagrams, deployment guidance, and validation plans, with user approval at each stage.

中文简介正在准备中。当前显示英语简介。

• Gather requirements for a new cloud workload
• Compare and select services for a cloud migration
• Create a diagram and explain system data flows

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.

中文简介正在准备中。当前显示英语简介。

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

Define reliability goals for Google Cloud services and generate Terraform files for Cloud Monitoring SLO alerts. A guided conversation gathers service scope, measurement metrics, targets, and alert conditions, then explains the PromQL queries used to evaluate them.

中文简介正在准备中。当前显示英语简介。

• Create availability SLO alerts for a service
• Define latency targets and measurement windows
• Configure SLO alerts for App Hub resources

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.

中文简介正在准备中。当前显示英语简介。

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

Plan and build AI agents on Google Cloud, from gathering requirements to choosing a single-agent or multi-agent design. Produce architecture diagrams, deployment code and instructions, and validation plans tailored to the workload.

中文简介正在准备中。当前显示英语简介。

• Plan an AI agent architecture on Google Cloud
• Choose between single-agent and multi-agent designs
• Prepare deployment code and step-by-step instructions