[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6997631CB9GNEWFFW3FFGH0":3,"skill-same:01M6997631CB9GNEWFFW3FFGH0":81},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6997631CB9GNEWFFW3FFGH0","google-cloud-waf-cost-optimization",null,"Evaluates Google Cloud workloads for cost efficiency and FinOps alignment using the Google Cloud Well-Architected Framework Cost Optimization pillar. Use when the user asks to analyze Google Cloud spend, reduce cloud bills, rightsize resources (for example, Compute, GKE, Storage, Databases), evaluate discount options (for example, CUDs, SUDs, Spot VMs), or eliminate idle capacity. Do not use for standalone product pricing lookups or non-cost architecture design.","google\u002Fskills","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M698WR0H76ENHE587T9EJT89",24235,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-waf-cost-optimization\u002FSKILL.md",[],[9,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"google cloud","google cloud waf cost optimization","cost optimization","cloud","waf","Optimization","cost","when","design","reduce","standalone","resources","efficiency","architecture design","alignment","databases","analyze","product","architecture","2026-11-10 10:12:30",false,"---\nname: google-cloud-waf-cost-optimization\nmetadata:\n  version: \"1.0.2\"\n  category: WellArchitectedFramework\ndescription: Evaluates Google Cloud workloads for cost efficiency and FinOps alignment using the Google Cloud Well-Architected Framework Cost Optimization pillar. Use when the user asks to analyze Google Cloud spend, reduce cloud bills, rightsize resources (for example, Compute, GKE, Storage, Databases), evaluate discount options (for example, CUDs, SUDs, Spot VMs), or eliminate idle capacity. Do not use for standalone product pricing lookups or non-cost architecture design.\n---\n\n# Google Cloud Well-Architected Framework skill for the Cost Optimization pillar\n\n## Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read and follow the instructions in\n[Usage Attribution](references\u002Fattribution.md).\n\n## Overview\n\nThe Cost Optimization pillar of the Google Cloud Well-Architected Framework\nprovides a structured approach to optimize the costs of your cloud workloads\nwhile maximizing business value. Cloud costs differ significantly from\non-premises capital expenditure (CapEx) models, requiring a shift to operational\nexpenditure (OpEx) management and a culture of accountability (FinOps).\nThe FinOps lifecycle consists of three iterative phases:\n- **Inform**: Visibility and allocation. Always start with **Cloud Billing\n  reports** for built-in console visibility (filtered by department labels).\n  Complement with **Looker Studio** for custom, shareable cross-departmental\n  dashboards.\n\n- **Optimize**: Rates and usage. Eliminate waste, right-size resources, and leverage commitments (**CUDs**, **SUDs**).\n- **Operate**: Continuous improvement. Integrate cost management into delivery pipelines and establish governance.\n\n## Operational instructions\n\n- **Comprehensive First**: Always provide a complete list of standard recommendations\u002Fstrategies relevant to the service or scenario mentioned. Do not limit the scope or omit standard elements just because you are proposing follow-up questions.\n- **Full Conjunction**: When an instruction bundles multiple actions (e.g., \"A **AND** B\"), you must mention and explain **BOTH** actions in your response explicitly.\n- **Conditional Assessment**: Only use the 'Workload assessment questions' to refine advice *after* providing standard framework recommendations, unless the user explicitly asks for an interview or assessment first.\n\n## Core principles\n\nThe recommendations in the cost optimization pillar of the Well-Architected\nFramework are aligned with the following core principles:\n\n-  **Align cloud spending with business value**: Ensure that your cloud\n   resources deliver measurable business value by aligning IT spending with\n   business objectives. Prioritize investments that directly contribute to\n   revenue, customer satisfaction, or operational efficiency. Grounding\n   document:\n   https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fframework\u002Fcost-optimization\u002Falign-cloud-spending-business-value.md.txt\n\n-  **Foster a culture of cost awareness**: Ensure that people across your\n   organization consider the cost impact of their decisions and activities.\n   Provide teams with the visibility and information they need to make informed,\n   cost-conscious choices. Grounding document:\n   https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fframework\u002Fcost-optimization\u002Ffoster-culture-cost-awareness.md.txt\n\n-  **Optimize resource usage**: Provision only the resources that you need and\n   pay only for what you consume. Select the most cost-effective resource types,\n   sizes, and locations that meet your technical and business requirements.\n   Grounding document:\n   https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fframework\u002Fcost-optimization\u002Foptimize-resource-usage.md.txt\n\n-  **Optimize continuously**: Continuously monitor your cloud resource usage and\n   costs, and proactively make adjustments as needed to optimize your spending.\n   This iterative approach helps identify and address inefficiencies before they\n   become significant. Grounding document:\n   https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fframework\u002Fcost-optimization\u002Foptimize-continuously.md.txt\n\n## Relevant Google Cloud products\n\nThe following are _examples_ of Google Cloud products and features that are\nrelevant to cost optimization:\n\n- **Visibility and monitoring**:\n\n  - **Cloud Billing reports**: Built-in dashboards for visualizing spending and\n    trends. **Essential for visibility within the console.**\n  - **BigQuery billing export**: Enables granular, custom analysis of billing\n    data using SQL and BI tools.\n  - **Looker Studio**: Used for creating detailed, shared cost dashboards and\n    reports. **Use alongside Cloud Billing reports for custom visual insights.**\n  - **Billing alerts and budgets**: Automated notifications when spending\n    reaches predefined thresholds.\n  - **Storage Insights**: Used to analyze Cloud Storage access patterns and identify\n    cost-saving opportunities.\n\n- **Automation and optimization tools**:\n\n  - **Recommender \u002F Active Assist**: Automatically identifies idle resources,\n    rightsizing opportunities, and unused commitments.\n  - **Cloud Hub Optimization**: Integrates billing and resource utilization data\n    to help developers and application owners quickly identify their most\n    expensive, fluctuating, or underutilized cloud resources.\n  - **FinOps hub**: Presents active savings and optimization opportunities in\n    one dashboard.\n  - **Billing quotas**: Limits on resource consumption to prevent unexpected\n    cost spikes.\n\n- **Efficient infrastructure**:\n\n  - **Managed services and serverless services**: Services like Cloud Run, Cloud\n    Run functions, and GKE Autopilot reduce operational overhead and pay-per-use\n    scaling.\n  - **Compute Engine**:\n    - **Committed Use Discounts (CUDs)**: Best for predictable, steady-state workloads.\n    - **Spot VMs**: Best for fault-tolerant, interruptible, or unpredictable batch tasks.\n    - **Sustained Use Discounts (SUDs)**: Passive, automatic discounts for instances running a significant portion of the month without commitments. **Always mention this as a passive alternative or complement to CUDs.**\n\n  - **Cloud Storage Lifecycle Policies**: Automated moves data to lower-cost\n    storage classes (Nearline, Coldline, Archive) based on age or access.\n    **Note**: Always recommend **Storage Insights** first to understand current\n    access patterns before defining lifecycle rules.\n\n  - **Networking and Content Delivery**:\n    - **Location awareness**: Keep traffic within a single region where possible to avoid inter-region data transfer costs.\n    - **Cloud CDN**: Caches content to reduce data egress from the origin.\n    - **Network Service Tiers**: Offers **Standard Tier** as a lower-cost option compared to **Premium Tier** for latency-tolerant traffic.\n    - **Cloud Interconnect \u002F Direct Peering**: Optimizes costs for high-volume data transfer to on-premises environments. **Note**: Always clarify hybrid connectivity options when discussing egress control, as on-premises sync is often a factor in multi-regional designs.\n  - **Managed Databases**:\n    - **Instance sizing**: Right-size CPU and memory based on Cloud Monitoring metrics.\n    - **High Availability (HA)**: Implement HA only for production environments to avoid doubling node costs for all environments.\n    - **Storage Optimization**: Optimize storage costs by managing backup retention policies **AND** explicitly identifying and deleting unused or idle resources (like unused and orphaned disks, expired snapshots, or idle instances).\n\n\n- **Organization and governance**:\n\n  - **Resource Manager**: Logical structure (Organizations, Folders, Projects)\n    for cost attribution.\n  - **Labels**: Metadata tags for categorizing and filtering costs by\n    environment, team, or application.\n  - **Organization Policy Service**: Enforces constraints (e.g., restricted\n    regions or machine types) to control costs.\n\n## Workload assessment questions\n\nAsk appropriate questions to understand the cost-related requirements and\nconstraints of the workload and the user's organization. Choose questions from\nthe following list:\n\n- How do you incorporate cost considerations into your cloud architecture design\n  process?\n- How do you foster a culture of cost awareness among your development teams?\n- How do you monitor and manage cloud costs across different projects or\n  departments?\n- What strategies do you use to optimize the cost of your compute resources?\n- How do you balance cost optimization with the need for agility and innovation?\n- How do you ensure that you are not over-provisioning cloud resources?\n- How do you use data and analytics to drive cost optimization decisions?\n- How do you optimize costs in different environments (e.g., development,\n  testing, production)?\n- How do you ensure that your cost optimization efforts are sustainable and\n  ongoing?\n- How do you measure the success of your cloud cost optimization initiatives?\n\n## Validation checklist\n\nUse the following checklist to evaluate the architecture's alignment with\ncost-optimization recommendations:\n\n- **Cost Attribution**: 100% of resources are labeled with key metadata\n  (e.g., `env`, `team`, `app`).\n- **Granular Visibility**: BigQuery billing export is enabled and used for\n  regular cost reviews.\n- **Budgets and Alerts**: Every project or business unit has defined budgets\n  and active alerts.\n- **Rightsizing**: Resources are regularly adjusted based on rightsizing\n  suggestions provided by Active Assist Recommender.\n- **Commitment Strategy**: Spend is reviewed monthly to optimize Committed Use Discount (CUD) coverage. For non-committed workloads, verify if **Sustained Use Discounts (SUDs)** are being captured automatically.\n- **Idle Resource Management**: Unused disks, IP addresses, and idle VMs are\n  identified and removed monthly.\n- **Managed Services**: Serverless options are preferred for new workloads\n  unless specific technical constraints exist.\n- **Storage Tiers**: Lifecycle policies are active for all major storage\n  buckets to minimize archival costs. Be aware of **retrieval fees**\n  associated with Nearline, Coldline and Archive storage classes.\n- **Network Egress**: Data transfer is minimized by keeping traffic regional,\n  using **Cloud CDN**, and leveraging **Standard Network Tier** where\n  appropriate. High-volume on-premises traffic uses **Direct Peering** or\n  **Cloud Interconnect** (always verify if hybrid connectivity is involved).\n- **Native Reporting**: **Cloud Billing reports** must be used for standard\n  views of spending trends in the console.\n- **Custom Dashboards**: **Looker Studio** is used for advanced, shareable, and\n  customized reporting.\n\n\n\n","# Google Cloud Well-Architected Framework skill for the Cost Optimization pillar\n\n## Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read and follow the instructions in\n[Usage Attribution](references\u002Fattribution.md).\n\n## Overview\n\nThe Cost Optimization pillar of the Google Cloud Well-Architected Framework\nprovides a structured approach to optimize the costs of your cloud workloads\nwhile maximizing business value. Cloud costs differ significantly from\non-premises capital expenditure (CapEx) models, requiring a shift to operational\nexpenditure (OpEx) management and a culture of accountability (FinOps).\nThe FinOps lifecycle consists of three iterative phases:\n- **Inform**: Visibility and allocation. Always start with **Cloud Billing\n  reports** for built-in console visibility (filtered by department labels).\n  Complement with **Looker Studio** for custom, shareable cross-departmental\n  dashboards.\n\n- **Optimize**: Rates and usage. Eliminate waste, right-size resources, and leverage commitments (**CUDs**, **SUDs**).\n- **Operate**: Continuous improvement. Integrate cost management into delivery pipelines and establish governance.\n\n## Operational instructions\n\n- **Comprehensive First**: Always provide a complete list of standard recommendations\u002Fstrategies relevant to the service or scenario mentioned. Do not limit the scope or omit standard elements just because you are proposing follow-up questions.\n- **Full Conjunction**: When an instruction bundles multiple actions (e.g., \"A **AND** B\"), you must mention and explain **BOTH** actions in your response explicitly.\n- **Conditional Assessment**: Only use the 'Workload assessment questions' to refine advice *after* providing standard framework recommendations, unless the user explicitly asks for an interview or assessment first.\n\n## Core principles\n\nThe recommendations in the cost optimization pillar of the Well-Architected\nFramework are aligned with the following core principles:\n\n-  **Align cloud spending with business value**: Ensure that your cloud\n   resources deliver measurable business value by aligning IT spending with\n   business objectives. Prioritize investments that directly contribute to\n   revenue, customer satisfaction, or operational efficiency. Grounding\n   document:\n   https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fframework\u002Fcost-optimization\u002Falign-cloud-spending-business-value.md.txt\n\n-  **Foster a culture of cost awareness**: Ensure that people across your\n   organization consider the cost impact of their decisions and activities.\n   Provide teams with the visibility and information they need to make informed,\n   cost-conscious choices. Grounding document:\n   https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fframework\u002Fcost-optimization\u002Ffoster-culture-cost-awareness.md.txt\n\n-  **Optimize resource usage**: Provision only the resources that you need and\n   pay only for what you consume. Select the most cost-effective resource types,\n   sizes, and locations that meet your technical and business requirements.\n   Grounding document:\n   https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fframework\u002Fcost-optimization\u002Foptimize-resource-usage.md.txt\n\n-  **Optimize continuously**: Continuously monitor your cloud resource usage and\n   costs, and proactively make adjustments as needed to optimize your spending.\n   This iterative approach helps identify and address inefficiencies before they\n   become significant. Grounding document:\n   https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fframework\u002Fcost-optimization\u002Foptimize-continuously.md.txt\n\n## Relevant Google Cloud products\n\nThe following are _examples_ of Google Cloud products and features that are\nrelevant to cost optimization:\n\n- **Visibility and monitoring**:\n\n  - **Cloud Billing reports**: Built-in dashboards for visualizing spending and\n    trends. **Essential for visibility within the console.**\n  - **BigQuery billing export**: Enables granular, custom analysis of billing\n    data using SQL and BI tools.\n  - **Looker Studio**: Used for creating detailed, shared cost dashboards and\n    reports. **Use alongside Cloud Billing reports for custom visual insights.**\n  - **Billing alerts and budgets**: Automated notifications when spending\n    reaches predefined thresholds.\n  - **Storage Insights**: Used to analyze Cloud Storage access patterns and identify\n    cost-saving opportunities.\n\n- **Automation and optimization tools**:\n\n  - **Recommender \u002F Active Assist**: Automatically identifies idle resources,\n    rightsizing opportunities, and unused commitments.\n  - **Cloud Hub Optimization**: Integrates billing and resource utilization data\n    to help developers and application owners quickly identify their most\n    expensive, fluctuating, or underutilized cloud resources.\n  - **FinOps hub**: Presents active savings and optimization opportunities in\n    one dashboard.\n  - **Billing quotas**: Limits on resource consumption to prevent unexpected\n    cost spikes.\n\n- **Efficient infrastructure**:\n\n  - **Managed services and serverless services**: Services like Cloud Run, Cloud\n    Run functions, and GKE Autopilot reduce operational overhead and pay-per-use\n    scaling.\n  - **Compute Engine**:\n    - **Committed Use Discounts (CUDs)**: Best for predictable, steady-state workloads.\n    - **Spot VMs**: Best for fault-tolerant, interruptible, or unpredictable batch tasks.\n    - **Sustained Use Discounts (SUDs)**: Passive, automatic discounts for instances running a significant portion of the month without commitments. **Always mention this as a passive alternative or complement to CUDs.**\n\n  - **Cloud Storage Lifecycle Policies**: Automated moves data to lower-cost\n    storage classes (Nearline, Coldline, Archive) based on age or access.\n    **Note**: Always recommend **Storage Insights** first to understand current\n    access patterns before defining lifecycle rules.\n\n  - **Networking and Content Delivery**:\n    - **Location awareness**: Keep traffic within a single region where possible to avoid inter-region data transfer costs.\n    - **Cloud CDN**: Caches content to reduce data egress from the origin.\n    - **Network Service Tiers**: Offers **Standard Tier** as a lower-cost option compared to **Premium Tier** for latency-tolerant traffic.\n    - **Cloud Interconnect \u002F Direct Peering**: Optimizes costs for high-volume data transfer to on-premises environments. **Note**: Always clarify hybrid connectivity options when discussing egress control, as on-premises sync is often a factor in multi-regional designs.\n  - **Managed Databases**:\n    - **Instance sizing**: Right-size CPU and memory based on Cloud Monitoring metrics.\n    - **High Availability (HA)**: Implement HA only for production environments to avoid doubling node costs for all environments.\n    - **Storage Optimization**: Optimize storage costs by managing backup retention policies **AND** explicitly identifying and deleting unused or idle resources (like unused and orphaned disks, expired snapshots, or idle instances).\n\n\n- **Organization and governance**:\n\n  - **Resource Manager**: Logical structure (Organizations, Folders, Projects)\n    for cost attribution.\n  - **Labels**: Metadata tags for categorizing and filtering costs by\n    environment, team, or application.\n  - **Organization Policy Service**: Enforces constraints (e.g., restricted\n    regions or machine types) to control costs.\n\n## Workload assessment questions\n\nAsk appropriate questions to understand the cost-related requirements and\nconstraints of the workload and the user's organization. Choose questions from\nthe following list:\n\n- How do you incorporate cost considerations into your cloud architecture design\n  process?\n- How do you foster a culture of cost awareness among your development teams?\n- How do you monitor and manage cloud costs across different projects or\n  departments?\n- What strategies do you use to optimize the cost of your compute resources?\n- How do you balance cost optimization with the need for agility and innovation?\n- How do you ensure that you are not over-provisioning cloud resources?\n- How do you use data and analytics to drive cost optimization decisions?\n- How do you optimize costs in different environments (e.g., development,\n  testing, production)?\n- How do you ensure that your cost optimization efforts are sustainable and\n  ongoing?\n- How do you measure the success of your cloud cost optimization initiatives?\n\n## Validation checklist\n\nUse the following checklist to evaluate the architecture's alignment with\ncost-optimization recommendations:\n\n- **Cost Attribution**: 100% of resources are labeled with key metadata\n  (e.g., `env`, `team`, `app`).\n- **Granular Visibility**: BigQuery billing export is enabled and used for\n  regular cost reviews.\n- **Budgets and Alerts**: Every project or business unit has defined budgets\n  and active alerts.\n- **Rightsizing**: Resources are regularly adjusted based on rightsizing\n  suggestions provided by Active Assist Recommender.\n- **Commitment Strategy**: Spend is reviewed monthly to optimize Committed Use Discount (CUD) coverage. For non-committed workloads, verify if **Sustained Use Discounts (SUDs)** are being captured automatically.\n- **Idle Resource Management**: Unused disks, IP addresses, and idle VMs are\n  identified and removed monthly.\n- **Managed Services**: Serverless options are preferred for new workloads\n  unless specific technical constraints exist.\n- **Storage Tiers**: Lifecycle policies are active for all major storage\n  buckets to minimize archival costs. Be aware of **retrieval fees**\n  associated with Nearline, Coldline and Archive storage classes.\n- **Network Egress**: Data transfer is minimized by keeping traffic regional,\n  using **Cloud CDN**, and leveraging **Standard Network Tier** where\n  appropriate. High-volume on-premises traffic uses **Direct Peering** or\n  **Cloud Interconnect** (always verify if hybrid connectivity is involved).\n- **Native Reporting**: **Cloud Billing reports** must be used for standard\n  views of spending trends in the console.\n- **Custom Dashboards**: **Looker Studio** is used for advanced, shareable, and\n  customized reporting.\n\n\n\n",{"name":5,"metadata":43,"description":7},{"version":44,"category":45},"1.0.2","WellArchitectedFramework","main","bb9b3f464aae37af360d079c1d863524955b0363","skills\u002Fcloud\u002Fgoogle-cloud-waf-cost-optimization",2014,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-14 23:31:00",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add google\u002Fskills --skill google-cloud-waf-cost-optimization",{"tool":61,"command":62},"bunx","bunx skills add google\u002Fskills --skill google-cloud-waf-cost-optimization",{"tool":64,"command":65},"pnpm","pnpm dlx skills add google\u002Fskills --skill google-cloud-waf-cost-optimization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-waf-cost-optimization\u002FSKILL.md",true,[69,75],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"methods.csv","ASSET","资产文件",9911,"https:\u002F\u002Fgithub.com\u002Fsherryswift1019-gif\u002FAI-DZHT\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fbmad-advanced-elicitation\u002Fmethods.csv",{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fattribution.md","REFERENCE","参考文档",1950,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-waf-cost-optimization\u002Freferences\u002Fattribution.md",[82,90,97,104,111,118],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":89},"01M7DQ9K7JF4T7NJZ2K1MQZ44Q","cloud-operator-share-context","Shares Google Cloud operating context the user or their team already have — environments, projects, services and regions, product preferences, best practices, architecture guidance, runbooks — found in agent instruction files, local memory, skills and workflows, and the repository's GCP docs, with the operator agent's memory after the user reviews the list. Use when the user runs this skill, accepts the cloud-operator or cloud-operator-setup skill's offer to share their existing Google Cloud context, or asks to share, import or save that context or a GCP fact for the operator agent. Don't use for ordinary GCP requests, which go to the cloud-operator skill.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fcloud-operator-share-context\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":89},"01M7DQ9ERFGGQCFAWQW0KRKYBY","cloud-operator-setup","Sets up the operator agent in a Google Cloud project via the autocloud MCP server: picks the operator project, creates or checks the user's operator agent, saves the project, and offers to share the user's existing Google Cloud operating context with the operator agent's memory. Use when the user runs this skill, asks to set up the operator or create their operator agent, or chooses setup when the cloud-operator skill asks. Don't use for ordinary GCP requests or installing gcloud.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fcloud-operator-setup\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":89},"01M7B4RHQCM0DK2XQ7S7ZXVN8D","developer-device-platform-device-run","Runs automated, non-interactive jobs on remote Android devices with Developer Device Platform (DDP) Device Run using `gcloud beta device-run sessions`: native Android executables or shell scripts (for example CLI tools, custom runners, test harnesses or benchmarks) and Android instrumentation tests, on one or many devices, then waits for completion and collects per-device outputs and logs. Use when running a binary or test suite on remote devices without an interactive connection. Don't use it for interactive device reservations, adb tunnels or screen streaming (use developer-device-platform-basics), or for local devices.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloper-device-platform-device-run\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":89},"01M7B4R9YXMRW7RZP9Q9FMZJ2P","compute-vm-creation","Guides the planning, configuration, and provisioning of standalone Google Compute Engine virtual machines (VMs) and bare metal (-metal) instances using gcloud CLI commands or direct MCP tool execution. Use ONLY when the user wants to create, configure, or provision a new standalone Compute Engine VM or bare metal instance from conversational intents (hardware sizing, region selection, OS image, networking, security defaults). DO NOT read or use for Google Kubernetes Engine (GKE) Autopilot or Standard clusters, Kubernetes node pools or Pods, container orchestration, managing existing VMs, Managed Instance Groups (MIGs), or Instance Templates.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fcompute-vm-creation\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":89},"01M7B4QD02N0YBVT0838Z5K5VC","agent-platform-autorater-customization","Customizes an autorater (evaluation metric) for an AI agent so its grades match the user's own judgment, starting from the agent's real trajectories. Use when a user wants a metric tailored to their agent, wants to turn failing trajectories into rubrics, says an existing autorater grades their agent wrong, or wants an autorater to agree with human labels (autorater hillclimbing, judge calibration). Don't use for quick evals with built-in metrics or for improving the agent itself (use agent-platform-eval-flywheel).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fagent-platform-autorater-customization\u002FSKILL.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":89},"01M78JP22K73KK96JH0JNDT5C4","iap-agent-platform-troubleshooting","Diagnoses Identity-Aware Proxy (IAP) denials of outbound requests from Gemini Enterprise Agent Platform agents that run on Agent Runtime and send traffic through Agent Gateway. Use when an agent request fails with \"Egress request is not authorized\", when Cloud Audit Logs show an IAP egressViaIAP decision with granted false, when IAP audit entries are missing while debugging agent egress, or when Access policies, IAP allow policies, policy bindings, or Agent Registry entries might block agent egress. Don't use for Gemini model IAM permission errors (such as aiplatform.endpoints.predict), Agent Platform API errors, or Agent Runtime deployment or 500 errors (use agent-platform-troubleshooting instead). Don't use for setting up, creating, or connecting an Agent Gateway, or for IAP web apps, IAP TCP forwarding, or SSH.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fiap-agent-platform-troubleshooting\u002FSKILL.md",[],[]]