[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-google-cloud-gke-productionize":3,"mdc-sofxms-key":34,"related-org-google-cloud-gke-productionize":602,"related-repo-google-cloud-gke-productionize":789},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":24,"repoUrl":25,"updatedAt":26,"license":27,"forks":28,"topics":29,"repo":30,"sourceUrl":32,"mdContent":33},"gke-productionize","prepare GKE applications for production","Assists in preparing applications and clusters on GKE for production.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"google-cloud","Google Cloud","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fgoogle-cloud.png","GoogleCloudPlatform",[13,17,20,23],{"name":14,"slug":15,"type":16},"Operations","operations","tag",{"name":18,"slug":19,"type":16},"Deployment","deployment",{"name":21,"slug":22,"type":16},"Kubernetes","kubernetes",{"name":9,"slug":8,"type":16},161,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgke-mcp","2026-07-12T07:39:54.60281",null,78,[],{"repoUrl":25,"stars":24,"forks":28,"topics":31,"description":27},[],"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgke-mcp\u002Ftree\u002FHEAD\u002Fskills\u002Fgke-productionize","---\nname: gke-productionize\ndescription: Assists in preparing applications and clusters on GKE for production.\n---\n\n# GKE Productionize Skill\n\nThis skill acts as a high-level orchestrator for preparing a GKE cluster and its workloads for production readiness.\n\n> [!IMPORTANT]\n> This is a **meta-skill** or **orchestrator skill**. You are expected to invoke and run many other specialized skills listed in this document as part of the overall productionization process. Do not attempt to implement all production readiness features directly within this skill; instead, use this skill to assess the environment and then delegate to the specific skills for each domain.\n\n## Scope\n\nThis skill is adaptable to:\n\n- A single application (already on Kubernetes or not).\n- A set of applications.\n- A target cluster.\n\n## Workflow\n\n### 1. Discovery Phase\n\nBefore making recommendations, discover the current state of the environment.\n\n#### Cluster Discovery\n\nRun these commands to understand the cluster setup:\n\n- Check cluster details: `gcloud container clusters describe \u003Ccluster-name> --location \u003Clocation> --project \u003Cproject>`\n- Check for Autopilot vs Standard: Look for `autopilot: true` in the describe output.\n- Check release channel: Look for `releaseChannel`.\n\n#### Workload Discovery\n\nIf a specific application is targeted, discover its configuration:\n\n- Get deployment\u002Fstatefulset details: `kubectl get deployment \u003Capp-name> -n \u003Cnamespace> -o yaml`\n- Check for dedicated namespace and labels: `kubectl get namespace \u003Cnamespace> -o yaml` (Look for Pod Security Standards labels).\n- Check for dedicated service account usage: kubectl get pods -n \u003Cnamespace> -o custom-columns=\"NAME:.metadata.name,SERVICE_ACCOUNT:.spec.serviceAccountName\"\n- Check for resource requests and limits.\n- Check for liveness, readiness, and startup probes.\n- Check for HPA: `kubectl get hpa -n \u003Cnamespace>`\n- Check for PDB: `kubectl get pdb -n \u003Cnamespace>`\n- Check for NetworkPolicies: `kubectl get networkpolicy -n \u003Cnamespace>`\n\n### 2. Production Readiness Assessment\n\n**Before implementation, you MUST run the skills for each relevant specialized area listed below and incorporate its guidance into your assessment and plan. Failure to do so will result in a non-compliant production configuration.**\n\n#### A. App Onboarding (Pre-Kubernetes)\n\nIf the application is not yet running on GKE, you MUST run the `gke-app-onboarding` skill for planning containerization, image building, and basic deployment.\n\n#### B. Scalability & Resource Management\n\nEnsure workloads have appropriate resources and autoscaling.\n\n- **Action**: You MUST run the `gke-workload-scaling` skill for configuring HPA, VPA, and resource limits.\n\n#### C. Observability\n\nEnsure adequate logging and monitoring are in place.\n\n- **Action**: You MUST run the `gke-observability` skill for setting up Cloud Logging, Monitoring, and Managed Prometheus.\n\n#### D. Reliability\n\nEnsure high availability and graceful degradation.\n\n- **Action**: You MUST run the `gke-reliability` skill for configuring regional clusters, PDBs, and health probes.\n\n#### E. Security\n\nHarden the cluster and workloads.\n\n- **Action**: You MUST run the `gke-workload-security` skill for Workload Identity, Network Policies, and Shielded Nodes.\n- **Namespace Isolation**: Ensure workloads run in dedicated namespaces with Pod Security Standards (PSS) enforced via labels.\n- **Least Privilege**: Ensure workloads use dedicated ServiceAccounts instead of the `default` ServiceAccount.\n\n#### F. Backup & Disaster Recovery\n\nEnsure stateful data is protected.\n\n- **Action**: You MUST run the `gke-backup-dr` skill for configuring Backup for GKE and restore procedures.\n\n#### G. Edge Security & Ingress\n\nSecure external access.\n\n- **Action**: You MUST run the `gke-networking-edge` skill for Gateway API, Ingress, and Cloud Armor.\n\n#### H. Cost Optimization\n\nEnsure efficient use of resources.\n\n- **Action**: You MUST run the `gke-cost-optimization` skill for strategies on rightsizing, quotas, and Spot VMs.\n\n### 3. Production Readiness Scoring\n\nAfter the assessment, provide a summary report with a RAG (Red, Amber, Green) status for each area and an overall readiness score. This helps prioritize remediation efforts.\n\n## Adaptability Guidelines\n\n- **Single App**: Focus on Health Probes, HPA, Resource Limits, PDB, and Workload Identity for that specific app.\n- **Cluster Wide**: Focus on Cluster Autoscaler, Multi-zonal setup, Release Channels, Maintenance Windows, and default Network Policies.\n- **Proactive Execution**: Proactively execute relevant skills (e.g., observability, security, scaling, reliability) to assess and propose improvements, seeking user confirmation before applying state-changing implementations.\n",{"data":35,"body":36},{"name":4,"description":6},{"type":37,"children":38},"root",[39,48,54,84,91,96,116,122,129,134,141,146,187,193,198,279,285,293,299,312,318,323,344,350,355,374,380,385,404,410,415,462,468,473,492,498,503,522,528,533,552,558,563,569],{"type":40,"tag":41,"props":42,"children":44},"element","h1",{"id":43},"gke-productionize-skill",[45],{"type":46,"value":47},"text","GKE Productionize Skill",{"type":40,"tag":49,"props":50,"children":51},"p",{},[52],{"type":46,"value":53},"This skill acts as a high-level orchestrator for preparing a GKE cluster and its workloads for production readiness.",{"type":40,"tag":55,"props":56,"children":57},"blockquote",{},[58],{"type":40,"tag":49,"props":59,"children":60},{},[61,67,69,75,77,82],{"type":40,"tag":62,"props":63,"children":64},"span",{},[65],{"type":46,"value":66},"!IMPORTANT",{"type":46,"value":68},"\nThis is a ",{"type":40,"tag":70,"props":71,"children":72},"strong",{},[73],{"type":46,"value":74},"meta-skill",{"type":46,"value":76}," or ",{"type":40,"tag":70,"props":78,"children":79},{},[80],{"type":46,"value":81},"orchestrator skill",{"type":46,"value":83},". You are expected to invoke and run many other specialized skills listed in this document as part of the overall productionization process. Do not attempt to implement all production readiness features directly within this skill; instead, use this skill to assess the environment and then delegate to the specific skills for each domain.",{"type":40,"tag":85,"props":86,"children":88},"h2",{"id":87},"scope",[89],{"type":46,"value":90},"Scope",{"type":40,"tag":49,"props":92,"children":93},{},[94],{"type":46,"value":95},"This skill is adaptable to:",{"type":40,"tag":97,"props":98,"children":99},"ul",{},[100,106,111],{"type":40,"tag":101,"props":102,"children":103},"li",{},[104],{"type":46,"value":105},"A single application (already on Kubernetes or not).",{"type":40,"tag":101,"props":107,"children":108},{},[109],{"type":46,"value":110},"A set of applications.",{"type":40,"tag":101,"props":112,"children":113},{},[114],{"type":46,"value":115},"A target cluster.",{"type":40,"tag":85,"props":117,"children":119},{"id":118},"workflow",[120],{"type":46,"value":121},"Workflow",{"type":40,"tag":123,"props":124,"children":126},"h3",{"id":125},"_1-discovery-phase",[127],{"type":46,"value":128},"1. Discovery Phase",{"type":40,"tag":49,"props":130,"children":131},{},[132],{"type":46,"value":133},"Before making recommendations, discover the current state of the environment.",{"type":40,"tag":135,"props":136,"children":138},"h4",{"id":137},"cluster-discovery",[139],{"type":46,"value":140},"Cluster Discovery",{"type":40,"tag":49,"props":142,"children":143},{},[144],{"type":46,"value":145},"Run these commands to understand the cluster setup:",{"type":40,"tag":97,"props":147,"children":148},{},[149,161,174],{"type":40,"tag":101,"props":150,"children":151},{},[152,154],{"type":46,"value":153},"Check cluster details: ",{"type":40,"tag":155,"props":156,"children":158},"code",{"className":157},[],[159],{"type":46,"value":160},"gcloud container clusters describe \u003Ccluster-name> --location \u003Clocation> --project \u003Cproject>",{"type":40,"tag":101,"props":162,"children":163},{},[164,166,172],{"type":46,"value":165},"Check for Autopilot vs Standard: Look for ",{"type":40,"tag":155,"props":167,"children":169},{"className":168},[],[170],{"type":46,"value":171},"autopilot: true",{"type":46,"value":173}," in the describe output.",{"type":40,"tag":101,"props":175,"children":176},{},[177,179,185],{"type":46,"value":178},"Check release channel: Look for ",{"type":40,"tag":155,"props":180,"children":182},{"className":181},[],[183],{"type":46,"value":184},"releaseChannel",{"type":46,"value":186},".",{"type":40,"tag":135,"props":188,"children":190},{"id":189},"workload-discovery",[191],{"type":46,"value":192},"Workload Discovery",{"type":40,"tag":49,"props":194,"children":195},{},[196],{"type":46,"value":197},"If a specific application is targeted, discover its configuration:",{"type":40,"tag":97,"props":199,"children":200},{},[201,212,225,236,241,246,257,268],{"type":40,"tag":101,"props":202,"children":203},{},[204,206],{"type":46,"value":205},"Get deployment\u002Fstatefulset details: ",{"type":40,"tag":155,"props":207,"children":209},{"className":208},[],[210],{"type":46,"value":211},"kubectl get deployment \u003Capp-name> -n \u003Cnamespace> -o yaml",{"type":40,"tag":101,"props":213,"children":214},{},[215,217,223],{"type":46,"value":216},"Check for dedicated namespace and labels: ",{"type":40,"tag":155,"props":218,"children":220},{"className":219},[],[221],{"type":46,"value":222},"kubectl get namespace \u003Cnamespace> -o yaml",{"type":46,"value":224}," (Look for Pod Security Standards labels).",{"type":40,"tag":101,"props":226,"children":227},{},[228,230],{"type":46,"value":229},"Check for dedicated service account usage: kubectl get pods -n ",{"type":40,"tag":231,"props":232,"children":233},"namespace",{},[234],{"type":46,"value":235}," -o custom-columns=\"NAME:.metadata.name,SERVICE_ACCOUNT:.spec.serviceAccountName\"",{"type":40,"tag":101,"props":237,"children":238},{},[239],{"type":46,"value":240},"Check for resource requests and limits.",{"type":40,"tag":101,"props":242,"children":243},{},[244],{"type":46,"value":245},"Check for liveness, readiness, and startup probes.",{"type":40,"tag":101,"props":247,"children":248},{},[249,251],{"type":46,"value":250},"Check for HPA: ",{"type":40,"tag":155,"props":252,"children":254},{"className":253},[],[255],{"type":46,"value":256},"kubectl get hpa -n \u003Cnamespace>",{"type":40,"tag":101,"props":258,"children":259},{},[260,262],{"type":46,"value":261},"Check for PDB: ",{"type":40,"tag":155,"props":263,"children":265},{"className":264},[],[266],{"type":46,"value":267},"kubectl get pdb -n \u003Cnamespace>",{"type":40,"tag":101,"props":269,"children":270},{},[271,273],{"type":46,"value":272},"Check for NetworkPolicies: ",{"type":40,"tag":155,"props":274,"children":276},{"className":275},[],[277],{"type":46,"value":278},"kubectl get networkpolicy -n \u003Cnamespace>",{"type":40,"tag":123,"props":280,"children":282},{"id":281},"_2-production-readiness-assessment",[283],{"type":46,"value":284},"2. Production Readiness Assessment",{"type":40,"tag":49,"props":286,"children":287},{},[288],{"type":40,"tag":70,"props":289,"children":290},{},[291],{"type":46,"value":292},"Before implementation, you MUST run the skills for each relevant specialized area listed below and incorporate its guidance into your assessment and plan. Failure to do so will result in a non-compliant production configuration.",{"type":40,"tag":135,"props":294,"children":296},{"id":295},"a-app-onboarding-pre-kubernetes",[297],{"type":46,"value":298},"A. App Onboarding (Pre-Kubernetes)",{"type":40,"tag":49,"props":300,"children":301},{},[302,304,310],{"type":46,"value":303},"If the application is not yet running on GKE, you MUST run the ",{"type":40,"tag":155,"props":305,"children":307},{"className":306},[],[308],{"type":46,"value":309},"gke-app-onboarding",{"type":46,"value":311}," skill for planning containerization, image building, and basic deployment.",{"type":40,"tag":135,"props":313,"children":315},{"id":314},"b-scalability-resource-management",[316],{"type":46,"value":317},"B. Scalability & Resource Management",{"type":40,"tag":49,"props":319,"children":320},{},[321],{"type":46,"value":322},"Ensure workloads have appropriate resources and autoscaling.",{"type":40,"tag":97,"props":324,"children":325},{},[326],{"type":40,"tag":101,"props":327,"children":328},{},[329,334,336,342],{"type":40,"tag":70,"props":330,"children":331},{},[332],{"type":46,"value":333},"Action",{"type":46,"value":335},": You MUST run the ",{"type":40,"tag":155,"props":337,"children":339},{"className":338},[],[340],{"type":46,"value":341},"gke-workload-scaling",{"type":46,"value":343}," skill for configuring HPA, VPA, and resource limits.",{"type":40,"tag":135,"props":345,"children":347},{"id":346},"c-observability",[348],{"type":46,"value":349},"C. Observability",{"type":40,"tag":49,"props":351,"children":352},{},[353],{"type":46,"value":354},"Ensure adequate logging and monitoring are in place.",{"type":40,"tag":97,"props":356,"children":357},{},[358],{"type":40,"tag":101,"props":359,"children":360},{},[361,365,366,372],{"type":40,"tag":70,"props":362,"children":363},{},[364],{"type":46,"value":333},{"type":46,"value":335},{"type":40,"tag":155,"props":367,"children":369},{"className":368},[],[370],{"type":46,"value":371},"gke-observability",{"type":46,"value":373}," skill for setting up Cloud Logging, Monitoring, and Managed Prometheus.",{"type":40,"tag":135,"props":375,"children":377},{"id":376},"d-reliability",[378],{"type":46,"value":379},"D. Reliability",{"type":40,"tag":49,"props":381,"children":382},{},[383],{"type":46,"value":384},"Ensure high availability and graceful degradation.",{"type":40,"tag":97,"props":386,"children":387},{},[388],{"type":40,"tag":101,"props":389,"children":390},{},[391,395,396,402],{"type":40,"tag":70,"props":392,"children":393},{},[394],{"type":46,"value":333},{"type":46,"value":335},{"type":40,"tag":155,"props":397,"children":399},{"className":398},[],[400],{"type":46,"value":401},"gke-reliability",{"type":46,"value":403}," skill for configuring regional clusters, PDBs, and health probes.",{"type":40,"tag":135,"props":405,"children":407},{"id":406},"e-security",[408],{"type":46,"value":409},"E. Security",{"type":40,"tag":49,"props":411,"children":412},{},[413],{"type":46,"value":414},"Harden the cluster and workloads.",{"type":40,"tag":97,"props":416,"children":417},{},[418,434,444],{"type":40,"tag":101,"props":419,"children":420},{},[421,425,426,432],{"type":40,"tag":70,"props":422,"children":423},{},[424],{"type":46,"value":333},{"type":46,"value":335},{"type":40,"tag":155,"props":427,"children":429},{"className":428},[],[430],{"type":46,"value":431},"gke-workload-security",{"type":46,"value":433}," skill for Workload Identity, Network Policies, and Shielded Nodes.",{"type":40,"tag":101,"props":435,"children":436},{},[437,442],{"type":40,"tag":70,"props":438,"children":439},{},[440],{"type":46,"value":441},"Namespace Isolation",{"type":46,"value":443},": Ensure workloads run in dedicated namespaces with Pod Security Standards (PSS) enforced via labels.",{"type":40,"tag":101,"props":445,"children":446},{},[447,452,454,460],{"type":40,"tag":70,"props":448,"children":449},{},[450],{"type":46,"value":451},"Least Privilege",{"type":46,"value":453},": Ensure workloads use dedicated ServiceAccounts instead of the ",{"type":40,"tag":155,"props":455,"children":457},{"className":456},[],[458],{"type":46,"value":459},"default",{"type":46,"value":461}," ServiceAccount.",{"type":40,"tag":135,"props":463,"children":465},{"id":464},"f-backup-disaster-recovery",[466],{"type":46,"value":467},"F. Backup & Disaster Recovery",{"type":40,"tag":49,"props":469,"children":470},{},[471],{"type":46,"value":472},"Ensure stateful data is protected.",{"type":40,"tag":97,"props":474,"children":475},{},[476],{"type":40,"tag":101,"props":477,"children":478},{},[479,483,484,490],{"type":40,"tag":70,"props":480,"children":481},{},[482],{"type":46,"value":333},{"type":46,"value":335},{"type":40,"tag":155,"props":485,"children":487},{"className":486},[],[488],{"type":46,"value":489},"gke-backup-dr",{"type":46,"value":491}," skill for configuring Backup for GKE and restore procedures.",{"type":40,"tag":135,"props":493,"children":495},{"id":494},"g-edge-security-ingress",[496],{"type":46,"value":497},"G. Edge Security & Ingress",{"type":40,"tag":49,"props":499,"children":500},{},[501],{"type":46,"value":502},"Secure external access.",{"type":40,"tag":97,"props":504,"children":505},{},[506],{"type":40,"tag":101,"props":507,"children":508},{},[509,513,514,520],{"type":40,"tag":70,"props":510,"children":511},{},[512],{"type":46,"value":333},{"type":46,"value":335},{"type":40,"tag":155,"props":515,"children":517},{"className":516},[],[518],{"type":46,"value":519},"gke-networking-edge",{"type":46,"value":521}," skill for Gateway API, Ingress, and Cloud Armor.",{"type":40,"tag":135,"props":523,"children":525},{"id":524},"h-cost-optimization",[526],{"type":46,"value":527},"H. Cost Optimization",{"type":40,"tag":49,"props":529,"children":530},{},[531],{"type":46,"value":532},"Ensure efficient use of resources.",{"type":40,"tag":97,"props":534,"children":535},{},[536],{"type":40,"tag":101,"props":537,"children":538},{},[539,543,544,550],{"type":40,"tag":70,"props":540,"children":541},{},[542],{"type":46,"value":333},{"type":46,"value":335},{"type":40,"tag":155,"props":545,"children":547},{"className":546},[],[548],{"type":46,"value":549},"gke-cost-optimization",{"type":46,"value":551}," skill for strategies on rightsizing, quotas, and Spot VMs.",{"type":40,"tag":123,"props":553,"children":555},{"id":554},"_3-production-readiness-scoring",[556],{"type":46,"value":557},"3. Production Readiness Scoring",{"type":40,"tag":49,"props":559,"children":560},{},[561],{"type":46,"value":562},"After the assessment, provide a summary report with a RAG (Red, Amber, Green) status for each area and an overall readiness score. This helps prioritize remediation efforts.",{"type":40,"tag":85,"props":564,"children":566},{"id":565},"adaptability-guidelines",[567],{"type":46,"value":568},"Adaptability Guidelines",{"type":40,"tag":97,"props":570,"children":571},{},[572,582,592],{"type":40,"tag":101,"props":573,"children":574},{},[575,580],{"type":40,"tag":70,"props":576,"children":577},{},[578],{"type":46,"value":579},"Single App",{"type":46,"value":581},": Focus on Health Probes, HPA, Resource Limits, PDB, and Workload Identity for that specific app.",{"type":40,"tag":101,"props":583,"children":584},{},[585,590],{"type":40,"tag":70,"props":586,"children":587},{},[588],{"type":46,"value":589},"Cluster Wide",{"type":46,"value":591},": Focus on Cluster Autoscaler, Multi-zonal setup, Release Channels, Maintenance Windows, and default Network Policies.",{"type":40,"tag":101,"props":593,"children":594},{},[595,600],{"type":40,"tag":70,"props":596,"children":597},{},[598],{"type":46,"value":599},"Proactive Execution",{"type":46,"value":601},": Proactively execute relevant skills (e.g., observability, security, scaling, reliability) to assess and propose improvements, seeking user confirmation before applying state-changing implementations.",{"items":603,"total":788},[604,622,638,660,674,683,697,714,731,744,760,770],{"slug":605,"name":605,"fn":606,"description":607,"org":608,"tags":609,"stars":619,"repoUrl":620,"updatedAt":621},"kb-search","search and extract local knowledge base documents","Allows listing, searching and extracting information from local knowledge base documents for information about tables\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[610,613,616],{"name":611,"slug":612,"type":16},"Documentation","documentation",{"name":614,"slug":615,"type":16},"Knowledge Base","knowledge-base",{"name":617,"slug":618,"type":16},"Search","search",6749,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog","2026-07-12T07:38:52.157375",{"slug":623,"name":624,"fn":625,"description":626,"org":627,"tags":628,"stars":619,"repoUrl":620,"updatedAt":637},"knowledgecatalogdiscoveryagent","knowledge_catalog_discovery_agent","search and rank Knowledge Catalog data entries","Analyzes user queries, extracts relevant predicates, and utilizes Knowledge Catalog Search to find and rank the most relevant data entries. Engages with the user throughout the process.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[629,632,633,636],{"name":630,"slug":631,"type":16},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":16},{"name":634,"slug":635,"type":16},"Knowledge Management","knowledge-management",{"name":617,"slug":618,"type":16},"2026-07-12T07:38:22.196851",{"slug":639,"name":639,"fn":640,"description":641,"org":642,"tags":643,"stars":657,"repoUrl":658,"updatedAt":659},"contributing","contribute to Cloud Foundation Fabric","End-to-end workflow for contributing to Cloud Foundation Fabric: triaging GitHub issues, proactive feature development, validating with tests and Policy Troubleshooter, and submitting sanitized Pull Requests. Use when addressing a Fabric GitHub issue, developing a module or FAST stage change, or preparing a branch for a pull request.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[644,647,650,653,654],{"name":645,"slug":646,"type":16},"Automation","automation",{"name":648,"slug":649,"type":16},"Engineering","engineering",{"name":651,"slug":652,"type":16},"GitHub","github",{"name":9,"slug":8,"type":16},{"name":655,"slug":656,"type":16},"Pull Requests","pull-requests",2062,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-foundation-fabric","2026-07-31T06:23:36.935005",{"slug":661,"name":661,"fn":662,"description":663,"org":664,"tags":665,"stars":657,"repoUrl":658,"updatedAt":673},"fabric-builder","generate Terraform code for Google Cloud","Generates idiomatic Cloud Foundation Fabric (CFF) Terraform code using CFF modules. Use when users ask to create GCP resources, use Fabric modules, or generate Terraform code for Google Cloud.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[666,667,670],{"name":9,"slug":8,"type":16},{"name":668,"slug":669,"type":16},"Infrastructure as Code","infrastructure-as-code",{"name":671,"slug":672,"type":16},"Terraform","terraform","2026-07-12T07:38:23.514555",{"slug":675,"name":675,"fn":676,"description":677,"org":678,"tags":679,"stars":657,"repoUrl":658,"updatedAt":682},"fast-0-org-setup-prereqs","prepare prerequisites for FAST 0-org-setup","Guides the user step-by-step through the prerequisites for the FAST 0-org-setup stage, supporting both Standard GCP and Google Cloud Dedicated (GCD) environments. Use when a user asks to prepare or run prerequisites for 0-org-setup or bootstrap the FAST landing zone.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[680,681],{"name":9,"slug":8,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:38:28.127148",{"slug":684,"name":684,"fn":685,"description":686,"org":687,"tags":688,"stars":694,"repoUrl":695,"updatedAt":696},"agent-aware-cli","design agent-aware command-line interfaces","Guide for designing and implementing command-line interfaces (CLIs) that are equally usable by human developers and automated coding agents. Use when the user wants to build a CLI, apply CLI best practices, or use Go with Cobra and Viper.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[689,692,693],{"name":690,"slug":691,"type":16},"CLI","cli",{"name":648,"slug":649,"type":16},{"name":9,"slug":8,"type":16},1150,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fvertex-ai-creative-studio","2026-07-12T07:39:08.41406",{"slug":698,"name":698,"fn":699,"description":700,"org":701,"tags":702,"stars":694,"repoUrl":695,"updatedAt":713},"build-mcp-genmedia","build and configure GenAI MCP servers","Builds the mcp-genmedia Go MCP servers (nanobanana, veo, lyria, gemini-multimodal, chirp3-hd, avtool) from source and wires them into settings.json. Use this skill whenever the MCP tools are missing or broken — typically at the start of a new session, after a container restart, or when \u002Ftmp has been wiped. The prebuilt binaries in \u002Fworkspace\u002F.local\u002Fbin\u002F have no exec bit and live on a noexec mount; this skill compiles fresh executables into \u002Ftmp\u002Fbin\u002F where execution is allowed.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[703,706,707,710],{"name":704,"slug":705,"type":16},"API Development","api-development",{"name":9,"slug":8,"type":16},{"name":708,"slug":709,"type":16},"LLM","llm",{"name":711,"slug":712,"type":16},"MCP","mcp","2026-07-12T07:39:10.911302",{"slug":715,"name":715,"fn":716,"description":717,"org":718,"tags":719,"stars":694,"repoUrl":695,"updatedAt":730},"genmedia-audio-engineer","synthesize and mix audio content","Expert in audio synthesis, music generation, and mixing. Use when creating podcasts, background scores, or multi-track audio layering using mcp-chirp3-go, mcp-lyria-go, mcp-gemini-go, mcp-nanobanana-go, and mcp-avtool-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[720,723,726,727],{"name":721,"slug":722,"type":16},"Audio","audio",{"name":724,"slug":725,"type":16},"Creative","creative",{"name":9,"slug":8,"type":16},{"name":728,"slug":729,"type":16},"Vertex AI","vertex-ai","2026-07-12T07:39:16.623879",{"slug":732,"name":732,"fn":733,"description":734,"org":735,"tags":736,"stars":694,"repoUrl":695,"updatedAt":743},"genmedia-image-artist","generate and edit AI images","Expert in AI image generation and editing. Use when the user needs high-quality textures, character-consistent visuals, or image-to-image editing using mcp-nanobanana-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[737,738,739,742],{"name":724,"slug":725,"type":16},{"name":9,"slug":8,"type":16},{"name":740,"slug":741,"type":16},"Image Generation","image-generation",{"name":728,"slug":729,"type":16},"2026-07-12T07:39:15.372822",{"slug":745,"name":745,"fn":746,"description":747,"org":748,"tags":749,"stars":694,"repoUrl":695,"updatedAt":759},"genmedia-producer","produce multi-step media content","Expert media production assistant. Use when requested to help with storyboarding, podcast creation, audio assembly, or complex multi-step media workflows using the GenMedia MCP servers (Veo, Lyria, Gemini TTS, NanoBanana).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[750,751,752,753,756],{"name":721,"slug":722,"type":16},{"name":724,"slug":725,"type":16},{"name":9,"slug":8,"type":16},{"name":754,"slug":755,"type":16},"Media","media",{"name":757,"slug":758,"type":16},"Video","video","2026-07-12T07:39:09.672849",{"slug":761,"name":761,"fn":762,"description":763,"org":764,"tags":765,"stars":694,"repoUrl":695,"updatedAt":769},"genmedia-video-editor","edit and compose video content","Expert in video composition, editing, and format conversion. Use when the user wants to generate high-quality video, overlay images on video, concatenate clips, create GIFs, or sync audio to video using mcp-avtool-go and mcp-veo-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[766,767,768],{"name":724,"slug":725,"type":16},{"name":9,"slug":8,"type":16},{"name":757,"slug":758,"type":16},"2026-07-12T07:39:13.749081",{"slug":771,"name":771,"fn":772,"description":773,"org":774,"tags":775,"stars":694,"repoUrl":695,"updatedAt":787},"genmedia-voice-director","generate expressive text-to-speech with Gemini","Expert in casting, directing, and generating expressive text-to-speech using Gemini TTS. Use this when the user needs virtual voice actor personas, expressive speech generation, or multiple variations of a voiceover (like \"take 3 on the bounce\").",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[776,777,778,781,784],{"name":721,"slug":722,"type":16},{"name":724,"slug":725,"type":16},{"name":779,"slug":780,"type":16},"Gemini","gemini",{"name":782,"slug":783,"type":16},"Speech","speech",{"name":785,"slug":786,"type":16},"Text-to-Speech","text-to-speech","2026-07-12T07:39:17.86673",80,{"items":790,"total":878},[791,801,816,829,842,853,868],{"slug":792,"name":792,"fn":793,"description":794,"org":795,"tags":796,"stars":24,"repoUrl":25,"updatedAt":800},"custom-golden-image-discovery","discover golden base images for GKE nodes","Expert at discovering golden base images for GKE custom nodes using technical specs or context clues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[797,798,799],{"name":18,"slug":19,"type":16},{"name":9,"slug":8,"type":16},{"name":21,"slug":22,"type":16},"2026-07-12T07:39:30.888879",{"slug":802,"name":802,"fn":803,"description":804,"org":805,"tags":806,"stars":24,"repoUrl":25,"updatedAt":815},"gke-ai-troubleshooting-handle-disruption-gpu-tpu","diagnose GPU and TPU workload disruptions","Diagnose and predict node disruption during Compute Engine host maintenance for GPU and TPU workloads.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[807,810,811,812],{"name":808,"slug":809,"type":16},"Debugging","debugging",{"name":9,"slug":8,"type":16},{"name":21,"slug":22,"type":16},{"name":813,"slug":814,"type":16},"Performance","performance","2026-07-28T05:34:18.149515",{"slug":817,"name":817,"fn":818,"description":819,"org":820,"tags":821,"stars":24,"repoUrl":25,"updatedAt":828},"gke-ai-troubleshooting-jobset-interruption","diagnose GKE JobSet interruptions","Systematically diagnose GKE JobSet interruptions, restarts, and preemptions for AI\u002FML training workloads. Identifies preemption events, maintenance interruptions, bad host VMs, unhealthy pods, and coordinator worker failures.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[822,823,824,825],{"name":808,"slug":809,"type":16},{"name":9,"slug":8,"type":16},{"name":21,"slug":22,"type":16},{"name":826,"slug":827,"type":16},"Observability","observability","2026-07-12T07:40:04.511878",{"slug":830,"name":830,"fn":831,"description":832,"org":833,"tags":834,"stars":24,"repoUrl":25,"updatedAt":841},"gke-ai-troubleshooting-skill-creation-guide","create GKE troubleshooting skill bundles","Expert instructions for building high-quality GKE troubleshooting skills. Codifies Step 0 context rules, zero-hallucination signatures, and explicit LQL\u002FPromQL query requirements.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[835,836,837,838],{"name":611,"slug":612,"type":16},{"name":648,"slug":649,"type":16},{"name":9,"slug":8,"type":16},{"name":839,"slug":840,"type":16},"Technical Writing","technical-writing","2026-07-12T07:39:50.73484",{"slug":843,"name":843,"fn":844,"description":845,"org":846,"tags":847,"stars":24,"repoUrl":25,"updatedAt":852},"gke-ai-troubleshooting-tpu-connection-failure-vbar-oom","diagnose GKE TPU connection failures","Diagnose and prevent `vbar_control_agent` segfaults and OOMs caused by race conditions during TPU device resets and frequent metrics collection (e.g. every 3s). Use when TPU slice initialization fails or `vbar_control_agent` crashes on TPU v6e nodes.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[848,849,850,851],{"name":808,"slug":809,"type":16},{"name":9,"slug":8,"type":16},{"name":21,"slug":22,"type":16},{"name":813,"slug":814,"type":16},"2026-07-12T07:39:49.482979",{"slug":309,"name":309,"fn":854,"description":855,"org":856,"tags":857,"stars":24,"repoUrl":25,"updatedAt":867},"containerize and deploy apps to GKE","Workflows for containerizing and deploying applications to GKE for the first time.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[858,861,862,863,864],{"name":859,"slug":860,"type":16},"Containers","containers",{"name":18,"slug":19,"type":16},{"name":9,"slug":8,"type":16},{"name":21,"slug":22,"type":16},{"name":865,"slug":866,"type":16},"Onboarding","onboarding","2026-07-12T07:39:41.935837",{"slug":489,"name":489,"fn":869,"description":870,"org":871,"tags":872,"stars":24,"repoUrl":25,"updatedAt":877},"configure GKE backup and disaster recovery","Workflows for configuring Backup for GKE and disaster recovery.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[873,874,875,876],{"name":18,"slug":19,"type":16},{"name":9,"slug":8,"type":16},{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:39:34.806995",25]