[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-google-cloud-gke-cost-optimization":3,"mdc--jmchly-key":31,"related-repo-google-cloud-gke-cost-optimization":552,"related-org-google-cloud-gke-cost-optimization":652},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":21,"repoUrl":22,"updatedAt":23,"license":24,"forks":25,"topics":26,"repo":27,"sourceUrl":29,"mdContent":30},"gke-cost-optimization","optimize costs for GKE clusters","Guidance on optimizing costs for Google Kubernetes Engine (GKE) clusters.",{"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],{"name":14,"slug":15,"type":16},"Cost Optimization","cost-optimization","tag",{"name":18,"slug":19,"type":16},"Kubernetes","kubernetes",{"name":9,"slug":8,"type":16},161,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgke-mcp","2026-07-12T07:39:45.710071",null,78,[],{"repoUrl":22,"stars":21,"forks":25,"topics":28,"description":24},[],"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgke-mcp\u002Ftree\u002FHEAD\u002Fskills\u002Fgke-cost-optimization","---\nname: gke-cost-optimization\ndescription: Guidance on optimizing costs for Google Kubernetes Engine (GKE) clusters.\n---\n\n# GKE Cost Optimization\n\nThis skill provides guidance on optimizing costs for Google Kubernetes Engine (GKE) clusters.\n\n## Overview\n\nCost optimization in GKE involves tracking costs, setting limits to prevent waste, and rightsizing workloads to match actual usage.\n\n## Workflows\n\n### 1. Enable GKE Cost Allocation\n\nGKE cost allocation allows you to see the cost of your GKE resources in Cloud Billing, broken down by namespace and cluster labels.\n\n**Steps:**\n\n1. Enable GKE cost allocation in the cluster settings.\n\n**Command:**\n\n```bash\ngcloud container clusters update \u003Ccluster-name> \\\n    --enable-cost-allocation \\\n    --region \u003Cregion>\n```\n\n2. View costs in the Cloud Billing reports by grouping by namespace or labels.\n\n### 2. Configure Resource Quotas\n\nResource quotas restrict the total resource consumption in a namespace, preventing any single tenant from consuming all cluster resources.\n\n**Example ResourceQuota Manifest:**\n\n```yaml\napiVersion: v1\nkind: ResourceQuota\nmetadata:\n  name: compute-quota\n  namespace: my-namespace\nspec:\n  hard:\n    requests.cpu: \"4\"\n    requests.memory: 16Gi\n    limits.cpu: \"8\"\n    limits.memory: 32Gi\n```\n\n### 3. Rightsizing Strategies\n\nRightsizing involves adjusting the requested resources of your workloads to match their actual utilization.\n\n- **Use VPA in Recommender Mode**: Let VPA observe usage and recommend CPU and memory requests.\n- **Use MPA**: Reconcile HPA and VPA to avoid conflicts.\n- **Review Cost Recommendations**: Check the Google Cloud Console for GKE cost optimization recommendations.\n\n## Best Practices\n\n1. **Enable Cost Allocation**: Always enable GKE cost allocation to understand where your money is going.\n2. **Use Resource Quotas**: Enforce resource quotas in multi-tenant clusters to prevent cost runaways.\n3. **Leverage Spot VMs**: Use Spot VMs for fault-tolerant, stateless workloads to save up to 91%.\n4. **Automate Scaling**: Use Cluster Autoscaler and HPA\u002FVPA to ensure you only pay for what you need.\n",{"data":32,"body":33},{"name":4,"description":6},{"type":34,"children":35},"root",[36,44,50,57,62,68,75,80,89,99,107,215,223,229,234,242,452,458,463,497,503,546],{"type":37,"tag":38,"props":39,"children":40},"element","h1",{"id":4},[41],{"type":42,"value":43},"text","GKE Cost Optimization",{"type":37,"tag":45,"props":46,"children":47},"p",{},[48],{"type":42,"value":49},"This skill provides guidance on optimizing costs for Google Kubernetes Engine (GKE) clusters.",{"type":37,"tag":51,"props":52,"children":54},"h2",{"id":53},"overview",[55],{"type":42,"value":56},"Overview",{"type":37,"tag":45,"props":58,"children":59},{},[60],{"type":42,"value":61},"Cost optimization in GKE involves tracking costs, setting limits to prevent waste, and rightsizing workloads to match actual usage.",{"type":37,"tag":51,"props":63,"children":65},{"id":64},"workflows",[66],{"type":42,"value":67},"Workflows",{"type":37,"tag":69,"props":70,"children":72},"h3",{"id":71},"_1-enable-gke-cost-allocation",[73],{"type":42,"value":74},"1. Enable GKE Cost Allocation",{"type":37,"tag":45,"props":76,"children":77},{},[78],{"type":42,"value":79},"GKE cost allocation allows you to see the cost of your GKE resources in Cloud Billing, broken down by namespace and cluster labels.",{"type":37,"tag":45,"props":81,"children":82},{},[83],{"type":37,"tag":84,"props":85,"children":86},"strong",{},[87],{"type":42,"value":88},"Steps:",{"type":37,"tag":90,"props":91,"children":92},"ol",{},[93],{"type":37,"tag":94,"props":95,"children":96},"li",{},[97],{"type":42,"value":98},"Enable GKE cost allocation in the cluster settings.",{"type":37,"tag":45,"props":100,"children":101},{},[102],{"type":37,"tag":84,"props":103,"children":104},{},[105],{"type":42,"value":106},"Command:",{"type":37,"tag":108,"props":109,"children":114},"pre",{"className":110,"code":111,"language":112,"meta":113,"style":113},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","gcloud container clusters update \u003Ccluster-name> \\\n    --enable-cost-allocation \\\n    --region \u003Cregion>\n","bash","",[115],{"type":37,"tag":116,"props":117,"children":118},"code",{"__ignoreMap":113},[119,174,187],{"type":37,"tag":120,"props":121,"children":124},"span",{"class":122,"line":123},"line",1,[125,131,137,142,147,153,158,164,169],{"type":37,"tag":120,"props":126,"children":128},{"style":127},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[129],{"type":42,"value":130},"gcloud",{"type":37,"tag":120,"props":132,"children":134},{"style":133},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[135],{"type":42,"value":136}," container",{"type":37,"tag":120,"props":138,"children":139},{"style":133},[140],{"type":42,"value":141}," clusters",{"type":37,"tag":120,"props":143,"children":144},{"style":133},[145],{"type":42,"value":146}," update",{"type":37,"tag":120,"props":148,"children":150},{"style":149},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[151],{"type":42,"value":152}," \u003C",{"type":37,"tag":120,"props":154,"children":155},{"style":133},[156],{"type":42,"value":157},"cluster-nam",{"type":37,"tag":120,"props":159,"children":161},{"style":160},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[162],{"type":42,"value":163},"e",{"type":37,"tag":120,"props":165,"children":166},{"style":149},[167],{"type":42,"value":168},">",{"type":37,"tag":120,"props":170,"children":171},{"style":160},[172],{"type":42,"value":173}," \\\n",{"type":37,"tag":120,"props":175,"children":177},{"class":122,"line":176},2,[178,183],{"type":37,"tag":120,"props":179,"children":180},{"style":133},[181],{"type":42,"value":182},"    --enable-cost-allocation",{"type":37,"tag":120,"props":184,"children":185},{"style":160},[186],{"type":42,"value":173},{"type":37,"tag":120,"props":188,"children":190},{"class":122,"line":189},3,[191,196,200,205,210],{"type":37,"tag":120,"props":192,"children":193},{"style":133},[194],{"type":42,"value":195},"    --region",{"type":37,"tag":120,"props":197,"children":198},{"style":149},[199],{"type":42,"value":152},{"type":37,"tag":120,"props":201,"children":202},{"style":133},[203],{"type":42,"value":204},"regio",{"type":37,"tag":120,"props":206,"children":207},{"style":160},[208],{"type":42,"value":209},"n",{"type":37,"tag":120,"props":211,"children":212},{"style":149},[213],{"type":42,"value":214},">\n",{"type":37,"tag":90,"props":216,"children":217},{"start":176},[218],{"type":37,"tag":94,"props":219,"children":220},{},[221],{"type":42,"value":222},"View costs in the Cloud Billing reports by grouping by namespace or labels.",{"type":37,"tag":69,"props":224,"children":226},{"id":225},"_2-configure-resource-quotas",[227],{"type":42,"value":228},"2. Configure Resource Quotas",{"type":37,"tag":45,"props":230,"children":231},{},[232],{"type":42,"value":233},"Resource quotas restrict the total resource consumption in a namespace, preventing any single tenant from consuming all cluster resources.",{"type":37,"tag":45,"props":235,"children":236},{},[237],{"type":37,"tag":84,"props":238,"children":239},{},[240],{"type":42,"value":241},"Example ResourceQuota Manifest:",{"type":37,"tag":108,"props":243,"children":247},{"className":244,"code":245,"language":246,"meta":113,"style":113},"language-yaml shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","apiVersion: v1\nkind: ResourceQuota\nmetadata:\n  name: compute-quota\n  namespace: my-namespace\nspec:\n  hard:\n    requests.cpu: \"4\"\n    requests.memory: 16Gi\n    limits.cpu: \"8\"\n    limits.memory: 32Gi\n","yaml",[248],{"type":37,"tag":116,"props":249,"children":250},{"__ignoreMap":113},[251,270,287,300,318,336,349,362,390,408,434],{"type":37,"tag":120,"props":252,"children":253},{"class":122,"line":123},[254,260,265],{"type":37,"tag":120,"props":255,"children":257},{"style":256},"--shiki-light:#E53935;--shiki-default:#F07178;--shiki-dark:#F07178",[258],{"type":42,"value":259},"apiVersion",{"type":37,"tag":120,"props":261,"children":262},{"style":149},[263],{"type":42,"value":264},":",{"type":37,"tag":120,"props":266,"children":267},{"style":133},[268],{"type":42,"value":269}," v1\n",{"type":37,"tag":120,"props":271,"children":272},{"class":122,"line":176},[273,278,282],{"type":37,"tag":120,"props":274,"children":275},{"style":256},[276],{"type":42,"value":277},"kind",{"type":37,"tag":120,"props":279,"children":280},{"style":149},[281],{"type":42,"value":264},{"type":37,"tag":120,"props":283,"children":284},{"style":133},[285],{"type":42,"value":286}," ResourceQuota\n",{"type":37,"tag":120,"props":288,"children":289},{"class":122,"line":189},[290,295],{"type":37,"tag":120,"props":291,"children":292},{"style":256},[293],{"type":42,"value":294},"metadata",{"type":37,"tag":120,"props":296,"children":297},{"style":149},[298],{"type":42,"value":299},":\n",{"type":37,"tag":120,"props":301,"children":303},{"class":122,"line":302},4,[304,309,313],{"type":37,"tag":120,"props":305,"children":306},{"style":256},[307],{"type":42,"value":308},"  name",{"type":37,"tag":120,"props":310,"children":311},{"style":149},[312],{"type":42,"value":264},{"type":37,"tag":120,"props":314,"children":315},{"style":133},[316],{"type":42,"value":317}," compute-quota\n",{"type":37,"tag":120,"props":319,"children":321},{"class":122,"line":320},5,[322,327,331],{"type":37,"tag":120,"props":323,"children":324},{"style":256},[325],{"type":42,"value":326},"  namespace",{"type":37,"tag":120,"props":328,"children":329},{"style":149},[330],{"type":42,"value":264},{"type":37,"tag":120,"props":332,"children":333},{"style":133},[334],{"type":42,"value":335}," my-namespace\n",{"type":37,"tag":120,"props":337,"children":339},{"class":122,"line":338},6,[340,345],{"type":37,"tag":120,"props":341,"children":342},{"style":256},[343],{"type":42,"value":344},"spec",{"type":37,"tag":120,"props":346,"children":347},{"style":149},[348],{"type":42,"value":299},{"type":37,"tag":120,"props":350,"children":352},{"class":122,"line":351},7,[353,358],{"type":37,"tag":120,"props":354,"children":355},{"style":256},[356],{"type":42,"value":357},"  hard",{"type":37,"tag":120,"props":359,"children":360},{"style":149},[361],{"type":42,"value":299},{"type":37,"tag":120,"props":363,"children":365},{"class":122,"line":364},8,[366,371,375,380,385],{"type":37,"tag":120,"props":367,"children":368},{"style":256},[369],{"type":42,"value":370},"    requests.cpu",{"type":37,"tag":120,"props":372,"children":373},{"style":149},[374],{"type":42,"value":264},{"type":37,"tag":120,"props":376,"children":377},{"style":149},[378],{"type":42,"value":379}," \"",{"type":37,"tag":120,"props":381,"children":382},{"style":133},[383],{"type":42,"value":384},"4",{"type":37,"tag":120,"props":386,"children":387},{"style":149},[388],{"type":42,"value":389},"\"\n",{"type":37,"tag":120,"props":391,"children":393},{"class":122,"line":392},9,[394,399,403],{"type":37,"tag":120,"props":395,"children":396},{"style":256},[397],{"type":42,"value":398},"    requests.memory",{"type":37,"tag":120,"props":400,"children":401},{"style":149},[402],{"type":42,"value":264},{"type":37,"tag":120,"props":404,"children":405},{"style":133},[406],{"type":42,"value":407}," 16Gi\n",{"type":37,"tag":120,"props":409,"children":411},{"class":122,"line":410},10,[412,417,421,425,430],{"type":37,"tag":120,"props":413,"children":414},{"style":256},[415],{"type":42,"value":416},"    limits.cpu",{"type":37,"tag":120,"props":418,"children":419},{"style":149},[420],{"type":42,"value":264},{"type":37,"tag":120,"props":422,"children":423},{"style":149},[424],{"type":42,"value":379},{"type":37,"tag":120,"props":426,"children":427},{"style":133},[428],{"type":42,"value":429},"8",{"type":37,"tag":120,"props":431,"children":432},{"style":149},[433],{"type":42,"value":389},{"type":37,"tag":120,"props":435,"children":437},{"class":122,"line":436},11,[438,443,447],{"type":37,"tag":120,"props":439,"children":440},{"style":256},[441],{"type":42,"value":442},"    limits.memory",{"type":37,"tag":120,"props":444,"children":445},{"style":149},[446],{"type":42,"value":264},{"type":37,"tag":120,"props":448,"children":449},{"style":133},[450],{"type":42,"value":451}," 32Gi\n",{"type":37,"tag":69,"props":453,"children":455},{"id":454},"_3-rightsizing-strategies",[456],{"type":42,"value":457},"3. Rightsizing Strategies",{"type":37,"tag":45,"props":459,"children":460},{},[461],{"type":42,"value":462},"Rightsizing involves adjusting the requested resources of your workloads to match their actual utilization.",{"type":37,"tag":464,"props":465,"children":466},"ul",{},[467,477,487],{"type":37,"tag":94,"props":468,"children":469},{},[470,475],{"type":37,"tag":84,"props":471,"children":472},{},[473],{"type":42,"value":474},"Use VPA in Recommender Mode",{"type":42,"value":476},": Let VPA observe usage and recommend CPU and memory requests.",{"type":37,"tag":94,"props":478,"children":479},{},[480,485],{"type":37,"tag":84,"props":481,"children":482},{},[483],{"type":42,"value":484},"Use MPA",{"type":42,"value":486},": Reconcile HPA and VPA to avoid conflicts.",{"type":37,"tag":94,"props":488,"children":489},{},[490,495],{"type":37,"tag":84,"props":491,"children":492},{},[493],{"type":42,"value":494},"Review Cost Recommendations",{"type":42,"value":496},": Check the Google Cloud Console for GKE cost optimization recommendations.",{"type":37,"tag":51,"props":498,"children":500},{"id":499},"best-practices",[501],{"type":42,"value":502},"Best Practices",{"type":37,"tag":90,"props":504,"children":505},{},[506,516,526,536],{"type":37,"tag":94,"props":507,"children":508},{},[509,514],{"type":37,"tag":84,"props":510,"children":511},{},[512],{"type":42,"value":513},"Enable Cost Allocation",{"type":42,"value":515},": Always enable GKE cost allocation to understand where your money is going.",{"type":37,"tag":94,"props":517,"children":518},{},[519,524],{"type":37,"tag":84,"props":520,"children":521},{},[522],{"type":42,"value":523},"Use Resource Quotas",{"type":42,"value":525},": Enforce resource quotas in multi-tenant clusters to prevent cost runaways.",{"type":37,"tag":94,"props":527,"children":528},{},[529,534],{"type":37,"tag":84,"props":530,"children":531},{},[532],{"type":42,"value":533},"Leverage Spot VMs",{"type":42,"value":535},": Use Spot VMs for fault-tolerant, stateless workloads to save up to 91%.",{"type":37,"tag":94,"props":537,"children":538},{},[539,544],{"type":37,"tag":84,"props":540,"children":541},{},[542],{"type":42,"value":543},"Automate Scaling",{"type":42,"value":545},": Use Cluster Autoscaler and HPA\u002FVPA to ensure you only pay for what you need.",{"type":37,"tag":547,"props":548,"children":549},"style",{},[550],{"type":42,"value":551},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":553,"total":651},[554,566,581,594,611,622,638],{"slug":555,"name":555,"fn":556,"description":557,"org":558,"tags":559,"stars":21,"repoUrl":22,"updatedAt":565},"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},[560,563,564],{"name":561,"slug":562,"type":16},"Deployment","deployment",{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},"2026-07-12T07:39:30.888879",{"slug":567,"name":567,"fn":568,"description":569,"org":570,"tags":571,"stars":21,"repoUrl":22,"updatedAt":580},"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},[572,575,576,577],{"name":573,"slug":574,"type":16},"Debugging","debugging",{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":578,"slug":579,"type":16},"Performance","performance","2026-07-28T05:34:18.149515",{"slug":582,"name":582,"fn":583,"description":584,"org":585,"tags":586,"stars":21,"repoUrl":22,"updatedAt":593},"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},[587,588,589,590],{"name":573,"slug":574,"type":16},{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":591,"slug":592,"type":16},"Observability","observability","2026-07-12T07:40:04.511878",{"slug":595,"name":595,"fn":596,"description":597,"org":598,"tags":599,"stars":21,"repoUrl":22,"updatedAt":610},"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},[600,603,606,607],{"name":601,"slug":602,"type":16},"Documentation","documentation",{"name":604,"slug":605,"type":16},"Engineering","engineering",{"name":9,"slug":8,"type":16},{"name":608,"slug":609,"type":16},"Technical Writing","technical-writing","2026-07-12T07:39:50.73484",{"slug":612,"name":612,"fn":613,"description":614,"org":615,"tags":616,"stars":21,"repoUrl":22,"updatedAt":621},"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},[617,618,619,620],{"name":573,"slug":574,"type":16},{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":578,"slug":579,"type":16},"2026-07-12T07:39:49.482979",{"slug":623,"name":623,"fn":624,"description":625,"org":626,"tags":627,"stars":21,"repoUrl":22,"updatedAt":637},"gke-app-onboarding","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},[628,631,632,633,634],{"name":629,"slug":630,"type":16},"Containers","containers",{"name":561,"slug":562,"type":16},{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":635,"slug":636,"type":16},"Onboarding","onboarding","2026-07-12T07:39:41.935837",{"slug":639,"name":639,"fn":640,"description":641,"org":642,"tags":643,"stars":21,"repoUrl":22,"updatedAt":650},"gke-backup-dr","configure GKE backup and disaster recovery","Workflows for configuring Backup for GKE and disaster recovery.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[644,645,646,647],{"name":561,"slug":562,"type":16},{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":648,"slug":649,"type":16},"Operations","operations","2026-07-12T07:39:34.806995",25,{"items":653,"total":834},[654,670,686,706,720,729,743,760,777,790,806,816],{"slug":655,"name":655,"fn":656,"description":657,"org":658,"tags":659,"stars":667,"repoUrl":668,"updatedAt":669},"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},[660,661,664],{"name":601,"slug":602,"type":16},{"name":662,"slug":663,"type":16},"Knowledge Base","knowledge-base",{"name":665,"slug":666,"type":16},"Search","search",6749,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog","2026-07-12T07:38:52.157375",{"slug":671,"name":672,"fn":673,"description":674,"org":675,"tags":676,"stars":667,"repoUrl":668,"updatedAt":685},"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},[677,680,681,684],{"name":678,"slug":679,"type":16},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":16},{"name":682,"slug":683,"type":16},"Knowledge Management","knowledge-management",{"name":665,"slug":666,"type":16},"2026-07-12T07:38:22.196851",{"slug":687,"name":687,"fn":688,"description":689,"org":690,"tags":691,"stars":703,"repoUrl":704,"updatedAt":705},"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},[692,695,696,699,700],{"name":693,"slug":694,"type":16},"Automation","automation",{"name":604,"slug":605,"type":16},{"name":697,"slug":698,"type":16},"GitHub","github",{"name":9,"slug":8,"type":16},{"name":701,"slug":702,"type":16},"Pull Requests","pull-requests",2062,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-foundation-fabric","2026-07-31T06:23:36.935005",{"slug":707,"name":707,"fn":708,"description":709,"org":710,"tags":711,"stars":703,"repoUrl":704,"updatedAt":719},"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},[712,713,716],{"name":9,"slug":8,"type":16},{"name":714,"slug":715,"type":16},"Infrastructure as Code","infrastructure-as-code",{"name":717,"slug":718,"type":16},"Terraform","terraform","2026-07-12T07:38:23.514555",{"slug":721,"name":721,"fn":722,"description":723,"org":724,"tags":725,"stars":703,"repoUrl":704,"updatedAt":728},"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},[726,727],{"name":9,"slug":8,"type":16},{"name":648,"slug":649,"type":16},"2026-07-12T07:38:28.127148",{"slug":730,"name":730,"fn":731,"description":732,"org":733,"tags":734,"stars":740,"repoUrl":741,"updatedAt":742},"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},[735,738,739],{"name":736,"slug":737,"type":16},"CLI","cli",{"name":604,"slug":605,"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":744,"name":744,"fn":745,"description":746,"org":747,"tags":748,"stars":740,"repoUrl":741,"updatedAt":759},"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},[749,752,753,756],{"name":750,"slug":751,"type":16},"API Development","api-development",{"name":9,"slug":8,"type":16},{"name":754,"slug":755,"type":16},"LLM","llm",{"name":757,"slug":758,"type":16},"MCP","mcp","2026-07-12T07:39:10.911302",{"slug":761,"name":761,"fn":762,"description":763,"org":764,"tags":765,"stars":740,"repoUrl":741,"updatedAt":776},"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},[766,769,772,773],{"name":767,"slug":768,"type":16},"Audio","audio",{"name":770,"slug":771,"type":16},"Creative","creative",{"name":9,"slug":8,"type":16},{"name":774,"slug":775,"type":16},"Vertex AI","vertex-ai","2026-07-12T07:39:16.623879",{"slug":778,"name":778,"fn":779,"description":780,"org":781,"tags":782,"stars":740,"repoUrl":741,"updatedAt":789},"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},[783,784,785,788],{"name":770,"slug":771,"type":16},{"name":9,"slug":8,"type":16},{"name":786,"slug":787,"type":16},"Image Generation","image-generation",{"name":774,"slug":775,"type":16},"2026-07-12T07:39:15.372822",{"slug":791,"name":791,"fn":792,"description":793,"org":794,"tags":795,"stars":740,"repoUrl":741,"updatedAt":805},"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},[796,797,798,799,802],{"name":767,"slug":768,"type":16},{"name":770,"slug":771,"type":16},{"name":9,"slug":8,"type":16},{"name":800,"slug":801,"type":16},"Media","media",{"name":803,"slug":804,"type":16},"Video","video","2026-07-12T07:39:09.672849",{"slug":807,"name":807,"fn":808,"description":809,"org":810,"tags":811,"stars":740,"repoUrl":741,"updatedAt":815},"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},[812,813,814],{"name":770,"slug":771,"type":16},{"name":9,"slug":8,"type":16},{"name":803,"slug":804,"type":16},"2026-07-12T07:39:13.749081",{"slug":817,"name":817,"fn":818,"description":819,"org":820,"tags":821,"stars":740,"repoUrl":741,"updatedAt":833},"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},[822,823,824,827,830],{"name":767,"slug":768,"type":16},{"name":770,"slug":771,"type":16},{"name":825,"slug":826,"type":16},"Gemini","gemini",{"name":828,"slug":829,"type":16},"Speech","speech",{"name":831,"slug":832,"type":16},"Text-to-Speech","text-to-speech","2026-07-12T07:39:17.86673",80]