[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-google-cloud-gke-cost-analysis":3,"mdc-c4zla7-key":34,"related-repo-google-cloud-gke-cost-analysis":535,"related-org-google-cloud-gke-cost-analysis":635},{"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-cost-analysis","analyze GKE infrastructure costs","Answer natural language questions about GKE-related costs by leveraging BigQuery export and cost allocation data.",{"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},"Cost Optimization","cost-optimization","tag",{"name":18,"slug":19,"type":16},"Kubernetes","kubernetes",{"name":21,"slug":22,"type":16},"Analytics","analytics",{"name":9,"slug":8,"type":16},161,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgke-mcp","2026-07-12T07:39:43.226837",null,78,[],{"repoUrl":25,"stars":24,"forks":28,"topics":31,"description":27},[],"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgke-mcp\u002Ftree\u002FHEAD\u002Fskills\u002Fgke-cost-analysis","---\nname: gke-cost-analysis\ndescription: Answer natural language questions about GKE-related costs by leveraging BigQuery export and cost allocation data.\n---\n\n# GKE Cost Analysis\n\nThis skill provides guidance on answering natural language questions about GKE-related costs, optimization, or billing.\n\n## Overview\n\nWhen users ask about GKE costs (e.g., \"What are my costs across projects?\", \"What's my most expensive namespace?\"), use this skill to provide a structured and expert response.\n\n## Instructions\n\nWhen handling a cost-related question:\n\n1. **Provide a Direct Answer**: Address the specific cost question or optimization request.\n2. **Explain BigQuery Integration**: Explain how to use BigQuery for cost analysis if relevant. Mention that GKE costs come from GCP Billing Detailed BigQuery Export.\n3. **Check Cost Allocation**: Mention that GKE Cost Allocation must be enabled for namespace and workload-level cost data.\n4. **Provide Actionable Steps**: Provide concrete next steps or commands when possible. Prefer BigQuery CLI (`bq`) over BigQuery Studio when available.\n5. **Reference Resources**: Point to relevant GCP documentation or console links.\n\n## Key Points to Remember\n\n- **Data Source**: GKE costs come from GCP Billing Detailed BigQuery Export. The user must provide the full path to their BigQuery table (dataset name and table name containing Billing Account ID).\n- **Granularity**: GKE Cost Allocation must be enabled for namespace and workload-level cost data.\n- **Tools**: BigQuery CLI (`bq`) is preferred. When writing Standard SQL queries, use a dot (`.`) instead of a colon (`:`) to separate the project ID and dataset name.\n- **Defaults**: Assume last 30 days, row limit 10, ordering by cost descending, unless specified otherwise.\n\n## Example BigQuery Queries\n\nUse these queries as templates to answer questions. All parameters (dataset, table, project, cluster, etc.) need to be replaced.\n\n### Cost of a Single Workload in a Single Cluster\n\n```sql\nbq query --nouse_legacy_sql '\nSELECT\n  SUM(cost) + SUM(IFNULL((SELECT SUM(c.amount) FROM UNNEST(credits) c), 0)) AS cost,\n  SUM(cost) AS cost_before_credits\nFROM {{.BQDatasetProjectID}}.{{.BQDatasetName}}.gcp_billing_export_resource_v1_XXXXXX_XXXXXX_XXXXXX AS bqe\nWHERE _PARTITIONTIME >= TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 30 DAY)\n  AND project.id = \"sample-project-id\"\n  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-location\" AND l.value = \"us-central1\")\n  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-name\" AND l.value = \"sample-cluster-name\")\n  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"k8s-namespace\" AND l.value = \"sample-namespace\")\n  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"k8s-workload-type\" AND l.value = \"apps\u002Fv1-Deployment\")\n  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"k8s-workload-name\" AND l.value = \"sample-workload-name\")\n;\n'\n```\n\n### Cost of Each Workload in Each Cluster\n\n```sql\nbq query --nouse_legacy_sql '\nSELECT\n  project.id AS project_id,\n  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-location\" LIMIT 1) AS cluster_location,\n  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-name\" LIMIT 1) AS cluster_name,\n  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"k8s-namespace\" LIMIT 1) AS k8s_namespace,\n  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"k8s-workload-type\" LIMIT 1) AS k8s_workload_type,\n  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"k8s-workload-name\" LIMIT 1) AS k8s_workload_name,\n  SUM(cost) + SUM(IFNULL((SELECT SUM(c.amount) FROM UNNEST(credits) c), 0)) AS cost,\n  SUM(cost) AS cost_before_credits\nFROM {{.BQDatasetProjectID}}.{{.BQDatasetName}}.gcp_billing_export_resource_v1_XXXXXX_XXXXXX_XXXXXX AS bqe\nWHERE _PARTITIONTIME >= TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 30 DAY)\n  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-name\")\nGROUP BY 1, 2, 3, 4, 5, 6\nORDER BY 7 DESC\nLIMIT 10\n;\n'\n```\n\nNote: Checking that the \"goog-k8s-cluster-name\" label exists scopes the total billing data to just GKE costs.\n",{"data":35,"body":36},{"name":4,"description":6},{"type":37,"children":38},"root",[39,47,53,60,65,71,76,141,147,214,220,225,232,371,377,524,529],{"type":40,"tag":41,"props":42,"children":43},"element","h1",{"id":4},[44],{"type":45,"value":46},"text","GKE Cost Analysis",{"type":40,"tag":48,"props":49,"children":50},"p",{},[51],{"type":45,"value":52},"This skill provides guidance on answering natural language questions about GKE-related costs, optimization, or billing.",{"type":40,"tag":54,"props":55,"children":57},"h2",{"id":56},"overview",[58],{"type":45,"value":59},"Overview",{"type":40,"tag":48,"props":61,"children":62},{},[63],{"type":45,"value":64},"When users ask about GKE costs (e.g., \"What are my costs across projects?\", \"What's my most expensive namespace?\"), use this skill to provide a structured and expert response.",{"type":40,"tag":54,"props":66,"children":68},{"id":67},"instructions",[69],{"type":45,"value":70},"Instructions",{"type":40,"tag":48,"props":72,"children":73},{},[74],{"type":45,"value":75},"When handling a cost-related question:",{"type":40,"tag":77,"props":78,"children":79},"ol",{},[80,92,102,112,131],{"type":40,"tag":81,"props":82,"children":83},"li",{},[84,90],{"type":40,"tag":85,"props":86,"children":87},"strong",{},[88],{"type":45,"value":89},"Provide a Direct Answer",{"type":45,"value":91},": Address the specific cost question or optimization request.",{"type":40,"tag":81,"props":93,"children":94},{},[95,100],{"type":40,"tag":85,"props":96,"children":97},{},[98],{"type":45,"value":99},"Explain BigQuery Integration",{"type":45,"value":101},": Explain how to use BigQuery for cost analysis if relevant. Mention that GKE costs come from GCP Billing Detailed BigQuery Export.",{"type":40,"tag":81,"props":103,"children":104},{},[105,110],{"type":40,"tag":85,"props":106,"children":107},{},[108],{"type":45,"value":109},"Check Cost Allocation",{"type":45,"value":111},": Mention that GKE Cost Allocation must be enabled for namespace and workload-level cost data.",{"type":40,"tag":81,"props":113,"children":114},{},[115,120,122,129],{"type":40,"tag":85,"props":116,"children":117},{},[118],{"type":45,"value":119},"Provide Actionable Steps",{"type":45,"value":121},": Provide concrete next steps or commands when possible. Prefer BigQuery CLI (",{"type":40,"tag":123,"props":124,"children":126},"code",{"className":125},[],[127],{"type":45,"value":128},"bq",{"type":45,"value":130},") over BigQuery Studio when available.",{"type":40,"tag":81,"props":132,"children":133},{},[134,139],{"type":40,"tag":85,"props":135,"children":136},{},[137],{"type":45,"value":138},"Reference Resources",{"type":45,"value":140},": Point to relevant GCP documentation or console links.",{"type":40,"tag":54,"props":142,"children":144},{"id":143},"key-points-to-remember",[145],{"type":45,"value":146},"Key Points to Remember",{"type":40,"tag":148,"props":149,"children":150},"ul",{},[151,161,171,204],{"type":40,"tag":81,"props":152,"children":153},{},[154,159],{"type":40,"tag":85,"props":155,"children":156},{},[157],{"type":45,"value":158},"Data Source",{"type":45,"value":160},": GKE costs come from GCP Billing Detailed BigQuery Export. The user must provide the full path to their BigQuery table (dataset name and table name containing Billing Account ID).",{"type":40,"tag":81,"props":162,"children":163},{},[164,169],{"type":40,"tag":85,"props":165,"children":166},{},[167],{"type":45,"value":168},"Granularity",{"type":45,"value":170},": GKE Cost Allocation must be enabled for namespace and workload-level cost data.",{"type":40,"tag":81,"props":172,"children":173},{},[174,179,181,186,188,194,196,202],{"type":40,"tag":85,"props":175,"children":176},{},[177],{"type":45,"value":178},"Tools",{"type":45,"value":180},": BigQuery CLI (",{"type":40,"tag":123,"props":182,"children":184},{"className":183},[],[185],{"type":45,"value":128},{"type":45,"value":187},") is preferred. When writing Standard SQL queries, use a dot (",{"type":40,"tag":123,"props":189,"children":191},{"className":190},[],[192],{"type":45,"value":193},".",{"type":45,"value":195},") instead of a colon (",{"type":40,"tag":123,"props":197,"children":199},{"className":198},[],[200],{"type":45,"value":201},":",{"type":45,"value":203},") to separate the project ID and dataset name.",{"type":40,"tag":81,"props":205,"children":206},{},[207,212],{"type":40,"tag":85,"props":208,"children":209},{},[210],{"type":45,"value":211},"Defaults",{"type":45,"value":213},": Assume last 30 days, row limit 10, ordering by cost descending, unless specified otherwise.",{"type":40,"tag":54,"props":215,"children":217},{"id":216},"example-bigquery-queries",[218],{"type":45,"value":219},"Example BigQuery Queries",{"type":40,"tag":48,"props":221,"children":222},{},[223],{"type":45,"value":224},"Use these queries as templates to answer questions. All parameters (dataset, table, project, cluster, etc.) need to be replaced.",{"type":40,"tag":226,"props":227,"children":229},"h3",{"id":228},"cost-of-a-single-workload-in-a-single-cluster",[230],{"type":45,"value":231},"Cost of a Single Workload in a Single Cluster",{"type":40,"tag":233,"props":234,"children":239},"pre",{"className":235,"code":236,"language":237,"meta":238,"style":238},"language-sql shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","bq query --nouse_legacy_sql '\nSELECT\n  SUM(cost) + SUM(IFNULL((SELECT SUM(c.amount) FROM UNNEST(credits) c), 0)) AS cost,\n  SUM(cost) AS cost_before_credits\nFROM {{.BQDatasetProjectID}}.{{.BQDatasetName}}.gcp_billing_export_resource_v1_XXXXXX_XXXXXX_XXXXXX AS bqe\nWHERE _PARTITIONTIME >= TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 30 DAY)\n  AND project.id = \"sample-project-id\"\n  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-location\" AND l.value = \"us-central1\")\n  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-name\" AND l.value = \"sample-cluster-name\")\n  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"k8s-namespace\" AND l.value = \"sample-namespace\")\n  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"k8s-workload-type\" AND l.value = \"apps\u002Fv1-Deployment\")\n  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"k8s-workload-name\" AND l.value = \"sample-workload-name\")\n;\n'\n","sql","",[240],{"type":40,"tag":123,"props":241,"children":242},{"__ignoreMap":238},[243,254,263,272,281,290,299,308,317,326,335,344,353,362],{"type":40,"tag":244,"props":245,"children":248},"span",{"class":246,"line":247},"line",1,[249],{"type":40,"tag":244,"props":250,"children":251},{},[252],{"type":45,"value":253},"bq query --nouse_legacy_sql '\n",{"type":40,"tag":244,"props":255,"children":257},{"class":246,"line":256},2,[258],{"type":40,"tag":244,"props":259,"children":260},{},[261],{"type":45,"value":262},"SELECT\n",{"type":40,"tag":244,"props":264,"children":266},{"class":246,"line":265},3,[267],{"type":40,"tag":244,"props":268,"children":269},{},[270],{"type":45,"value":271},"  SUM(cost) + SUM(IFNULL((SELECT SUM(c.amount) FROM UNNEST(credits) c), 0)) AS cost,\n",{"type":40,"tag":244,"props":273,"children":275},{"class":246,"line":274},4,[276],{"type":40,"tag":244,"props":277,"children":278},{},[279],{"type":45,"value":280},"  SUM(cost) AS cost_before_credits\n",{"type":40,"tag":244,"props":282,"children":284},{"class":246,"line":283},5,[285],{"type":40,"tag":244,"props":286,"children":287},{},[288],{"type":45,"value":289},"FROM {{.BQDatasetProjectID}}.{{.BQDatasetName}}.gcp_billing_export_resource_v1_XXXXXX_XXXXXX_XXXXXX AS bqe\n",{"type":40,"tag":244,"props":291,"children":293},{"class":246,"line":292},6,[294],{"type":40,"tag":244,"props":295,"children":296},{},[297],{"type":45,"value":298},"WHERE _PARTITIONTIME >= TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 30 DAY)\n",{"type":40,"tag":244,"props":300,"children":302},{"class":246,"line":301},7,[303],{"type":40,"tag":244,"props":304,"children":305},{},[306],{"type":45,"value":307},"  AND project.id = \"sample-project-id\"\n",{"type":40,"tag":244,"props":309,"children":311},{"class":246,"line":310},8,[312],{"type":40,"tag":244,"props":313,"children":314},{},[315],{"type":45,"value":316},"  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-location\" AND l.value = \"us-central1\")\n",{"type":40,"tag":244,"props":318,"children":320},{"class":246,"line":319},9,[321],{"type":40,"tag":244,"props":322,"children":323},{},[324],{"type":45,"value":325},"  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-name\" AND l.value = \"sample-cluster-name\")\n",{"type":40,"tag":244,"props":327,"children":329},{"class":246,"line":328},10,[330],{"type":40,"tag":244,"props":331,"children":332},{},[333],{"type":45,"value":334},"  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"k8s-namespace\" AND l.value = \"sample-namespace\")\n",{"type":40,"tag":244,"props":336,"children":338},{"class":246,"line":337},11,[339],{"type":40,"tag":244,"props":340,"children":341},{},[342],{"type":45,"value":343},"  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"k8s-workload-type\" AND l.value = \"apps\u002Fv1-Deployment\")\n",{"type":40,"tag":244,"props":345,"children":347},{"class":246,"line":346},12,[348],{"type":40,"tag":244,"props":349,"children":350},{},[351],{"type":45,"value":352},"  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"k8s-workload-name\" AND l.value = \"sample-workload-name\")\n",{"type":40,"tag":244,"props":354,"children":356},{"class":246,"line":355},13,[357],{"type":40,"tag":244,"props":358,"children":359},{},[360],{"type":45,"value":361},";\n",{"type":40,"tag":244,"props":363,"children":365},{"class":246,"line":364},14,[366],{"type":40,"tag":244,"props":367,"children":368},{},[369],{"type":45,"value":370},"'\n",{"type":40,"tag":226,"props":372,"children":374},{"id":373},"cost-of-each-workload-in-each-cluster",[375],{"type":45,"value":376},"Cost of Each Workload in Each Cluster",{"type":40,"tag":233,"props":378,"children":380},{"className":235,"code":379,"language":237,"meta":238,"style":238},"bq query --nouse_legacy_sql '\nSELECT\n  project.id AS project_id,\n  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-location\" LIMIT 1) AS cluster_location,\n  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-name\" LIMIT 1) AS cluster_name,\n  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"k8s-namespace\" LIMIT 1) AS k8s_namespace,\n  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"k8s-workload-type\" LIMIT 1) AS k8s_workload_type,\n  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"k8s-workload-name\" LIMIT 1) AS k8s_workload_name,\n  SUM(cost) + SUM(IFNULL((SELECT SUM(c.amount) FROM UNNEST(credits) c), 0)) AS cost,\n  SUM(cost) AS cost_before_credits\nFROM {{.BQDatasetProjectID}}.{{.BQDatasetName}}.gcp_billing_export_resource_v1_XXXXXX_XXXXXX_XXXXXX AS bqe\nWHERE _PARTITIONTIME >= TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 30 DAY)\n  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-name\")\nGROUP BY 1, 2, 3, 4, 5, 6\nORDER BY 7 DESC\nLIMIT 10\n;\n'\n",[381],{"type":40,"tag":123,"props":382,"children":383},{"__ignoreMap":238},[384,391,398,406,414,422,430,438,446,453,460,467,474,482,490,499,508,516],{"type":40,"tag":244,"props":385,"children":386},{"class":246,"line":247},[387],{"type":40,"tag":244,"props":388,"children":389},{},[390],{"type":45,"value":253},{"type":40,"tag":244,"props":392,"children":393},{"class":246,"line":256},[394],{"type":40,"tag":244,"props":395,"children":396},{},[397],{"type":45,"value":262},{"type":40,"tag":244,"props":399,"children":400},{"class":246,"line":265},[401],{"type":40,"tag":244,"props":402,"children":403},{},[404],{"type":45,"value":405},"  project.id AS project_id,\n",{"type":40,"tag":244,"props":407,"children":408},{"class":246,"line":274},[409],{"type":40,"tag":244,"props":410,"children":411},{},[412],{"type":45,"value":413},"  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-location\" LIMIT 1) AS cluster_location,\n",{"type":40,"tag":244,"props":415,"children":416},{"class":246,"line":283},[417],{"type":40,"tag":244,"props":418,"children":419},{},[420],{"type":45,"value":421},"  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-name\" LIMIT 1) AS cluster_name,\n",{"type":40,"tag":244,"props":423,"children":424},{"class":246,"line":292},[425],{"type":40,"tag":244,"props":426,"children":427},{},[428],{"type":45,"value":429},"  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"k8s-namespace\" LIMIT 1) AS k8s_namespace,\n",{"type":40,"tag":244,"props":431,"children":432},{"class":246,"line":301},[433],{"type":40,"tag":244,"props":434,"children":435},{},[436],{"type":45,"value":437},"  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"k8s-workload-type\" LIMIT 1) AS k8s_workload_type,\n",{"type":40,"tag":244,"props":439,"children":440},{"class":246,"line":310},[441],{"type":40,"tag":244,"props":442,"children":443},{},[444],{"type":45,"value":445},"  (SELECT l.value FROM bqe.labels AS l WHERE l.key = \"k8s-workload-name\" LIMIT 1) AS k8s_workload_name,\n",{"type":40,"tag":244,"props":447,"children":448},{"class":246,"line":319},[449],{"type":40,"tag":244,"props":450,"children":451},{},[452],{"type":45,"value":271},{"type":40,"tag":244,"props":454,"children":455},{"class":246,"line":328},[456],{"type":40,"tag":244,"props":457,"children":458},{},[459],{"type":45,"value":280},{"type":40,"tag":244,"props":461,"children":462},{"class":246,"line":337},[463],{"type":40,"tag":244,"props":464,"children":465},{},[466],{"type":45,"value":289},{"type":40,"tag":244,"props":468,"children":469},{"class":246,"line":346},[470],{"type":40,"tag":244,"props":471,"children":472},{},[473],{"type":45,"value":298},{"type":40,"tag":244,"props":475,"children":476},{"class":246,"line":355},[477],{"type":40,"tag":244,"props":478,"children":479},{},[480],{"type":45,"value":481},"  AND EXISTS(SELECT * FROM bqe.labels AS l WHERE l.key = \"goog-k8s-cluster-name\")\n",{"type":40,"tag":244,"props":483,"children":484},{"class":246,"line":364},[485],{"type":40,"tag":244,"props":486,"children":487},{},[488],{"type":45,"value":489},"GROUP BY 1, 2, 3, 4, 5, 6\n",{"type":40,"tag":244,"props":491,"children":493},{"class":246,"line":492},15,[494],{"type":40,"tag":244,"props":495,"children":496},{},[497],{"type":45,"value":498},"ORDER BY 7 DESC\n",{"type":40,"tag":244,"props":500,"children":502},{"class":246,"line":501},16,[503],{"type":40,"tag":244,"props":504,"children":505},{},[506],{"type":45,"value":507},"LIMIT 10\n",{"type":40,"tag":244,"props":509,"children":511},{"class":246,"line":510},17,[512],{"type":40,"tag":244,"props":513,"children":514},{},[515],{"type":45,"value":361},{"type":40,"tag":244,"props":517,"children":519},{"class":246,"line":518},18,[520],{"type":40,"tag":244,"props":521,"children":522},{},[523],{"type":45,"value":370},{"type":40,"tag":48,"props":525,"children":526},{},[527],{"type":45,"value":528},"Note: Checking that the \"goog-k8s-cluster-name\" label exists scopes the total billing data to just GKE costs.",{"type":40,"tag":530,"props":531,"children":532},"style",{},[533],{"type":45,"value":534},"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":536,"total":634},[537,549,564,577,594,605,621],{"slug":538,"name":538,"fn":539,"description":540,"org":541,"tags":542,"stars":24,"repoUrl":25,"updatedAt":548},"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},[543,546,547],{"name":544,"slug":545,"type":16},"Deployment","deployment",{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},"2026-07-12T07:39:30.888879",{"slug":550,"name":550,"fn":551,"description":552,"org":553,"tags":554,"stars":24,"repoUrl":25,"updatedAt":563},"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},[555,558,559,560],{"name":556,"slug":557,"type":16},"Debugging","debugging",{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":561,"slug":562,"type":16},"Performance","performance","2026-07-28T05:34:18.149515",{"slug":565,"name":565,"fn":566,"description":567,"org":568,"tags":569,"stars":24,"repoUrl":25,"updatedAt":576},"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},[570,571,572,573],{"name":556,"slug":557,"type":16},{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":574,"slug":575,"type":16},"Observability","observability","2026-07-12T07:40:04.511878",{"slug":578,"name":578,"fn":579,"description":580,"org":581,"tags":582,"stars":24,"repoUrl":25,"updatedAt":593},"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},[583,586,589,590],{"name":584,"slug":585,"type":16},"Documentation","documentation",{"name":587,"slug":588,"type":16},"Engineering","engineering",{"name":9,"slug":8,"type":16},{"name":591,"slug":592,"type":16},"Technical Writing","technical-writing","2026-07-12T07:39:50.73484",{"slug":595,"name":595,"fn":596,"description":597,"org":598,"tags":599,"stars":24,"repoUrl":25,"updatedAt":604},"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},[600,601,602,603],{"name":556,"slug":557,"type":16},{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":561,"slug":562,"type":16},"2026-07-12T07:39:49.482979",{"slug":606,"name":606,"fn":607,"description":608,"org":609,"tags":610,"stars":24,"repoUrl":25,"updatedAt":620},"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},[611,614,615,616,617],{"name":612,"slug":613,"type":16},"Containers","containers",{"name":544,"slug":545,"type":16},{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":618,"slug":619,"type":16},"Onboarding","onboarding","2026-07-12T07:39:41.935837",{"slug":622,"name":622,"fn":623,"description":624,"org":625,"tags":626,"stars":24,"repoUrl":25,"updatedAt":633},"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},[627,628,629,630],{"name":544,"slug":545,"type":16},{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":631,"slug":632,"type":16},"Operations","operations","2026-07-12T07:39:34.806995",25,{"items":636,"total":817},[637,653,669,689,703,712,726,743,760,773,789,799],{"slug":638,"name":638,"fn":639,"description":640,"org":641,"tags":642,"stars":650,"repoUrl":651,"updatedAt":652},"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},[643,644,647],{"name":584,"slug":585,"type":16},{"name":645,"slug":646,"type":16},"Knowledge Base","knowledge-base",{"name":648,"slug":649,"type":16},"Search","search",6749,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog","2026-07-12T07:38:52.157375",{"slug":654,"name":655,"fn":656,"description":657,"org":658,"tags":659,"stars":650,"repoUrl":651,"updatedAt":668},"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},[660,663,664,667],{"name":661,"slug":662,"type":16},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":16},{"name":665,"slug":666,"type":16},"Knowledge Management","knowledge-management",{"name":648,"slug":649,"type":16},"2026-07-12T07:38:22.196851",{"slug":670,"name":670,"fn":671,"description":672,"org":673,"tags":674,"stars":686,"repoUrl":687,"updatedAt":688},"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},[675,678,679,682,683],{"name":676,"slug":677,"type":16},"Automation","automation",{"name":587,"slug":588,"type":16},{"name":680,"slug":681,"type":16},"GitHub","github",{"name":9,"slug":8,"type":16},{"name":684,"slug":685,"type":16},"Pull Requests","pull-requests",2062,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-foundation-fabric","2026-07-31T06:23:36.935005",{"slug":690,"name":690,"fn":691,"description":692,"org":693,"tags":694,"stars":686,"repoUrl":687,"updatedAt":702},"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},[695,696,699],{"name":9,"slug":8,"type":16},{"name":697,"slug":698,"type":16},"Infrastructure as Code","infrastructure-as-code",{"name":700,"slug":701,"type":16},"Terraform","terraform","2026-07-12T07:38:23.514555",{"slug":704,"name":704,"fn":705,"description":706,"org":707,"tags":708,"stars":686,"repoUrl":687,"updatedAt":711},"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},[709,710],{"name":9,"slug":8,"type":16},{"name":631,"slug":632,"type":16},"2026-07-12T07:38:28.127148",{"slug":713,"name":713,"fn":714,"description":715,"org":716,"tags":717,"stars":723,"repoUrl":724,"updatedAt":725},"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},[718,721,722],{"name":719,"slug":720,"type":16},"CLI","cli",{"name":587,"slug":588,"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":727,"name":727,"fn":728,"description":729,"org":730,"tags":731,"stars":723,"repoUrl":724,"updatedAt":742},"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},[732,735,736,739],{"name":733,"slug":734,"type":16},"API Development","api-development",{"name":9,"slug":8,"type":16},{"name":737,"slug":738,"type":16},"LLM","llm",{"name":740,"slug":741,"type":16},"MCP","mcp","2026-07-12T07:39:10.911302",{"slug":744,"name":744,"fn":745,"description":746,"org":747,"tags":748,"stars":723,"repoUrl":724,"updatedAt":759},"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},[749,752,755,756],{"name":750,"slug":751,"type":16},"Audio","audio",{"name":753,"slug":754,"type":16},"Creative","creative",{"name":9,"slug":8,"type":16},{"name":757,"slug":758,"type":16},"Vertex AI","vertex-ai","2026-07-12T07:39:16.623879",{"slug":761,"name":761,"fn":762,"description":763,"org":764,"tags":765,"stars":723,"repoUrl":724,"updatedAt":772},"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},[766,767,768,771],{"name":753,"slug":754,"type":16},{"name":9,"slug":8,"type":16},{"name":769,"slug":770,"type":16},"Image Generation","image-generation",{"name":757,"slug":758,"type":16},"2026-07-12T07:39:15.372822",{"slug":774,"name":774,"fn":775,"description":776,"org":777,"tags":778,"stars":723,"repoUrl":724,"updatedAt":788},"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},[779,780,781,782,785],{"name":750,"slug":751,"type":16},{"name":753,"slug":754,"type":16},{"name":9,"slug":8,"type":16},{"name":783,"slug":784,"type":16},"Media","media",{"name":786,"slug":787,"type":16},"Video","video","2026-07-12T07:39:09.672849",{"slug":790,"name":790,"fn":791,"description":792,"org":793,"tags":794,"stars":723,"repoUrl":724,"updatedAt":798},"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},[795,796,797],{"name":753,"slug":754,"type":16},{"name":9,"slug":8,"type":16},{"name":786,"slug":787,"type":16},"2026-07-12T07:39:13.749081",{"slug":800,"name":800,"fn":801,"description":802,"org":803,"tags":804,"stars":723,"repoUrl":724,"updatedAt":816},"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},[805,806,807,810,813],{"name":750,"slug":751,"type":16},{"name":753,"slug":754,"type":16},{"name":808,"slug":809,"type":16},"Gemini","gemini",{"name":811,"slug":812,"type":16},"Speech","speech",{"name":814,"slug":815,"type":16},"Text-to-Speech","text-to-speech","2026-07-12T07:39:17.86673",80]