[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M699J2PM75TMS15T6CR2D4TT":3,"skill-same:01M699J2PM75TMS15T6CR2D4TT":116},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M699J2PM75TMS15T6CR2D4TT","aks-gpu-inference",null,"Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com\u002Fgpu', GPU pod Pending, model-load OOM, DCGM\u002FVRAM, KAITO Workspace not ready, or GPU autoscaling. DO NOT USE FOR: setup (airunway-aks-setup), non-GPU incidents (aks-troubleshooting), standalone VM quota (azure-quotas), or generic cost (cost-analysis or cost-optimization from the optional azure-cost plugin).","microsoft\u002Fazure-skills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M699HXPKQFT1BH5KD1PG0CB4",1640,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Faks-skills\u002Fskills\u002Faks-gpu-inference\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,9],"aks gpu inference","gpu","aks","inference","only","when","generic","for","autoscaling","standalone","vram","read-only","do","ready","evidence","read","model","analysis","NVIDIA","diagnose","2026-11-10 10:12:30",false,"---\nname: aks-gpu-inference\ndescription: \"Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com\u002Fgpu', GPU pod Pending, model-load OOM, DCGM\u002FVRAM, KAITO Workspace not ready, or GPU autoscaling. DO NOT USE FOR: setup (airunway-aks-setup), non-GPU incidents (aks-troubleshooting), standalone VM quota (azure-quotas), or generic cost (cost-analysis or cost-optimization from the optional azure-cost plugin).\"\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.1.1\"\n---\n\n# AKS GPU Inference Day-2\n\n## Quick Reference\n\n| Property | Value |\n|---|---|\n| Best for | AKS GPU\u002FKAITO failures |\n| Evidence | Bound target, events\u002Fstatus, `gpuProfile`, DCGM |\n\n## When to Use This Skill\n\nUse for scheduling, VRAM\u002FOOM, KAITO readiness, and workload scaling. Route\nexclusions as described above.\n\n## MCP Tools\n\nUse a fitting host-advertised Azure read or the references' read-only queries.\n\n## Host Capability Gate\n\nBefore executing any referenced pipeline, verify that the host authorizes\nthe required shell and `kubectl`\u002F`az` commands against the bound target.\nFile-backed collection also requires approved artifact storage and access to\nany bundled files it uses. A governed Azure CLI tool alone does not establish\nthese capabilities. Equivalent host reads may replace commands only where\ntheir advertised schemas provide the required evidence.\n\nIf execution is unavailable or prohibited, say so and analyze supplied or\nredacted events, status, logs, and metrics, or give the operator a scoped\ncollection plan. State which reads did not run and leave conclusions requiring\nmissing evidence unconfirmed. Never route `kubectl` through Azure MCP or\nbypass host policy. The authorization requirements below still apply.\n\n## Workflow\n\n1. Bind subscription, cluster, kube context, pool, and affected resource.\n2. Capture exact events\u002Fstatus and observed `gpuProfile`; state which reads ran.\n3. Route to [scheduling](references\u002Fgpu-scheduling.md),\n   [observability](references\u002Fgpu-observability.md),\n   [KAITO](references\u002Fkaito-workspaces.md), or\n   [scaling](references\u002Fgpu-cost-and-scaling.md).\n4. Separate container\u002Fhost OOM from device-allocation failures. For `OOMKilled`,\n   correlate container memory limits\u002Fusage and node conditions. For\n   Managed+Install device-memory evidence, use the exporter on port 19400 and\n   incident-window `FB_USED`\u002F`FB_FREE`; sizing tables do not establish a cause.\n5. For KAITO not-ready, warn that Workspace deletion leaves its GPU pools;\n   cleanup is separate and needs explicit authorization.\n6. Report evidence, confidence, missing evidence, and owner handoff.\n\nRequire explicit authorization before scaling, cordon\u002Fdrain, deletion,\nadd-on enablement, or monitoring mutation.\n\n## Error Handling\n\n| Condition | Response |\n|---|---|\n| Missing\u002Fcontradictory evidence | Mark unconfirmed; request the owner\u002Fread |\n| Unknown profile | Preserve evidence; do not prescribe stack repair |\n| Mutation required | Propose separately and wait for authorization |\n","# AKS GPU Inference Day-2\n\n## Quick Reference\n\n| Property | Value |\n|---|---|\n| Best for | AKS GPU\u002FKAITO failures |\n| Evidence | Bound target, events\u002Fstatus, `gpuProfile`, DCGM |\n\n## When to Use This Skill\n\nUse for scheduling, VRAM\u002FOOM, KAITO readiness, and workload scaling. Route\nexclusions as described above.\n\n## MCP Tools\n\nUse a fitting host-advertised Azure read or the references' read-only queries.\n\n## Host Capability Gate\n\nBefore executing any referenced pipeline, verify that the host authorizes\nthe required shell and `kubectl`\u002F`az` commands against the bound target.\nFile-backed collection also requires approved artifact storage and access to\nany bundled files it uses. A governed Azure CLI tool alone does not establish\nthese capabilities. Equivalent host reads may replace commands only where\ntheir advertised schemas provide the required evidence.\n\nIf execution is unavailable or prohibited, say so and analyze supplied or\nredacted events, status, logs, and metrics, or give the operator a scoped\ncollection plan. State which reads did not run and leave conclusions requiring\nmissing evidence unconfirmed. Never route `kubectl` through Azure MCP or\nbypass host policy. The authorization requirements below still apply.\n\n## Workflow\n\n1. Bind subscription, cluster, kube context, pool, and affected resource.\n2. Capture exact events\u002Fstatus and observed `gpuProfile`; state which reads ran.\n3. Route to [scheduling](references\u002Fgpu-scheduling.md),\n   [observability](references\u002Fgpu-observability.md),\n   [KAITO](references\u002Fkaito-workspaces.md), or\n   [scaling](references\u002Fgpu-cost-and-scaling.md).\n4. Separate container\u002Fhost OOM from device-allocation failures. For `OOMKilled`,\n   correlate container memory limits\u002Fusage and node conditions. For\n   Managed+Install device-memory evidence, use the exporter on port 19400 and\n   incident-window `FB_USED`\u002F`FB_FREE`; sizing tables do not establish a cause.\n5. For KAITO not-ready, warn that Workspace deletion leaves its GPU pools;\n   cleanup is separate and needs explicit authorization.\n6. Report evidence, confidence, missing evidence, and owner handoff.\n\nRequire explicit authorization before scaling, cordon\u002Fdrain, deletion,\nadd-on enablement, or monitoring mutation.\n\n## Error Handling\n\n| Condition | Response |\n|---|---|\n| Missing\u002Fcontradictory evidence | Mark unconfirmed; request the owner\u002Fread |\n| Unknown profile | Preserve evidence; do not prescribe stack repair |\n| Mutation required | Propose separately and wait for authorization |\n",{"name":5,"license":15,"metadata":49,"description":7},{"author":12,"version":50},"1.1.1","main","fbda857c484a85c7ce644f56809b7f204471fb69",".github\u002Fplugins\u002Faks-skills\u002Fskills\u002Faks-gpu-inference",267,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 01:56:00",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add microsoft\u002Fazure-skills --skill aks-gpu-inference",{"tool":66,"command":67},"bunx","bunx skills add microsoft\u002Fazure-skills --skill aks-gpu-inference",{"tool":69,"command":70},"pnpm","pnpm dlx skills add microsoft\u002Fazure-skills --skill aks-gpu-inference","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Faks-skills\u002Fskills\u002Faks-gpu-inference\u002FSKILL.md",true,[74,80,86,90,94,98,104,108,112],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"assets\u002Fpi\u002Fno-progress-guard.ts","SCRIPT","脚本",21492,"https:\u002F\u002Fgithub.com\u002Fmattwag05\u002Fmw-plugins\u002Fblob\u002Fmain\u002Fclient-adapters\u002Fclaude-code\u002Fplugins\u002Fanti-loop\u002Fskills\u002Fanti-loop\u002Fassets\u002Fpi\u002Fno-progress-guard.ts",{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"assets\u002Fpi\u002Ftest\u002Flabyrinth-loop-20261019.json","ASSET","资产文件",27850,"https:\u002F\u002Fgithub.com\u002Fmattwag05\u002Fmw-plugins\u002Fblob\u002Fmain\u002Fclient-adapters\u002Fclaude-code\u002Fplugins\u002Fanti-loop\u002Fskills\u002Fanti-loop\u002Fassets\u002Fpi\u002Ftest\u002Flabyrinth-loop-20261019.json",{"path":87,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":88,"sourceHtmlUrl":89},"assets\u002Fpi\u002Ftest\u002Flabyrinth-paging-20261019.json",133444,"https:\u002F\u002Fgithub.com\u002Fmattwag05\u002Fmw-plugins\u002Fblob\u002Fmain\u002Fclient-adapters\u002Fclaude-code\u002Fplugins\u002Fanti-loop\u002Fskills\u002Fanti-loop\u002Fassets\u002Fpi\u002Ftest\u002Flabyrinth-paging-20261019.json",{"path":91,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":92,"sourceHtmlUrl":93},"assets\u002Fpi\u002Ftest\u002Fno-progress-guard.test.ts",18912,"https:\u002F\u002Fgithub.com\u002Fmattwag05\u002Fmw-plugins\u002Fblob\u002Fmain\u002Fclient-adapters\u002Fclaude-code\u002Fplugins\u002Fanti-loop\u002Fskills\u002Fanti-loop\u002Fassets\u002Fpi\u002Ftest\u002Fno-progress-guard.test.ts",{"path":95,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":96,"sourceHtmlUrl":97},"assets\u002Fpi\u002Ftest\u002Fvoxel-forest-20261019.json",116097,"https:\u002F\u002Fgithub.com\u002Fmattwag05\u002Fmw-plugins\u002Fblob\u002Fmain\u002Fclient-adapters\u002Fclaude-code\u002Fplugins\u002Fanti-loop\u002Fskills\u002Fanti-loop\u002Fassets\u002Fpi\u002Ftest\u002Fvoxel-forest-20261019.json",{"path":99,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fgpu-cost-and-scaling.md","REFERENCE","参考文档",1616,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Faks-skills\u002Fskills\u002Faks-gpu-inference\u002Freferences\u002Fgpu-cost-and-scaling.md",{"path":105,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fgpu-observability.md",2721,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Faks-skills\u002Fskills\u002Faks-gpu-inference\u002Freferences\u002Fgpu-observability.md",{"path":109,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fgpu-scheduling.md",3306,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Faks-skills\u002Fskills\u002Faks-gpu-inference\u002Freferences\u002Fgpu-scheduling.md",{"path":113,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Fkaito-workspaces.md",1802,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Faks-skills\u002Fskills\u002Faks-gpu-inference\u002Freferences\u002Fkaito-workspaces.md",[117,125,152,177,198,214],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":124},"01M741F125HZK56E6BKPW36WRA","azure-advisor-cost-optimization","Analyze Azure Advisor Cost\u002FIdleResources findings and prevalidate deletion safety, including Service Groups. WHEN: \"find unused Azure resources\", \"what resources am I paying for but no longer using\", \"idle-resource savings\", \"historical idle-resource savings\", \"are these idle resources safe to delete\". Generic Cost, other subcategories, and cross-category requests use azure-advisor.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-advisor\u002Fskills\u002Fazure-advisor-cost-optimization\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":134,"publishedAt":44},"01M699VFT1T15GFDGC4K4ZHY4N","python-appservice-deploy","Deploy Python (Flask\u002FDjango\u002FFastAPI) code to Azure App Service Linux. WHEN: \"Flask App Service\", \"Django App Service\", \"FastAPI App Service\", \"deploy Python to App Service\". DO NOT USE FOR: Container Apps, Functions, non-Python, Terraform\u002FBicep\u002FIaC, full infra — use azure-prepare.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002Fskills\u002Fpython-appservice-deploy\u002FSKILL.md",[131],{"categoryNo":132,"categoryName":133,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",[135,136,137,138,139,140,36,141,31,142,143,144,145,146,147,148,29,149,150,151],"python appservice deploy","deploy","python","linux","infra","app","django","azure app service","azure","container","iac","fastapi","use","apps","code","functions","fastapi app",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":160,"publishedAt":44},"01M699VDV3PT5P0YDXRT4GM2TJ","preset","Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fpreset\u002FSKILL.md",[158,159],{"categoryNo":132,"categoryName":133,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[154,136,161,9,162,163,36,164,165,31,166,167,168,143,169,170,171,147,172,173,174,175,176],"setup","capacity","customize","quick","availability","deployment","alternatives","selection","custom","deployments","high availability","version","across","check","multi","first",{"skillNo":178,"name":163,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":183,"publishedAt":44},"01M699VBT6YFAKBWCK890XDB6N","Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard\u002FStandard\u002FProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcustomize\u002FSKILL.md",[182],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[163,154,9,162,184,185,164,186,187,40,188,189,168,190,191,192,193,194,195,196,197,36,31,166],"policy","SET","processing","advanced","select","choose","configure","filter","azure openai","options","flow","openai","throughput","full",{"skillNo":199,"name":162,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":203,"publishedAt":44},"01M699V9FXHBSWG3Y48057VAYZ","Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcapacity\u002FSKILL.md",[],[162,154,136,9,163,204,40,205,206,41,207,208,173,192,209,210,195,211,212,36,165,31,213,166],"projects","project","search","listing","hand","limits","azure portal","direct","TPM","discovery",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":222,"publishedAt":44},"01M699V7GW2RF4AB3RE3Z8Y048","deploy-model","Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version\u002FSKU\u002Fcapacity\u002FRAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent\u002Fcreate), project creation (use project\u002Fcreate).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002FSKILL.md",[220,221],{"categoryNo":132,"categoryName":133,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[136,223,40,154,224,225,9,162,184,185,204,164,226,205,227,41,207,173,228,192,229,230,195,36,165],"deploy model","MCP","foundry","creation","up","create","intent","list"]