[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-microsoft-airunway-aks-setup":3,"mdc--mvkdro-key":40,"related-repo-microsoft-airunway-aks-setup":707,"related-org-microsoft-airunway-aks-setup":827},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":28,"repoUrl":29,"updatedAt":30,"license":31,"forks":32,"topics":33,"repo":35,"sourceUrl":38,"mdContent":39},"airunway-aks-setup","set up AI Runway on Azure Kubernetes Service","Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: \"setup AI Runway\", \"onboard AKS cluster\", \"install AI Runway\", \"airunway setup\", \"deploy model to AKS\", \"GPU inference on AKS\", \"KAITO setup on AKS\", \"run LLM on AKS\", \"vLLM on AKS\", \"set up model serving on AKS\", \"AI Runway controller\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"microsoft","Microsoft","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fmicrosoft.png",[12,16,19,22,25],{"name":13,"slug":14,"type":15},"Azure","azure","tag",{"name":17,"slug":18,"type":15},"Runway","runway",{"name":20,"slug":21,"type":15},"Deployment","deployment",{"name":23,"slug":24,"type":15},"AI Infrastructure","ai-infrastructure",{"name":26,"slug":27,"type":15},"Kubernetes","kubernetes",1324,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills","2026-07-31T05:56:13.054971","MIT",220,[34],"agent-skills",{"repoUrl":29,"stars":28,"forks":32,"topics":36,"description":37},[34],"Official agent plugin providing skills and MCP server configurations for Azure scenarios.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Ftree\u002FHEAD\u002Fskills\u002Fairunway-aks-setup","---\nname: airunway-aks-setup\ndescription: \"Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: \\\"setup AI Runway\\\", \\\"onboard AKS cluster\\\", \\\"install AI Runway\\\", \\\"airunway setup\\\", \\\"deploy model to AKS\\\", \\\"GPU inference on AKS\\\", \\\"KAITO setup on AKS\\\", \\\"run LLM on AKS\\\", \\\"vLLM on AKS\\\", \\\"set up model serving on AKS\\\", \\\"AI Runway controller\\\".\"\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.1.1\"\nargument-hint: \"[skip-to-step N]\"\n---\n\n# AI Runway AKS Setup\n\nThis skill walks users from a bare Kubernetes cluster to a running AI model deployment. Follow each step in sequence unless the user provides `skip-to-step N` to resume from a specific phase.\n\n> **Cost awareness:** GPU node pools incur significant compute charges (A100-80GB can cost $3–5+\u002Fhr). Confirm the user understands cost implications before provisioning GPU resources.\n\n## Prerequisites\n\nThis skill assumes an AKS cluster already exists. If the user does not have a cluster, hand off to the `azure-kubernetes` skill first to provision one (with a GPU node pool unless CPU-only inference is acceptable), then return here.\n\n## Quick Reference\n\n| Property | Value |\n|----------|-------|\n| Best for | End-to-end AI Runway onboarding on AKS |\n| CLI tools | `kubectl`, `make`, `curl` |\n| MCP tools | None |\n| Related skills | `azure-kubernetes` (cluster setup), `azure-diagnostics` (troubleshooting) |\n\n## When to Use This Skill\n\nUse this skill when the user wants to:\n- Set up AI Runway on an existing AKS cluster from scratch\n- Install the AI Runway controller and CRDs\n- Assess GPU hardware compatibility for model deployment\n- Choose and install an inference provider (KAITO, Dynamo, KubeRay)\n- Deploy their first AI model to AKS via AI Runway\n- Resume a partially-complete AI Runway setup from a specific step\n\n## MCP Tools\n\nThis skill uses no MCP tools. All cluster operations are performed directly via `kubectl` and `make`.\n\n## Rules\n\n1. Execute steps in sequence — load the reference for each step as you reach it\n2. Report cluster state at each step: ✓ healthy, ✗ missing\u002Ffailed\n3. Ask for user confirmation before any install or deployment action\n4. If a step is already complete, report status and skip to the next step\n5. If the user provides `skip-to-step N`, start at step N; assume prior steps are complete\n\n## Steps\n\n| # | Step | Reference |\n|---|------|-----------|\n| 1 | **Cluster Verification** — context check, node inventory, GPU detection | [step-1-verify.md](references\u002Fsteps\u002Fstep-1-verify.md) |\n| 2 | **Controller Installation** — CRD + controller deployment | [step-2-controller.md](references\u002Fsteps\u002Fstep-2-controller.md) |\n| 3 | **GPU Assessment** — detect GPU models, flag dtype\u002Fattention constraints | [step-3-gpu.md](references\u002Fsteps\u002Fstep-3-gpu.md) |\n| 4 | **Provider Setup** — recommend and install inference provider | [step-4-provider.md](references\u002Fsteps\u002Fstep-4-provider.md) |\n| 5 | **First Deployment** — pick a model, deploy, verify Ready | [step-5-deploy.md](references\u002Fsteps\u002Fstep-5-deploy.md) |\n| 6 | **Summary** — recap, smoke test, next steps | [step-6-summary.md](references\u002Fsteps\u002Fstep-6-summary.md) |\n\n## Error Handling\n\n| Error \u002F Symptom | Likely Cause | Remediation |\n|-----------------|--------------|-------------|\n| No kubeconfig context | Not connected to a cluster | Run `az aks get-credentials` or equivalent |\n| Controller in CrashLoopBackOff | Config or RBAC issue | `kubectl logs -n airunway-system -l control-plane=controller-manager --previous` |\n| Provider not ready | Image pull or RBAC issue | `kubectl logs \u003Cpod-name> -n \u003Cnamespace>` for the provider pod |\n| ModelDeployment stuck in Pending | GPU scheduling failure or provider not ready | `kubectl describe modeldeployment \u003Cname> -n \u003Cnamespace>` events |\n| `bfloat16` errors at inference | T4 or V100 lacks bfloat16 support | Add `--dtype float16` to serving args |\n\nFor full error handling and rollback procedures, see [troubleshooting.md](references\u002Ftroubleshooting.md).\n",{"data":41,"body":45},{"name":4,"description":6,"license":31,"metadata":42,"argument-hint":44},{"author":9,"version":43},"1.1.1","[skip-to-step N]",{"type":46,"children":47},"root",[48,57,72,87,94,107,113,225,231,236,271,277,296,302,338,344,534,540,695],{"type":49,"tag":50,"props":51,"children":53},"element","h1",{"id":52},"ai-runway-aks-setup",[54],{"type":55,"value":56},"text","AI Runway AKS Setup",{"type":49,"tag":58,"props":59,"children":60},"p",{},[61,63,70],{"type":55,"value":62},"This skill walks users from a bare Kubernetes cluster to a running AI model deployment. Follow each step in sequence unless the user provides ",{"type":49,"tag":64,"props":65,"children":67},"code",{"className":66},[],[68],{"type":55,"value":69},"skip-to-step N",{"type":55,"value":71}," to resume from a specific phase.",{"type":49,"tag":73,"props":74,"children":75},"blockquote",{},[76],{"type":49,"tag":58,"props":77,"children":78},{},[79,85],{"type":49,"tag":80,"props":81,"children":82},"strong",{},[83],{"type":55,"value":84},"Cost awareness:",{"type":55,"value":86}," GPU node pools incur significant compute charges (A100-80GB can cost $3–5+\u002Fhr). Confirm the user understands cost implications before provisioning GPU resources.",{"type":49,"tag":88,"props":89,"children":91},"h2",{"id":90},"prerequisites",[92],{"type":55,"value":93},"Prerequisites",{"type":49,"tag":58,"props":95,"children":96},{},[97,99,105],{"type":55,"value":98},"This skill assumes an AKS cluster already exists. If the user does not have a cluster, hand off to the ",{"type":49,"tag":64,"props":100,"children":102},{"className":101},[],[103],{"type":55,"value":104},"azure-kubernetes",{"type":55,"value":106}," skill first to provision one (with a GPU node pool unless CPU-only inference is acceptable), then return here.",{"type":49,"tag":88,"props":108,"children":110},{"id":109},"quick-reference",[111],{"type":55,"value":112},"Quick Reference",{"type":49,"tag":114,"props":115,"children":116},"table",{},[117,136],{"type":49,"tag":118,"props":119,"children":120},"thead",{},[121],{"type":49,"tag":122,"props":123,"children":124},"tr",{},[125,131],{"type":49,"tag":126,"props":127,"children":128},"th",{},[129],{"type":55,"value":130},"Property",{"type":49,"tag":126,"props":132,"children":133},{},[134],{"type":55,"value":135},"Value",{"type":49,"tag":137,"props":138,"children":139},"tbody",{},[140,154,186,199],{"type":49,"tag":122,"props":141,"children":142},{},[143,149],{"type":49,"tag":144,"props":145,"children":146},"td",{},[147],{"type":55,"value":148},"Best for",{"type":49,"tag":144,"props":150,"children":151},{},[152],{"type":55,"value":153},"End-to-end AI Runway onboarding on AKS",{"type":49,"tag":122,"props":155,"children":156},{},[157,162],{"type":49,"tag":144,"props":158,"children":159},{},[160],{"type":55,"value":161},"CLI tools",{"type":49,"tag":144,"props":163,"children":164},{},[165,171,173,179,180],{"type":49,"tag":64,"props":166,"children":168},{"className":167},[],[169],{"type":55,"value":170},"kubectl",{"type":55,"value":172},", ",{"type":49,"tag":64,"props":174,"children":176},{"className":175},[],[177],{"type":55,"value":178},"make",{"type":55,"value":172},{"type":49,"tag":64,"props":181,"children":183},{"className":182},[],[184],{"type":55,"value":185},"curl",{"type":49,"tag":122,"props":187,"children":188},{},[189,194],{"type":49,"tag":144,"props":190,"children":191},{},[192],{"type":55,"value":193},"MCP tools",{"type":49,"tag":144,"props":195,"children":196},{},[197],{"type":55,"value":198},"None",{"type":49,"tag":122,"props":200,"children":201},{},[202,207],{"type":49,"tag":144,"props":203,"children":204},{},[205],{"type":55,"value":206},"Related skills",{"type":49,"tag":144,"props":208,"children":209},{},[210,215,217,223],{"type":49,"tag":64,"props":211,"children":213},{"className":212},[],[214],{"type":55,"value":104},{"type":55,"value":216}," (cluster setup), ",{"type":49,"tag":64,"props":218,"children":220},{"className":219},[],[221],{"type":55,"value":222},"azure-diagnostics",{"type":55,"value":224}," (troubleshooting)",{"type":49,"tag":88,"props":226,"children":228},{"id":227},"when-to-use-this-skill",[229],{"type":55,"value":230},"When to Use This Skill",{"type":49,"tag":58,"props":232,"children":233},{},[234],{"type":55,"value":235},"Use this skill when the user wants to:",{"type":49,"tag":237,"props":238,"children":239},"ul",{},[240,246,251,256,261,266],{"type":49,"tag":241,"props":242,"children":243},"li",{},[244],{"type":55,"value":245},"Set up AI Runway on an existing AKS cluster from scratch",{"type":49,"tag":241,"props":247,"children":248},{},[249],{"type":55,"value":250},"Install the AI Runway controller and CRDs",{"type":49,"tag":241,"props":252,"children":253},{},[254],{"type":55,"value":255},"Assess GPU hardware compatibility for model deployment",{"type":49,"tag":241,"props":257,"children":258},{},[259],{"type":55,"value":260},"Choose and install an inference provider (KAITO, Dynamo, KubeRay)",{"type":49,"tag":241,"props":262,"children":263},{},[264],{"type":55,"value":265},"Deploy their first AI model to AKS via AI Runway",{"type":49,"tag":241,"props":267,"children":268},{},[269],{"type":55,"value":270},"Resume a partially-complete AI Runway setup from a specific step",{"type":49,"tag":88,"props":272,"children":274},{"id":273},"mcp-tools",[275],{"type":55,"value":276},"MCP Tools",{"type":49,"tag":58,"props":278,"children":279},{},[280,282,287,289,294],{"type":55,"value":281},"This skill uses no MCP tools. All cluster operations are performed directly via ",{"type":49,"tag":64,"props":283,"children":285},{"className":284},[],[286],{"type":55,"value":170},{"type":55,"value":288}," and ",{"type":49,"tag":64,"props":290,"children":292},{"className":291},[],[293],{"type":55,"value":178},{"type":55,"value":295},".",{"type":49,"tag":88,"props":297,"children":299},{"id":298},"rules",[300],{"type":55,"value":301},"Rules",{"type":49,"tag":303,"props":304,"children":305},"ol",{},[306,311,316,321,326],{"type":49,"tag":241,"props":307,"children":308},{},[309],{"type":55,"value":310},"Execute steps in sequence — load the reference for each step as you reach it",{"type":49,"tag":241,"props":312,"children":313},{},[314],{"type":55,"value":315},"Report cluster state at each step: ✓ healthy, ✗ missing\u002Ffailed",{"type":49,"tag":241,"props":317,"children":318},{},[319],{"type":55,"value":320},"Ask for user confirmation before any install or deployment action",{"type":49,"tag":241,"props":322,"children":323},{},[324],{"type":55,"value":325},"If a step is already complete, report status and skip to the next step",{"type":49,"tag":241,"props":327,"children":328},{},[329,331,336],{"type":55,"value":330},"If the user provides ",{"type":49,"tag":64,"props":332,"children":334},{"className":333},[],[335],{"type":55,"value":69},{"type":55,"value":337},", start at step N; assume prior steps are complete",{"type":49,"tag":88,"props":339,"children":341},{"id":340},"steps",[342],{"type":55,"value":343},"Steps",{"type":49,"tag":114,"props":345,"children":346},{},[347,368],{"type":49,"tag":118,"props":348,"children":349},{},[350],{"type":49,"tag":122,"props":351,"children":352},{},[353,358,363],{"type":49,"tag":126,"props":354,"children":355},{},[356],{"type":55,"value":357},"#",{"type":49,"tag":126,"props":359,"children":360},{},[361],{"type":55,"value":362},"Step",{"type":49,"tag":126,"props":364,"children":365},{},[366],{"type":55,"value":367},"Reference",{"type":49,"tag":137,"props":369,"children":370},{},[371,399,426,453,480,507],{"type":49,"tag":122,"props":372,"children":373},{},[374,379,389],{"type":49,"tag":144,"props":375,"children":376},{},[377],{"type":55,"value":378},"1",{"type":49,"tag":144,"props":380,"children":381},{},[382,387],{"type":49,"tag":80,"props":383,"children":384},{},[385],{"type":55,"value":386},"Cluster Verification",{"type":55,"value":388}," — context check, node inventory, GPU detection",{"type":49,"tag":144,"props":390,"children":391},{},[392],{"type":49,"tag":393,"props":394,"children":396},"a",{"href":395},"references\u002Fsteps\u002Fstep-1-verify.md",[397],{"type":55,"value":398},"step-1-verify.md",{"type":49,"tag":122,"props":400,"children":401},{},[402,407,417],{"type":49,"tag":144,"props":403,"children":404},{},[405],{"type":55,"value":406},"2",{"type":49,"tag":144,"props":408,"children":409},{},[410,415],{"type":49,"tag":80,"props":411,"children":412},{},[413],{"type":55,"value":414},"Controller Installation",{"type":55,"value":416}," — CRD + controller deployment",{"type":49,"tag":144,"props":418,"children":419},{},[420],{"type":49,"tag":393,"props":421,"children":423},{"href":422},"references\u002Fsteps\u002Fstep-2-controller.md",[424],{"type":55,"value":425},"step-2-controller.md",{"type":49,"tag":122,"props":427,"children":428},{},[429,434,444],{"type":49,"tag":144,"props":430,"children":431},{},[432],{"type":55,"value":433},"3",{"type":49,"tag":144,"props":435,"children":436},{},[437,442],{"type":49,"tag":80,"props":438,"children":439},{},[440],{"type":55,"value":441},"GPU Assessment",{"type":55,"value":443}," — detect GPU models, flag dtype\u002Fattention constraints",{"type":49,"tag":144,"props":445,"children":446},{},[447],{"type":49,"tag":393,"props":448,"children":450},{"href":449},"references\u002Fsteps\u002Fstep-3-gpu.md",[451],{"type":55,"value":452},"step-3-gpu.md",{"type":49,"tag":122,"props":454,"children":455},{},[456,461,471],{"type":49,"tag":144,"props":457,"children":458},{},[459],{"type":55,"value":460},"4",{"type":49,"tag":144,"props":462,"children":463},{},[464,469],{"type":49,"tag":80,"props":465,"children":466},{},[467],{"type":55,"value":468},"Provider Setup",{"type":55,"value":470}," — recommend and install inference provider",{"type":49,"tag":144,"props":472,"children":473},{},[474],{"type":49,"tag":393,"props":475,"children":477},{"href":476},"references\u002Fsteps\u002Fstep-4-provider.md",[478],{"type":55,"value":479},"step-4-provider.md",{"type":49,"tag":122,"props":481,"children":482},{},[483,488,498],{"type":49,"tag":144,"props":484,"children":485},{},[486],{"type":55,"value":487},"5",{"type":49,"tag":144,"props":489,"children":490},{},[491,496],{"type":49,"tag":80,"props":492,"children":493},{},[494],{"type":55,"value":495},"First Deployment",{"type":55,"value":497}," — pick a model, deploy, verify Ready",{"type":49,"tag":144,"props":499,"children":500},{},[501],{"type":49,"tag":393,"props":502,"children":504},{"href":503},"references\u002Fsteps\u002Fstep-5-deploy.md",[505],{"type":55,"value":506},"step-5-deploy.md",{"type":49,"tag":122,"props":508,"children":509},{},[510,515,525],{"type":49,"tag":144,"props":511,"children":512},{},[513],{"type":55,"value":514},"6",{"type":49,"tag":144,"props":516,"children":517},{},[518,523],{"type":49,"tag":80,"props":519,"children":520},{},[521],{"type":55,"value":522},"Summary",{"type":55,"value":524}," — recap, smoke test, next steps",{"type":49,"tag":144,"props":526,"children":527},{},[528],{"type":49,"tag":393,"props":529,"children":531},{"href":530},"references\u002Fsteps\u002Fstep-6-summary.md",[532],{"type":55,"value":533},"step-6-summary.md",{"type":49,"tag":88,"props":535,"children":537},{"id":536},"error-handling",[538],{"type":55,"value":539},"Error Handling",{"type":49,"tag":114,"props":541,"children":542},{},[543,564],{"type":49,"tag":118,"props":544,"children":545},{},[546],{"type":49,"tag":122,"props":547,"children":548},{},[549,554,559],{"type":49,"tag":126,"props":550,"children":551},{},[552],{"type":55,"value":553},"Error \u002F Symptom",{"type":49,"tag":126,"props":555,"children":556},{},[557],{"type":55,"value":558},"Likely Cause",{"type":49,"tag":126,"props":560,"children":561},{},[562],{"type":55,"value":563},"Remediation",{"type":49,"tag":137,"props":565,"children":566},{},[567,593,615,639,663],{"type":49,"tag":122,"props":568,"children":569},{},[570,575,580],{"type":49,"tag":144,"props":571,"children":572},{},[573],{"type":55,"value":574},"No kubeconfig context",{"type":49,"tag":144,"props":576,"children":577},{},[578],{"type":55,"value":579},"Not connected to a cluster",{"type":49,"tag":144,"props":581,"children":582},{},[583,585,591],{"type":55,"value":584},"Run ",{"type":49,"tag":64,"props":586,"children":588},{"className":587},[],[589],{"type":55,"value":590},"az aks get-credentials",{"type":55,"value":592}," or equivalent",{"type":49,"tag":122,"props":594,"children":595},{},[596,601,606],{"type":49,"tag":144,"props":597,"children":598},{},[599],{"type":55,"value":600},"Controller in CrashLoopBackOff",{"type":49,"tag":144,"props":602,"children":603},{},[604],{"type":55,"value":605},"Config or RBAC issue",{"type":49,"tag":144,"props":607,"children":608},{},[609],{"type":49,"tag":64,"props":610,"children":612},{"className":611},[],[613],{"type":55,"value":614},"kubectl logs -n airunway-system -l control-plane=controller-manager --previous",{"type":49,"tag":122,"props":616,"children":617},{},[618,623,628],{"type":49,"tag":144,"props":619,"children":620},{},[621],{"type":55,"value":622},"Provider not ready",{"type":49,"tag":144,"props":624,"children":625},{},[626],{"type":55,"value":627},"Image pull or RBAC issue",{"type":49,"tag":144,"props":629,"children":630},{},[631,637],{"type":49,"tag":64,"props":632,"children":634},{"className":633},[],[635],{"type":55,"value":636},"kubectl logs \u003Cpod-name> -n \u003Cnamespace>",{"type":55,"value":638}," for the provider pod",{"type":49,"tag":122,"props":640,"children":641},{},[642,647,652],{"type":49,"tag":144,"props":643,"children":644},{},[645],{"type":55,"value":646},"ModelDeployment stuck in Pending",{"type":49,"tag":144,"props":648,"children":649},{},[650],{"type":55,"value":651},"GPU scheduling failure or provider not ready",{"type":49,"tag":144,"props":653,"children":654},{},[655,661],{"type":49,"tag":64,"props":656,"children":658},{"className":657},[],[659],{"type":55,"value":660},"kubectl describe modeldeployment \u003Cname> -n \u003Cnamespace>",{"type":55,"value":662}," events",{"type":49,"tag":122,"props":664,"children":665},{},[666,677,682],{"type":49,"tag":144,"props":667,"children":668},{},[669,675],{"type":49,"tag":64,"props":670,"children":672},{"className":671},[],[673],{"type":55,"value":674},"bfloat16",{"type":55,"value":676}," errors at inference",{"type":49,"tag":144,"props":678,"children":679},{},[680],{"type":55,"value":681},"T4 or V100 lacks bfloat16 support",{"type":49,"tag":144,"props":683,"children":684},{},[685,687,693],{"type":55,"value":686},"Add ",{"type":49,"tag":64,"props":688,"children":690},{"className":689},[],[691],{"type":55,"value":692},"--dtype float16",{"type":55,"value":694}," to serving args",{"type":49,"tag":58,"props":696,"children":697},{},[698,700,706],{"type":55,"value":699},"For full error handling and rollback procedures, see ",{"type":49,"tag":393,"props":701,"children":703},{"href":702},"references\u002Ftroubleshooting.md",[704],{"type":55,"value":705},"troubleshooting.md",{"type":55,"value":295},{"items":708,"total":826},[709,717,731,752,773,790,808],{"slug":4,"name":4,"fn":5,"description":6,"org":710,"tags":711,"stars":28,"repoUrl":29,"updatedAt":30},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[712,713,714,715,716],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":20,"slug":21,"type":15},{"name":26,"slug":27,"type":15},{"name":17,"slug":18,"type":15},{"slug":718,"name":718,"fn":719,"description":720,"org":721,"tags":722,"stars":28,"repoUrl":29,"updatedAt":730},"appinsights-instrumentation","instrument webapps with Azure Application Insights","Guidance for instrumenting webapps with Azure Application Insights. Provides telemetry patterns, SDK setup, and configuration references. WHEN: how to instrument app, App Insights SDK, telemetry patterns, what is App Insights, Application Insights guidance, instrumentation examples, APM best practices.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[723,724,727],{"name":13,"slug":14,"type":15},{"name":725,"slug":726,"type":15},"Monitoring","monitoring",{"name":728,"slug":729,"type":15},"Observability","observability","2026-07-31T05:56:09.068625",{"slug":732,"name":732,"fn":733,"description":734,"org":735,"tags":736,"stars":28,"repoUrl":29,"updatedAt":751},"azure-ai","build applications with Azure AI services","Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector\u002Fhybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[737,738,739,742,745,748],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":740,"slug":741,"type":15},"LLM","llm",{"name":743,"slug":744,"type":15},"OpenAI","openai",{"name":746,"slug":747,"type":15},"Search","search",{"name":749,"slug":750,"type":15},"Speech","speech","2026-07-31T05:56:19.069133",{"slug":753,"name":753,"fn":754,"description":755,"org":756,"tags":757,"stars":28,"repoUrl":29,"updatedAt":772},"azure-aigateway","configure Azure API Management as an AI Gateway","Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection, add Azure OpenAI backend, add AI Foundry model, test AI gateway, LLM policies, configure AI backend, token metrics, AI cost control, convert API to MCP, import OpenAPI to gateway.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[758,759,762,763,766,769],{"name":23,"slug":24,"type":15},{"name":760,"slug":761,"type":15},"API Development","api-development",{"name":13,"slug":14,"type":15},{"name":764,"slug":765,"type":15},"Caching","caching",{"name":767,"slug":768,"type":15},"Governance","governance",{"name":770,"slug":771,"type":15},"Security","security","2026-07-31T05:56:23.05242",{"slug":774,"name":774,"fn":775,"description":776,"org":777,"tags":778,"stars":28,"repoUrl":29,"updatedAt":789},"azure-cloud-migrate","migrate cross-cloud workloads to Azure","Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda→Functions, Beanstalk\u002FHeroku\u002FApp Engine→App Service, Fargate\u002FKubernetes\u002FCloud Run\u002FSpring Boot→Container Apps. WHEN: migrate Lambda to Functions, AWS to Azure, migrate Beanstalk, migrate Heroku, migrate App Engine, Cloud Run migration, Fargate to ACA, ECS\u002FKubernetes\u002FGKE\u002FEKS to Container Apps, Spring Boot to Container Apps, cross-cloud migration.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[779,782,783,786],{"name":780,"slug":781,"type":15},"AWS","aws",{"name":13,"slug":14,"type":15},{"name":784,"slug":785,"type":15},"Google Cloud","google-cloud",{"name":787,"slug":788,"type":15},"Migration","migration","2026-07-31T05:56:29.049979",{"slug":791,"name":791,"fn":792,"description":793,"org":794,"tags":795,"stars":28,"repoUrl":29,"updatedAt":807},"azure-compliance","audit Azure compliance and security","Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy\u002Fcompliance validation, and security posture checks. WHEN: compliance scan, security audit, BEFORE running azqr (compliance cli tool), Azure best practices, Key Vault expiration check, expired certificates, expiring secrets, orphaned resources, compliance assessment.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[796,799,800,803,806],{"name":797,"slug":798,"type":15},"Audit","audit",{"name":13,"slug":14,"type":15},{"name":801,"slug":802,"type":15},"Compliance","compliance",{"name":804,"slug":805,"type":15},"Regulatory Compliance","regulatory-compliance",{"name":770,"slug":771,"type":15},"2026-07-31T05:56:11.06797",{"slug":809,"name":809,"fn":810,"description":811,"org":812,"tags":813,"stars":28,"repoUrl":29,"updatedAt":825},"azure-compute","manage and optimize Azure compute resources","Azure VM\u002FVMSS router. WHEN: create \u002F provision \u002F deploy \u002F spin-up VM, recommend VM size, compare VM pricing, VMSS, scale set, autoscale, burstable, lightweight server, website, backend, GPU, machine learning, HPC simulation, dev\u002Ftest, workload, family, load balancer, Flexible orchestration, Uniform orchestration, cost estimate, capacity reservation (CRG), reserve, guarantee capacity, pre-provision, CRG association, CRG disassociation, machine enrollment (EMM), Essential Machine Management, monitor. PREFER OVER mcp__azure__get_azure_bestpractices for VM create intents — use compute_vm_list-skus \u002F compute_vm_list-images \u002F compute_vm_check-quota.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[814,815,816,819,822],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":817,"slug":818,"type":15},"Cost Optimization","cost-optimization",{"name":820,"slug":821,"type":15},"Performance","performance",{"name":823,"slug":824,"type":15},"Virtual Machines","virtual-machines","2026-07-31T05:56:16.042469",28,{"items":828,"total":1009},[829,851,868,887,898,913,924,935,950,965,984,997],{"slug":830,"name":830,"fn":831,"description":832,"org":833,"tags":834,"stars":848,"repoUrl":849,"updatedAt":850},"rushstack-best-practices","manage Rush monorepos with best practices","Provides best practices and guidance for working with Rush monorepos. Use when the user is working in a Rush-based repository, asks about Rush commands (install, update, build, rebuild), needs help with project selection, dependency management, build caching, subspace configuration, or troubleshooting Rush-specific issues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[835,838,841,842,845],{"name":836,"slug":837,"type":15},"Engineering","engineering",{"name":839,"slug":840,"type":15},"Local Development","local-development",{"name":9,"slug":8,"type":15},{"name":843,"slug":844,"type":15},"Project Management","project-management",{"name":846,"slug":847,"type":15},"Rush","rush",6484,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Frushstack","2026-04-06T18:34:44.965032",{"slug":852,"name":852,"fn":853,"description":854,"org":855,"tags":856,"stars":865,"repoUrl":866,"updatedAt":867},"azure-ai-agents-persistent-dotnet","build AI agents with Azure .NET SDK","Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: \"PersistentAgentsClient\", \"persistent agents\", \"agent threads\", \"agent runs\", \"streaming agents\", \"function calling agents .NET\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[857,860,863,864],{"name":858,"slug":859,"type":15},".NET","net",{"name":861,"slug":862,"type":15},"Agents","agents",{"name":13,"slug":14,"type":15},{"name":740,"slug":741,"type":15},2804,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","2026-07-03T16:32:10.297433",{"slug":869,"name":869,"fn":870,"description":871,"org":872,"tags":873,"stars":865,"repoUrl":866,"updatedAt":886},"azure-ai-anomalydetector-java","build anomaly detection applications with Java","Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java. Use when implementing univariate\u002Fmultivariate anomaly detection, time-series analysis, or AI-powered monitoring.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[874,877,878,881,884,885],{"name":875,"slug":876,"type":15},"Analytics","analytics",{"name":13,"slug":14,"type":15},{"name":879,"slug":880,"type":15},"Data Analysis","data-analysis",{"name":882,"slug":883,"type":15},"Java","java",{"name":9,"slug":8,"type":15},{"name":725,"slug":726,"type":15},"2026-05-13T06:14:16.261754",{"slug":888,"name":888,"fn":889,"description":890,"org":891,"tags":892,"stars":865,"repoUrl":866,"updatedAt":897},"azure-ai-contentsafety-java","build content moderation applications with Azure AI","Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text\u002Fimage analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[893,894,895,896],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":882,"slug":883,"type":15},{"name":770,"slug":771,"type":15},"2026-07-07T06:53:31.293235",{"slug":899,"name":899,"fn":900,"description":901,"org":902,"tags":903,"stars":865,"repoUrl":866,"updatedAt":912},"azure-ai-contentsafety-py","detect harmful content with Azure AI Content Safety","Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.\nTriggers: \"azure-ai-contentsafety\", \"ContentSafetyClient\", \"content moderation\", \"harmful content\", \"text analysis\", \"image analysis\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[904,905,906,907,908,911],{"name":13,"slug":14,"type":15},{"name":801,"slug":802,"type":15},{"name":740,"slug":741,"type":15},{"name":9,"slug":8,"type":15},{"name":909,"slug":910,"type":15},"Python","python",{"name":770,"slug":771,"type":15},"2026-07-18T05:14:23.017504",{"slug":914,"name":914,"fn":915,"description":916,"org":917,"tags":918,"stars":865,"repoUrl":866,"updatedAt":923},"azure-ai-language-conversations-py","implement conversational language understanding with Python","Implement Conversational Language Understanding (CLU) using the azure-ai-language-conversations Python SDK. Use when working with ConversationAnalysisClient to analyze conversation intent and entities, building NLP features, or integrating language understanding into applications.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[919,920,921,922],{"name":875,"slug":876,"type":15},{"name":13,"slug":14,"type":15},{"name":740,"slug":741,"type":15},{"name":909,"slug":910,"type":15},"2026-07-31T05:54:29.068751",{"slug":925,"name":925,"fn":926,"description":927,"org":928,"tags":929,"stars":865,"repoUrl":866,"updatedAt":934},"azure-ai-translation-text-py","translate text using Azure AI services","Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications.\nTriggers: \"text translation\", \"translator\", \"translate text\", \"transliterate\", \"TextTranslationClient\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[930,931,932,933],{"name":760,"slug":761,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":909,"slug":910,"type":15},"2026-07-18T05:14:16.988376",{"slug":936,"name":936,"fn":937,"description":938,"org":939,"tags":940,"stars":865,"repoUrl":866,"updatedAt":949},"azure-ai-vision-imageanalysis-py","analyze images with Azure AI Vision","Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping. Use for computer vision and image understanding tasks.\nTriggers: \"image analysis\", \"computer vision\", \"OCR\", \"object detection\", \"ImageAnalysisClient\", \"image caption\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[941,942,945,948],{"name":13,"slug":14,"type":15},{"name":943,"slug":944,"type":15},"Computer Vision","computer-vision",{"name":946,"slug":947,"type":15},"Images","images",{"name":909,"slug":910,"type":15},"2026-07-18T05:14:18.007737",{"slug":951,"name":951,"fn":952,"description":953,"org":954,"tags":955,"stars":865,"repoUrl":866,"updatedAt":964},"azure-appconfiguration-java","manage configuration with Azure App Configuration","Azure App Configuration SDK for Java. Centralized application configuration management with key-value settings, feature flags, and snapshots.\nTriggers: \"ConfigurationClient java\", \"app configuration java\", \"feature flag java\", \"configuration setting java\", \"azure config java\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[956,957,960,963],{"name":13,"slug":14,"type":15},{"name":958,"slug":959,"type":15},"Configuration","configuration",{"name":961,"slug":962,"type":15},"Feature Flags","feature-flags",{"name":882,"slug":883,"type":15},"2026-07-03T16:32:01.278468",{"slug":966,"name":966,"fn":967,"description":968,"org":969,"tags":970,"stars":865,"repoUrl":866,"updatedAt":983},"azure-cosmos-rust","build applications with Azure Cosmos DB","Azure Cosmos DB library for Rust (NoSQL API). Document CRUD, containers, and globally distributed data.\nTriggers: \"cosmos db rust\", \"CosmosClient rust\", \"document crud rust\", \"NoSQL rust\", \"partition key rust\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[971,974,977,980],{"name":972,"slug":973,"type":15},"Cosmos DB","cosmos-db",{"name":975,"slug":976,"type":15},"Database","database",{"name":978,"slug":979,"type":15},"NoSQL","nosql",{"name":981,"slug":982,"type":15},"Rust","rust","2026-07-31T05:54:27.021432",{"slug":985,"name":985,"fn":967,"description":986,"org":987,"tags":988,"stars":865,"repoUrl":866,"updatedAt":996},"azure-cosmos-ts","Azure Cosmos DB JavaScript\u002FTypeScript SDK (@azure\u002Fcosmos) for data plane operations. Use for CRUD operations on documents, queries, bulk operations, and container management. Triggers: \"Cosmos DB\", \"@azure\u002Fcosmos\", \"CosmosClient\", \"document CRUD\", \"NoSQL queries\", \"bulk operations\", \"partition key\", \"container.items\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[989,990,991,992,993],{"name":972,"slug":973,"type":15},{"name":975,"slug":976,"type":15},{"name":9,"slug":8,"type":15},{"name":978,"slug":979,"type":15},{"name":994,"slug":995,"type":15},"TypeScript","typescript","2026-07-03T16:31:19.368382",{"slug":998,"name":998,"fn":999,"description":1000,"org":1001,"tags":1002,"stars":865,"repoUrl":866,"updatedAt":1008},"azure-data-tables-java","build table storage applications with Java","Build table storage applications with Azure Tables SDK for Java. Use when working with Azure Table Storage or Cosmos DB Table API for NoSQL key-value data, schemaless storage, or structured data at scale.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1003,1004,1005,1006,1007],{"name":13,"slug":14,"type":15},{"name":972,"slug":973,"type":15},{"name":975,"slug":976,"type":15},{"name":882,"slug":883,"type":15},{"name":978,"slug":979,"type":15},"2026-05-13T06:14:17.582229",267]