[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-microsoft-capacity":3,"mdc--75jp6t-key":37,"related-repo-microsoft-capacity":1398,"related-org-microsoft-capacity":1524},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":25,"repoUrl":26,"updatedAt":27,"license":28,"forks":29,"topics":30,"repo":32,"sourceUrl":35,"mdContent":36},"capacity","discover Azure OpenAI model capacity","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.",{"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],{"name":13,"slug":14,"type":15},"Azure","azure","tag",{"name":17,"slug":18,"type":15},"Deployment","deployment",{"name":20,"slug":21,"type":15},"OpenAI","openai",{"name":23,"slug":24,"type":15},"AI Infrastructure","ai-infrastructure",1324,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills","2026-04-06T18:37:12.394925","MIT",220,[31],"agent-skills",{"repoUrl":26,"stars":25,"forks":29,"topics":33,"description":34},[31],"Official agent plugin providing skills and MCP server configurations for Azure scenarios.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Ftree\u002FHEAD\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcapacity","---\nname: capacity\ndescription: \"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.\"\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n---\n\n# Capacity Discovery\n\nFinds available Azure OpenAI model capacity across all accessible regions and projects. Recommends the best deployment location based on capacity requirements.\n\n## Quick Reference\n\n| Property | Description |\n|----------|-------------|\n| **Purpose** | Find where you can deploy a model with sufficient capacity |\n| **Scope** | All regions and projects the user has access to |\n| **Output** | Ranked table of regions\u002Fprojects with available capacity |\n| **Action** | Read-only analysis — does NOT deploy. Hands off to preset or customize |\n| **Authentication** | Azure CLI (`az login`) |\n\n## When to Use This Skill\n\n- ✅ User asks \"where can I deploy gpt-4o?\"\n- ✅ User specifies a capacity target: \"find a region with 10K TPM for gpt-4o\"\n- ✅ User wants to compare availability: \"which regions have gpt-4o available?\"\n- ✅ User got a quota error and needs to find an alternative location\n- ✅ User asks \"best region and project for deploying model X\"\n\n**After discovery → hand off to [preset](..\u002Fpreset\u002FSKILL.md) or [customize](..\u002Fcustomize\u002FSKILL.md) for actual deployment.**\n\n## Scripts\n\nPre-built scripts handle the complex REST API calls and data processing. Use these instead of constructing commands manually.\n\n| Script | Purpose | Usage |\n|--------|---------|-------|\n| `scripts\u002Fdiscover_and_rank.ps1` | Full discovery: capacity + projects + ranking | Primary script for capacity discovery |\n| `scripts\u002Fdiscover_and_rank.sh` | Same as above (bash) | Primary script for capacity discovery |\n| `scripts\u002Fquery_capacity.ps1` | Raw capacity query (no project matching) | Quick capacity check or version listing |\n| `scripts\u002Fquery_capacity.sh` | Same as above (bash) | Quick capacity check or version listing |\n\n## Workflow\n\n### Phase 1: Validate Prerequisites\n\n```bash\naz account show --query \"{Subscription:name, SubscriptionId:id}\" --output table\n```\n\n### Phase 2: Identify Model and Version\n\nExtract model name from user prompt. If version is unknown, query available versions:\n\n```powershell\n.\\scripts\\query_capacity.ps1 -ModelName \u003Cmodel-name>\n```\n```bash\n.\u002Fscripts\u002Fquery_capacity.sh \u003Cmodel-name>\n```\n\nThis lists available versions. Use the latest version unless user specifies otherwise.\n\n### Phase 3: Run Discovery\n\nRun the full discovery script with model name, version, and minimum capacity target:\n\n```powershell\n.\\scripts\\discover_and_rank.ps1 -ModelName \u003Cmodel-name> -ModelVersion \u003Cversion> -MinCapacity \u003Ctarget>\n```\n```bash\n.\u002Fscripts\u002Fdiscover_and_rank.sh \u003Cmodel-name> \u003Cversion> \u003Cmin-capacity>\n```\n\n> 💡 The script automatically queries capacity across ALL regions, cross-references with the user's existing projects, and outputs a ranked table sorted by: meets target → project count → available capacity.\n\n### Phase 3.5: Validate Subscription Quota\n\nAfter discovery identifies candidate regions, validate that the user's subscription actually has available quota in each region. Model capacity (from Phase 3) shows what the platform can support, but subscription quota limits what this specific user can deploy.\n\n```powershell\n# For each candidate region from discovery results:\n$usageData = az cognitiveservices usage list --location \u003Cregion> --subscription $SUBSCRIPTION_ID -o json 2>$null | ConvertFrom-Json\n\n# Check quota for each SKU the model supports\n# Quota names follow pattern: OpenAI.\u003CSKU>.\u003Cmodel-name>\n$usageEntry = $usageData | Where-Object { $_.name.value -eq \"OpenAI.\u003CSKU>.\u003Cmodel-name>\" }\n\nif ($usageEntry) {\n  $quotaAvailable = $usageEntry.limit - $usageEntry.currentValue\n} else {\n  $quotaAvailable = 0  # No quota allocated\n}\n```\n```bash\n# For each candidate region from discovery results:\nusage_json=$(az cognitiveservices usage list --location \u003Cregion> --subscription \"$SUBSCRIPTION_ID\" -o json 2>\u002Fdev\u002Fnull)\n\n# Extract quota for specific SKU+model\nquota_available=$(echo \"$usage_json\" | jq -r --arg name \"OpenAI.\u003CSKU>.\u003Cmodel-name>\" \\\n  '.[] | select(.name.value == $name) | .limit - .currentValue')\n```\n\n**Annotate discovery results:**\n\nAdd a \"Quota Available\" column to the ranked output from Phase 3:\n\n| Region | Available Capacity | Meets Target | Projects | Quota Available |\n|--------|-------------------|--------------|----------|-----------------|\n| eastus2 | 120K TPM | ✅ | 3 | ✅ 80K |\n| westus3 | 90K TPM | ✅ | 1 | ❌ 0 (at limit) |\n| swedencentral | 100K TPM | ✅ | 0 | ✅ 100K |\n\nRegions\u002FSKUs where `quotaAvailable = 0` should be marked with ❌ in the results. If no region has available quota, hand off to the [quota skill](..\u002F..\u002F..\u002Fquota\u002Fquota.md) for increase requests and troubleshooting.\n\n### Phase 4: Present Results and Hand Off\n\nAfter the script outputs the ranked table (now annotated with quota info), present it to the user and ask:\n\n1. 🚀 **Quick deploy** to top recommendation with defaults → route to [preset](..\u002Fpreset\u002FSKILL.md)\n2. ⚙️ **Custom deploy** with version\u002FSKU\u002Fcapacity\u002FRAI selection → route to [customize](..\u002Fcustomize\u002FSKILL.md)\n3. 📊 **Check another model** or capacity target → re-run Phase 2\n4. ❌ Cancel\n\n### Phase 5: Confirm Project Before Deploying\n\nBefore handing off to preset or customize, **always confirm the target project** with the user. See the [Project Selection](..\u002FSKILL.md#project-selection-all-modes) rules in the parent router.\n\nIf the discovery table shows a sample project for the chosen region, suggest it as the default. Otherwise, query projects in that region and let the user pick.\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|------------|\n| \"No capacity found\" | Model not available or all at quota | Hand off to [quota skill](..\u002F..\u002F..\u002Fquota\u002Fquota.md) for increase requests and troubleshooting |\n| Script auth error | `az login` expired | Re-run `az login` |\n| Empty version list | Model not in region catalog | Try a different region: `.\u002Fscripts\u002Fquery_capacity.sh \u003Cmodel> \"\" eastus` |\n| \"No projects found\" | No AI Services resources | Guide to `project\u002Fcreate` skill or Azure Portal |\n\n## Related Skills\n\n- **[preset](..\u002Fpreset\u002FSKILL.md)** — Quick deployment after capacity discovery\n- **[customize](..\u002Fcustomize\u002FSKILL.md)** — Custom deployment after capacity discovery\n- **[quota](..\u002F..\u002F..\u002Fquota\u002Fquota.md)** — For quota viewing, increase requests, and troubleshooting quota errors, defer to this skill instead of duplicating guidance\n",{"data":38,"body":41},{"name":4,"description":6,"license":28,"metadata":39},{"author":9,"version":40},"1.0.0",{"type":42,"children":43},"root",[44,53,59,66,184,190,220,245,251,256,367,373,380,445,451,456,472,508,513,519,524,538,606,615,621,626,740,963,971,976,1095,1116,1122,1127,1180,1186,1206,1211,1217,1346,1352,1392],{"type":45,"tag":46,"props":47,"children":49},"element","h1",{"id":48},"capacity-discovery",[50],{"type":51,"value":52},"text","Capacity Discovery",{"type":45,"tag":54,"props":55,"children":56},"p",{},[57],{"type":51,"value":58},"Finds available Azure OpenAI model capacity across all accessible regions and projects. Recommends the best deployment location based on capacity requirements.",{"type":45,"tag":60,"props":61,"children":63},"h2",{"id":62},"quick-reference",[64],{"type":51,"value":65},"Quick Reference",{"type":45,"tag":67,"props":68,"children":69},"table",{},[70,89],{"type":45,"tag":71,"props":72,"children":73},"thead",{},[74],{"type":45,"tag":75,"props":76,"children":77},"tr",{},[78,84],{"type":45,"tag":79,"props":80,"children":81},"th",{},[82],{"type":51,"value":83},"Property",{"type":45,"tag":79,"props":85,"children":86},{},[87],{"type":51,"value":88},"Description",{"type":45,"tag":90,"props":91,"children":92},"tbody",{},[93,111,127,143,159],{"type":45,"tag":75,"props":94,"children":95},{},[96,106],{"type":45,"tag":97,"props":98,"children":99},"td",{},[100],{"type":45,"tag":101,"props":102,"children":103},"strong",{},[104],{"type":51,"value":105},"Purpose",{"type":45,"tag":97,"props":107,"children":108},{},[109],{"type":51,"value":110},"Find where you can deploy a model with sufficient capacity",{"type":45,"tag":75,"props":112,"children":113},{},[114,122],{"type":45,"tag":97,"props":115,"children":116},{},[117],{"type":45,"tag":101,"props":118,"children":119},{},[120],{"type":51,"value":121},"Scope",{"type":45,"tag":97,"props":123,"children":124},{},[125],{"type":51,"value":126},"All regions and projects the user has access to",{"type":45,"tag":75,"props":128,"children":129},{},[130,138],{"type":45,"tag":97,"props":131,"children":132},{},[133],{"type":45,"tag":101,"props":134,"children":135},{},[136],{"type":51,"value":137},"Output",{"type":45,"tag":97,"props":139,"children":140},{},[141],{"type":51,"value":142},"Ranked table of regions\u002Fprojects with available capacity",{"type":45,"tag":75,"props":144,"children":145},{},[146,154],{"type":45,"tag":97,"props":147,"children":148},{},[149],{"type":45,"tag":101,"props":150,"children":151},{},[152],{"type":51,"value":153},"Action",{"type":45,"tag":97,"props":155,"children":156},{},[157],{"type":51,"value":158},"Read-only analysis — does NOT deploy. Hands off to preset or customize",{"type":45,"tag":75,"props":160,"children":161},{},[162,170],{"type":45,"tag":97,"props":163,"children":164},{},[165],{"type":45,"tag":101,"props":166,"children":167},{},[168],{"type":51,"value":169},"Authentication",{"type":45,"tag":97,"props":171,"children":172},{},[173,175,182],{"type":51,"value":174},"Azure CLI (",{"type":45,"tag":176,"props":177,"children":179},"code",{"className":178},[],[180],{"type":51,"value":181},"az login",{"type":51,"value":183},")",{"type":45,"tag":60,"props":185,"children":187},{"id":186},"when-to-use-this-skill",[188],{"type":51,"value":189},"When to Use This Skill",{"type":45,"tag":191,"props":192,"children":193},"ul",{},[194,200,205,210,215],{"type":45,"tag":195,"props":196,"children":197},"li",{},[198],{"type":51,"value":199},"✅ User asks \"where can I deploy gpt-4o?\"",{"type":45,"tag":195,"props":201,"children":202},{},[203],{"type":51,"value":204},"✅ User specifies a capacity target: \"find a region with 10K TPM for gpt-4o\"",{"type":45,"tag":195,"props":206,"children":207},{},[208],{"type":51,"value":209},"✅ User wants to compare availability: \"which regions have gpt-4o available?\"",{"type":45,"tag":195,"props":211,"children":212},{},[213],{"type":51,"value":214},"✅ User got a quota error and needs to find an alternative location",{"type":45,"tag":195,"props":216,"children":217},{},[218],{"type":51,"value":219},"✅ User asks \"best region and project for deploying model X\"",{"type":45,"tag":54,"props":221,"children":222},{},[223],{"type":45,"tag":101,"props":224,"children":225},{},[226,228,235,237,243],{"type":51,"value":227},"After discovery → hand off to ",{"type":45,"tag":229,"props":230,"children":232},"a",{"href":231},"..\u002Fpreset\u002FSKILL.md",[233],{"type":51,"value":234},"preset",{"type":51,"value":236}," or ",{"type":45,"tag":229,"props":238,"children":240},{"href":239},"..\u002Fcustomize\u002FSKILL.md",[241],{"type":51,"value":242},"customize",{"type":51,"value":244}," for actual deployment.",{"type":45,"tag":60,"props":246,"children":248},{"id":247},"scripts",[249],{"type":51,"value":250},"Scripts",{"type":45,"tag":54,"props":252,"children":253},{},[254],{"type":51,"value":255},"Pre-built scripts handle the complex REST API calls and data processing. Use these instead of constructing commands manually.",{"type":45,"tag":67,"props":257,"children":258},{},[259,279],{"type":45,"tag":71,"props":260,"children":261},{},[262],{"type":45,"tag":75,"props":263,"children":264},{},[265,270,274],{"type":45,"tag":79,"props":266,"children":267},{},[268],{"type":51,"value":269},"Script",{"type":45,"tag":79,"props":271,"children":272},{},[273],{"type":51,"value":105},{"type":45,"tag":79,"props":275,"children":276},{},[277],{"type":51,"value":278},"Usage",{"type":45,"tag":90,"props":280,"children":281},{},[282,304,325,347],{"type":45,"tag":75,"props":283,"children":284},{},[285,294,299],{"type":45,"tag":97,"props":286,"children":287},{},[288],{"type":45,"tag":176,"props":289,"children":291},{"className":290},[],[292],{"type":51,"value":293},"scripts\u002Fdiscover_and_rank.ps1",{"type":45,"tag":97,"props":295,"children":296},{},[297],{"type":51,"value":298},"Full discovery: capacity + projects + ranking",{"type":45,"tag":97,"props":300,"children":301},{},[302],{"type":51,"value":303},"Primary script for capacity discovery",{"type":45,"tag":75,"props":305,"children":306},{},[307,316,321],{"type":45,"tag":97,"props":308,"children":309},{},[310],{"type":45,"tag":176,"props":311,"children":313},{"className":312},[],[314],{"type":51,"value":315},"scripts\u002Fdiscover_and_rank.sh",{"type":45,"tag":97,"props":317,"children":318},{},[319],{"type":51,"value":320},"Same as above (bash)",{"type":45,"tag":97,"props":322,"children":323},{},[324],{"type":51,"value":303},{"type":45,"tag":75,"props":326,"children":327},{},[328,337,342],{"type":45,"tag":97,"props":329,"children":330},{},[331],{"type":45,"tag":176,"props":332,"children":334},{"className":333},[],[335],{"type":51,"value":336},"scripts\u002Fquery_capacity.ps1",{"type":45,"tag":97,"props":338,"children":339},{},[340],{"type":51,"value":341},"Raw capacity query (no project matching)",{"type":45,"tag":97,"props":343,"children":344},{},[345],{"type":51,"value":346},"Quick capacity check or version listing",{"type":45,"tag":75,"props":348,"children":349},{},[350,359,363],{"type":45,"tag":97,"props":351,"children":352},{},[353],{"type":45,"tag":176,"props":354,"children":356},{"className":355},[],[357],{"type":51,"value":358},"scripts\u002Fquery_capacity.sh",{"type":45,"tag":97,"props":360,"children":361},{},[362],{"type":51,"value":320},{"type":45,"tag":97,"props":364,"children":365},{},[366],{"type":51,"value":346},{"type":45,"tag":60,"props":368,"children":370},{"id":369},"workflow",[371],{"type":51,"value":372},"Workflow",{"type":45,"tag":374,"props":375,"children":377},"h3",{"id":376},"phase-1-validate-prerequisites",[378],{"type":51,"value":379},"Phase 1: Validate Prerequisites",{"type":45,"tag":381,"props":382,"children":387},"pre",{"className":383,"code":384,"language":385,"meta":386,"style":386},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","az account show --query \"{Subscription:name, SubscriptionId:id}\" --output table\n","bash","",[388],{"type":45,"tag":176,"props":389,"children":390},{"__ignoreMap":386},[391],{"type":45,"tag":392,"props":393,"children":396},"span",{"class":394,"line":395},"line",1,[397,403,409,414,419,425,430,435,440],{"type":45,"tag":392,"props":398,"children":400},{"style":399},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[401],{"type":51,"value":402},"az",{"type":45,"tag":392,"props":404,"children":406},{"style":405},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[407],{"type":51,"value":408}," account",{"type":45,"tag":392,"props":410,"children":411},{"style":405},[412],{"type":51,"value":413}," show",{"type":45,"tag":392,"props":415,"children":416},{"style":405},[417],{"type":51,"value":418}," --query",{"type":45,"tag":392,"props":420,"children":422},{"style":421},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[423],{"type":51,"value":424}," \"",{"type":45,"tag":392,"props":426,"children":427},{"style":405},[428],{"type":51,"value":429},"{Subscription:name, SubscriptionId:id}",{"type":45,"tag":392,"props":431,"children":432},{"style":421},[433],{"type":51,"value":434},"\"",{"type":45,"tag":392,"props":436,"children":437},{"style":405},[438],{"type":51,"value":439}," --output",{"type":45,"tag":392,"props":441,"children":442},{"style":405},[443],{"type":51,"value":444}," table\n",{"type":45,"tag":374,"props":446,"children":448},{"id":447},"phase-2-identify-model-and-version",[449],{"type":51,"value":450},"Phase 2: Identify Model and Version",{"type":45,"tag":54,"props":452,"children":453},{},[454],{"type":51,"value":455},"Extract model name from user prompt. If version is unknown, query available versions:",{"type":45,"tag":381,"props":457,"children":461},{"className":458,"code":459,"language":460,"meta":386,"style":386},"language-powershell shiki shiki-themes material-theme-lighter material-theme material-theme-palenight",".\\scripts\\query_capacity.ps1 -ModelName \u003Cmodel-name>\n","powershell",[462],{"type":45,"tag":176,"props":463,"children":464},{"__ignoreMap":386},[465],{"type":45,"tag":392,"props":466,"children":467},{"class":394,"line":395},[468],{"type":45,"tag":392,"props":469,"children":470},{},[471],{"type":51,"value":459},{"type":45,"tag":381,"props":473,"children":475},{"className":383,"code":474,"language":385,"meta":386,"style":386},".\u002Fscripts\u002Fquery_capacity.sh \u003Cmodel-name>\n",[476],{"type":45,"tag":176,"props":477,"children":478},{"__ignoreMap":386},[479],{"type":45,"tag":392,"props":480,"children":481},{"class":394,"line":395},[482,487,492,497,503],{"type":45,"tag":392,"props":483,"children":484},{"style":399},[485],{"type":51,"value":486},".\u002Fscripts\u002Fquery_capacity.sh",{"type":45,"tag":392,"props":488,"children":489},{"style":421},[490],{"type":51,"value":491}," \u003C",{"type":45,"tag":392,"props":493,"children":494},{"style":405},[495],{"type":51,"value":496},"model-nam",{"type":45,"tag":392,"props":498,"children":500},{"style":499},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[501],{"type":51,"value":502},"e",{"type":45,"tag":392,"props":504,"children":505},{"style":421},[506],{"type":51,"value":507},">\n",{"type":45,"tag":54,"props":509,"children":510},{},[511],{"type":51,"value":512},"This lists available versions. Use the latest version unless user specifies otherwise.",{"type":45,"tag":374,"props":514,"children":516},{"id":515},"phase-3-run-discovery",[517],{"type":51,"value":518},"Phase 3: Run Discovery",{"type":45,"tag":54,"props":520,"children":521},{},[522],{"type":51,"value":523},"Run the full discovery script with model name, version, and minimum capacity target:",{"type":45,"tag":381,"props":525,"children":527},{"className":458,"code":526,"language":460,"meta":386,"style":386},".\\scripts\\discover_and_rank.ps1 -ModelName \u003Cmodel-name> -ModelVersion \u003Cversion> -MinCapacity \u003Ctarget>\n",[528],{"type":45,"tag":176,"props":529,"children":530},{"__ignoreMap":386},[531],{"type":45,"tag":392,"props":532,"children":533},{"class":394,"line":395},[534],{"type":45,"tag":392,"props":535,"children":536},{},[537],{"type":51,"value":526},{"type":45,"tag":381,"props":539,"children":541},{"className":383,"code":540,"language":385,"meta":386,"style":386},".\u002Fscripts\u002Fdiscover_and_rank.sh \u003Cmodel-name> \u003Cversion> \u003Cmin-capacity>\n",[542],{"type":45,"tag":176,"props":543,"children":544},{"__ignoreMap":386},[545],{"type":45,"tag":392,"props":546,"children":547},{"class":394,"line":395},[548,553,557,561,565,570,574,579,584,588,592,597,602],{"type":45,"tag":392,"props":549,"children":550},{"style":399},[551],{"type":51,"value":552},".\u002Fscripts\u002Fdiscover_and_rank.sh",{"type":45,"tag":392,"props":554,"children":555},{"style":421},[556],{"type":51,"value":491},{"type":45,"tag":392,"props":558,"children":559},{"style":405},[560],{"type":51,"value":496},{"type":45,"tag":392,"props":562,"children":563},{"style":499},[564],{"type":51,"value":502},{"type":45,"tag":392,"props":566,"children":567},{"style":421},[568],{"type":51,"value":569},">",{"type":45,"tag":392,"props":571,"children":572},{"style":421},[573],{"type":51,"value":491},{"type":45,"tag":392,"props":575,"children":576},{"style":405},[577],{"type":51,"value":578},"versio",{"type":45,"tag":392,"props":580,"children":581},{"style":499},[582],{"type":51,"value":583},"n",{"type":45,"tag":392,"props":585,"children":586},{"style":421},[587],{"type":51,"value":569},{"type":45,"tag":392,"props":589,"children":590},{"style":421},[591],{"type":51,"value":491},{"type":45,"tag":392,"props":593,"children":594},{"style":405},[595],{"type":51,"value":596},"min-capacit",{"type":45,"tag":392,"props":598,"children":599},{"style":499},[600],{"type":51,"value":601},"y",{"type":45,"tag":392,"props":603,"children":604},{"style":421},[605],{"type":51,"value":507},{"type":45,"tag":607,"props":608,"children":609},"blockquote",{},[610],{"type":45,"tag":54,"props":611,"children":612},{},[613],{"type":51,"value":614},"💡 The script automatically queries capacity across ALL regions, cross-references with the user's existing projects, and outputs a ranked table sorted by: meets target → project count → available capacity.",{"type":45,"tag":374,"props":616,"children":618},{"id":617},"phase-35-validate-subscription-quota",[619],{"type":51,"value":620},"Phase 3.5: Validate Subscription Quota",{"type":45,"tag":54,"props":622,"children":623},{},[624],{"type":51,"value":625},"After discovery identifies candidate regions, validate that the user's subscription actually has available quota in each region. Model capacity (from Phase 3) shows what the platform can support, but subscription quota limits what this specific user can deploy.",{"type":45,"tag":381,"props":627,"children":629},{"className":458,"code":628,"language":460,"meta":386,"style":386},"# For each candidate region from discovery results:\n$usageData = az cognitiveservices usage list --location \u003Cregion> --subscription $SUBSCRIPTION_ID -o json 2>$null | ConvertFrom-Json\n\n# Check quota for each SKU the model supports\n# Quota names follow pattern: OpenAI.\u003CSKU>.\u003Cmodel-name>\n$usageEntry = $usageData | Where-Object { $_.name.value -eq \"OpenAI.\u003CSKU>.\u003Cmodel-name>\" }\n\nif ($usageEntry) {\n  $quotaAvailable = $usageEntry.limit - $usageEntry.currentValue\n} else {\n  $quotaAvailable = 0  # No quota allocated\n}\n",[630],{"type":45,"tag":176,"props":631,"children":632},{"__ignoreMap":386},[633,641,650,660,669,678,687,695,704,713,722,731],{"type":45,"tag":392,"props":634,"children":635},{"class":394,"line":395},[636],{"type":45,"tag":392,"props":637,"children":638},{},[639],{"type":51,"value":640},"# For each candidate region from discovery results:\n",{"type":45,"tag":392,"props":642,"children":644},{"class":394,"line":643},2,[645],{"type":45,"tag":392,"props":646,"children":647},{},[648],{"type":51,"value":649},"$usageData = az cognitiveservices usage list --location \u003Cregion> --subscription $SUBSCRIPTION_ID -o json 2>$null | ConvertFrom-Json\n",{"type":45,"tag":392,"props":651,"children":653},{"class":394,"line":652},3,[654],{"type":45,"tag":392,"props":655,"children":657},{"emptyLinePlaceholder":656},true,[658],{"type":51,"value":659},"\n",{"type":45,"tag":392,"props":661,"children":663},{"class":394,"line":662},4,[664],{"type":45,"tag":392,"props":665,"children":666},{},[667],{"type":51,"value":668},"# Check quota for each SKU the model supports\n",{"type":45,"tag":392,"props":670,"children":672},{"class":394,"line":671},5,[673],{"type":45,"tag":392,"props":674,"children":675},{},[676],{"type":51,"value":677},"# Quota names follow pattern: OpenAI.\u003CSKU>.\u003Cmodel-name>\n",{"type":45,"tag":392,"props":679,"children":681},{"class":394,"line":680},6,[682],{"type":45,"tag":392,"props":683,"children":684},{},[685],{"type":51,"value":686},"$usageEntry = $usageData | Where-Object { $_.name.value -eq \"OpenAI.\u003CSKU>.\u003Cmodel-name>\" }\n",{"type":45,"tag":392,"props":688,"children":690},{"class":394,"line":689},7,[691],{"type":45,"tag":392,"props":692,"children":693},{"emptyLinePlaceholder":656},[694],{"type":51,"value":659},{"type":45,"tag":392,"props":696,"children":698},{"class":394,"line":697},8,[699],{"type":45,"tag":392,"props":700,"children":701},{},[702],{"type":51,"value":703},"if ($usageEntry) {\n",{"type":45,"tag":392,"props":705,"children":707},{"class":394,"line":706},9,[708],{"type":45,"tag":392,"props":709,"children":710},{},[711],{"type":51,"value":712},"  $quotaAvailable = $usageEntry.limit - $usageEntry.currentValue\n",{"type":45,"tag":392,"props":714,"children":716},{"class":394,"line":715},10,[717],{"type":45,"tag":392,"props":718,"children":719},{},[720],{"type":51,"value":721},"} else {\n",{"type":45,"tag":392,"props":723,"children":725},{"class":394,"line":724},11,[726],{"type":45,"tag":392,"props":727,"children":728},{},[729],{"type":51,"value":730},"  $quotaAvailable = 0  # No quota allocated\n",{"type":45,"tag":392,"props":732,"children":734},{"class":394,"line":733},12,[735],{"type":45,"tag":392,"props":736,"children":737},{},[738],{"type":51,"value":739},"}\n",{"type":45,"tag":381,"props":741,"children":743},{"className":383,"code":742,"language":385,"meta":386,"style":386},"# For each candidate region from discovery results:\nusage_json=$(az cognitiveservices usage list --location \u003Cregion> --subscription \"$SUBSCRIPTION_ID\" -o json 2>\u002Fdev\u002Fnull)\n\n# Extract quota for specific SKU+model\nquota_available=$(echo \"$usage_json\" | jq -r --arg name \"OpenAI.\u003CSKU>.\u003Cmodel-name>\" \\\n  '.[] | select(.name.value == $name) | .limit - .currentValue')\n",[744],{"type":45,"tag":176,"props":745,"children":746},{"__ignoreMap":386},[747,755,852,859,867,941],{"type":45,"tag":392,"props":748,"children":749},{"class":394,"line":395},[750],{"type":45,"tag":392,"props":751,"children":753},{"style":752},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[754],{"type":51,"value":640},{"type":45,"tag":392,"props":756,"children":757},{"class":394,"line":643},[758,763,768,772,777,782,787,792,796,801,805,809,814,818,823,827,832,837,842,847],{"type":45,"tag":392,"props":759,"children":760},{"style":499},[761],{"type":51,"value":762},"usage_json",{"type":45,"tag":392,"props":764,"children":765},{"style":421},[766],{"type":51,"value":767},"=$(",{"type":45,"tag":392,"props":769,"children":770},{"style":399},[771],{"type":51,"value":402},{"type":45,"tag":392,"props":773,"children":774},{"style":405},[775],{"type":51,"value":776}," cognitiveservices",{"type":45,"tag":392,"props":778,"children":779},{"style":405},[780],{"type":51,"value":781}," usage",{"type":45,"tag":392,"props":783,"children":784},{"style":405},[785],{"type":51,"value":786}," list",{"type":45,"tag":392,"props":788,"children":789},{"style":405},[790],{"type":51,"value":791}," --location",{"type":45,"tag":392,"props":793,"children":794},{"style":421},[795],{"type":51,"value":491},{"type":45,"tag":392,"props":797,"children":798},{"style":405},[799],{"type":51,"value":800},"regio",{"type":45,"tag":392,"props":802,"children":803},{"style":499},[804],{"type":51,"value":583},{"type":45,"tag":392,"props":806,"children":807},{"style":421},[808],{"type":51,"value":569},{"type":45,"tag":392,"props":810,"children":811},{"style":405},[812],{"type":51,"value":813}," --subscription",{"type":45,"tag":392,"props":815,"children":816},{"style":421},[817],{"type":51,"value":424},{"type":45,"tag":392,"props":819,"children":820},{"style":499},[821],{"type":51,"value":822},"$SUBSCRIPTION_ID",{"type":45,"tag":392,"props":824,"children":825},{"style":421},[826],{"type":51,"value":434},{"type":45,"tag":392,"props":828,"children":829},{"style":405},[830],{"type":51,"value":831}," -o",{"type":45,"tag":392,"props":833,"children":834},{"style":405},[835],{"type":51,"value":836}," json",{"type":45,"tag":392,"props":838,"children":839},{"style":421},[840],{"type":51,"value":841}," 2>",{"type":45,"tag":392,"props":843,"children":844},{"style":405},[845],{"type":51,"value":846},"\u002Fdev\u002Fnull",{"type":45,"tag":392,"props":848,"children":849},{"style":421},[850],{"type":51,"value":851},")\n",{"type":45,"tag":392,"props":853,"children":854},{"class":394,"line":652},[855],{"type":45,"tag":392,"props":856,"children":857},{"emptyLinePlaceholder":656},[858],{"type":51,"value":659},{"type":45,"tag":392,"props":860,"children":861},{"class":394,"line":662},[862],{"type":45,"tag":392,"props":863,"children":864},{"style":752},[865],{"type":51,"value":866},"# Extract quota for specific SKU+model\n",{"type":45,"tag":392,"props":868,"children":869},{"class":394,"line":671},[870,875,879,885,889,894,898,903,908,913,918,923,927,932,936],{"type":45,"tag":392,"props":871,"children":872},{"style":499},[873],{"type":51,"value":874},"quota_available",{"type":45,"tag":392,"props":876,"children":877},{"style":421},[878],{"type":51,"value":767},{"type":45,"tag":392,"props":880,"children":882},{"style":881},"--shiki-light:#6182B8;--shiki-default:#82AAFF;--shiki-dark:#82AAFF",[883],{"type":51,"value":884},"echo",{"type":45,"tag":392,"props":886,"children":887},{"style":421},[888],{"type":51,"value":424},{"type":45,"tag":392,"props":890,"children":891},{"style":499},[892],{"type":51,"value":893},"$usage_json",{"type":45,"tag":392,"props":895,"children":896},{"style":421},[897],{"type":51,"value":434},{"type":45,"tag":392,"props":899,"children":900},{"style":421},[901],{"type":51,"value":902}," |",{"type":45,"tag":392,"props":904,"children":905},{"style":399},[906],{"type":51,"value":907}," jq",{"type":45,"tag":392,"props":909,"children":910},{"style":405},[911],{"type":51,"value":912}," -r",{"type":45,"tag":392,"props":914,"children":915},{"style":405},[916],{"type":51,"value":917}," --arg",{"type":45,"tag":392,"props":919,"children":920},{"style":405},[921],{"type":51,"value":922}," name",{"type":45,"tag":392,"props":924,"children":925},{"style":421},[926],{"type":51,"value":424},{"type":45,"tag":392,"props":928,"children":929},{"style":405},[930],{"type":51,"value":931},"OpenAI.\u003CSKU>.\u003Cmodel-name>",{"type":45,"tag":392,"props":933,"children":934},{"style":421},[935],{"type":51,"value":434},{"type":45,"tag":392,"props":937,"children":938},{"style":499},[939],{"type":51,"value":940}," \\\n",{"type":45,"tag":392,"props":942,"children":943},{"class":394,"line":680},[944,949,954,959],{"type":45,"tag":392,"props":945,"children":946},{"style":421},[947],{"type":51,"value":948},"  '",{"type":45,"tag":392,"props":950,"children":951},{"style":405},[952],{"type":51,"value":953},".[] | select(.name.value == $name) | .limit - .currentValue",{"type":45,"tag":392,"props":955,"children":956},{"style":421},[957],{"type":51,"value":958},"'",{"type":45,"tag":392,"props":960,"children":961},{"style":421},[962],{"type":51,"value":851},{"type":45,"tag":54,"props":964,"children":965},{},[966],{"type":45,"tag":101,"props":967,"children":968},{},[969],{"type":51,"value":970},"Annotate discovery results:",{"type":45,"tag":54,"props":972,"children":973},{},[974],{"type":51,"value":975},"Add a \"Quota Available\" column to the ranked output from Phase 3:",{"type":45,"tag":67,"props":977,"children":978},{},[979,1010],{"type":45,"tag":71,"props":980,"children":981},{},[982],{"type":45,"tag":75,"props":983,"children":984},{},[985,990,995,1000,1005],{"type":45,"tag":79,"props":986,"children":987},{},[988],{"type":51,"value":989},"Region",{"type":45,"tag":79,"props":991,"children":992},{},[993],{"type":51,"value":994},"Available Capacity",{"type":45,"tag":79,"props":996,"children":997},{},[998],{"type":51,"value":999},"Meets Target",{"type":45,"tag":79,"props":1001,"children":1002},{},[1003],{"type":51,"value":1004},"Projects",{"type":45,"tag":79,"props":1006,"children":1007},{},[1008],{"type":51,"value":1009},"Quota Available",{"type":45,"tag":90,"props":1011,"children":1012},{},[1013,1041,1068],{"type":45,"tag":75,"props":1014,"children":1015},{},[1016,1021,1026,1031,1036],{"type":45,"tag":97,"props":1017,"children":1018},{},[1019],{"type":51,"value":1020},"eastus2",{"type":45,"tag":97,"props":1022,"children":1023},{},[1024],{"type":51,"value":1025},"120K TPM",{"type":45,"tag":97,"props":1027,"children":1028},{},[1029],{"type":51,"value":1030},"✅",{"type":45,"tag":97,"props":1032,"children":1033},{},[1034],{"type":51,"value":1035},"3",{"type":45,"tag":97,"props":1037,"children":1038},{},[1039],{"type":51,"value":1040},"✅ 80K",{"type":45,"tag":75,"props":1042,"children":1043},{},[1044,1049,1054,1058,1063],{"type":45,"tag":97,"props":1045,"children":1046},{},[1047],{"type":51,"value":1048},"westus3",{"type":45,"tag":97,"props":1050,"children":1051},{},[1052],{"type":51,"value":1053},"90K TPM",{"type":45,"tag":97,"props":1055,"children":1056},{},[1057],{"type":51,"value":1030},{"type":45,"tag":97,"props":1059,"children":1060},{},[1061],{"type":51,"value":1062},"1",{"type":45,"tag":97,"props":1064,"children":1065},{},[1066],{"type":51,"value":1067},"❌ 0 (at limit)",{"type":45,"tag":75,"props":1069,"children":1070},{},[1071,1076,1081,1085,1090],{"type":45,"tag":97,"props":1072,"children":1073},{},[1074],{"type":51,"value":1075},"swedencentral",{"type":45,"tag":97,"props":1077,"children":1078},{},[1079],{"type":51,"value":1080},"100K TPM",{"type":45,"tag":97,"props":1082,"children":1083},{},[1084],{"type":51,"value":1030},{"type":45,"tag":97,"props":1086,"children":1087},{},[1088],{"type":51,"value":1089},"0",{"type":45,"tag":97,"props":1091,"children":1092},{},[1093],{"type":51,"value":1094},"✅ 100K",{"type":45,"tag":54,"props":1096,"children":1097},{},[1098,1100,1106,1108,1114],{"type":51,"value":1099},"Regions\u002FSKUs where ",{"type":45,"tag":176,"props":1101,"children":1103},{"className":1102},[],[1104],{"type":51,"value":1105},"quotaAvailable = 0",{"type":51,"value":1107}," should be marked with ❌ in the results. If no region has available quota, hand off to the ",{"type":45,"tag":229,"props":1109,"children":1111},{"href":1110},"..\u002F..\u002F..\u002Fquota\u002Fquota.md",[1112],{"type":51,"value":1113},"quota skill",{"type":51,"value":1115}," for increase requests and troubleshooting.",{"type":45,"tag":374,"props":1117,"children":1119},{"id":1118},"phase-4-present-results-and-hand-off",[1120],{"type":51,"value":1121},"Phase 4: Present Results and Hand Off",{"type":45,"tag":54,"props":1123,"children":1124},{},[1125],{"type":51,"value":1126},"After the script outputs the ranked table (now annotated with quota info), present it to the user and ask:",{"type":45,"tag":1128,"props":1129,"children":1130},"ol",{},[1131,1147,1163,1175],{"type":45,"tag":195,"props":1132,"children":1133},{},[1134,1136,1141,1143],{"type":51,"value":1135},"🚀 ",{"type":45,"tag":101,"props":1137,"children":1138},{},[1139],{"type":51,"value":1140},"Quick deploy",{"type":51,"value":1142}," to top recommendation with defaults → route to ",{"type":45,"tag":229,"props":1144,"children":1145},{"href":231},[1146],{"type":51,"value":234},{"type":45,"tag":195,"props":1148,"children":1149},{},[1150,1152,1157,1159],{"type":51,"value":1151},"⚙️ ",{"type":45,"tag":101,"props":1153,"children":1154},{},[1155],{"type":51,"value":1156},"Custom deploy",{"type":51,"value":1158}," with version\u002FSKU\u002Fcapacity\u002FRAI selection → route to ",{"type":45,"tag":229,"props":1160,"children":1161},{"href":239},[1162],{"type":51,"value":242},{"type":45,"tag":195,"props":1164,"children":1165},{},[1166,1168,1173],{"type":51,"value":1167},"📊 ",{"type":45,"tag":101,"props":1169,"children":1170},{},[1171],{"type":51,"value":1172},"Check another model",{"type":51,"value":1174}," or capacity target → re-run Phase 2",{"type":45,"tag":195,"props":1176,"children":1177},{},[1178],{"type":51,"value":1179},"❌ Cancel",{"type":45,"tag":374,"props":1181,"children":1183},{"id":1182},"phase-5-confirm-project-before-deploying",[1184],{"type":51,"value":1185},"Phase 5: Confirm Project Before Deploying",{"type":45,"tag":54,"props":1187,"children":1188},{},[1189,1191,1196,1198,1204],{"type":51,"value":1190},"Before handing off to preset or customize, ",{"type":45,"tag":101,"props":1192,"children":1193},{},[1194],{"type":51,"value":1195},"always confirm the target project",{"type":51,"value":1197}," with the user. See the ",{"type":45,"tag":229,"props":1199,"children":1201},{"href":1200},"..\u002FSKILL.md#project-selection-all-modes",[1202],{"type":51,"value":1203},"Project Selection",{"type":51,"value":1205}," rules in the parent router.",{"type":45,"tag":54,"props":1207,"children":1208},{},[1209],{"type":51,"value":1210},"If the discovery table shows a sample project for the chosen region, suggest it as the default. Otherwise, query projects in that region and let the user pick.",{"type":45,"tag":60,"props":1212,"children":1214},{"id":1213},"error-handling",[1215],{"type":51,"value":1216},"Error Handling",{"type":45,"tag":67,"props":1218,"children":1219},{},[1220,1241],{"type":45,"tag":71,"props":1221,"children":1222},{},[1223],{"type":45,"tag":75,"props":1224,"children":1225},{},[1226,1231,1236],{"type":45,"tag":79,"props":1227,"children":1228},{},[1229],{"type":51,"value":1230},"Error",{"type":45,"tag":79,"props":1232,"children":1233},{},[1234],{"type":51,"value":1235},"Cause",{"type":45,"tag":79,"props":1237,"children":1238},{},[1239],{"type":51,"value":1240},"Resolution",{"type":45,"tag":90,"props":1242,"children":1243},{},[1244,1268,1296,1320],{"type":45,"tag":75,"props":1245,"children":1246},{},[1247,1252,1257],{"type":45,"tag":97,"props":1248,"children":1249},{},[1250],{"type":51,"value":1251},"\"No capacity found\"",{"type":45,"tag":97,"props":1253,"children":1254},{},[1255],{"type":51,"value":1256},"Model not available or all at quota",{"type":45,"tag":97,"props":1258,"children":1259},{},[1260,1262,1266],{"type":51,"value":1261},"Hand off to ",{"type":45,"tag":229,"props":1263,"children":1264},{"href":1110},[1265],{"type":51,"value":1113},{"type":51,"value":1267}," for increase requests and troubleshooting",{"type":45,"tag":75,"props":1269,"children":1270},{},[1271,1276,1286],{"type":45,"tag":97,"props":1272,"children":1273},{},[1274],{"type":51,"value":1275},"Script auth error",{"type":45,"tag":97,"props":1277,"children":1278},{},[1279,1284],{"type":45,"tag":176,"props":1280,"children":1282},{"className":1281},[],[1283],{"type":51,"value":181},{"type":51,"value":1285}," expired",{"type":45,"tag":97,"props":1287,"children":1288},{},[1289,1291],{"type":51,"value":1290},"Re-run ",{"type":45,"tag":176,"props":1292,"children":1294},{"className":1293},[],[1295],{"type":51,"value":181},{"type":45,"tag":75,"props":1297,"children":1298},{},[1299,1304,1309],{"type":45,"tag":97,"props":1300,"children":1301},{},[1302],{"type":51,"value":1303},"Empty version list",{"type":45,"tag":97,"props":1305,"children":1306},{},[1307],{"type":51,"value":1308},"Model not in region catalog",{"type":45,"tag":97,"props":1310,"children":1311},{},[1312,1314],{"type":51,"value":1313},"Try a different region: ",{"type":45,"tag":176,"props":1315,"children":1317},{"className":1316},[],[1318],{"type":51,"value":1319},".\u002Fscripts\u002Fquery_capacity.sh \u003Cmodel> \"\" eastus",{"type":45,"tag":75,"props":1321,"children":1322},{},[1323,1328,1333],{"type":45,"tag":97,"props":1324,"children":1325},{},[1326],{"type":51,"value":1327},"\"No projects found\"",{"type":45,"tag":97,"props":1329,"children":1330},{},[1331],{"type":51,"value":1332},"No AI Services resources",{"type":45,"tag":97,"props":1334,"children":1335},{},[1336,1338,1344],{"type":51,"value":1337},"Guide to ",{"type":45,"tag":176,"props":1339,"children":1341},{"className":1340},[],[1342],{"type":51,"value":1343},"project\u002Fcreate",{"type":51,"value":1345}," skill or Azure Portal",{"type":45,"tag":60,"props":1347,"children":1349},{"id":1348},"related-skills",[1350],{"type":51,"value":1351},"Related Skills",{"type":45,"tag":191,"props":1353,"children":1354},{},[1355,1367,1379],{"type":45,"tag":195,"props":1356,"children":1357},{},[1358,1365],{"type":45,"tag":101,"props":1359,"children":1360},{},[1361],{"type":45,"tag":229,"props":1362,"children":1363},{"href":231},[1364],{"type":51,"value":234},{"type":51,"value":1366}," — Quick deployment after capacity discovery",{"type":45,"tag":195,"props":1368,"children":1369},{},[1370,1377],{"type":45,"tag":101,"props":1371,"children":1372},{},[1373],{"type":45,"tag":229,"props":1374,"children":1375},{"href":239},[1376],{"type":51,"value":242},{"type":51,"value":1378}," — Custom deployment after capacity discovery",{"type":45,"tag":195,"props":1380,"children":1381},{},[1382,1390],{"type":45,"tag":101,"props":1383,"children":1384},{},[1385],{"type":45,"tag":229,"props":1386,"children":1387},{"href":1110},[1388],{"type":51,"value":1389},"quota",{"type":51,"value":1391}," — For quota viewing, increase requests, and troubleshooting quota errors, defer to this skill instead of duplicating guidance",{"type":45,"tag":1393,"props":1394,"children":1395},"style",{},[1396],{"type":51,"value":1397},"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":1399,"total":1523},[1400,1416,1430,1449,1470,1487,1505],{"slug":1401,"name":1401,"fn":1402,"description":1403,"org":1404,"tags":1405,"stars":25,"repoUrl":26,"updatedAt":1415},"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},[1406,1407,1408,1409,1412],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"name":1410,"slug":1411,"type":15},"Kubernetes","kubernetes",{"name":1413,"slug":1414,"type":15},"Runway","runway","2026-07-31T05:56:13.054971",{"slug":1417,"name":1417,"fn":1418,"description":1419,"org":1420,"tags":1421,"stars":25,"repoUrl":26,"updatedAt":1429},"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},[1422,1423,1426],{"name":13,"slug":14,"type":15},{"name":1424,"slug":1425,"type":15},"Monitoring","monitoring",{"name":1427,"slug":1428,"type":15},"Observability","observability","2026-07-31T05:56:09.068625",{"slug":1431,"name":1431,"fn":1432,"description":1433,"org":1434,"tags":1435,"stars":25,"repoUrl":26,"updatedAt":1448},"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},[1436,1437,1438,1441,1442,1445],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":1439,"slug":1440,"type":15},"LLM","llm",{"name":20,"slug":21,"type":15},{"name":1443,"slug":1444,"type":15},"Search","search",{"name":1446,"slug":1447,"type":15},"Speech","speech","2026-07-31T05:56:19.069133",{"slug":1450,"name":1450,"fn":1451,"description":1452,"org":1453,"tags":1454,"stars":25,"repoUrl":26,"updatedAt":1469},"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},[1455,1456,1459,1460,1463,1466],{"name":23,"slug":24,"type":15},{"name":1457,"slug":1458,"type":15},"API Development","api-development",{"name":13,"slug":14,"type":15},{"name":1461,"slug":1462,"type":15},"Caching","caching",{"name":1464,"slug":1465,"type":15},"Governance","governance",{"name":1467,"slug":1468,"type":15},"Security","security","2026-07-31T05:56:23.05242",{"slug":1471,"name":1471,"fn":1472,"description":1473,"org":1474,"tags":1475,"stars":25,"repoUrl":26,"updatedAt":1486},"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},[1476,1479,1480,1483],{"name":1477,"slug":1478,"type":15},"AWS","aws",{"name":13,"slug":14,"type":15},{"name":1481,"slug":1482,"type":15},"Google Cloud","google-cloud",{"name":1484,"slug":1485,"type":15},"Migration","migration","2026-07-31T05:56:29.049979",{"slug":1488,"name":1488,"fn":1489,"description":1490,"org":1491,"tags":1492,"stars":25,"repoUrl":26,"updatedAt":1504},"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},[1493,1496,1497,1500,1503],{"name":1494,"slug":1495,"type":15},"Audit","audit",{"name":13,"slug":14,"type":15},{"name":1498,"slug":1499,"type":15},"Compliance","compliance",{"name":1501,"slug":1502,"type":15},"Regulatory Compliance","regulatory-compliance",{"name":1467,"slug":1468,"type":15},"2026-07-31T05:56:11.06797",{"slug":1506,"name":1506,"fn":1507,"description":1508,"org":1509,"tags":1510,"stars":25,"repoUrl":26,"updatedAt":1522},"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},[1511,1512,1513,1516,1519],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":1514,"slug":1515,"type":15},"Cost Optimization","cost-optimization",{"name":1517,"slug":1518,"type":15},"Performance","performance",{"name":1520,"slug":1521,"type":15},"Virtual Machines","virtual-machines","2026-07-31T05:56:16.042469",28,{"items":1525,"total":1706},[1526,1548,1565,1584,1595,1610,1621,1632,1647,1662,1681,1694],{"slug":1527,"name":1527,"fn":1528,"description":1529,"org":1530,"tags":1531,"stars":1545,"repoUrl":1546,"updatedAt":1547},"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},[1532,1535,1538,1539,1542],{"name":1533,"slug":1534,"type":15},"Engineering","engineering",{"name":1536,"slug":1537,"type":15},"Local Development","local-development",{"name":9,"slug":8,"type":15},{"name":1540,"slug":1541,"type":15},"Project Management","project-management",{"name":1543,"slug":1544,"type":15},"Rush","rush",6484,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Frushstack","2026-04-06T18:34:44.965032",{"slug":1549,"name":1549,"fn":1550,"description":1551,"org":1552,"tags":1553,"stars":1562,"repoUrl":1563,"updatedAt":1564},"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},[1554,1557,1560,1561],{"name":1555,"slug":1556,"type":15},".NET","net",{"name":1558,"slug":1559,"type":15},"Agents","agents",{"name":13,"slug":14,"type":15},{"name":1439,"slug":1440,"type":15},2804,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","2026-07-03T16:32:10.297433",{"slug":1566,"name":1566,"fn":1567,"description":1568,"org":1569,"tags":1570,"stars":1562,"repoUrl":1563,"updatedAt":1583},"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},[1571,1574,1575,1578,1581,1582],{"name":1572,"slug":1573,"type":15},"Analytics","analytics",{"name":13,"slug":14,"type":15},{"name":1576,"slug":1577,"type":15},"Data Analysis","data-analysis",{"name":1579,"slug":1580,"type":15},"Java","java",{"name":9,"slug":8,"type":15},{"name":1424,"slug":1425,"type":15},"2026-05-13T06:14:16.261754",{"slug":1585,"name":1585,"fn":1586,"description":1587,"org":1588,"tags":1589,"stars":1562,"repoUrl":1563,"updatedAt":1594},"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},[1590,1591,1592,1593],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":1579,"slug":1580,"type":15},{"name":1467,"slug":1468,"type":15},"2026-07-07T06:53:31.293235",{"slug":1596,"name":1596,"fn":1597,"description":1598,"org":1599,"tags":1600,"stars":1562,"repoUrl":1563,"updatedAt":1609},"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},[1601,1602,1603,1604,1605,1608],{"name":13,"slug":14,"type":15},{"name":1498,"slug":1499,"type":15},{"name":1439,"slug":1440,"type":15},{"name":9,"slug":8,"type":15},{"name":1606,"slug":1607,"type":15},"Python","python",{"name":1467,"slug":1468,"type":15},"2026-07-18T05:14:23.017504",{"slug":1611,"name":1611,"fn":1612,"description":1613,"org":1614,"tags":1615,"stars":1562,"repoUrl":1563,"updatedAt":1620},"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},[1616,1617,1618,1619],{"name":1572,"slug":1573,"type":15},{"name":13,"slug":14,"type":15},{"name":1439,"slug":1440,"type":15},{"name":1606,"slug":1607,"type":15},"2026-07-31T05:54:29.068751",{"slug":1622,"name":1622,"fn":1623,"description":1624,"org":1625,"tags":1626,"stars":1562,"repoUrl":1563,"updatedAt":1631},"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},[1627,1628,1629,1630],{"name":1457,"slug":1458,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":1606,"slug":1607,"type":15},"2026-07-18T05:14:16.988376",{"slug":1633,"name":1633,"fn":1634,"description":1635,"org":1636,"tags":1637,"stars":1562,"repoUrl":1563,"updatedAt":1646},"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},[1638,1639,1642,1645],{"name":13,"slug":14,"type":15},{"name":1640,"slug":1641,"type":15},"Computer Vision","computer-vision",{"name":1643,"slug":1644,"type":15},"Images","images",{"name":1606,"slug":1607,"type":15},"2026-07-18T05:14:18.007737",{"slug":1648,"name":1648,"fn":1649,"description":1650,"org":1651,"tags":1652,"stars":1562,"repoUrl":1563,"updatedAt":1661},"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},[1653,1654,1657,1660],{"name":13,"slug":14,"type":15},{"name":1655,"slug":1656,"type":15},"Configuration","configuration",{"name":1658,"slug":1659,"type":15},"Feature Flags","feature-flags",{"name":1579,"slug":1580,"type":15},"2026-07-03T16:32:01.278468",{"slug":1663,"name":1663,"fn":1664,"description":1665,"org":1666,"tags":1667,"stars":1562,"repoUrl":1563,"updatedAt":1680},"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},[1668,1671,1674,1677],{"name":1669,"slug":1670,"type":15},"Cosmos DB","cosmos-db",{"name":1672,"slug":1673,"type":15},"Database","database",{"name":1675,"slug":1676,"type":15},"NoSQL","nosql",{"name":1678,"slug":1679,"type":15},"Rust","rust","2026-07-31T05:54:27.021432",{"slug":1682,"name":1682,"fn":1664,"description":1683,"org":1684,"tags":1685,"stars":1562,"repoUrl":1563,"updatedAt":1693},"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},[1686,1687,1688,1689,1690],{"name":1669,"slug":1670,"type":15},{"name":1672,"slug":1673,"type":15},{"name":9,"slug":8,"type":15},{"name":1675,"slug":1676,"type":15},{"name":1691,"slug":1692,"type":15},"TypeScript","typescript","2026-07-03T16:31:19.368382",{"slug":1695,"name":1695,"fn":1696,"description":1697,"org":1698,"tags":1699,"stars":1562,"repoUrl":1563,"updatedAt":1705},"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},[1700,1701,1702,1703,1704],{"name":13,"slug":14,"type":15},{"name":1669,"slug":1670,"type":15},{"name":1672,"slug":1673,"type":15},{"name":1579,"slug":1580,"type":15},{"name":1675,"slug":1676,"type":15},"2026-05-13T06:14:17.582229",267]