[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-microsoft-deploy-model":3,"mdc-tulgyd-key":37,"related-org-microsoft-deploy-model":1039,"related-repo-microsoft-deploy-model":1232},{"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},"deploy-model","deploy Azure OpenAI models","Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version\u002FSKU\u002Fcapacity\u002FRAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent\u002Fcreate), project creation (use project\u002Fcreate).",{"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","2026-04-06T18:37:30.039139","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","---\nname: deploy-model\ndescription: \"Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version\u002FSKU\u002Fcapacity\u002FRAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent\u002Fcreate), project creation (use project\u002Fcreate).\"\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n---\n\n# Deploy Model\n\n> **Scope — read this first.** This skill creates model deployments **out-of-band** via Azure CLI \u002F MCP \u002F portal. For azd-managed Foundry projects (those scaffolded from `azd-ai-starter-basic` or via `azd ai agent init`), declare deployments in `azure.yaml services.ai-project.deployments[]` instead — `azd ai agent init` writes the entry from the sample manifest and `azd provision` creates the deployment through Bicep. See [foundry-agent\u002Fcreate\u002Fcreate-hosted.md](..\u002F..\u002Ffoundry-agent\u002Fcreate\u002Fcreate-hosted.md) for the Golden Path. Use this skill only for: (a) Foundry projects not managed by an azd project, (b) ad-hoc deployments outside the azd lifecycle.\n\nUnified entry point for all Azure OpenAI model deployment workflows. Analyzes user intent and routes to the appropriate deployment mode.\n\n## Quick Reference\n\n| Mode | When to Use | Sub-Skill |\n|------|-------------|-----------|\n| **Preset** | Quick deployment, no customization needed | [preset\u002FSKILL.md](preset\u002FSKILL.md) |\n| **Customize** | Full control: version, SKU, capacity, RAI policy | [customize\u002FSKILL.md](customize\u002FSKILL.md) |\n| **Capacity Discovery** | Find where you can deploy with specific capacity | [capacity\u002FSKILL.md](capacity\u002FSKILL.md) |\n\n## Intent Detection\n\nAnalyze the user's prompt and route to the correct mode:\n\n```\nUser Prompt\n    │\n    ├─ Simple deployment (no modifiers)\n    │  \"deploy gpt-4o\", \"set up a model\"\n    │  └─> PRESET mode\n    │\n    ├─ Customization keywords present\n    │  \"custom settings\", \"choose version\", \"select SKU\",\n    │  \"set capacity to X\", \"configure content filter\",\n    │  \"PTU deployment\", \"with specific quota\"\n    │  └─> CUSTOMIZE mode\n    │\n    ├─ Capacity\u002Favailability query\n    │  \"find where I can deploy\", \"check capacity\",\n    │  \"which region has X capacity\", \"best region for 10K TPM\",\n    │  \"where is this model available\"\n    │  └─> CAPACITY DISCOVERY mode\n    │\n    └─ Ambiguous (has capacity target + deploy intent)\n       \"deploy gpt-4o with 10K capacity to best region\"\n       └─> CAPACITY DISCOVERY first → then PRESET or CUSTOMIZE\n```\n\n### Routing Rules\n\n| Signal in Prompt | Route To | Reason |\n|------------------|----------|--------|\n| Just model name, no options | **Preset** | User wants quick deployment |\n| \"custom\", \"configure\", \"choose\", \"select\" | **Customize** | User wants control |\n| \"find\", \"check\", \"where\", \"which region\", \"available\" | **Capacity** | User wants discovery |\n| Specific capacity number + \"best region\" | **Capacity → Preset** | Discover then deploy quickly |\n| Specific capacity number + \"custom\" keywords | **Capacity → Customize** | Discover then deploy with options |\n| \"PTU\", \"provisioned throughput\" | **Customize** | PTU requires SKU selection |\n| \"optimal region\", \"best region\" (no capacity target) | **Preset** | Region optimization is preset's specialty |\n\n### Multi-Mode Chaining\n\nSome prompts require two modes in sequence:\n\n**Pattern: Capacity → Deploy**\nWhen a user specifies a capacity requirement AND wants deployment:\n1. Run **Capacity Discovery** to find regions\u002Fprojects with sufficient quota\n2. Present findings to user\n3. Ask: \"Would you like to deploy with **quick defaults** or **customize settings**?\"\n4. Route to **Preset** or **Customize** based on answer\n\n> 💡 **Tip:** If unsure which mode the user wants, default to **Preset** (quick deployment). Users who want customization will typically use explicit keywords like \"custom\", \"configure\", or \"with specific settings\".\n\n## Project Selection (All Modes)\n\nBefore any deployment, resolve which project to deploy to. This applies to **all** modes (preset, customize, and after capacity discovery).\n\n### Resolution Order\n\n1. **Check `PROJECT_RESOURCE_ID` env var** — if set, use it as the default\n2. **Check user prompt** — if user named a specific project or region, use that\n3. **If neither** — query the user's projects and suggest the current one\n\n### Confirmation Step (Required)\n\n**Always confirm the target before deploying.** Show the user what will be used and give them a chance to change it:\n\n```\nDeploying to:\n  Project:  \u003Cproject-name>\n  Region:   \u003Cregion>\n  Resource: \u003Cresource-group>\n\nIs this correct? Or choose a different project:\n  1. ✅ Yes, deploy here (default)\n  2. 📋 Show me other projects in this region\n  3. 🌍 Choose a different region\n```\n\nIf user picks option 2, show top 5 projects in that region:\n\n```\nProjects in \u003Cregion>:\n  1. project-alpha (rg-alpha)\n  2. project-beta (rg-beta)\n  3. project-gamma (rg-gamma)\n  ...\n```\n\n> ⚠️ **Never deploy without showing the user which project will be used.** This prevents accidental deployments to the wrong resource.\n\n## Pre-Deployment Validation (All Modes)\n\nBefore presenting any deployment options (SKU, capacity), always validate both of these:\n\n1. **Model supports the SKU** — query the model catalog to confirm the selected model+version supports the target SKU:\n   ```bash\n   az cognitiveservices model list --location \u003Cregion> --subscription \u003Csub-id> -o json\n   ```\n   Filter for the model, extract `.model.skus[].name` to get supported SKUs.\n\n2. **Subscription has available quota** — check that the user's subscription has unallocated quota for the SKU+model combination:\n   ```bash\n   az cognitiveservices usage list --location \u003Cregion> --subscription \u003Csub-id> -o json\n   ```\n   Match by usage name pattern `OpenAI.\u003CSKU>.\u003Cmodel-name>` (e.g., `OpenAI.GlobalStandard.gpt-4o`). Compute `available = limit - currentValue`.\n\n> ⚠️ **Warning:** Only present options that pass both checks. Do NOT show hardcoded SKU lists — always query dynamically. SKUs with 0 available quota should be shown as ❌ informational items, not selectable options.\n\n> 💡 **Quota management:** For quota increase requests, usage monitoring, and troubleshooting quota errors, defer to the [quota skill](..\u002F..\u002Fquota\u002Fquota.md) instead of duplicating that guidance inline.\n\n## Prerequisites\n\nAll deployment modes require:\n- Azure CLI installed and authenticated (`az login`)\n- Active Azure subscription with deployment permissions\n- Azure AI Foundry project resource ID (or agent will help discover it via `PROJECT_RESOURCE_ID` env var)\n\n## Sub-Skills\n\n- **[preset\u002FSKILL.md](preset\u002FSKILL.md)** — Quick deployment to optimal region with sensible defaults\n- **[customize\u002FSKILL.md](customize\u002FSKILL.md)** — Interactive guided flow with full configuration control\n- **[capacity\u002FSKILL.md](capacity\u002FSKILL.md)** — Discover available capacity across regions and projects\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",[44,52,124,129,136,241,247,252,264,271,441,447,452,462,518,539,545,557,563,604,610,620,629,634,643,658,664,669,907,921,943,949,954,988,994,1033],{"type":45,"tag":46,"props":47,"children":48},"element","h1",{"id":4},[49],{"type":50,"value":51},"text","Deploy Model",{"type":45,"tag":53,"props":54,"children":55},"blockquote",{},[56],{"type":45,"tag":57,"props":58,"children":59},"p",{},[60,66,68,73,75,82,84,90,92,98,100,105,107,113,115,122],{"type":45,"tag":61,"props":62,"children":63},"strong",{},[64],{"type":50,"value":65},"Scope — read this first.",{"type":50,"value":67}," This skill creates model deployments ",{"type":45,"tag":61,"props":69,"children":70},{},[71],{"type":50,"value":72},"out-of-band",{"type":50,"value":74}," via Azure CLI \u002F MCP \u002F portal. For azd-managed Foundry projects (those scaffolded from ",{"type":45,"tag":76,"props":77,"children":79},"code",{"className":78},[],[80],{"type":50,"value":81},"azd-ai-starter-basic",{"type":50,"value":83}," or via ",{"type":45,"tag":76,"props":85,"children":87},{"className":86},[],[88],{"type":50,"value":89},"azd ai agent init",{"type":50,"value":91},"), declare deployments in ",{"type":45,"tag":76,"props":93,"children":95},{"className":94},[],[96],{"type":50,"value":97},"azure.yaml services.ai-project.deployments[]",{"type":50,"value":99}," instead — ",{"type":45,"tag":76,"props":101,"children":103},{"className":102},[],[104],{"type":50,"value":89},{"type":50,"value":106}," writes the entry from the sample manifest and ",{"type":45,"tag":76,"props":108,"children":110},{"className":109},[],[111],{"type":50,"value":112},"azd provision",{"type":50,"value":114}," creates the deployment through Bicep. See ",{"type":45,"tag":116,"props":117,"children":119},"a",{"href":118},"..\u002F..\u002Ffoundry-agent\u002Fcreate\u002Fcreate-hosted.md",[120],{"type":50,"value":121},"foundry-agent\u002Fcreate\u002Fcreate-hosted.md",{"type":50,"value":123}," for the Golden Path. Use this skill only for: (a) Foundry projects not managed by an azd project, (b) ad-hoc deployments outside the azd lifecycle.",{"type":45,"tag":57,"props":125,"children":126},{},[127],{"type":50,"value":128},"Unified entry point for all Azure OpenAI model deployment workflows. Analyzes user intent and routes to the appropriate deployment mode.",{"type":45,"tag":130,"props":131,"children":133},"h2",{"id":132},"quick-reference",[134],{"type":50,"value":135},"Quick Reference",{"type":45,"tag":137,"props":138,"children":139},"table",{},[140,164],{"type":45,"tag":141,"props":142,"children":143},"thead",{},[144],{"type":45,"tag":145,"props":146,"children":147},"tr",{},[148,154,159],{"type":45,"tag":149,"props":150,"children":151},"th",{},[152],{"type":50,"value":153},"Mode",{"type":45,"tag":149,"props":155,"children":156},{},[157],{"type":50,"value":158},"When to Use",{"type":45,"tag":149,"props":160,"children":161},{},[162],{"type":50,"value":163},"Sub-Skill",{"type":45,"tag":165,"props":166,"children":167},"tbody",{},[168,193,217],{"type":45,"tag":145,"props":169,"children":170},{},[171,180,185],{"type":45,"tag":172,"props":173,"children":174},"td",{},[175],{"type":45,"tag":61,"props":176,"children":177},{},[178],{"type":50,"value":179},"Preset",{"type":45,"tag":172,"props":181,"children":182},{},[183],{"type":50,"value":184},"Quick deployment, no customization needed",{"type":45,"tag":172,"props":186,"children":187},{},[188],{"type":45,"tag":116,"props":189,"children":191},{"href":190},"preset\u002FSKILL.md",[192],{"type":50,"value":190},{"type":45,"tag":145,"props":194,"children":195},{},[196,204,209],{"type":45,"tag":172,"props":197,"children":198},{},[199],{"type":45,"tag":61,"props":200,"children":201},{},[202],{"type":50,"value":203},"Customize",{"type":45,"tag":172,"props":205,"children":206},{},[207],{"type":50,"value":208},"Full control: version, SKU, capacity, RAI policy",{"type":45,"tag":172,"props":210,"children":211},{},[212],{"type":45,"tag":116,"props":213,"children":215},{"href":214},"customize\u002FSKILL.md",[216],{"type":50,"value":214},{"type":45,"tag":145,"props":218,"children":219},{},[220,228,233],{"type":45,"tag":172,"props":221,"children":222},{},[223],{"type":45,"tag":61,"props":224,"children":225},{},[226],{"type":50,"value":227},"Capacity Discovery",{"type":45,"tag":172,"props":229,"children":230},{},[231],{"type":50,"value":232},"Find where you can deploy with specific capacity",{"type":45,"tag":172,"props":234,"children":235},{},[236],{"type":45,"tag":116,"props":237,"children":239},{"href":238},"capacity\u002FSKILL.md",[240],{"type":50,"value":238},{"type":45,"tag":130,"props":242,"children":244},{"id":243},"intent-detection",[245],{"type":50,"value":246},"Intent Detection",{"type":45,"tag":57,"props":248,"children":249},{},[250],{"type":50,"value":251},"Analyze the user's prompt and route to the correct mode:",{"type":45,"tag":253,"props":254,"children":258},"pre",{"className":255,"code":257,"language":50},[256],"language-text","User Prompt\n    │\n    ├─ Simple deployment (no modifiers)\n    │  \"deploy gpt-4o\", \"set up a model\"\n    │  └─> PRESET mode\n    │\n    ├─ Customization keywords present\n    │  \"custom settings\", \"choose version\", \"select SKU\",\n    │  \"set capacity to X\", \"configure content filter\",\n    │  \"PTU deployment\", \"with specific quota\"\n    │  └─> CUSTOMIZE mode\n    │\n    ├─ Capacity\u002Favailability query\n    │  \"find where I can deploy\", \"check capacity\",\n    │  \"which region has X capacity\", \"best region for 10K TPM\",\n    │  \"where is this model available\"\n    │  └─> CAPACITY DISCOVERY mode\n    │\n    └─ Ambiguous (has capacity target + deploy intent)\n       \"deploy gpt-4o with 10K capacity to best region\"\n       └─> CAPACITY DISCOVERY first → then PRESET or CUSTOMIZE\n",[259],{"type":45,"tag":76,"props":260,"children":262},{"__ignoreMap":261},"",[263],{"type":50,"value":257},{"type":45,"tag":265,"props":266,"children":268},"h3",{"id":267},"routing-rules",[269],{"type":50,"value":270},"Routing Rules",{"type":45,"tag":137,"props":272,"children":273},{},[274,295],{"type":45,"tag":141,"props":275,"children":276},{},[277],{"type":45,"tag":145,"props":278,"children":279},{},[280,285,290],{"type":45,"tag":149,"props":281,"children":282},{},[283],{"type":50,"value":284},"Signal in Prompt",{"type":45,"tag":149,"props":286,"children":287},{},[288],{"type":50,"value":289},"Route To",{"type":45,"tag":149,"props":291,"children":292},{},[293],{"type":50,"value":294},"Reason",{"type":45,"tag":165,"props":296,"children":297},{},[298,318,338,359,380,401,421],{"type":45,"tag":145,"props":299,"children":300},{},[301,306,313],{"type":45,"tag":172,"props":302,"children":303},{},[304],{"type":50,"value":305},"Just model name, no options",{"type":45,"tag":172,"props":307,"children":308},{},[309],{"type":45,"tag":61,"props":310,"children":311},{},[312],{"type":50,"value":179},{"type":45,"tag":172,"props":314,"children":315},{},[316],{"type":50,"value":317},"User wants quick deployment",{"type":45,"tag":145,"props":319,"children":320},{},[321,326,333],{"type":45,"tag":172,"props":322,"children":323},{},[324],{"type":50,"value":325},"\"custom\", \"configure\", \"choose\", \"select\"",{"type":45,"tag":172,"props":327,"children":328},{},[329],{"type":45,"tag":61,"props":330,"children":331},{},[332],{"type":50,"value":203},{"type":45,"tag":172,"props":334,"children":335},{},[336],{"type":50,"value":337},"User wants control",{"type":45,"tag":145,"props":339,"children":340},{},[341,346,354],{"type":45,"tag":172,"props":342,"children":343},{},[344],{"type":50,"value":345},"\"find\", \"check\", \"where\", \"which region\", \"available\"",{"type":45,"tag":172,"props":347,"children":348},{},[349],{"type":45,"tag":61,"props":350,"children":351},{},[352],{"type":50,"value":353},"Capacity",{"type":45,"tag":172,"props":355,"children":356},{},[357],{"type":50,"value":358},"User wants discovery",{"type":45,"tag":145,"props":360,"children":361},{},[362,367,375],{"type":45,"tag":172,"props":363,"children":364},{},[365],{"type":50,"value":366},"Specific capacity number + \"best region\"",{"type":45,"tag":172,"props":368,"children":369},{},[370],{"type":45,"tag":61,"props":371,"children":372},{},[373],{"type":50,"value":374},"Capacity → Preset",{"type":45,"tag":172,"props":376,"children":377},{},[378],{"type":50,"value":379},"Discover then deploy quickly",{"type":45,"tag":145,"props":381,"children":382},{},[383,388,396],{"type":45,"tag":172,"props":384,"children":385},{},[386],{"type":50,"value":387},"Specific capacity number + \"custom\" keywords",{"type":45,"tag":172,"props":389,"children":390},{},[391],{"type":45,"tag":61,"props":392,"children":393},{},[394],{"type":50,"value":395},"Capacity → Customize",{"type":45,"tag":172,"props":397,"children":398},{},[399],{"type":50,"value":400},"Discover then deploy with options",{"type":45,"tag":145,"props":402,"children":403},{},[404,409,416],{"type":45,"tag":172,"props":405,"children":406},{},[407],{"type":50,"value":408},"\"PTU\", \"provisioned throughput\"",{"type":45,"tag":172,"props":410,"children":411},{},[412],{"type":45,"tag":61,"props":413,"children":414},{},[415],{"type":50,"value":203},{"type":45,"tag":172,"props":417,"children":418},{},[419],{"type":50,"value":420},"PTU requires SKU selection",{"type":45,"tag":145,"props":422,"children":423},{},[424,429,436],{"type":45,"tag":172,"props":425,"children":426},{},[427],{"type":50,"value":428},"\"optimal region\", \"best region\" (no capacity target)",{"type":45,"tag":172,"props":430,"children":431},{},[432],{"type":45,"tag":61,"props":433,"children":434},{},[435],{"type":50,"value":179},{"type":45,"tag":172,"props":437,"children":438},{},[439],{"type":50,"value":440},"Region optimization is preset's specialty",{"type":45,"tag":265,"props":442,"children":444},{"id":443},"multi-mode-chaining",[445],{"type":50,"value":446},"Multi-Mode Chaining",{"type":45,"tag":57,"props":448,"children":449},{},[450],{"type":50,"value":451},"Some prompts require two modes in sequence:",{"type":45,"tag":57,"props":453,"children":454},{},[455,460],{"type":45,"tag":61,"props":456,"children":457},{},[458],{"type":50,"value":459},"Pattern: Capacity → Deploy",{"type":50,"value":461},"\nWhen a user specifies a capacity requirement AND wants deployment:",{"type":45,"tag":463,"props":464,"children":465},"ol",{},[466,478,483,502],{"type":45,"tag":467,"props":468,"children":469},"li",{},[470,472,476],{"type":50,"value":471},"Run ",{"type":45,"tag":61,"props":473,"children":474},{},[475],{"type":50,"value":227},{"type":50,"value":477}," to find regions\u002Fprojects with sufficient quota",{"type":45,"tag":467,"props":479,"children":480},{},[481],{"type":50,"value":482},"Present findings to user",{"type":45,"tag":467,"props":484,"children":485},{},[486,488,493,495,500],{"type":50,"value":487},"Ask: \"Would you like to deploy with ",{"type":45,"tag":61,"props":489,"children":490},{},[491],{"type":50,"value":492},"quick defaults",{"type":50,"value":494}," or ",{"type":45,"tag":61,"props":496,"children":497},{},[498],{"type":50,"value":499},"customize settings",{"type":50,"value":501},"?\"",{"type":45,"tag":467,"props":503,"children":504},{},[505,507,511,512,516],{"type":50,"value":506},"Route to ",{"type":45,"tag":61,"props":508,"children":509},{},[510],{"type":50,"value":179},{"type":50,"value":494},{"type":45,"tag":61,"props":513,"children":514},{},[515],{"type":50,"value":203},{"type":50,"value":517}," based on answer",{"type":45,"tag":53,"props":519,"children":520},{},[521],{"type":45,"tag":57,"props":522,"children":523},{},[524,526,531,533,537],{"type":50,"value":525},"💡 ",{"type":45,"tag":61,"props":527,"children":528},{},[529],{"type":50,"value":530},"Tip:",{"type":50,"value":532}," If unsure which mode the user wants, default to ",{"type":45,"tag":61,"props":534,"children":535},{},[536],{"type":50,"value":179},{"type":50,"value":538}," (quick deployment). Users who want customization will typically use explicit keywords like \"custom\", \"configure\", or \"with specific settings\".",{"type":45,"tag":130,"props":540,"children":542},{"id":541},"project-selection-all-modes",[543],{"type":50,"value":544},"Project Selection (All Modes)",{"type":45,"tag":57,"props":546,"children":547},{},[548,550,555],{"type":50,"value":549},"Before any deployment, resolve which project to deploy to. This applies to ",{"type":45,"tag":61,"props":551,"children":552},{},[553],{"type":50,"value":554},"all",{"type":50,"value":556}," modes (preset, customize, and after capacity discovery).",{"type":45,"tag":265,"props":558,"children":560},{"id":559},"resolution-order",[561],{"type":50,"value":562},"Resolution Order",{"type":45,"tag":463,"props":564,"children":565},{},[566,584,594],{"type":45,"tag":467,"props":567,"children":568},{},[569,582],{"type":45,"tag":61,"props":570,"children":571},{},[572,574,580],{"type":50,"value":573},"Check ",{"type":45,"tag":76,"props":575,"children":577},{"className":576},[],[578],{"type":50,"value":579},"PROJECT_RESOURCE_ID",{"type":50,"value":581}," env var",{"type":50,"value":583}," — if set, use it as the default",{"type":45,"tag":467,"props":585,"children":586},{},[587,592],{"type":45,"tag":61,"props":588,"children":589},{},[590],{"type":50,"value":591},"Check user prompt",{"type":50,"value":593}," — if user named a specific project or region, use that",{"type":45,"tag":467,"props":595,"children":596},{},[597,602],{"type":45,"tag":61,"props":598,"children":599},{},[600],{"type":50,"value":601},"If neither",{"type":50,"value":603}," — query the user's projects and suggest the current one",{"type":45,"tag":265,"props":605,"children":607},{"id":606},"confirmation-step-required",[608],{"type":50,"value":609},"Confirmation Step (Required)",{"type":45,"tag":57,"props":611,"children":612},{},[613,618],{"type":45,"tag":61,"props":614,"children":615},{},[616],{"type":50,"value":617},"Always confirm the target before deploying.",{"type":50,"value":619}," Show the user what will be used and give them a chance to change it:",{"type":45,"tag":253,"props":621,"children":624},{"className":622,"code":623,"language":50},[256],"Deploying to:\n  Project:  \u003Cproject-name>\n  Region:   \u003Cregion>\n  Resource: \u003Cresource-group>\n\nIs this correct? Or choose a different project:\n  1. ✅ Yes, deploy here (default)\n  2. 📋 Show me other projects in this region\n  3. 🌍 Choose a different region\n",[625],{"type":45,"tag":76,"props":626,"children":627},{"__ignoreMap":261},[628],{"type":50,"value":623},{"type":45,"tag":57,"props":630,"children":631},{},[632],{"type":50,"value":633},"If user picks option 2, show top 5 projects in that region:",{"type":45,"tag":253,"props":635,"children":638},{"className":636,"code":637,"language":50},[256],"Projects in \u003Cregion>:\n  1. project-alpha (rg-alpha)\n  2. project-beta (rg-beta)\n  3. project-gamma (rg-gamma)\n  ...\n",[639],{"type":45,"tag":76,"props":640,"children":641},{"__ignoreMap":261},[642],{"type":50,"value":637},{"type":45,"tag":53,"props":644,"children":645},{},[646],{"type":45,"tag":57,"props":647,"children":648},{},[649,651,656],{"type":50,"value":650},"⚠️ ",{"type":45,"tag":61,"props":652,"children":653},{},[654],{"type":50,"value":655},"Never deploy without showing the user which project will be used.",{"type":50,"value":657}," This prevents accidental deployments to the wrong resource.",{"type":45,"tag":130,"props":659,"children":661},{"id":660},"pre-deployment-validation-all-modes",[662],{"type":50,"value":663},"Pre-Deployment Validation (All Modes)",{"type":45,"tag":57,"props":665,"children":666},{},[667],{"type":50,"value":668},"Before presenting any deployment options (SKU, capacity), always validate both of these:",{"type":45,"tag":463,"props":670,"children":671},{},[672,793],{"type":45,"tag":467,"props":673,"children":674},{},[675,680,682,779,783,785,791],{"type":45,"tag":61,"props":676,"children":677},{},[678],{"type":50,"value":679},"Model supports the SKU",{"type":50,"value":681}," — query the model catalog to confirm the selected model+version supports the target SKU:",{"type":45,"tag":253,"props":683,"children":687},{"className":684,"code":685,"language":686,"meta":261,"style":261},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","az cognitiveservices model list --location \u003Cregion> --subscription \u003Csub-id> -o json\n","bash",[688],{"type":45,"tag":76,"props":689,"children":690},{"__ignoreMap":261},[691],{"type":45,"tag":692,"props":693,"children":696},"span",{"class":694,"line":695},"line",1,[697,703,709,714,719,724,730,735,741,746,751,755,760,765,769,774],{"type":45,"tag":692,"props":698,"children":700},{"style":699},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[701],{"type":50,"value":702},"az",{"type":45,"tag":692,"props":704,"children":706},{"style":705},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[707],{"type":50,"value":708}," cognitiveservices",{"type":45,"tag":692,"props":710,"children":711},{"style":705},[712],{"type":50,"value":713}," model",{"type":45,"tag":692,"props":715,"children":716},{"style":705},[717],{"type":50,"value":718}," list",{"type":45,"tag":692,"props":720,"children":721},{"style":705},[722],{"type":50,"value":723}," --location",{"type":45,"tag":692,"props":725,"children":727},{"style":726},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[728],{"type":50,"value":729}," \u003C",{"type":45,"tag":692,"props":731,"children":732},{"style":705},[733],{"type":50,"value":734},"regio",{"type":45,"tag":692,"props":736,"children":738},{"style":737},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[739],{"type":50,"value":740},"n",{"type":45,"tag":692,"props":742,"children":743},{"style":726},[744],{"type":50,"value":745},">",{"type":45,"tag":692,"props":747,"children":748},{"style":705},[749],{"type":50,"value":750}," --subscription",{"type":45,"tag":692,"props":752,"children":753},{"style":726},[754],{"type":50,"value":729},{"type":45,"tag":692,"props":756,"children":757},{"style":705},[758],{"type":50,"value":759},"sub-i",{"type":45,"tag":692,"props":761,"children":762},{"style":737},[763],{"type":50,"value":764},"d",{"type":45,"tag":692,"props":766,"children":767},{"style":726},[768],{"type":50,"value":745},{"type":45,"tag":692,"props":770,"children":771},{"style":705},[772],{"type":50,"value":773}," -o",{"type":45,"tag":692,"props":775,"children":776},{"style":705},[777],{"type":50,"value":778}," json\n",{"type":45,"tag":780,"props":781,"children":782},"br",{},[],{"type":50,"value":784},"Filter for the model, extract ",{"type":45,"tag":76,"props":786,"children":788},{"className":787},[],[789],{"type":50,"value":790},".model.skus[].name",{"type":50,"value":792}," to get supported SKUs.",{"type":45,"tag":467,"props":794,"children":795},{},[796,801,803,878,881,883,889,891,897,899,905],{"type":45,"tag":61,"props":797,"children":798},{},[799],{"type":50,"value":800},"Subscription has available quota",{"type":50,"value":802}," — check that the user's subscription has unallocated quota for the SKU+model combination:",{"type":45,"tag":253,"props":804,"children":806},{"className":684,"code":805,"language":686,"meta":261,"style":261},"az cognitiveservices usage list --location \u003Cregion> --subscription \u003Csub-id> -o json\n",[807],{"type":45,"tag":76,"props":808,"children":809},{"__ignoreMap":261},[810],{"type":45,"tag":692,"props":811,"children":812},{"class":694,"line":695},[813,817,821,826,830,834,838,842,846,850,854,858,862,866,870,874],{"type":45,"tag":692,"props":814,"children":815},{"style":699},[816],{"type":50,"value":702},{"type":45,"tag":692,"props":818,"children":819},{"style":705},[820],{"type":50,"value":708},{"type":45,"tag":692,"props":822,"children":823},{"style":705},[824],{"type":50,"value":825}," usage",{"type":45,"tag":692,"props":827,"children":828},{"style":705},[829],{"type":50,"value":718},{"type":45,"tag":692,"props":831,"children":832},{"style":705},[833],{"type":50,"value":723},{"type":45,"tag":692,"props":835,"children":836},{"style":726},[837],{"type":50,"value":729},{"type":45,"tag":692,"props":839,"children":840},{"style":705},[841],{"type":50,"value":734},{"type":45,"tag":692,"props":843,"children":844},{"style":737},[845],{"type":50,"value":740},{"type":45,"tag":692,"props":847,"children":848},{"style":726},[849],{"type":50,"value":745},{"type":45,"tag":692,"props":851,"children":852},{"style":705},[853],{"type":50,"value":750},{"type":45,"tag":692,"props":855,"children":856},{"style":726},[857],{"type":50,"value":729},{"type":45,"tag":692,"props":859,"children":860},{"style":705},[861],{"type":50,"value":759},{"type":45,"tag":692,"props":863,"children":864},{"style":737},[865],{"type":50,"value":764},{"type":45,"tag":692,"props":867,"children":868},{"style":726},[869],{"type":50,"value":745},{"type":45,"tag":692,"props":871,"children":872},{"style":705},[873],{"type":50,"value":773},{"type":45,"tag":692,"props":875,"children":876},{"style":705},[877],{"type":50,"value":778},{"type":45,"tag":780,"props":879,"children":880},{},[],{"type":50,"value":882},"Match by usage name pattern ",{"type":45,"tag":76,"props":884,"children":886},{"className":885},[],[887],{"type":50,"value":888},"OpenAI.\u003CSKU>.\u003Cmodel-name>",{"type":50,"value":890}," (e.g., ",{"type":45,"tag":76,"props":892,"children":894},{"className":893},[],[895],{"type":50,"value":896},"OpenAI.GlobalStandard.gpt-4o",{"type":50,"value":898},"). Compute ",{"type":45,"tag":76,"props":900,"children":902},{"className":901},[],[903],{"type":50,"value":904},"available = limit - currentValue",{"type":50,"value":906},".",{"type":45,"tag":53,"props":908,"children":909},{},[910],{"type":45,"tag":57,"props":911,"children":912},{},[913,914,919],{"type":50,"value":650},{"type":45,"tag":61,"props":915,"children":916},{},[917],{"type":50,"value":918},"Warning:",{"type":50,"value":920}," Only present options that pass both checks. Do NOT show hardcoded SKU lists — always query dynamically. SKUs with 0 available quota should be shown as ❌ informational items, not selectable options.",{"type":45,"tag":53,"props":922,"children":923},{},[924],{"type":45,"tag":57,"props":925,"children":926},{},[927,928,933,935,941],{"type":50,"value":525},{"type":45,"tag":61,"props":929,"children":930},{},[931],{"type":50,"value":932},"Quota management:",{"type":50,"value":934}," For quota increase requests, usage monitoring, and troubleshooting quota errors, defer to the ",{"type":45,"tag":116,"props":936,"children":938},{"href":937},"..\u002F..\u002Fquota\u002Fquota.md",[939],{"type":50,"value":940},"quota skill",{"type":50,"value":942}," instead of duplicating that guidance inline.",{"type":45,"tag":130,"props":944,"children":946},{"id":945},"prerequisites",[947],{"type":50,"value":948},"Prerequisites",{"type":45,"tag":57,"props":950,"children":951},{},[952],{"type":50,"value":953},"All deployment modes require:",{"type":45,"tag":955,"props":956,"children":957},"ul",{},[958,971,976],{"type":45,"tag":467,"props":959,"children":960},{},[961,963,969],{"type":50,"value":962},"Azure CLI installed and authenticated (",{"type":45,"tag":76,"props":964,"children":966},{"className":965},[],[967],{"type":50,"value":968},"az login",{"type":50,"value":970},")",{"type":45,"tag":467,"props":972,"children":973},{},[974],{"type":50,"value":975},"Active Azure subscription with deployment permissions",{"type":45,"tag":467,"props":977,"children":978},{},[979,981,986],{"type":50,"value":980},"Azure AI Foundry project resource ID (or agent will help discover it via ",{"type":45,"tag":76,"props":982,"children":984},{"className":983},[],[985],{"type":50,"value":579},{"type":50,"value":987}," env var)",{"type":45,"tag":130,"props":989,"children":991},{"id":990},"sub-skills",[992],{"type":50,"value":993},"Sub-Skills",{"type":45,"tag":955,"props":995,"children":996},{},[997,1009,1021],{"type":45,"tag":467,"props":998,"children":999},{},[1000,1007],{"type":45,"tag":61,"props":1001,"children":1002},{},[1003],{"type":45,"tag":116,"props":1004,"children":1005},{"href":190},[1006],{"type":50,"value":190},{"type":50,"value":1008}," — Quick deployment to optimal region with sensible defaults",{"type":45,"tag":467,"props":1010,"children":1011},{},[1012,1019],{"type":45,"tag":61,"props":1013,"children":1014},{},[1015],{"type":45,"tag":116,"props":1016,"children":1017},{"href":214},[1018],{"type":50,"value":214},{"type":50,"value":1020}," — Interactive guided flow with full configuration control",{"type":45,"tag":467,"props":1022,"children":1023},{},[1024,1031],{"type":45,"tag":61,"props":1025,"children":1026},{},[1027],{"type":45,"tag":116,"props":1028,"children":1029},{"href":238},[1030],{"type":50,"value":238},{"type":50,"value":1032}," — Discover available capacity across regions and projects",{"type":45,"tag":1034,"props":1035,"children":1036},"style",{},[1037],{"type":50,"value":1038},"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":1040,"total":1231},[1041,1063,1082,1103,1116,1133,1144,1157,1172,1187,1206,1219],{"slug":1042,"name":1042,"fn":1043,"description":1044,"org":1045,"tags":1046,"stars":1060,"repoUrl":1061,"updatedAt":1062},"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},[1047,1050,1053,1054,1057],{"name":1048,"slug":1049,"type":15},"Engineering","engineering",{"name":1051,"slug":1052,"type":15},"Local Development","local-development",{"name":9,"slug":8,"type":15},{"name":1055,"slug":1056,"type":15},"Project Management","project-management",{"name":1058,"slug":1059,"type":15},"Rush","rush",6484,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Frushstack","2026-04-06T18:34:44.965032",{"slug":1064,"name":1064,"fn":1065,"description":1066,"org":1067,"tags":1068,"stars":1079,"repoUrl":1080,"updatedAt":1081},"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},[1069,1072,1075,1076],{"name":1070,"slug":1071,"type":15},".NET","net",{"name":1073,"slug":1074,"type":15},"Agents","agents",{"name":13,"slug":14,"type":15},{"name":1077,"slug":1078,"type":15},"LLM","llm",2804,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","2026-07-03T16:32:10.297433",{"slug":1083,"name":1083,"fn":1084,"description":1085,"org":1086,"tags":1087,"stars":1079,"repoUrl":1080,"updatedAt":1102},"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},[1088,1091,1092,1095,1098,1099],{"name":1089,"slug":1090,"type":15},"Analytics","analytics",{"name":13,"slug":14,"type":15},{"name":1093,"slug":1094,"type":15},"Data Analysis","data-analysis",{"name":1096,"slug":1097,"type":15},"Java","java",{"name":9,"slug":8,"type":15},{"name":1100,"slug":1101,"type":15},"Monitoring","monitoring","2026-05-13T06:14:16.261754",{"slug":1104,"name":1104,"fn":1105,"description":1106,"org":1107,"tags":1108,"stars":1079,"repoUrl":1080,"updatedAt":1115},"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},[1109,1110,1111,1112],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":1096,"slug":1097,"type":15},{"name":1113,"slug":1114,"type":15},"Security","security","2026-07-07T06:53:31.293235",{"slug":1117,"name":1117,"fn":1118,"description":1119,"org":1120,"tags":1121,"stars":1079,"repoUrl":1080,"updatedAt":1132},"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},[1122,1123,1126,1127,1128,1131],{"name":13,"slug":14,"type":15},{"name":1124,"slug":1125,"type":15},"Compliance","compliance",{"name":1077,"slug":1078,"type":15},{"name":9,"slug":8,"type":15},{"name":1129,"slug":1130,"type":15},"Python","python",{"name":1113,"slug":1114,"type":15},"2026-07-18T05:14:23.017504",{"slug":1134,"name":1134,"fn":1135,"description":1136,"org":1137,"tags":1138,"stars":1079,"repoUrl":1080,"updatedAt":1143},"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},[1139,1140,1141,1142],{"name":1089,"slug":1090,"type":15},{"name":13,"slug":14,"type":15},{"name":1077,"slug":1078,"type":15},{"name":1129,"slug":1130,"type":15},"2026-07-31T05:54:29.068751",{"slug":1145,"name":1145,"fn":1146,"description":1147,"org":1148,"tags":1149,"stars":1079,"repoUrl":1080,"updatedAt":1156},"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},[1150,1153,1154,1155],{"name":1151,"slug":1152,"type":15},"API Development","api-development",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":1129,"slug":1130,"type":15},"2026-07-18T05:14:16.988376",{"slug":1158,"name":1158,"fn":1159,"description":1160,"org":1161,"tags":1162,"stars":1079,"repoUrl":1080,"updatedAt":1171},"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},[1163,1164,1167,1170],{"name":13,"slug":14,"type":15},{"name":1165,"slug":1166,"type":15},"Computer Vision","computer-vision",{"name":1168,"slug":1169,"type":15},"Images","images",{"name":1129,"slug":1130,"type":15},"2026-07-18T05:14:18.007737",{"slug":1173,"name":1173,"fn":1174,"description":1175,"org":1176,"tags":1177,"stars":1079,"repoUrl":1080,"updatedAt":1186},"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},[1178,1179,1182,1185],{"name":13,"slug":14,"type":15},{"name":1180,"slug":1181,"type":15},"Configuration","configuration",{"name":1183,"slug":1184,"type":15},"Feature Flags","feature-flags",{"name":1096,"slug":1097,"type":15},"2026-07-03T16:32:01.278468",{"slug":1188,"name":1188,"fn":1189,"description":1190,"org":1191,"tags":1192,"stars":1079,"repoUrl":1080,"updatedAt":1205},"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},[1193,1196,1199,1202],{"name":1194,"slug":1195,"type":15},"Cosmos DB","cosmos-db",{"name":1197,"slug":1198,"type":15},"Database","database",{"name":1200,"slug":1201,"type":15},"NoSQL","nosql",{"name":1203,"slug":1204,"type":15},"Rust","rust","2026-07-31T05:54:27.021432",{"slug":1207,"name":1207,"fn":1189,"description":1208,"org":1209,"tags":1210,"stars":1079,"repoUrl":1080,"updatedAt":1218},"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},[1211,1212,1213,1214,1215],{"name":1194,"slug":1195,"type":15},{"name":1197,"slug":1198,"type":15},{"name":9,"slug":8,"type":15},{"name":1200,"slug":1201,"type":15},{"name":1216,"slug":1217,"type":15},"TypeScript","typescript","2026-07-03T16:31:19.368382",{"slug":1220,"name":1220,"fn":1221,"description":1222,"org":1223,"tags":1224,"stars":1079,"repoUrl":1080,"updatedAt":1230},"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},[1225,1226,1227,1228,1229],{"name":13,"slug":14,"type":15},{"name":1194,"slug":1195,"type":15},{"name":1197,"slug":1198,"type":15},{"name":1096,"slug":1097,"type":15},{"name":1200,"slug":1201,"type":15},"2026-05-13T06:14:17.582229",267,{"items":1233,"total":1347},[1234,1250,1262,1279,1296,1313,1329],{"slug":1235,"name":1235,"fn":1236,"description":1237,"org":1238,"tags":1239,"stars":25,"repoUrl":26,"updatedAt":1249},"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},[1240,1241,1242,1243,1246],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"name":1244,"slug":1245,"type":15},"Kubernetes","kubernetes",{"name":1247,"slug":1248,"type":15},"Runway","runway","2026-07-31T05:56:13.054971",{"slug":1251,"name":1251,"fn":1252,"description":1253,"org":1254,"tags":1255,"stars":25,"repoUrl":26,"updatedAt":1261},"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},[1256,1257,1258],{"name":13,"slug":14,"type":15},{"name":1100,"slug":1101,"type":15},{"name":1259,"slug":1260,"type":15},"Observability","observability","2026-07-31T05:56:09.068625",{"slug":1263,"name":1263,"fn":1264,"description":1265,"org":1266,"tags":1267,"stars":25,"repoUrl":26,"updatedAt":1278},"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},[1268,1269,1270,1271,1272,1275],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":1077,"slug":1078,"type":15},{"name":20,"slug":21,"type":15},{"name":1273,"slug":1274,"type":15},"Search","search",{"name":1276,"slug":1277,"type":15},"Speech","speech","2026-07-31T05:56:19.069133",{"slug":1280,"name":1280,"fn":1281,"description":1282,"org":1283,"tags":1284,"stars":25,"repoUrl":26,"updatedAt":1295},"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},[1285,1286,1287,1288,1291,1294],{"name":23,"slug":24,"type":15},{"name":1151,"slug":1152,"type":15},{"name":13,"slug":14,"type":15},{"name":1289,"slug":1290,"type":15},"Caching","caching",{"name":1292,"slug":1293,"type":15},"Governance","governance",{"name":1113,"slug":1114,"type":15},"2026-07-31T05:56:23.05242",{"slug":1297,"name":1297,"fn":1298,"description":1299,"org":1300,"tags":1301,"stars":25,"repoUrl":26,"updatedAt":1312},"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},[1302,1305,1306,1309],{"name":1303,"slug":1304,"type":15},"AWS","aws",{"name":13,"slug":14,"type":15},{"name":1307,"slug":1308,"type":15},"Google Cloud","google-cloud",{"name":1310,"slug":1311,"type":15},"Migration","migration","2026-07-31T05:56:29.049979",{"slug":1314,"name":1314,"fn":1315,"description":1316,"org":1317,"tags":1318,"stars":25,"repoUrl":26,"updatedAt":1328},"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},[1319,1322,1323,1324,1327],{"name":1320,"slug":1321,"type":15},"Audit","audit",{"name":13,"slug":14,"type":15},{"name":1124,"slug":1125,"type":15},{"name":1325,"slug":1326,"type":15},"Regulatory Compliance","regulatory-compliance",{"name":1113,"slug":1114,"type":15},"2026-07-31T05:56:11.06797",{"slug":1330,"name":1330,"fn":1331,"description":1332,"org":1333,"tags":1334,"stars":25,"repoUrl":26,"updatedAt":1346},"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},[1335,1336,1337,1340,1343],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":1338,"slug":1339,"type":15},"Cost Optimization","cost-optimization",{"name":1341,"slug":1342,"type":15},"Performance","performance",{"name":1344,"slug":1345,"type":15},"Virtual Machines","virtual-machines","2026-07-31T05:56:16.042469",28]