{"id":"a89c676b-2d4d-463e-a785-5d4576233e94","shortId":"BvREAN","kind":"skill","title":"azure-architecture-autopilot","tagline":"Design Azure infrastructure using natural language, or analyze existing Azure resources to auto-generate architecture diagrams, refine them through conversation, and deploy with Bicep.  When to use this skill: - \"Create X on Azure\", \"Set up a RAG architecture\" (new design) - \"Ana","description":"# Azure Architecture Builder\n\nA pipeline that designs Azure infrastructure using natural language, or analyzes existing resources to visualize architecture and proceed through modification and deployment.\n\nThe diagram engine is **embedded within the skill** (`scripts/` folder).\nNo `pip install` needed — it directly uses the bundled Python scripts\nto generate interactive HTML diagrams with 605+ official Azure icons.\nReady to use immediately without network access or package installation.\n\n## Automatic User Language Detection\n\n**🚨 Detect the language of the user's first message and provide all subsequent responses in that language. This is the highest-priority principle.**\n\n- If the user writes in Korean → respond in Korean\n- If the user writes in English → **respond in English** (ask_user, progress updates, reports, Bicep comments — all in English)\n- The instructions and examples in this document are written in English, and **all user-facing output must match the user's language**\n\n**⚠️ Do not copy examples from this document verbatim to the user.**\nUse only the structure as reference, and adapt text to the user's language.\n\n## Tool Usage Guide (GHCP Environment)\n\n| Feature | Tool Name | Notes |\n|---------|-----------|-------|\n| Fetch URL content | `web_fetch` | For MS Docs lookups, etc. |\n| Web search | `web_search` | URL discovery |\n| Ask user | `ask_user` | `choices` must be a string array |\n| Sub-agents | `task` | explore/task/general-purpose |\n| Shell command execution | `powershell` | Windows PowerShell |\n\n> All sub-agents (explore/task/general-purpose) cannot use `web_fetch` or `web_search`.\n> Fact-checking that requires MS Docs lookups must be performed **directly by the main agent**.\n\n## External Tool Path Discovery\n\n`az`, `python`, `bicep`, etc. are often not on PATH.\n**Discover once before starting a Phase and cache the result. Do not re-discover every time.**\n\n> **⚠️ Do not use `Get-Command python`** — risk of Windows Store alias.\n> Direct filesystem discovery (`$env:LOCALAPPDATA\\Programs\\Python`) takes priority.\n\naz CLI path:\n```powershell\n$azCmd = $null\nif (Get-Command az -ErrorAction SilentlyContinue) { $azCmd = 'az' }\nif (-not $azCmd) {\n  $azExe = Get-ChildItem -Path \"$env:ProgramFiles\\Microsoft SDKs\\Azure\\CLI2\\wbin\", \"$env:LOCALAPPDATA\\Programs\\Azure CLI\\wbin\" -Filter \"az.cmd\" -ErrorAction SilentlyContinue | Select-Object -First 1 -ExpandProperty FullName\n  if ($azExe) { $azCmd = $azExe }\n}\n```\n\nPython path + embedded diagram engine: refer to the diagram generation section in `references/phase1-advisor.md`.\n\n## Progress Updates Required\n\nUse blockquote + emoji + bold format:\n```markdown\n> **⏳ [Action]** — [Reason]\n> **✅ [Complete]** — [Result]\n> **⚠️ [Warning]** — [Details]\n> **❌ [Failed]** — [Cause]\n```\n\n## Parallel Preload Principle\n\nWhile waiting for user input via `ask_user`, preload information needed for the next step in parallel.\n\n| ask_user Question | Preload Simultaneously |\n|---|---|\n| Project name / scan scope | Reference files, MS Docs, Python path discovery, **diagram module path verification** |\n| Model/SKU selection | MS Docs for next question choices |\n| Architecture confirmation | `az account show/list`, `az group list` |\n| Subscription selection | `az group list` |\n\n---\n\n## Path Branching — Automatically Determined by User Request\n\n### Path A: New Design (New Build)\n\n**Trigger**: \"create\", \"set up\", \"deploy\", \"build\", etc.\n```\nPhase 1 (references/phase1-advisor.md) — Interactive architecture design + diagram\n    ↓\nPhase 2 (references/bicep-generator.md) — Bicep code generation\n    ↓\nPhase 3 (references/bicep-reviewer.md) — Code review + compilation verification\n    ↓\nPhase 4 (references/phase4-deployer.md) — validate → what-if → deploy\n```\n\n### Path B: Existing Analysis + Modification (Analyze & Modify)\n\n**Trigger**: \"analyze\", \"current resources\", \"scan\", \"draw a diagram\", \"show my infrastructure\", etc.\n```\nPhase 0 (references/phase0-scanner.md) — Existing resource scan + diagram\n    ↓\nModification conversation — \"What would you like to change here?\" (natural language modification request → follow-up questions)\n    ↓\nPhase 1 (references/phase1-advisor.md) — Confirm modifications + update diagram\n    ↓\nPhase 2~4 — Same as above\n```\n\n### When Path Determination Is Ambiguous\n\nAsk the user directly:\n```\nask_user({\n  question: \"What would you like to do?\",\n  choices: [\n    \"Design a new Azure architecture (Recommended)\",\n    \"Analyze + modify existing Azure resources\"\n  ]\n})\n```\n\n---\n\n## Phase Transition Rules\n\n- Each Phase reads and follows the instructions in its corresponding `references/*.md` file\n- When transitioning between Phases, always inform the user about the next step\n- Do not skip Phases (especially the what-if between Phase 3 → Phase 4)\n- **🚨 Required condition for Phase 1 → Phase 2 transition**: `01_arch_diagram_draft.html` must have been generated using the embedded diagram engine and shown to the user. **Do not proceed to Bicep generation without a diagram.** Completing spec collection alone does not mean Phase 1 is done — Phase 1 includes diagram generation + user confirmation.\n- Modification request after deployment → return to Phase 1, not Phase 0 (Delta Confirmation Rule)\n\n## Service Coverage & Fallback\n\n### Optimized Services\nMicrosoft Foundry, Azure OpenAI, AI Search, ADLS Gen2, Key Vault, Microsoft Fabric, Azure Data Factory, VNet/Private Endpoint, AML/AI Hub\n\n### Other Azure Services\nAll supported — MS Docs are automatically consulted to generate at the same quality standard.\n**Do not send messages that cause user anxiety such as \"out of scope\" or \"best-effort\".**\n\n### Stable vs Dynamic Information Handling\n\n| Category | Handling Method | Examples |\n|----------|----------------|---------|\n| **Stable** | Reference files first | `isHnsEnabled: true`, PE triple set |\n| **Dynamic** | **Always fetch MS Docs** | API version, model availability, SKU, region |\n\n## Quick Reference\n\n| File | Role |\n|------|------|\n| `references/phase0-scanner.md` | Existing resource scan + relationship inference + diagram |\n| `references/phase1-advisor.md` | Interactive architecture design + fact checking |\n| `references/bicep-generator.md` | Bicep code generation rules |\n| `references/bicep-reviewer.md` | Code review checklist |\n| `references/phase4-deployer.md` | validate → what-if → deploy |\n| `references/service-gotchas.md` | Required properties, PE mappings |\n| `references/azure-dynamic-sources.md` | MS Docs URL registry |\n| `references/azure-common-patterns.md` | PE/security/naming patterns |\n| `references/ai-data.md` | AI/Data service guide |","tags":["azure","architecture","autopilot","awesome","copilot","github","agent-skills","agents","custom-agents","github-copilot","hacktoberfest","prompt-engineering"],"capabilities":["skill","source-github","skill-azure-architecture-autopilot","topic-agent-skills","topic-agents","topic-awesome","topic-custom-agents","topic-github-copilot","topic-hacktoberfest","topic-prompt-engineering"],"categories":["awesome-copilot"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/github/awesome-copilot/azure-architecture-autopilot","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add github/awesome-copilot","source_repo":"https://github.com/github/awesome-copilot","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 33270 github stars · SKILL.md body (6,603 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:52:05.595Z","embedding":null,"createdAt":"2026-04-18T20:33:19.006Z","updatedAt":"2026-05-18T18:52:05.595Z","lastSeenAt":"2026-05-18T18:52:05.595Z","tsv":"'0':552,720 '01_arch_diagram_draft.html':668 '1':386,505,576,664,700,704,717 '2':512,583,666 '3':518,657 '4':525,659 '605':99 'access':109 'account':474 'action':415 'adapt':210 'adl':735 'agent':254,266,290 'ai':733 'ai/data':857 'alia':332 'alon':695 'alway':638,801 'ambigu':592 'aml/ai':746 'ana':46 'analysi':535 'analyz':12,60,537,540,613 'anxieti':772 'api':805 'architectur':3,20,43,48,65,471,508,611,824 'array':251 'ask':159,242,244,432,443,593,597 'auto':18 'auto-gener':17 'automat':113,486,756 'autopilot':4 'avail':808 'az':295,342,352,356,473,476,481 'az.cmd':379 'azcmd':346,355,359,391 'azex':360,390,392 'azur':2,6,14,38,47,54,101,369,375,610,616,731,741,749 'azure-architecture-autopilot':1 'b':533 'best':780 'best-effort':779 'bicep':29,164,297,514,687,829 'blockquot':410 'bold':412 'branch':485 'build':496,502 'builder':49 'bundl':90 'cach':311 'cannot':268 'categori':787 'caus':422,770 'chang':565 'check':277,827 'checklist':836 'childitem':363 'choic':246,470,606 'cli':343,376 'cli2':370 'code':515,520,830,834 'collect':694 'command':258,326,351 'comment':165 'compil':522 'complet':417,692 'condit':661 'confirm':472,578,709,722 'consult':757 'content':228 'convers':25,559 'copi':194 'correspond':630 'coverag':725 'creat':35,498 'current':541 'data':742 'delta':721 'deploy':27,71,501,531,713,842 'design':5,45,53,494,509,607,825 'detail':420 'detect':116,117 'determin':487,590 'diagram':21,73,97,396,401,459,510,546,557,581,676,691,706,821 'direct':87,286,333,596 'discov':304,318 'discoveri':241,294,335,458 'doc':233,281,455,466,754,804,850 'document':175,198 'done':702 'draw':544 'dynam':784,800 'effort':781 'embed':76,395,675 'emoji':411 'endpoint':745 'engin':74,397,677 'english':155,158,168,179 'env':336,365,372 'environ':221 'erroract':353,380 'especi':650 'etc':235,298,503,550 'everi':319 'exampl':172,195,790 'execut':259 'exist':13,61,534,554,615,816 'expandproperti':387 'explore/task/general-purpose':256,267 'extern':291 'fabric':740 'face':184 'fact':276,826 'fact-check':275 'factori':743 'fail':421 'fallback':726 'featur':222 'fetch':226,230,271,802 'file':453,633,793,813 'filesystem':334 'filter':378 'first':124,385,794 'folder':81 'follow':572,625 'follow-up':571 'format':413 'foundri':730 'fullnam':388 'gen2':736 'generat':19,94,402,516,672,688,707,759,831 'get':325,350,362 'get-childitem':361 'get-command':324,349 'ghcp':220 'group':477,482 'guid':219,859 'handl':786,788 'highest':138 'highest-prior':137 'html':96 'hub':747 'icon':102 'immedi':106 'includ':705 'infer':820 'inform':435,639,785 'infrastructur':7,55,549 'input':430 'instal':84,112 'instruct':170,627 'interact':95,507,823 'ishnsen':795 'key':737 'korean':146,149 'languag':10,58,115,119,133,191,216,568 'like':563,603 'list':478,483 'localappdata':337,373 'lookup':234,282 'main':289 'map':847 'markdown':414 'match':187 'md':632 'mean':698 'messag':125,768 'method':789 'microsoft':367,729,739 'model':807 'model/sku':463 'modif':69,536,558,569,579,710 'modifi':538,614 'modul':460 'ms':232,280,454,465,753,803,849 'must':186,247,283,669 'name':224,449 'natur':9,57,567 'need':85,436 'network':108 'new':44,493,495,609 'next':439,468,644 'note':225 'null':347 'object':384 'offici':100 'often':300 'openai':732 'optim':727 'output':185 'packag':111 'parallel':423,442 'path':293,303,344,364,394,457,461,484,491,532,589 'pattern':855 'pe':797,846 'pe/security/naming':854 'perform':285 'phase':309,504,511,517,524,551,575,582,618,622,637,649,656,658,663,665,699,703,716,719 'pip':83 'pipelin':51 'powershel':260,262,345 'preload':424,434,446 'principl':140,425 'prioriti':139,341 'proceed':67,685 'program':338,374 'programfil':366 'progress':161,406 'project':448 'properti':845 'provid':127 'python':91,296,327,339,393,456 'qualiti':763 'question':445,469,574,599 'quick':811 'rag':42 're':317 're-discov':316 'read':623 'readi':103 'reason':416 'recommend':612 'refer':208,398,452,631,792,812 'references/ai-data.md':856 'references/azure-common-patterns.md':853 'references/azure-dynamic-sources.md':848 'references/bicep-generator.md':513,828 'references/bicep-reviewer.md':519,833 'references/phase0-scanner.md':553,815 'references/phase1-advisor.md':405,506,577,822 'references/phase4-deployer.md':526,837 'references/service-gotchas.md':843 'refin':22 'region':810 'registri':852 'relationship':819 'report':163 'request':490,570,711 'requir':279,408,660,844 'resourc':15,62,542,555,617,817 'respond':147,156 'respons':130 'result':313,418 'return':714 'review':521,835 'risk':328 'role':814 'rule':620,723,832 'scan':450,543,556,818 'scope':451,777 'script':80,92 'sdks':368 'search':237,239,274,734 'section':403 'select':383,464,480 'select-object':382 'send':767 'servic':724,728,750,858 'set':39,499,799 'shell':257 'show':547 'show/list':475 'shown':679 'silentlycontinu':354,381 'simultan':447 'skill':34,79 'skill-azure-architecture-autopilot' 'skip':648 'sku':809 'source-github' 'spec':693 'stabl':782,791 'standard':764 'start':307 'step':440,645 'store':331 'string':250 'structur':206 'sub':253,265 'sub-ag':252,264 'subscript':479 'subsequ':129 'support':752 'take':340 'task':255 'text':211 'time':320 'tool':217,223,292 'topic-agent-skills' 'topic-agents' 'topic-awesome' 'topic-custom-agents' 'topic-github-copilot' 'topic-hacktoberfest' 'topic-prompt-engineering' 'transit':619,635,667 'trigger':497,539 'tripl':798 'true':796 'updat':162,407,580 'url':227,240,851 'usag':218 'use':8,32,56,88,105,203,269,323,409,673 'user':114,122,143,152,160,183,189,202,214,243,245,429,433,444,489,595,598,641,682,708,771 'user-fac':182 'valid':527,838 'vault':738 'verbatim':199 'verif':462,523 'version':806 'via':431 'visual':64 'vnet/private':744 'vs':783 'wait':427 'warn':419 'wbin':371,377 'web':229,236,238,270,273 'what-if':528,652,839 'window':261,330 'within':77 'without':107,689 'would':561,601 'write':144,153 'written':177 'x':36 '~4':584","prices":[{"id":"c1e2293f-2cc9-4775-95f1-10fdbab3a84a","listingId":"a89c676b-2d4d-463e-a785-5d4576233e94","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"github","category":"awesome-copilot","install_from":"skills.sh"},"createdAt":"2026-04-18T20:33:19.006Z"}],"sources":[{"listingId":"a89c676b-2d4d-463e-a785-5d4576233e94","source":"github","sourceId":"github/awesome-copilot/azure-architecture-autopilot","sourceUrl":"https://github.com/github/awesome-copilot/tree/main/skills/azure-architecture-autopilot","isPrimary":false,"firstSeenAt":"2026-04-18T21:48:22.724Z","lastSeenAt":"2026-05-18T18:52:05.595Z"},{"listingId":"a89c676b-2d4d-463e-a785-5d4576233e94","source":"skills_sh","sourceId":"github/awesome-copilot/azure-architecture-autopilot","sourceUrl":"https://skills.sh/github/awesome-copilot/azure-architecture-autopilot","isPrimary":true,"firstSeenAt":"2026-04-18T20:33:19.006Z","lastSeenAt":"2026-05-07T22:40:37.475Z"}],"details":{"listingId":"a89c676b-2d4d-463e-a785-5d4576233e94","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"github","slug":"azure-architecture-autopilot","github":{"repo":"github/awesome-copilot","stars":33270,"topics":["agent-skills","agents","ai","awesome","custom-agents","github-copilot","hacktoberfest","prompt-engineering"],"license":"mit","html_url":"https://github.com/github/awesome-copilot","pushed_at":"2026-05-18T01:26:59Z","description":"Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.","skill_md_sha":"ac981d0754e86d353bf84baf46c3f8e3d37d7889","skill_md_path":"skills/azure-architecture-autopilot/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/github/awesome-copilot/tree/main/skills/azure-architecture-autopilot"},"layout":"multi","source":"github","category":"awesome-copilot","frontmatter":{"name":"azure-architecture-autopilot","description":"Design Azure infrastructure using natural language, or analyze existing Azure resources to auto-generate architecture diagrams, refine them through conversation, and deploy with Bicep.  When to use this skill: - \"Create X on Azure\", \"Set up a RAG architecture\" (new design) - \"Analyze my current Azure infrastructure\", \"Draw a diagram for rg-xxx\" (existing analysis) - \"Foundry is slow\", \"I want to reduce costs\", \"Strengthen security\" (natural language modification) - Azure resource deployment, Bicep template generation, IaC code generation - Microsoft Foundry, AI Search, OpenAI, Fabric, ADLS Gen2, Databricks, and all Azure services"},"skills_sh_url":"https://skills.sh/github/awesome-copilot/azure-architecture-autopilot"},"updatedAt":"2026-05-18T18:52:05.595Z"}}