{"id":"c4b47161-e550-45b1-8409-f4a6a11e8f3a","shortId":"VTbTf5","kind":"skill","title":"azure-ai-vision","tagline":"Expert knowledge for Azure AI Vision development including decision making, limits & quotas, configuration, integrations & coding patterns, and deployment. Use when using Image Analysis, Read OCR containers, smart-crop thumbnails, background removal, or video frame analysis, and ","description":"# Azure AI Vision Skill\n\nThis skill provides expert guidance for Azure AI Vision. Covers decision making, limits & quotas, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.\n\n## How to Use This Skill\n\n> **IMPORTANT for Agent**: Use the **Category Index** below to locate relevant sections. For categories with line ranges (e.g., `L35-L120`), use `read_file` with the specified lines. For categories with file links (e.g., `[security.md](security.md)`), use `read_file` on the linked reference file\n\n> **IMPORTANT for Agent**: If `metadata.generated_at` is more than 3 months old, suggest the user pull the latest version from the repository. If `mcp_microsoftdocs` tools are not available, suggest the user install it: [Installation Guide](https://github.com/MicrosoftDocs/mcp/blob/main/README.md)\n\nThis skill requires **network access** to fetch documentation content:\n- **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown.\n- **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown.\n\n## Category Index\n\n| Category | Lines | Description |\n|----------|-------|-------------|\n| Decision Making | L33-L39 | Guides for planning and executing migrations and upgrades between Azure Vision Image Analysis and Read OCR versions/containers, including breaking changes and app update steps. |\n| Limits & Quotas | L40-L50 | Limits, thresholds, and taxonomies for Image Analysis: category lists, adult content scores, object/people detection constraints, smart-crop behavior, and OCR language support. |\n| Configuration | L51-L56 | Configuring Vision Read OCR containers and setting up Azure Blob Storage access for image input, including environment settings, storage permissions, and connection details. |\n| Integrations & Coding Patterns | L57-L67 | How to call and configure Azure Vision/Read APIs and SDKs for OCR, embeddings, thumbnails, background removal, domain models, and live video frame analysis. |\n| Deployment | L68-L71 | Installing, configuring, and running the Azure AI Vision Read OCR container locally or on-premises, including prerequisites, deployment steps, and runtime settings. |\n\n### Decision Making\n| Topic | URL |\n|-------|-----|\n| Plan migration from Azure Vision Image Analysis | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/migration-options |\n| Migrate to Azure Vision Read OCR container v3.x | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/read-container-migration-guide |\n| Upgrade applications from Read v2.x to v3.0 | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/upgrade-api-versions |\n\n### Limits & Quotas\n| Topic | URL |\n|-------|-----|\n| Reference taxonomy categories for Azure Vision | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/category-taxonomy |\n| Understand Image Analysis 3.2 categorization taxonomy limits | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-categorizing-images |\n| Interpret adult content detection scores and thresholds | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-detecting-adult-content |\n| Use object detection and understand feature limits | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-object-detection |\n| Understand Image Analysis 4.0 object detection limits | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-object-detection-40 |\n| Use people detection and understand its limits | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-people-detection |\n| Check supported languages for Azure Vision OCR | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/language-support |\n\n### Configuration\n| Topic | URL |\n|-------|-----|\n| Configure Azure Vision Read OCR containers | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/computer-vision-resource-container-config |\n| Configure Azure Blob Storage for Vision image retrieval | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/blob-storage-search |\n\n### Integrations & Coding Patterns\n| Topic | URL |\n|-------|-----|\n| Call domain-specific models with Azure Vision | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-detecting-domain-content |\n| Analyze live video frames with Azure Vision API | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/analyze-video |\n| Call and configure Image Analysis 3.2 API | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/call-analyze-image |\n| Call and configure Image Analysis 4.0 API | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/call-analyze-image-40 |\n| Call and configure Azure Vision Read v3.2 API | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/call-read-api |\n| Use multimodal embeddings for image retrieval | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/image-retrieval |\n| Use OCR client libraries for text extraction | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/quickstarts-sdk/client-library |\n\n### Deployment\n| Topic | URL |\n|-------|-----|\n| Install and run Azure Vision Read OCR container | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/computer-vision-how-to-install-containers |","tags":["azure","vision","agent","skills","microsoftdocs","agent-skills","agentic-skills","agentskill","ai-agents","ai-coding","azure-functions","azure-kubernetes-service"],"capabilities":["skill","source-microsoftdocs","skill-azure-ai-vision","topic-agent","topic-agent-skills","topic-agentic-skills","topic-agentskill","topic-ai-agents","topic-ai-coding","topic-azure","topic-azure-functions","topic-azure-kubernetes-service","topic-azure-openai","topic-azure-sql-database","topic-azure-storage"],"categories":["Agent-Skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/MicrosoftDocs/Agent-Skills/azure-ai-vision","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add MicrosoftDocs/Agent-Skills","source_repo":"https://github.com/MicrosoftDocs/Agent-Skills","install_from":"skills.sh"}},"qualityScore":"0.698","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 497 github stars · SKILL.md body (5,579 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":"2026-04-22T12:53:29.097Z","embedding":null,"createdAt":"2026-04-18T21:58:04.684Z","updatedAt":"2026-04-22T12:53:29.097Z","lastSeenAt":"2026-04-22T12:53:29.097Z","tsv":"'/en-us/azure/ai-services/computer-vision/category-taxonomy':400 '/en-us/azure/ai-services/computer-vision/computer-vision-how-to-install-containers':574 '/en-us/azure/ai-services/computer-vision/computer-vision-resource-container-config':472 '/en-us/azure/ai-services/computer-vision/concept-categorizing-images':410 '/en-us/azure/ai-services/computer-vision/concept-detecting-adult-content':420 '/en-us/azure/ai-services/computer-vision/concept-detecting-domain-content':499 '/en-us/azure/ai-services/computer-vision/concept-object-detection':430 '/en-us/azure/ai-services/computer-vision/concept-object-detection-40':440 '/en-us/azure/ai-services/computer-vision/concept-people-detection':450 '/en-us/azure/ai-services/computer-vision/how-to/analyze-video':510 '/en-us/azure/ai-services/computer-vision/how-to/blob-storage-search':483 '/en-us/azure/ai-services/computer-vision/how-to/call-analyze-image':520 '/en-us/azure/ai-services/computer-vision/how-to/call-analyze-image-40':530 '/en-us/azure/ai-services/computer-vision/how-to/call-read-api':541 '/en-us/azure/ai-services/computer-vision/how-to/image-retrieval':550 '/en-us/azure/ai-services/computer-vision/language-support':460 '/en-us/azure/ai-services/computer-vision/migration-options':366 '/en-us/azure/ai-services/computer-vision/quickstarts-sdk/client-library':560 '/en-us/azure/ai-services/computer-vision/read-container-migration-guide':377 '/en-us/azure/ai-services/computer-vision/upgrade-api-versions':387 '/microsoftdocs/mcp/blob/main/readme.md)':165 '3':136 '3.2':404,516 '4.0':434,526 'accept':204 'access':170,285 'adult':256,412 'agent':85,129,188,202 'ai':3,9,43,53,336 'analysi':27,40,230,253,325,363,403,433,515,525 'analyz':500 'api':310,507,517,527,538 'app':239 'applic':379 'avail':155 'azur':2,8,42,52,227,282,308,335,360,369,396,455,465,474,495,505,534,567 'azure-ai-vis':1 'background':35,317 'behavior':265 'blob':283,475 'break':236 'call':305,489,511,521,531 'capabl':77 'categor':405 'categori':88,96,112,208,210,254,394 'chang':237 'check':451 'client':553 'code':19,62,298,485 'combin':67 'configur':17,60,270,274,307,331,461,464,473,513,523,533 'connect':295 'constraint':261 'contain':30,278,340,373,469,571 'content':72,174,257,413 'cover':55 'crop':33,264 'decis':13,56,213,353 'deploy':22,65,326,348,561 'descript':212 'detail':296 'detect':260,414,423,436,443 'develop':11 'doc':180 'document':75,173 'domain':319,491 'domain-specif':490 'e.g':100,116 'embed':315,544 'environ':290 'execut':222 'expert':5,49 'extract':557 'fallback':192 'featur':426 'fetch':76,172,181,194 'file':106,114,121,126 'frame':39,324,503 'github.com':164 'github.com/microsoftdocs/mcp/blob/main/readme.md)':163 'guid':162,218 'guidanc':50 'imag':26,229,252,287,362,402,432,479,514,524,546 'import':83,127 'includ':12,235,289,346 'index':89,209 'input':288 'instal':159,161,330,564 'integr':18,61,297,484 'interpret':411 'knowledg':6 'l120':103 'l33':216 'l33-l39':215 'l35':102 'l35-l120':101 'l39':217 'l40':245 'l40-l50':244 'l50':246 'l51':272 'l51-l56':271 'l56':273 'l57':301 'l57-l67':300 'l67':302 'l68':328 'l68-l71':327 'l71':329 'languag':268,453 'latest':144 'learn':187,201 'learn-agent-skil':186,200 'learn.microsoft.com':365,376,386,399,409,419,429,439,449,459,471,482,498,509,519,529,540,549,559,573 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/category-taxonomy':398 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/computer-vision-how-to-install-containers':572 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/computer-vision-resource-container-config':470 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-categorizing-images':408 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-detecting-adult-content':418 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-detecting-domain-content':497 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-object-detection':428 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-object-detection-40':438 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-people-detection':448 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/analyze-video':508 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/blob-storage-search':481 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/call-analyze-image':518 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/call-analyze-image-40':528 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/call-read-api':539 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/image-retrieval':548 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/language-support':458 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/migration-options':364 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/quickstarts-sdk/client-library':558 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/read-container-migration-guide':375 'learn.microsoft.com/en-us/azure/ai-services/computer-vision/upgrade-api-versions':385 'librari':554 'limit':15,58,242,247,388,407,427,437,447 'line':98,110,211 'link':115,124 'list':255 'live':322,501 'local':68,341 'locat':92 'make':14,57,214,354 'markdown':191,207 'mcp':150,177 'metadata.generated':131 'microsoft':179 'microsoftdoc':151,178 'migrat':223,358,367 'model':320,493 'month':137 'multimod':543 'network':169 'object':422,435 'object/people':259 'ocr':29,233,267,277,314,339,372,457,468,552,570 'old':138 'on-premis':343 'pattern':20,63,299,486 'peopl':442 'permiss':293 'plan':220,357 'prefer':175 'premis':345 'prerequisit':347 'provid':48 'pull':142 'queri':183,197 'quick':70 'quick-refer':69 'quota':16,59,243,389 'rang':99 'read':28,105,120,232,276,338,371,381,467,536,569 'refer':71,125,392 'relev':93 'remot':74 'remov':36,318 'repositori':148 'requir':168 'retriev':480,547 'return':190,206 'run':333,566 'runtim':351 'score':258,415 'sdks':312 'section':94 'security.md':117,118 'set':280,291,352 'skill':45,47,82,167,189,203 'skill-azure-ai-vision' 'smart':32,263 'smart-crop':31,262 'source-microsoftdocs' 'specif':492 'specifi':109 'step':241,349 'storag':284,292,476 'string':184,198 'suggest':139,156 'support':269,452 'taxonomi':250,393,406 'text':556 'text/markdown':205 'threshold':248,417 'thumbnail':34,316 'tool':152 'topic':355,390,462,487,562 'topic-agent' 'topic-agent-skills' 'topic-agentic-skills' 'topic-agentskill' 'topic-ai-agents' 'topic-ai-coding' 'topic-azure' 'topic-azure-functions' 'topic-azure-kubernetes-service' 'topic-azure-openai' 'topic-azure-sql-database' 'topic-azure-storage' 'understand':401,425,431,445 'updat':240 'upgrad':225,378 'url':356,391,463,488,563 'use':23,25,80,86,104,119,176,193,421,441,542,551 'user':141,158 'v2.x':382 'v3.0':384 'v3.2':537 'v3.x':374 'version':145 'versions/containers':234 'video':38,323,502 'vision':4,10,44,54,228,275,337,361,370,397,456,466,478,496,506,535,568 'vision/read':309 'webpag':195","prices":[{"id":"b1113065-dc8d-4466-b0d2-4bb3dd91690c","listingId":"c4b47161-e550-45b1-8409-f4a6a11e8f3a","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"MicrosoftDocs","category":"Agent-Skills","install_from":"skills.sh"},"createdAt":"2026-04-18T21:58:04.684Z"}],"sources":[{"listingId":"c4b47161-e550-45b1-8409-f4a6a11e8f3a","source":"github","sourceId":"MicrosoftDocs/Agent-Skills/azure-ai-vision","sourceUrl":"https://github.com/MicrosoftDocs/Agent-Skills/tree/main/skills/azure-ai-vision","isPrimary":false,"firstSeenAt":"2026-04-18T21:58:04.684Z","lastSeenAt":"2026-04-22T12:53:29.097Z"}],"details":{"listingId":"c4b47161-e550-45b1-8409-f4a6a11e8f3a","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"MicrosoftDocs","slug":"azure-ai-vision","github":{"repo":"MicrosoftDocs/Agent-Skills","stars":497,"topics":["agent","agent-skills","agentic-skills","agentskill","ai","ai-agents","ai-coding","azure","azure-functions","azure-kubernetes-service","azure-openai","azure-sql-database","azure-storage","azure-virtual-machine","claude-code","github-copilot","microsoft-learn","openai-codex","skills"],"license":"cc-by-4.0","html_url":"https://github.com/MicrosoftDocs/Agent-Skills","pushed_at":"2026-04-22T01:37:27Z","description":"Curated Agent Skills for Microsoft & Azure – giving AI coding assistants structured, real-time expertise from Microsoft Learn docs.","skill_md_sha":"e9c3dd0ed9be0f2123c716aa2531b6102552b062","skill_md_path":"skills/azure-ai-vision/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/MicrosoftDocs/Agent-Skills/tree/main/skills/azure-ai-vision"},"layout":"multi","source":"github","category":"Agent-Skills","frontmatter":{"name":"azure-ai-vision","description":"Expert knowledge for Azure AI Vision development including decision making, limits & quotas, configuration, integrations & coding patterns, and deployment. Use when using Image Analysis, Read OCR containers, smart-crop thumbnails, background removal, or video frame analysis, and other Azure AI Vision related development tasks. Not for Azure AI Custom Vision (use azure-custom-vision), Azure AI Video Indexer (use azure-video-indexer), Azure AI Document Intelligence (use azure-document-intelligence), Azure AI Immersive Reader (use azure-immersive-reader).","compatibility":"Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation."},"skills_sh_url":"https://skills.sh/MicrosoftDocs/Agent-Skills/azure-ai-vision"},"updatedAt":"2026-04-22T12:53:29.097Z"}}