[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AR5DAEHA221XE6JA6WAXF":3,"skill-same:01M69AR5DAEHA221XE6JA6WAXF":89},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M69AR5DAEHA221XE6JA6WAXF","azure-ai-contentunderstanding-py",null,"Azure AI Content Understanding SDK for Python. Use for multimodal content extraction from documents, images, audio, and video.\nTriggers: \"azure-ai-contentunderstanding\", \"ContentUnderstandingClient\", \"multimodal analysis\", \"document extraction\", \"video analysis\", \"audio transcription\".","microsoft\u002Fskills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69AJYYW4E1RMSYCQDJ4FJSH",3204,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-ai-contentunderstanding-py\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,9,45],"azure ai","azure","azure ai contentunderstanding py","analysis","for","ai content","triggers","transcription","document","images","use","Audio","Video","python","extraction","content","multimodal","documents","sdk","2026-11-10 10:12:30",false,"---\nname: azure-ai-contentunderstanding-py\ndescription: |\n  Azure AI Content Understanding SDK for Python. Use for multimodal content extraction from documents, images, audio, and video.\n  Triggers: \"azure-ai-contentunderstanding\", \"ContentUnderstandingClient\", \"multimodal analysis\", \"document extraction\", \"video analysis\", \"audio transcription\".\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n  package: azure-ai-contentunderstanding\n---\n\n# Azure AI Content Understanding SDK for Python\n\nMultimodal AI service that extracts semantic content from documents, video, audio, and image files for RAG and automated workflows.\n\n## Installation\n\n```bash\npip install azure-ai-contentunderstanding\n```\n\n## Environment Variables\n\n```bash\nCONTENTUNDERSTANDING_ENDPOINT=https:\u002F\u002F\u003Cresource>.cognitiveservices.azure.com\u002F  # Required for all auth methods\nAZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production\n```\n\n## Authentication & Lifecycle\n\n> **? Two rules apply to every code sample below:**\n>\n> 1. **Prefer `DefaultAzureCredential`.** It works locally (Azure CLI \u002F VS Code \u002F Developer CLI) and in Azure (managed identity, workload identity) with no code change. Avoid connection strings, account\u002FAPI keys — they bypass Entra audit and rotation.\n>    - Local dev: `DefaultAzureCredential` works as-is.\n>    - Production: set `AZURE_TOKEN_CREDENTIALS=prod` (or `AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>`) to constrain the credential chain to production-safe credentials.\n> 2. **Wrap every client in a context manager** so HTTP transports, sockets, and token caches are released deterministically:\n>    - Sync: `with \u003CClient>(...) as client:`\n>    - Async: `async with \u003CClient>(...) as client:` **and** `async with DefaultAzureCredential() as credential:` (from `azure.identity.aio`)\n>\n> Snippets may abbreviate this setup, but production code should always follow both rules.\n\n```python\nimport os\nfrom azure.ai.contentunderstanding import ContentUnderstandingClient\nfrom azure.identity import DefaultAzureCredential, ManagedIdentityCredential\n\nendpoint = os.environ[\"CONTENTUNDERSTANDING_ENDPOINT\"]\n# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>\ncredential = DefaultAzureCredential(require_envvar=True)\n# Or use a specific credential directly in production:\n# See https:\u002F\u002Flearn.microsoft.com\u002Fpython\u002Fapi\u002Foverview\u002Fazure\u002Fidentity-readme?view=azure-python#credential-classes\n# credential = ManagedIdentityCredential()\nwith ContentUnderstandingClient(endpoint=endpoint, credential=credential) as client:\n    analyzers = list(client.list_analyzers())\n```\n\n## Core Workflow\n\nContent Understanding operations are asynchronous long-running operations:\n\n1. **Begin Analysis** — Start the analysis operation with `begin_analyze()` (returns a poller)\n2. **Poll for Results** — Poll until analysis completes (SDK handles this with `.result()`)\n3. **Process Results** — Extract structured results from `AnalyzeResult.contents`\n\n## Prebuilt Analyzers\n\n| Analyzer | Content Type | Purpose |\n|----------|--------------|---------|\n| `prebuilt-documentSearch` | Documents | Extract markdown for RAG applications |\n| `prebuilt-imageSearch` | Images | Extract content from images |\n| `prebuilt-audioSearch` | Audio | Transcribe audio with timing |\n| `prebuilt-videoSearch` | Video | Extract frames, transcripts, summaries |\n| `prebuilt-invoice` | Documents | Extract invoice fields |\n\n## Analyze Document\n\n```python\nimport os\nfrom azure.ai.contentunderstanding import ContentUnderstandingClient\nfrom azure.ai.contentunderstanding.models import AnalyzeInput\nfrom azure.identity import DefaultAzureCredential\n\nendpoint = os.environ[\"CONTENTUNDERSTANDING_ENDPOINT\"]\nwith ContentUnderstandingClient(\n    endpoint=endpoint,\n    credential=DefaultAzureCredential()\n) as client:\n    # Analyze document from URL\n    poller = client.begin_analyze(\n        analyzer_id=\"prebuilt-documentSearch\",\n        inputs=[AnalyzeInput(url=\"https:\u002F\u002Fexample.com\u002Fdocument.pdf\")]\n    )\n\n    result = poller.result()\n\n    # Access markdown content (contents is a list)\n    content = result.contents[0]\n    print(content.markdown)\n```\n\n## Access Document Content Details\n\n```python\nfrom azure.ai.contentunderstanding.models import MediaContentKind, DocumentContent\n\ncontent = result.contents[0]\nif content.kind == MediaContentKind.DOCUMENT:\n    document_content: DocumentContent = content  # type: ignore\n    print(document_content.start_page_number)\n```\n\n## Analyze Image\n\n```python\nfrom azure.ai.contentunderstanding.models import AnalyzeInput\n\npoller = client.begin_analyze(\n    analyzer_id=\"prebuilt-imageSearch\",\n    inputs=[AnalyzeInput(url=\"https:\u002F\u002Fexample.com\u002Fimage.jpg\")]\n)\nresult = poller.result()\ncontent = result.contents[0]\nprint(content.markdown)\n```\n\n## Analyze Video\n\n```python\nfrom azure.ai.contentunderstanding.models import AnalyzeInput\n\npoller = client.begin_analyze(\n    analyzer_id=\"prebuilt-videoSearch\",\n    inputs=[AnalyzeInput(url=\"https:\u002F\u002Fexample.com\u002Fvideo.mp4\")]\n)\n\nresult = poller.result()\n\n# Access video content (AudioVisualContent)\ncontent = result.contents[0]\n\n# Get transcript phrases with timing\nfor phrase in content.transcript_phrases:\n    print(f\"[{phrase.start_time} - {phrase.end_time}]: {phrase.text}\")\n\n# Get key frames (for video)\nfor frame in content.key_frames:\n    print(f\"Frame at {frame.time}: {frame.description}\")\n```\n\n## Analyze Audio\n\n```python\nfrom azure.ai.contentunderstanding.models import AnalyzeInput\n\npoller = client.begin_analyze(\n    analyzer_id=\"prebuilt-audioSearch\",\n    inputs=[AnalyzeInput(url=\"https:\u002F\u002Fexample.com\u002Faudio.mp3\")]\n)\n\nresult = poller.result()\n\n# Access audio transcript\ncontent = result.contents[0]\nfor phrase in content.transcript_phrases:\n    print(f\"[{phrase.start_time}] {phrase.text}\")\n```\n\n## Custom Analyzers\n\nCreate custom analyzers with field schemas for specialized extraction:\n\n```python\n# Create custom analyzer\nanalyzer = client.create_analyzer(\n    analyzer_id=\"my-invoice-analyzer\",\n    analyzer={\n        \"description\": \"Custom invoice analyzer\",\n        \"base_analyzer_id\": \"prebuilt-documentSearch\",\n        \"field_schema\": {\n            \"fields\": {\n                \"vendor_name\": {\"type\": \"string\"},\n                \"invoice_total\": {\"type\": \"number\"},\n                \"line_items\": {\n                    \"type\": \"array\",\n                    \"items\": {\n                        \"type\": \"object\",\n                        \"properties\": {\n                            \"description\": {\"type\": \"string\"},\n                            \"amount\": {\"type\": \"number\"}\n                        }\n                    }\n                }\n            }\n        }\n    }\n)\n\n# Use custom analyzer\nfrom azure.ai.contentunderstanding.models import AnalyzeInput\n\npoller = client.begin_analyze(\n    analyzer_id=\"my-invoice-analyzer\",\n    inputs=[AnalyzeInput(url=\"https:\u002F\u002Fexample.com\u002Finvoice.pdf\")]\n)\n\nresult = poller.result()\n\n# Access extracted fields\nprint(result.fields[\"vendor_name\"])\nprint(result.fields[\"invoice_total\"])\n```\n\n## Analyzer Management\n\n```python\n# List all analyzers\nanalyzers = client.list_analyzers()\nfor analyzer in analyzers:\n    print(f\"{analyzer.analyzer_id}: {analyzer.description}\")\n\n# Get specific analyzer\nanalyzer = client.get_analyzer(\"prebuilt-documentSearch\")\n\n# Delete custom analyzer\nclient.delete_analyzer(\"my-custom-analyzer\")\n```\n\n## Async Client\n\n```python\nimport asyncio\nimport os\nfrom azure.ai.contentunderstanding.aio import ContentUnderstandingClient\nfrom azure.ai.contentunderstanding.models import AnalyzeInput\nfrom azure.identity.aio import DefaultAzureCredential\n\nasync def analyze_document():\n    endpoint = os.environ[\"CONTENTUNDERSTANDING_ENDPOINT\"]\n    async with DefaultAzureCredential() as credential:\n        async with ContentUnderstandingClient(\n            endpoint=endpoint,\n            credential=credential\n        ) as client:\n            poller = await client.begin_analyze(\n                analyzer_id=\"prebuilt-documentSearch\",\n                inputs=[AnalyzeInput(url=\"https:\u002F\u002Fexample.com\u002Fdoc.pdf\")]\n            )\n            result = await poller.result()\n            content = result.contents[0]\n            return content.markdown\n\nasyncio.run(analyze_document())\n```\n\n## Content Types\n\n| Class | For | Provides |\n|-------|-----|----------|\n| `DocumentContent` | PDF, images, Office docs | Pages, tables, figures, paragraphs |\n| `AudioVisualContent` | Audio, video files | Transcript phrases, timing, key frames |\n\nBoth derive from `MediaContent` which provides basic info and markdown representation.\n\n## Model Imports\n\n```python\nfrom azure.ai.contentunderstanding.models import (\n    AnalyzeInput,\n    AnalyzeResult,\n    MediaContentKind,\n    DocumentContent,\n    AudioVisualContent,\n)\n```\n\n## Client Types\n\n| Client | Purpose |\n|--------|---------|\n| `ContentUnderstandingClient` | Sync client for all operations |\n| `ContentUnderstandingClient` (aio) | Async client for all operations |\n\n## Best Practices\n\n1. **Pick sync OR async and stay consistent.** Do not mix `azure.ai.contentunderstanding` sync clients with `azure.ai.contentunderstanding.aio` async clients in the same call path. Choose one mode per module.\n2. **Always use context managers for clients and async credentials.** Wrap every client in `with ContentUnderstandingClient(...) as client:` (sync) or `async with ContentUnderstandingClient(...) as client:` (async). For async `DefaultAzureCredential` from `azure.identity.aio`, also use `async with credential:` so tokens and transports are cleaned up.\n3. **Use `begin_analyze` with `AnalyzeInput`** — this is the correct method signature\n4. **Access results via `result.contents[0]`** — results are returned as a list\n5. **Use prebuilt analyzers** for common scenarios (document\u002Fimage\u002Faudio\u002Fvideo search)\n6. **Create custom analyzers** only for domain-specific field extraction\n7. **Use async client** for high-throughput scenarios with `azure.identity.aio` credentials\n8. **Handle long-running operations** — video\u002Faudio analysis can take minutes\n9. **Use URL sources** when possible to avoid upload overhead\n\n## Reference Files\n\n| File | Contents |\n|------|----------|\n| [references\u002Fcapabilities.md](references\u002Fcapabilities.md) | Additional non-hero capabilities, operation-group coverage, and production checklists. |\n| [references\u002Fnon-hero-scenarios.md](references\u002Fnon-hero-scenarios.md) | Dedicated non-hero examples for secondary\u002Fadvanced scenarios. |\n","# Azure AI Content Understanding SDK for Python\n\nMultimodal AI service that extracts semantic content from documents, video, audio, and image files for RAG and automated workflows.\n\n## Installation\n\n```bash\npip install azure-ai-contentunderstanding\n```\n\n## Environment Variables\n\n```bash\nCONTENTUNDERSTANDING_ENDPOINT=https:\u002F\u002F\u003Cresource>.cognitiveservices.azure.com\u002F  # Required for all auth methods\nAZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production\n```\n\n## Authentication & Lifecycle\n\n> **? Two rules apply to every code sample below:**\n>\n> 1. **Prefer `DefaultAzureCredential`.** It works locally (Azure CLI \u002F VS Code \u002F Developer CLI) and in Azure (managed identity, workload identity) with no code change. Avoid connection strings, account\u002FAPI keys — they bypass Entra audit and rotation.\n>    - Local dev: `DefaultAzureCredential` works as-is.\n>    - Production: set `AZURE_TOKEN_CREDENTIALS=prod` (or `AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>`) to constrain the credential chain to production-safe credentials.\n> 2. **Wrap every client in a context manager** so HTTP transports, sockets, and token caches are released deterministically:\n>    - Sync: `with \u003CClient>(...) as client:`\n>    - Async: `async with \u003CClient>(...) as client:` **and** `async with DefaultAzureCredential() as credential:` (from `azure.identity.aio`)\n>\n> Snippets may abbreviate this setup, but production code should always follow both rules.\n\n```python\nimport os\nfrom azure.ai.contentunderstanding import ContentUnderstandingClient\nfrom azure.identity import DefaultAzureCredential, ManagedIdentityCredential\n\nendpoint = os.environ[\"CONTENTUNDERSTANDING_ENDPOINT\"]\n# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>\ncredential = DefaultAzureCredential(require_envvar=True)\n# Or use a specific credential directly in production:\n# See https:\u002F\u002Flearn.microsoft.com\u002Fpython\u002Fapi\u002Foverview\u002Fazure\u002Fidentity-readme?view=azure-python#credential-classes\n# credential = ManagedIdentityCredential()\nwith ContentUnderstandingClient(endpoint=endpoint, credential=credential) as client:\n    analyzers = list(client.list_analyzers())\n```\n\n## Core Workflow\n\nContent Understanding operations are asynchronous long-running operations:\n\n1. **Begin Analysis** — Start the analysis operation with `begin_analyze()` (returns a poller)\n2. **Poll for Results** — Poll until analysis completes (SDK handles this with `.result()`)\n3. **Process Results** — Extract structured results from `AnalyzeResult.contents`\n\n## Prebuilt Analyzers\n\n| Analyzer | Content Type | Purpose |\n|----------|--------------|---------|\n| `prebuilt-documentSearch` | Documents | Extract markdown for RAG applications |\n| `prebuilt-imageSearch` | Images | Extract content from images |\n| `prebuilt-audioSearch` | Audio | Transcribe audio with timing |\n| `prebuilt-videoSearch` | Video | Extract frames, transcripts, summaries |\n| `prebuilt-invoice` | Documents | Extract invoice fields |\n\n## Analyze Document\n\n```python\nimport os\nfrom azure.ai.contentunderstanding import ContentUnderstandingClient\nfrom azure.ai.contentunderstanding.models import AnalyzeInput\nfrom azure.identity import DefaultAzureCredential\n\nendpoint = os.environ[\"CONTENTUNDERSTANDING_ENDPOINT\"]\nwith ContentUnderstandingClient(\n    endpoint=endpoint,\n    credential=DefaultAzureCredential()\n) as client:\n    # Analyze document from URL\n    poller = client.begin_analyze(\n        analyzer_id=\"prebuilt-documentSearch\",\n        inputs=[AnalyzeInput(url=\"https:\u002F\u002Fexample.com\u002Fdocument.pdf\")]\n    )\n\n    result = poller.result()\n\n    # Access markdown content (contents is a list)\n    content = result.contents[0]\n    print(content.markdown)\n```\n\n## Access Document Content Details\n\n```python\nfrom azure.ai.contentunderstanding.models import MediaContentKind, DocumentContent\n\ncontent = result.contents[0]\nif content.kind == MediaContentKind.DOCUMENT:\n    document_content: DocumentContent = content  # type: ignore\n    print(document_content.start_page_number)\n```\n\n## Analyze Image\n\n```python\nfrom azure.ai.contentunderstanding.models import AnalyzeInput\n\npoller = client.begin_analyze(\n    analyzer_id=\"prebuilt-imageSearch\",\n    inputs=[AnalyzeInput(url=\"https:\u002F\u002Fexample.com\u002Fimage.jpg\")]\n)\nresult = poller.result()\ncontent = result.contents[0]\nprint(content.markdown)\n```\n\n## Analyze Video\n\n```python\nfrom azure.ai.contentunderstanding.models import AnalyzeInput\n\npoller = client.begin_analyze(\n    analyzer_id=\"prebuilt-videoSearch\",\n    inputs=[AnalyzeInput(url=\"https:\u002F\u002Fexample.com\u002Fvideo.mp4\")]\n)\n\nresult = poller.result()\n\n# Access video content (AudioVisualContent)\ncontent = result.contents[0]\n\n# Get transcript phrases with timing\nfor phrase in content.transcript_phrases:\n    print(f\"[{phrase.start_time} - {phrase.end_time}]: {phrase.text}\")\n\n# Get key frames (for video)\nfor frame in content.key_frames:\n    print(f\"Frame at {frame.time}: {frame.description}\")\n```\n\n## Analyze Audio\n\n```python\nfrom azure.ai.contentunderstanding.models import AnalyzeInput\n\npoller = client.begin_analyze(\n    analyzer_id=\"prebuilt-audioSearch\",\n    inputs=[AnalyzeInput(url=\"https:\u002F\u002Fexample.com\u002Faudio.mp3\")]\n)\n\nresult = poller.result()\n\n# Access audio transcript\ncontent = result.contents[0]\nfor phrase in content.transcript_phrases:\n    print(f\"[{phrase.start_time}] {phrase.text}\")\n```\n\n## Custom Analyzers\n\nCreate custom analyzers with field schemas for specialized extraction:\n\n```python\n# Create custom analyzer\nanalyzer = client.create_analyzer(\n    analyzer_id=\"my-invoice-analyzer\",\n    analyzer={\n        \"description\": \"Custom invoice analyzer\",\n        \"base_analyzer_id\": \"prebuilt-documentSearch\",\n        \"field_schema\": {\n            \"fields\": {\n                \"vendor_name\": {\"type\": \"string\"},\n                \"invoice_total\": {\"type\": \"number\"},\n                \"line_items\": {\n                    \"type\": \"array\",\n                    \"items\": {\n                        \"type\": \"object\",\n                        \"properties\": {\n                            \"description\": {\"type\": \"string\"},\n                            \"amount\": {\"type\": \"number\"}\n                        }\n                    }\n                }\n            }\n        }\n    }\n)\n\n# Use custom analyzer\nfrom azure.ai.contentunderstanding.models import AnalyzeInput\n\npoller = client.begin_analyze(\n    analyzer_id=\"my-invoice-analyzer\",\n    inputs=[AnalyzeInput(url=\"https:\u002F\u002Fexample.com\u002Finvoice.pdf\")]\n)\n\nresult = poller.result()\n\n# Access extracted fields\nprint(result.fields[\"vendor_name\"])\nprint(result.fields[\"invoice_total\"])\n```\n\n## Analyzer Management\n\n```python\n# List all analyzers\nanalyzers = client.list_analyzers()\nfor analyzer in analyzers:\n    print(f\"{analyzer.analyzer_id}: {analyzer.description}\")\n\n# Get specific analyzer\nanalyzer = client.get_analyzer(\"prebuilt-documentSearch\")\n\n# Delete custom analyzer\nclient.delete_analyzer(\"my-custom-analyzer\")\n```\n\n## Async Client\n\n```python\nimport asyncio\nimport os\nfrom azure.ai.contentunderstanding.aio import ContentUnderstandingClient\nfrom azure.ai.contentunderstanding.models import AnalyzeInput\nfrom azure.identity.aio import DefaultAzureCredential\n\nasync def analyze_document():\n    endpoint = os.environ[\"CONTENTUNDERSTANDING_ENDPOINT\"]\n    async with DefaultAzureCredential() as credential:\n        async with ContentUnderstandingClient(\n            endpoint=endpoint,\n            credential=credential\n        ) as client:\n            poller = await client.begin_analyze(\n                analyzer_id=\"prebuilt-documentSearch\",\n                inputs=[AnalyzeInput(url=\"https:\u002F\u002Fexample.com\u002Fdoc.pdf\")]\n            )\n            result = await poller.result()\n            content = result.contents[0]\n            return content.markdown\n\nasyncio.run(analyze_document())\n```\n\n## Content Types\n\n| Class | For | Provides |\n|-------|-----|----------|\n| `DocumentContent` | PDF, images, Office docs | Pages, tables, figures, paragraphs |\n| `AudioVisualContent` | Audio, video files | Transcript phrases, timing, key frames |\n\nBoth derive from `MediaContent` which provides basic info and markdown representation.\n\n## Model Imports\n\n```python\nfrom azure.ai.contentunderstanding.models import (\n    AnalyzeInput,\n    AnalyzeResult,\n    MediaContentKind,\n    DocumentContent,\n    AudioVisualContent,\n)\n```\n\n## Client Types\n\n| Client | Purpose |\n|--------|---------|\n| `ContentUnderstandingClient` | Sync client for all operations |\n| `ContentUnderstandingClient` (aio) | Async client for all operations |\n\n## Best Practices\n\n1. **Pick sync OR async and stay consistent.** Do not mix `azure.ai.contentunderstanding` sync clients with `azure.ai.contentunderstanding.aio` async clients in the same call path. Choose one mode per module.\n2. **Always use context managers for clients and async credentials.** Wrap every client in `with ContentUnderstandingClient(...) as client:` (sync) or `async with ContentUnderstandingClient(...) as client:` (async). For async `DefaultAzureCredential` from `azure.identity.aio`, also use `async with credential:` so tokens and transports are cleaned up.\n3. **Use `begin_analyze` with `AnalyzeInput`** — this is the correct method signature\n4. **Access results via `result.contents[0]`** — results are returned as a list\n5. **Use prebuilt analyzers** for common scenarios (document\u002Fimage\u002Faudio\u002Fvideo search)\n6. **Create custom analyzers** only for domain-specific field extraction\n7. **Use async client** for high-throughput scenarios with `azure.identity.aio` credentials\n8. **Handle long-running operations** — video\u002Faudio analysis can take minutes\n9. **Use URL sources** when possible to avoid upload overhead\n\n## Reference Files\n\n| File | Contents |\n|------|----------|\n| [references\u002Fcapabilities.md](references\u002Fcapabilities.md) | Additional non-hero capabilities, operation-group coverage, and production checklists. |\n| [references\u002Fnon-hero-scenarios.md](references\u002Fnon-hero-scenarios.md) | Dedicated non-hero examples for secondary\u002Fadvanced scenarios. |\n",{"name":5,"license":15,"metadata":51,"description":54},{"author":12,"package":52,"version":53},"azure-ai-contentunderstanding","1.0.0","Azure AI Content Understanding SDK for Python. Use for multimodal content extraction from documents, images, audio, and video.\nTriggers: \"azure-ai-contentunderstanding\", \"ContentUnderstandingClient\", \"multimodal analysis\", \"document extraction\", \"video analysis\", \"audio transcription\".\n","main","3f5b461b2314e01c400564051e92469114c5b68f",".github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-ai-contentunderstanding-py",368,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","https:\u002F\u002Fmicrosoft.github.io\u002Fskills\u002F","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 06:48:25",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add microsoft\u002Fskills --skill azure-ai-contentunderstanding-py",{"tool":71,"command":72},"bunx","bunx skills add microsoft\u002Fskills --skill azure-ai-contentunderstanding-py",{"tool":74,"command":75},"pnpm","pnpm dlx skills add microsoft\u002Fskills --skill azure-ai-contentunderstanding-py","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-ai-contentunderstanding-py\u002FSKILL.md",true,[79,85],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fcapabilities.md","REFERENCE","参考文档",2344,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-ai-contentunderstanding-py\u002Freferences\u002Fcapabilities.md",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fnon-hero-scenarios.md",5132,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-ai-contentunderstanding-py\u002Freferences\u002Fnon-hero-scenarios.md",[90,98,121,155,182,202],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":97},"01M741JBE1VH8A2Y3FXX2P7386","azure-advisor-cost-optimization","Analyze Azure Advisor Cost\u002FIdleResources findings and prevalidate deletion safety, including Service Groups. WHEN: \"find unused Azure resources\", \"what resources am I paying for but no longer using\", \"idle-resource savings\", \"historical idle-resource savings\", \"are these idle resources safe to delete\". Generic Cost, other subcategories, and cross-category requests use azure-advisor.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-advisor\u002Fskills\u002Fazure-advisor-cost-optimization\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":105,"publishedAt":46},"01M69B4JCRQV5SPXAFCKXQRV0H","skill-creator","Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fskill-creator\u002FSKILL.md",[104],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[106,107,108,109,9,28,110,111,112,113,31,37,114,115,116,117,118,119,120],"skill creator","creator","ai coding agents","coding agents","foundry","microsoft foundry","coding","guide","Existing","services","new","when","sdks","with","ai coding",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":135,"publishedAt":46},"01M69B4FD57V1MYKRWAJJECTZ7","podcast-generation","Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fpodcast-generation\u002FSKILL.md",[127,130,133,134],{"categoryNo":128,"categoryName":129,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":131,"categoryName":132,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[136,137,138,139,28,140,141,142,40,38,143,144,145,146,147,117,148,149,150,151,152,153,154],"podcast generation","generation","podcast","frontend","azure openai","realtime","react","creation","model","fastapi backend","python fastapi","fastapi","api","streaming","text","narrative","stack","generate","features",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":162,"publishedAt":46},"01M69B4CYPM5SESY5ZWEFDXEQZ","microsoft-docs","Understand Microsoft technologies by querying official documentation. Use whenever the user asks how something works, wants tutorials, needs configuration options, limits, quotas, or best practices for any Microsoft technology (Azure, .NET, M365, Windows, Power Platform, etc.)—even if they don't mention \"docs.\" If the question is about understanding a concept rather than writing code, this is the right skill.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmicrosoft-docs\u002FSKILL.md",[161],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[163,9,164,165,166,167,168,28,169,170,171,172,173,174,175,176,31,177,68,178,37,179,180,181],"microsoft docs","docs","documentation","windows","official","cli","MCP","writing","power platform","mcp server","back","concept","power","platform","technology","question","learn mcp","learn","best practices",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":189,"publishedAt":46},"01M69B49C3YPD1ZJ3NC0HPCY58","mcp-builder","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP), Node\u002FTypeScript (MCP SDK), or C#\u002F.NET (Microsoft MCP SDK).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmcp-builder\u002FSKILL.md",[188],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[190,169,191,192,45,9,40,193,194,144,195,117,196,197,198,113,199,200,31,201,37,119],"mcp builder","builder","llms","typescript","model context protocol","building mcp servers","node","integrate","Tools","context","fastmcp","mcp sdk",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":220,"publishedAt":46},"01M69B467A7CDMFQ0T6Q0ZA12Q","kql","KQL language expertise for writing correct, efficient Kusto Query Language queries. Covers syntax gotchas, join patterns, dynamic types, datetime pitfalls, regex patterns, serialization, memory management, result-size discipline, and advanced functions (geo, vector, graph). USE THIS SKILL whenever writing, debugging, or reviewing KQL queries — even simple ones — because the gotchas section prevents the most common errors that waste tool calls and cause expensive retry cascades. Trigger on: KQL, Kusto, ADX, Azure Data Explorer, Fabric Real-Time Intelligence, EventHouse, Log Analytics, log analysis, data exploration, time series, anomaly detection, summarize, where clause, join, extend, project, let statement, parse operator, extract function, any mention of pipe-forward query syntax.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fkql\u002FSKILL.md",[208,211,212,217],{"categoryNo":209,"categoryName":210,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":213,"categoryName":214,"taxonomyType":215,"taxonomyTypeDesc":216},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",{"categoryNo":218,"categoryName":219,"taxonomyType":215,"taxonomyTypeDesc":216},"01JBSEEDCAT000000000000036","内容创作者",[204,28,170,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,31,237,238,239],"analytics","memory","summarize","exploration","parse","project","time","vector","join","log","pipe","datetime","discipline","time series","regex","anomaly","section","tool","geo"]