[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AR3B9PJAKBG5AXD2PQDSZ":3,"skill-same:01M69AR3B9PJAKBG5AXD2PQDSZ":88},{"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":23,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M69AR3B9PJAKBG5AXD2PQDSZ","azure-ai-contentsafety-py",null,"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\".","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-contentsafety-py\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,9,43,44],"azure ai","azure","azure ai contentsafety py","classification","for","detecting","with","image analysis","triggers","content safety","images","use","moderation","text","image","analysis","Safety","severity","Content Moderation","sdk","python","2026-11-10 10:12:30",false,"---\nname: azure-ai-contentsafety-py\ndescription: |\n  Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.\n  Triggers: \"azure-ai-contentsafety\", \"ContentSafetyClient\", \"content moderation\", \"harmful content\", \"text analysis\", \"image analysis\".\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n  package: azure-ai-contentsafety\n---\n\n# Azure AI Content Safety SDK for Python\n\nDetect harmful user-generated and AI-generated content in applications.\n\n## Installation\n\n```bash\npip install azure-ai-contentsafety\n```\n\n## Environment Variables\n\n```bash\nCONTENT_SAFETY_ENDPOINT=https:\u002F\u002F\u003Cresource>.cognitiveservices.azure.com  # Required for all auth methods\nAZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production\nCONTENT_SAFETY_KEY=\u003Cyour-api-key>  # Only required for the legacy API-key auth path below\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.identity import DefaultAzureCredential, ManagedIdentityCredential\nfrom azure.ai.contentsafety import ContentSafetyClient\nfrom azure.ai.contentsafety.models import AnalyzeTextOptions\n\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()\n\nwith ContentSafetyClient(\n    endpoint=os.environ[\"CONTENT_SAFETY_ENDPOINT\"],\n    credential=credential,\n) as client:\n    response = client.analyze_text(AnalyzeTextOptions(text=\"Hello, world!\"))\n```\n\n### Legacy: API Key (existing keyed deployments)\n\nNew code should use `DefaultAzureCredential` above. Use `AzureKeyCredential` only if you have an existing keyed deployment that hasn't been migrated to Entra ID yet — for example, regulated environments still completing their Entra rollout.\n\n```python\nimport os\nfrom azure.core.credentials import AzureKeyCredential\nfrom azure.ai.contentsafety import ContentSafetyClient\nfrom azure.ai.contentsafety.models import AnalyzeTextOptions\n\nwith ContentSafetyClient(\n    endpoint=os.environ[\"CONTENT_SAFETY_ENDPOINT\"],\n    credential=AzureKeyCredential(os.environ[\"CONTENT_SAFETY_KEY\"]),\n) as client:\n    response = client.analyze_text(AnalyzeTextOptions(text=\"Hello, world!\"))\n```\n\nThe `BlocklistClient` accepts the same `AzureKeyCredential` if you also need to manage blocklists with a key.\n\n## Analyze Text\n\n```python\nfrom azure.ai.contentsafety import ContentSafetyClient\nfrom azure.ai.contentsafety.models import AnalyzeTextOptions, TextCategory\nfrom azure.identity import DefaultAzureCredential\n\nwith ContentSafetyClient(endpoint, DefaultAzureCredential()) as client:\n    request = AnalyzeTextOptions(text=\"Your text content to analyze\")\n    response = client.analyze_text(request)\n\n    # Check each category\n    for category in [TextCategory.HATE, TextCategory.SELF_HARM, \n                     TextCategory.SEXUAL, TextCategory.VIOLENCE]:\n        result = next((r for r in response.categories_analysis \n                       if r.category == category), None)\n        if result:\n            print(f\"{category}: severity {result.severity}\")\n```\n\n## Analyze Image\n\n```python\nfrom azure.ai.contentsafety import ContentSafetyClient\nfrom azure.ai.contentsafety.models import AnalyzeImageOptions, ImageData\nfrom azure.identity import DefaultAzureCredential\nimport base64\n\nwith ContentSafetyClient(endpoint, DefaultAzureCredential()) as client:\n    # From file\n    with open(\"image.jpg\", \"rb\") as f:\n        image_data = base64.b64encode(f.read()).decode(\"utf-8\")\n\n    request = AnalyzeImageOptions(\n        image=ImageData(content=image_data)\n    )\n\n    response = client.analyze_image(request)\n\n    for result in response.categories_analysis:\n        print(f\"{result.category}: severity {result.severity}\")\n```\n\n### Image from URL\n\n```python\nfrom azure.ai.contentsafety.models import AnalyzeImageOptions, ImageData\n\nrequest = AnalyzeImageOptions(\n    image=ImageData(blob_url=\"https:\u002F\u002Fexample.com\u002Fimage.jpg\")\n)\n\nresponse = client.analyze_image(request)\n```\n\n## Text Blocklist Management\n\n### Create Blocklist\n\n```python\nfrom azure.ai.contentsafety import BlocklistClient\nfrom azure.ai.contentsafety.models import TextBlocklist\nfrom azure.identity import DefaultAzureCredential\n\nwith BlocklistClient(endpoint, DefaultAzureCredential()) as blocklist_client:\n    blocklist = TextBlocklist(\n        blocklist_name=\"my-blocklist\",\n        description=\"Custom terms to block\"\n    )\n\n    result = blocklist_client.create_or_update_text_blocklist(\n        blocklist_name=\"my-blocklist\",\n        options=blocklist\n    )\n```\n\n### Add Block Items\n\n```python\nfrom azure.ai.contentsafety.models import AddOrUpdateTextBlocklistItemsOptions, TextBlocklistItem\n\nitems = AddOrUpdateTextBlocklistItemsOptions(\n    blocklist_items=[\n        TextBlocklistItem(text=\"blocked-term-1\"),\n        TextBlocklistItem(text=\"blocked-term-2\")\n    ]\n)\n\nresult = blocklist_client.add_or_update_blocklist_items(\n    blocklist_name=\"my-blocklist\",\n    options=items\n)\n```\n\n### Analyze with Blocklist\n\n```python\nfrom azure.ai.contentsafety.models import AnalyzeTextOptions\n\nrequest = AnalyzeTextOptions(\n    text=\"Text containing blocked-term-1\",\n    blocklist_names=[\"my-blocklist\"],\n    halt_on_blocklist_hit=True\n)\n\nresponse = client.analyze_text(request)\n\nif response.blocklists_match:\n    for match in response.blocklists_match:\n        print(f\"Blocked: {match.blocklist_item_text}\")\n```\n\n## Severity Levels\n\nText analysis returns 4 severity levels (0, 2, 4, 6) by default. For 8 levels (0-7):\n\n```python\nfrom azure.ai.contentsafety.models import AnalyzeTextOptions, AnalyzeTextOutputType\n\nrequest = AnalyzeTextOptions(\n    text=\"Your text\",\n    output_type=AnalyzeTextOutputType.EIGHT_SEVERITY_LEVELS\n)\n```\n\n## Harm Categories\n\n| Category | Description |\n|----------|-------------|\n| `Hate` | Attacks based on identity (race, religion, gender, etc.) |\n| `Sexual` | Sexual content, relationships, anatomy |\n| `Violence` | Physical harm, weapons, injury |\n| `SelfHarm` | Self-injury, suicide, eating disorders |\n\n## Severity Scale\n\n| Level | Text Range | Image Range | Meaning |\n|-------|------------|-------------|---------|\n| 0 | Safe | Safe | No harmful content |\n| 2 | Low | Low | Mild references |\n| 4 | Medium | Medium | Moderate content |\n| 6 | High | High | Severe content |\n\n## Client Types\n\n| Client | Purpose |\n|--------|---------|\n| `ContentSafetyClient` | Analyze text and images |\n| `BlocklistClient` | Manage custom blocklists |\n\n## Best Practices\n\n1. **Pick sync OR async and stay consistent.** Do not mix `azure.ai.contentsafety` sync clients with `azure.ai.contentsafety.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 ContentSafetyClient(...) as client:` (sync) or `async with ContentSafetyClient(...) as client:` (async). For async `DefaultAzureCredential` from `azure.identity.aio`, also use `async with credential:` so tokens and transports are cleaned up.\n3. **Use blocklists** for domain-specific terms\n4. **Set severity thresholds** appropriate for your use case\n5. **Handle multiple categories** — content can be harmful in multiple ways\n6. **Use halt_on_blocklist_hit** for immediate rejection\n7. **Log analysis results** for audit and improvement\n8. **Consider 8-severity mode** for finer-grained control\n9. **Pre-moderate AI outputs** before showing to users\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 Safety SDK for Python\n\nDetect harmful user-generated and AI-generated content in applications.\n\n## Installation\n\n```bash\npip install azure-ai-contentsafety\n```\n\n## Environment Variables\n\n```bash\nCONTENT_SAFETY_ENDPOINT=https:\u002F\u002F\u003Cresource>.cognitiveservices.azure.com  # Required for all auth methods\nAZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production\nCONTENT_SAFETY_KEY=\u003Cyour-api-key>  # Only required for the legacy API-key auth path below\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.identity import DefaultAzureCredential, ManagedIdentityCredential\nfrom azure.ai.contentsafety import ContentSafetyClient\nfrom azure.ai.contentsafety.models import AnalyzeTextOptions\n\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()\n\nwith ContentSafetyClient(\n    endpoint=os.environ[\"CONTENT_SAFETY_ENDPOINT\"],\n    credential=credential,\n) as client:\n    response = client.analyze_text(AnalyzeTextOptions(text=\"Hello, world!\"))\n```\n\n### Legacy: API Key (existing keyed deployments)\n\nNew code should use `DefaultAzureCredential` above. Use `AzureKeyCredential` only if you have an existing keyed deployment that hasn't been migrated to Entra ID yet — for example, regulated environments still completing their Entra rollout.\n\n```python\nimport os\nfrom azure.core.credentials import AzureKeyCredential\nfrom azure.ai.contentsafety import ContentSafetyClient\nfrom azure.ai.contentsafety.models import AnalyzeTextOptions\n\nwith ContentSafetyClient(\n    endpoint=os.environ[\"CONTENT_SAFETY_ENDPOINT\"],\n    credential=AzureKeyCredential(os.environ[\"CONTENT_SAFETY_KEY\"]),\n) as client:\n    response = client.analyze_text(AnalyzeTextOptions(text=\"Hello, world!\"))\n```\n\nThe `BlocklistClient` accepts the same `AzureKeyCredential` if you also need to manage blocklists with a key.\n\n## Analyze Text\n\n```python\nfrom azure.ai.contentsafety import ContentSafetyClient\nfrom azure.ai.contentsafety.models import AnalyzeTextOptions, TextCategory\nfrom azure.identity import DefaultAzureCredential\n\nwith ContentSafetyClient(endpoint, DefaultAzureCredential()) as client:\n    request = AnalyzeTextOptions(text=\"Your text content to analyze\")\n    response = client.analyze_text(request)\n\n    # Check each category\n    for category in [TextCategory.HATE, TextCategory.SELF_HARM, \n                     TextCategory.SEXUAL, TextCategory.VIOLENCE]:\n        result = next((r for r in response.categories_analysis \n                       if r.category == category), None)\n        if result:\n            print(f\"{category}: severity {result.severity}\")\n```\n\n## Analyze Image\n\n```python\nfrom azure.ai.contentsafety import ContentSafetyClient\nfrom azure.ai.contentsafety.models import AnalyzeImageOptions, ImageData\nfrom azure.identity import DefaultAzureCredential\nimport base64\n\nwith ContentSafetyClient(endpoint, DefaultAzureCredential()) as client:\n    # From file\n    with open(\"image.jpg\", \"rb\") as f:\n        image_data = base64.b64encode(f.read()).decode(\"utf-8\")\n\n    request = AnalyzeImageOptions(\n        image=ImageData(content=image_data)\n    )\n\n    response = client.analyze_image(request)\n\n    for result in response.categories_analysis:\n        print(f\"{result.category}: severity {result.severity}\")\n```\n\n### Image from URL\n\n```python\nfrom azure.ai.contentsafety.models import AnalyzeImageOptions, ImageData\n\nrequest = AnalyzeImageOptions(\n    image=ImageData(blob_url=\"https:\u002F\u002Fexample.com\u002Fimage.jpg\")\n)\n\nresponse = client.analyze_image(request)\n```\n\n## Text Blocklist Management\n\n### Create Blocklist\n\n```python\nfrom azure.ai.contentsafety import BlocklistClient\nfrom azure.ai.contentsafety.models import TextBlocklist\nfrom azure.identity import DefaultAzureCredential\n\nwith BlocklistClient(endpoint, DefaultAzureCredential()) as blocklist_client:\n    blocklist = TextBlocklist(\n        blocklist_name=\"my-blocklist\",\n        description=\"Custom terms to block\"\n    )\n\n    result = blocklist_client.create_or_update_text_blocklist(\n        blocklist_name=\"my-blocklist\",\n        options=blocklist\n    )\n```\n\n### Add Block Items\n\n```python\nfrom azure.ai.contentsafety.models import AddOrUpdateTextBlocklistItemsOptions, TextBlocklistItem\n\nitems = AddOrUpdateTextBlocklistItemsOptions(\n    blocklist_items=[\n        TextBlocklistItem(text=\"blocked-term-1\"),\n        TextBlocklistItem(text=\"blocked-term-2\")\n    ]\n)\n\nresult = blocklist_client.add_or_update_blocklist_items(\n    blocklist_name=\"my-blocklist\",\n    options=items\n)\n```\n\n### Analyze with Blocklist\n\n```python\nfrom azure.ai.contentsafety.models import AnalyzeTextOptions\n\nrequest = AnalyzeTextOptions(\n    text=\"Text containing blocked-term-1\",\n    blocklist_names=[\"my-blocklist\"],\n    halt_on_blocklist_hit=True\n)\n\nresponse = client.analyze_text(request)\n\nif response.blocklists_match:\n    for match in response.blocklists_match:\n        print(f\"Blocked: {match.blocklist_item_text}\")\n```\n\n## Severity Levels\n\nText analysis returns 4 severity levels (0, 2, 4, 6) by default. For 8 levels (0-7):\n\n```python\nfrom azure.ai.contentsafety.models import AnalyzeTextOptions, AnalyzeTextOutputType\n\nrequest = AnalyzeTextOptions(\n    text=\"Your text\",\n    output_type=AnalyzeTextOutputType.EIGHT_SEVERITY_LEVELS\n)\n```\n\n## Harm Categories\n\n| Category | Description |\n|----------|-------------|\n| `Hate` | Attacks based on identity (race, religion, gender, etc.) |\n| `Sexual` | Sexual content, relationships, anatomy |\n| `Violence` | Physical harm, weapons, injury |\n| `SelfHarm` | Self-injury, suicide, eating disorders |\n\n## Severity Scale\n\n| Level | Text Range | Image Range | Meaning |\n|-------|------------|-------------|---------|\n| 0 | Safe | Safe | No harmful content |\n| 2 | Low | Low | Mild references |\n| 4 | Medium | Medium | Moderate content |\n| 6 | High | High | Severe content |\n\n## Client Types\n\n| Client | Purpose |\n|--------|---------|\n| `ContentSafetyClient` | Analyze text and images |\n| `BlocklistClient` | Manage custom blocklists |\n\n## Best Practices\n\n1. **Pick sync OR async and stay consistent.** Do not mix `azure.ai.contentsafety` sync clients with `azure.ai.contentsafety.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 ContentSafetyClient(...) as client:` (sync) or `async with ContentSafetyClient(...) as client:` (async). For async `DefaultAzureCredential` from `azure.identity.aio`, also use `async with credential:` so tokens and transports are cleaned up.\n3. **Use blocklists** for domain-specific terms\n4. **Set severity thresholds** appropriate for your use case\n5. **Handle multiple categories** — content can be harmful in multiple ways\n6. **Use halt_on_blocklist_hit** for immediate rejection\n7. **Log analysis results** for audit and improvement\n8. **Consider 8-severity mode** for finer-grained control\n9. **Pre-moderate AI outputs** before showing to users\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":50,"description":53},{"author":12,"package":51,"version":52},"azure-ai-contentsafety","1.0.0","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","main","3f5b461b2314e01c400564051e92469114c5b68f",".github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-ai-contentsafety-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":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add microsoft\u002Fskills --skill azure-ai-contentsafety-py",{"tool":70,"command":71},"bunx","bunx skills add microsoft\u002Fskills --skill azure-ai-contentsafety-py",{"tool":73,"command":74},"pnpm","pnpm dlx skills add microsoft\u002Fskills --skill azure-ai-contentsafety-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-contentsafety-py\u002FSKILL.md",true,[78,84],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fcapabilities.md","REFERENCE","参考文档",1384,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-ai-contentsafety-py\u002Freferences\u002Fcapabilities.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fnon-hero-scenarios.md",957,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-ai-contentsafety-py\u002Freferences\u002Fnon-hero-scenarios.md",[89,97,121,155,182,202],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":96},"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":106,"publishedAt":45},"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",[103],{"categoryNo":104,"categoryName":105,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[107,108,109,110,9,25,111,112,113,114,28,35,115,116,117,118,119,30,120],"skill creator","creator","ai coding agents","coding agents","foundry","microsoft foundry","coding","guide","Existing","services","new","when","sdks","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":45},"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":104,"categoryName":105,"taxonomyType":21,"taxonomyTypeDesc":22},[136,137,138,139,25,140,141,142,44,143,144,145,146,147,148,118,149,150,37,151,152,153,154],"podcast generation","generation","podcast","frontend","azure openai","realtime","react","Audio","creation","model","fastapi backend","python fastapi","fastapi","api","streaming","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":45},"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":104,"categoryName":105,"taxonomyType":21,"taxonomyTypeDesc":22},[163,9,164,165,166,167,168,25,169,170,171,172,173,174,175,176,28,177,67,178,35,179,180,181],"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":45},"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":104,"categoryName":105,"taxonomyType":21,"taxonomyTypeDesc":22},[190,169,191,192,43,9,44,193,194,145,195,118,196,197,198,114,199,200,28,201,35,30],"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":45},"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":104,"categoryName":105,"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",[204,25,170,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,28,237,238,239],"analytics","memory","summarize","exploration","parse","project","time","vector","join","log","pipe","datetime","discipline","time series","regex","anomaly","section","tool","geo"]