[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AT0J69779FWPVEY2RBK74":3,"skill-same:01M69AT0J69779FWPVEY2RBK74":78},{"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":18,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M69AT0J69779FWPVEY2RBK74","azure-monitor-query-py",null,"Azure Monitor Query SDK for Python. Use for querying Log Analytics workspaces and Azure Monitor metrics.\nTriggers: \"azure-monitor-query\", \"LogsQueryClient\", \"MetricsQueryClient\", \"Log Analytics\", \"Kusto queries\", \"Azure metrics\".","microsoft\u002Fskills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69AJYYW4E1RMSYCQDJ4FJSH",3199,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-monitor-query-py\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,9,34],"azure monitor","azure","azure monitor query py","monitor","query","azure-monitor","for","triggers","queries","workspaces","log","use","python","metrics","analytics","sdk","2026-11-10 10:12:30",false,"---\nname: azure-monitor-query-py\ndescription: |\n  Azure Monitor Query SDK for Python. Use for querying Log Analytics workspaces and Azure Monitor metrics.\n  Triggers: \"azure-monitor-query\", \"LogsQueryClient\", \"MetricsQueryClient\", \"Log Analytics\", \"Kusto queries\", \"Azure metrics\".\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n  package: azure-monitor-query\n---\n\n# Azure Monitor Query SDK for Python\n\nQuery logs and metrics from Azure Monitor and Log Analytics workspaces.\n\n## Installation\n\n```bash\npip install azure-monitor-query\n```\n\n## Environment Variables\n\n```bash\n# Log Analytics\nAZURE_LOG_ANALYTICS_WORKSPACE_ID=\u003Cworkspace-id>  # Required for log queries\n\n# Metrics\nAZURE_METRICS_RESOURCE_URI=\u002Fsubscriptions\u002F\u003Csub>\u002FresourceGroups\u002F\u003Crg>\u002Fproviders\u002F\u003Cprovider>\u002F\u003Ctype>\u002F\u003Cname>  # Required for metric queries\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\nfrom azure.identity import DefaultAzureCredential, ManagedIdentityCredential\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```\n\n## Logs Query Client\n\n### Basic Query\n\n```python\nfrom azure.monitor.query import LogsQueryClient\nfrom datetime import timedelta\n\nquery = \"\"\"\nAppRequests\n| where TimeGenerated > ago(1h)\n| summarize count() by bin(TimeGenerated, 5m), ResultCode\n| order by TimeGenerated desc\n\"\"\"\n\nwith LogsQueryClient(credential) as client:\n    response = client.query_workspace(\n        workspace_id=os.environ[\"AZURE_LOG_ANALYTICS_WORKSPACE_ID\"],\n        query=query,\n        timespan=timedelta(hours=1)\n    )\n\n    for table in response.tables:\n        for row in table.rows:\n            print(row)\n```\n\n### Query with Time Range\n\n```python\nfrom datetime import datetime, timezone\n\nresponse = client.query_workspace(\n    workspace_id=workspace_id,\n    query=\"AppRequests | take 10\",\n    timespan=(\n        datetime(2024, 1, 1, tzinfo=timezone.utc),\n        datetime(2024, 1, 2, tzinfo=timezone.utc)\n    )\n)\n```\n\n### Convert to DataFrame\n\n```python\nimport pandas as pd\n\nresponse = client.query_workspace(workspace_id, query, timespan=timedelta(hours=1))\n\nif response.tables:\n    table = response.tables[0]\n    df = pd.DataFrame(data=table.rows, columns=[col.name for col in table.columns])\n    print(df.head())\n```\n\n### Batch Query\n\n```python\nfrom azure.monitor.query import LogsBatchQuery\n\nqueries = [\n    LogsBatchQuery(workspace_id=workspace_id, query=\"AppRequests | take 5\", timespan=timedelta(hours=1)),\n    LogsBatchQuery(workspace_id=workspace_id, query=\"AppExceptions | take 5\", timespan=timedelta(hours=1))\n]\n\nresponses = client.query_batch(queries)\n\nfor response in responses:\n    if response.tables:\n        print(f\"Rows: {len(response.tables[0].rows)}\")\n```\n\n### Handle Partial Results\n\n```python\nfrom azure.monitor.query import LogsQueryStatus\n\nresponse = client.query_workspace(workspace_id, query, timespan=timedelta(hours=24))\n\nif response.status == LogsQueryStatus.PARTIAL:\n    print(f\"Partial results: {response.partial_error}\")\nelif response.status == LogsQueryStatus.FAILURE:\n    print(f\"Query failed: {response.partial_error}\")\n```\n\n## Metrics Query Client\n\n### Query Resource Metrics\n\n```python\nfrom azure.monitor.query import MetricsQueryClient\nfrom datetime import timedelta\n\nwith MetricsQueryClient(credential) as metrics_client:\n    response = metrics_client.query_resource(\n        resource_uri=os.environ[\"AZURE_METRICS_RESOURCE_URI\"],\n        metric_names=[\"Percentage CPU\", \"Network In Total\"],\n        timespan=timedelta(hours=1),\n        granularity=timedelta(minutes=5)\n    )\n\n    for metric in response.metrics:\n        print(f\"{metric.name}:\")\n        for time_series in metric.timeseries:\n            for data in time_series.data:\n                print(f\"  {data.timestamp}: {data.average}\")\n```\n\n### Aggregations\n\n```python\nfrom azure.monitor.query import MetricAggregationType\n\nresponse = metrics_client.query_resource(\n    resource_uri=resource_uri,\n    metric_names=[\"Requests\"],\n    timespan=timedelta(hours=1),\n    aggregations=[\n        MetricAggregationType.AVERAGE,\n        MetricAggregationType.MAXIMUM,\n        MetricAggregationType.MINIMUM,\n        MetricAggregationType.COUNT\n    ]\n)\n```\n\n### Filter by Dimension\n\n```python\nresponse = metrics_client.query_resource(\n    resource_uri=resource_uri,\n    metric_names=[\"Requests\"],\n    timespan=timedelta(hours=1),\n    filter=\"ApiName eq 'GetBlob'\"\n)\n```\n\n### List Metric Definitions\n\n```python\ndefinitions = metrics_client.list_metric_definitions(resource_uri)\nfor definition in definitions:\n    print(f\"{definition.name}: {definition.unit}\")\n```\n\n### List Metric Namespaces\n\n```python\nnamespaces = metrics_client.list_metric_namespaces(resource_uri)\nfor ns in namespaces:\n    print(ns.fully_qualified_namespace)\n```\n\n## Async Clients\n\n```python\nfrom azure.monitor.query.aio import LogsQueryClient, MetricsQueryClient\nfrom azure.identity.aio import DefaultAzureCredential\n\nasync def query_logs():\n    async with DefaultAzureCredential() as credential:\n        async with LogsQueryClient(credential) as client:\n            response = await client.query_workspace(\n                workspace_id=workspace_id,\n                query=\"AppRequests | take 10\",\n                timespan=timedelta(hours=1)\n            )\n            return response\n```\n\n## Common Kusto Queries\n\n```kusto\n\u002F\u002F Requests by status code\nAppRequests\n| summarize count() by ResultCode\n| order by count_ desc\n\n\u002F\u002F Exceptions over time\nAppExceptions\n| summarize count() by bin(TimeGenerated, 1h)\n\n\u002F\u002F Slow requests\nAppRequests\n| where DurationMs > 1000\n| project TimeGenerated, Name, DurationMs\n| order by DurationMs desc\n\n\u002F\u002F Top errors\nAppExceptions\n| summarize count() by ExceptionType\n| top 10 by count_\n```\n\n## Client Types\n\n| Client | Purpose |\n|--------|---------|\n| `LogsQueryClient` | Query Log Analytics workspaces |\n| `MetricsQueryClient` | Query Azure Monitor metrics |\n\n## Best Practices\n\n1. **Pick sync OR async and stay consistent.** Do not mix `azure.xxx` sync clients with `azure.xxx.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 Client(...) as client:` (sync) or `async with Client(...) as client:` (async). For async `DefaultAzureCredential` from `azure.identity.aio`, also use `async with credential:` so tokens and transports are cleaned up.\n3. **Use `DefaultAzureCredential`** for portable auth across local dev and Azure (avoid connection strings \u002F API keys when possible).\n4. **Use timedelta** for relative time ranges\n4. **Handle partial results** for large queries\n5. **Use batch queries** when running multiple queries\n6. **Set appropriate granularity** for metrics to reduce data points\n7. **Convert to DataFrame** for easier data analysis\n8. **Use aggregations** to summarize metric data\n9. **Filter by dimensions** to narrow metric results\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 Monitor Query SDK for Python\n\nQuery logs and metrics from Azure Monitor and Log Analytics workspaces.\n\n## Installation\n\n```bash\npip install azure-monitor-query\n```\n\n## Environment Variables\n\n```bash\n# Log Analytics\nAZURE_LOG_ANALYTICS_WORKSPACE_ID=\u003Cworkspace-id>  # Required for log queries\n\n# Metrics\nAZURE_METRICS_RESOURCE_URI=\u002Fsubscriptions\u002F\u003Csub>\u002FresourceGroups\u002F\u003Crg>\u002Fproviders\u002F\u003Cprovider>\u002F\u003Ctype>\u002F\u003Cname>  # Required for metric queries\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\nfrom azure.identity import DefaultAzureCredential, ManagedIdentityCredential\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```\n\n## Logs Query Client\n\n### Basic Query\n\n```python\nfrom azure.monitor.query import LogsQueryClient\nfrom datetime import timedelta\n\nquery = \"\"\"\nAppRequests\n| where TimeGenerated > ago(1h)\n| summarize count() by bin(TimeGenerated, 5m), ResultCode\n| order by TimeGenerated desc\n\"\"\"\n\nwith LogsQueryClient(credential) as client:\n    response = client.query_workspace(\n        workspace_id=os.environ[\"AZURE_LOG_ANALYTICS_WORKSPACE_ID\"],\n        query=query,\n        timespan=timedelta(hours=1)\n    )\n\n    for table in response.tables:\n        for row in table.rows:\n            print(row)\n```\n\n### Query with Time Range\n\n```python\nfrom datetime import datetime, timezone\n\nresponse = client.query_workspace(\n    workspace_id=workspace_id,\n    query=\"AppRequests | take 10\",\n    timespan=(\n        datetime(2024, 1, 1, tzinfo=timezone.utc),\n        datetime(2024, 1, 2, tzinfo=timezone.utc)\n    )\n)\n```\n\n### Convert to DataFrame\n\n```python\nimport pandas as pd\n\nresponse = client.query_workspace(workspace_id, query, timespan=timedelta(hours=1))\n\nif response.tables:\n    table = response.tables[0]\n    df = pd.DataFrame(data=table.rows, columns=[col.name for col in table.columns])\n    print(df.head())\n```\n\n### Batch Query\n\n```python\nfrom azure.monitor.query import LogsBatchQuery\n\nqueries = [\n    LogsBatchQuery(workspace_id=workspace_id, query=\"AppRequests | take 5\", timespan=timedelta(hours=1)),\n    LogsBatchQuery(workspace_id=workspace_id, query=\"AppExceptions | take 5\", timespan=timedelta(hours=1))\n]\n\nresponses = client.query_batch(queries)\n\nfor response in responses:\n    if response.tables:\n        print(f\"Rows: {len(response.tables[0].rows)}\")\n```\n\n### Handle Partial Results\n\n```python\nfrom azure.monitor.query import LogsQueryStatus\n\nresponse = client.query_workspace(workspace_id, query, timespan=timedelta(hours=24))\n\nif response.status == LogsQueryStatus.PARTIAL:\n    print(f\"Partial results: {response.partial_error}\")\nelif response.status == LogsQueryStatus.FAILURE:\n    print(f\"Query failed: {response.partial_error}\")\n```\n\n## Metrics Query Client\n\n### Query Resource Metrics\n\n```python\nfrom azure.monitor.query import MetricsQueryClient\nfrom datetime import timedelta\n\nwith MetricsQueryClient(credential) as metrics_client:\n    response = metrics_client.query_resource(\n        resource_uri=os.environ[\"AZURE_METRICS_RESOURCE_URI\"],\n        metric_names=[\"Percentage CPU\", \"Network In Total\"],\n        timespan=timedelta(hours=1),\n        granularity=timedelta(minutes=5)\n    )\n\n    for metric in response.metrics:\n        print(f\"{metric.name}:\")\n        for time_series in metric.timeseries:\n            for data in time_series.data:\n                print(f\"  {data.timestamp}: {data.average}\")\n```\n\n### Aggregations\n\n```python\nfrom azure.monitor.query import MetricAggregationType\n\nresponse = metrics_client.query_resource(\n    resource_uri=resource_uri,\n    metric_names=[\"Requests\"],\n    timespan=timedelta(hours=1),\n    aggregations=[\n        MetricAggregationType.AVERAGE,\n        MetricAggregationType.MAXIMUM,\n        MetricAggregationType.MINIMUM,\n        MetricAggregationType.COUNT\n    ]\n)\n```\n\n### Filter by Dimension\n\n```python\nresponse = metrics_client.query_resource(\n    resource_uri=resource_uri,\n    metric_names=[\"Requests\"],\n    timespan=timedelta(hours=1),\n    filter=\"ApiName eq 'GetBlob'\"\n)\n```\n\n### List Metric Definitions\n\n```python\ndefinitions = metrics_client.list_metric_definitions(resource_uri)\nfor definition in definitions:\n    print(f\"{definition.name}: {definition.unit}\")\n```\n\n### List Metric Namespaces\n\n```python\nnamespaces = metrics_client.list_metric_namespaces(resource_uri)\nfor ns in namespaces:\n    print(ns.fully_qualified_namespace)\n```\n\n## Async Clients\n\n```python\nfrom azure.monitor.query.aio import LogsQueryClient, MetricsQueryClient\nfrom azure.identity.aio import DefaultAzureCredential\n\nasync def query_logs():\n    async with DefaultAzureCredential() as credential:\n        async with LogsQueryClient(credential) as client:\n            response = await client.query_workspace(\n                workspace_id=workspace_id,\n                query=\"AppRequests | take 10\",\n                timespan=timedelta(hours=1)\n            )\n            return response\n```\n\n## Common Kusto Queries\n\n```kusto\n\u002F\u002F Requests by status code\nAppRequests\n| summarize count() by ResultCode\n| order by count_ desc\n\n\u002F\u002F Exceptions over time\nAppExceptions\n| summarize count() by bin(TimeGenerated, 1h)\n\n\u002F\u002F Slow requests\nAppRequests\n| where DurationMs > 1000\n| project TimeGenerated, Name, DurationMs\n| order by DurationMs desc\n\n\u002F\u002F Top errors\nAppExceptions\n| summarize count() by ExceptionType\n| top 10 by count_\n```\n\n## Client Types\n\n| Client | Purpose |\n|--------|---------|\n| `LogsQueryClient` | Query Log Analytics workspaces |\n| `MetricsQueryClient` | Query Azure Monitor metrics |\n\n## Best Practices\n\n1. **Pick sync OR async and stay consistent.** Do not mix `azure.xxx` sync clients with `azure.xxx.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 Client(...) as client:` (sync) or `async with Client(...) as client:` (async). For async `DefaultAzureCredential` from `azure.identity.aio`, also use `async with credential:` so tokens and transports are cleaned up.\n3. **Use `DefaultAzureCredential`** for portable auth across local dev and Azure (avoid connection strings \u002F API keys when possible).\n4. **Use timedelta** for relative time ranges\n4. **Handle partial results** for large queries\n5. **Use batch queries** when running multiple queries\n6. **Set appropriate granularity** for metrics to reduce data points\n7. **Convert to DataFrame** for easier data analysis\n8. **Use aggregations** to summarize metric data\n9. **Filter by dimensions** to narrow metric results\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":40,"description":43},{"author":12,"package":41,"version":42},"azure-monitor-query","1.0.0","Azure Monitor Query SDK for Python. Use for querying Log Analytics workspaces and Azure Monitor metrics.\nTriggers: \"azure-monitor-query\", \"LogsQueryClient\", \"MetricsQueryClient\", \"Log Analytics\", \"Kusto queries\", \"Azure metrics\".\n","main","3f5b461b2314e01c400564051e92469114c5b68f",".github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-monitor-query-py",366,"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","2026-11-13 02:10:26",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add microsoft\u002Fskills --skill azure-monitor-query-py",{"tool":60,"command":61},"bunx","bunx skills add microsoft\u002Fskills --skill azure-monitor-query-py",{"tool":63,"command":64},"pnpm","pnpm dlx skills add microsoft\u002Fskills --skill azure-monitor-query-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-monitor-query-py\u002FSKILL.md",true,[68,74],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fcapabilities.md","REFERENCE","参考文档",1090,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-monitor-query-py\u002Freferences\u002Fcapabilities.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fnon-hero-scenarios.md",389,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-monitor-query-py\u002Freferences\u002Fnon-hero-scenarios.md",[79,106,143,170,190,226],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":90,"publishedAt":35},"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",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[91,92,93,9,94,95,96,20,97,98,99,30,100,101,102,25,103,104,105],"skill creator","creator","coding agents","foundry","microsoft foundry","ai coding agents","services","coding","guide","ai coding","with","sdks","Existing","when","new",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":122,"publishedAt":35},"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",[112,115,118,121],{"categoryNo":113,"categoryName":114,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":116,"categoryName":117,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":119,"categoryName":120,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},[123,124,125,126,31,127,128,20,129,130,131,132,133,134,135,136,137,138,139,140,141,104,142],"podcast generation","podcast","generation","frontend","react","realtime","azure openai","generate","streaming","api","Audio","stack","text","model","fastapi","creation","python fastapi","narrative","features","fastapi backend",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":150,"publishedAt":35},"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",[149],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},[151,9,152,153,154,155,156,157,158,159,160,20,161,162,163,30,164,57,165,166,167,168,169,25],"docs","microsoft docs","MCP","writing","cli","mcp server","windows","power platform","official","documentation","learn","best practices","question","power","back","technology","platform","learn mcp","concept",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":177,"publishedAt":35},"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",[176],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},[153,178,179,180,31,181,34,182,9,183,184,136,185,186,99,30,187,188,189,101,25,104],"mcp builder","builder","typescript","llms","model context protocol","fastmcp","Tools","node","context","integrate","mcp sdk","building mcp servers",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":208,"publishedAt":35},"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",[196,199,200,205],{"categoryNo":197,"categoryName":198,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},{"categoryNo":201,"categoryName":202,"taxonomyType":203,"taxonomyTypeDesc":204},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",{"categoryNo":206,"categoryName":207,"taxonomyType":203,"taxonomyTypeDesc":204},"01JBSEEDCAT000000000000036","内容创作者",[192,154,209,210,33,20,211,212,213,214,29,215,216,217,218,219,220,221,222,25,223,224,225],"summarize","memory","vector","time series","tool","discipline","geo","exploration","pipe","time","project","regex","join","datetime","section","anomaly","parse",{"skillNo":227,"name":228,"nameZh":6,"description":229,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":230,"categories":231,"keywords":232,"publishedAt":35},"01M69B44HJQ7897EZ7NE7DWQX3","github-issue-creator","Convert raw notes, error logs, voice dictation, or screenshots into crisp GitHub-flavored markdown issue reports. Use when the user pastes bug info, error messages, or informal descriptions and wants a structured GitHub issue. Supports images\u002FGIFs for visual evidence.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fgithub-issue-creator\u002FSKILL.md",[],[233,234,235,236,92,237,238,239,240,241,242,243,30,244,245,246,247,248,249,25,104],"github","github issue creator","github issue","issue","issue creator","screenshots","notes","logs","error messages","messages","convert","evidence","reports","images","info","visual","error"]