[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AR9YKSQGS8Y0DBVWNDEW8":3,"skill-same:01M69AR9YKSQGS8Y0DBVWNDEW8":83},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M69AR9YKSQGS8Y0DBVWNDEW8","azure-ai-ml-py",null,"Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines.\nTriggers: \"azure-ai-ml\", \"MLClient\", \"workspace\", \"model registry\", \"training jobs\", \"datasets\".","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-ml-py\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,9,38,39],"azure ai","azure","ml","azure ai ml py","ai ml","model","Training Jobs","for","Model Registry","machine","triggers","compute","models","workspaces","use","python","learning","registry","training","machine learning","sdk","2026-11-10 10:12:30",false,"---\nname: azure-ai-ml-py\ndescription: |\n  Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines.\n  Triggers: \"azure-ai-ml\", \"MLClient\", \"workspace\", \"model registry\", \"training jobs\", \"datasets\".\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n  package: azure-ai-ml\n---\n\n# Azure Machine Learning SDK v2 for Python\n\nClient library for managing Azure ML resources: workspaces, jobs, models, data, and compute.\n\n## Installation\n\n```bash\npip install azure-ai-ml\n```\n\n## Environment Variables\n\n```bash\nAZURE_SUBSCRIPTION_ID=\u003Cyour-subscription-id>  # Required for all auth methods\nAZURE_RESOURCE_GROUP=\u003Cyour-resource-group>  # Required for all auth methods\nAZURE_ML_WORKSPACE_NAME=\u003Cyour-workspace-name>  # 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\nfrom azure.ai.ml import MLClient\nfrom azure.identity import DefaultAzureCredential, ManagedIdentityCredential\nimport os\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()\nwith MLClient(\n    credential=credential,\n    subscription_id=os.environ[\"AZURE_SUBSCRIPTION_ID\"],\n    resource_group_name=os.environ[\"AZURE_RESOURCE_GROUP\"],\n    workspace_name=os.environ[\"AZURE_ML_WORKSPACE_NAME\"]\n) as ml_client:\n    for ws in ml_client.workspaces.list():\n        print(ws.name)\n```\n\n### From Config File\n\n```python\nfrom azure.ai.ml import MLClient\nfrom azure.identity import DefaultAzureCredential\n\n# Uses config.json in current directory or parent\nwith MLClient.from_config(\n    credential=DefaultAzureCredential()\n) as ml_client:\n    for ws in ml_client.workspaces.list():\n        print(ws.name)\n```\n\n> **Long-lived `ml_client`:** Subsequent examples in this skill assume `ml_client` was created via the pattern above and is alive for the lifetime of your script. In production, wrap your top-level workflow in a single `with MLClient(...) as ml_client:` block so the underlying HTTP transport closes cleanly on exit.\n\n## Workspace Management\n\n### Create Workspace\n\n```python\nfrom azure.ai.ml.entities import Workspace\n\nws = Workspace(\n    name=\"my-workspace\",\n    location=\"eastus\",\n    display_name=\"My Workspace\",\n    description=\"ML workspace for experiments\",\n    tags={\"purpose\": \"demo\"}\n)\n\nml_client.workspaces.begin_create(ws).result()\n```\n\n### List Workspaces\n\n```python\nfor ws in ml_client.workspaces.list():\n    print(f\"{ws.name}: {ws.location}\")\n```\n\n## Data Assets\n\n### Register Data\n\n```python\nfrom azure.ai.ml.entities import Data\nfrom azure.ai.ml.constants import AssetTypes\n\n# Register a file\nmy_data = Data(\n    name=\"my-dataset\",\n    version=\"1\",\n    path=\"azureml:\u002F\u002Fdatastores\u002Fworkspaceblobstore\u002Fpaths\u002Fdata\u002Ftrain.csv\",\n    type=AssetTypes.URI_FILE,\n    description=\"Training data\"\n)\n\nml_client.data.create_or_update(my_data)\n```\n\n### Register Folder\n\n```python\nmy_data = Data(\n    name=\"my-folder-dataset\",\n    version=\"1\",\n    path=\"azureml:\u002F\u002Fdatastores\u002Fworkspaceblobstore\u002Fpaths\u002Fdata\u002F\",\n    type=AssetTypes.URI_FOLDER\n)\n\nml_client.data.create_or_update(my_data)\n```\n\n## Model Registry\n\n### Register Model\n\n```python\nfrom azure.ai.ml.entities import Model\nfrom azure.ai.ml.constants import AssetTypes\n\nmodel = Model(\n    name=\"my-model\",\n    version=\"1\",\n    path=\".\u002Fmodel\u002F\",\n    type=AssetTypes.CUSTOM_MODEL,\n    description=\"My trained model\"\n)\n\nml_client.models.create_or_update(model)\n```\n\n### List Models\n\n```python\nfor model in ml_client.models.list(name=\"my-model\"):\n    print(f\"{model.name} v{model.version}\")\n```\n\n## Compute\n\n### Create Compute Cluster\n\n```python\nfrom azure.ai.ml.entities import AmlCompute\n\ncluster = AmlCompute(\n    name=\"cpu-cluster\",\n    type=\"amlcompute\",\n    size=\"Standard_DS3_v2\",\n    min_instances=0,\n    max_instances=4,\n    idle_time_before_scale_down=120\n)\n\nml_client.compute.begin_create_or_update(cluster).result()\n```\n\n### List Compute\n\n```python\nfor compute in ml_client.compute.list():\n    print(f\"{compute.name}: {compute.type}\")\n```\n\n## Jobs\n\n### Command Job\n\n```python\nfrom azure.ai.ml import command, Input\n\njob = command(\n    code=\".\u002Fsrc\",\n    command=\"python train.py --data ${{inputs.data}} --lr ${{inputs.learning_rate}}\",\n    inputs={\n        \"data\": Input(type=\"uri_folder\", path=\"azureml:my-dataset:1\"),\n        \"learning_rate\": 0.01\n    },\n    environment=\"AzureML-sklearn-1.0-ubuntu20.04-py38-cpu@latest\",\n    compute=\"cpu-cluster\",\n    display_name=\"training-job\"\n)\n\nreturned_job = ml_client.jobs.create_or_update(job)\nprint(f\"Job URL: {returned_job.studio_url}\")\n```\n\n### Monitor Job\n\n```python\nml_client.jobs.stream(returned_job.name)\n```\n\n## Pipelines\n\n```python\nfrom azure.ai.ml import dsl, Input, Output\nfrom azure.ai.ml.entities import Pipeline\n\n@dsl.pipeline(\n    compute=\"cpu-cluster\",\n    description=\"Training pipeline\"\n)\ndef training_pipeline(data_input):\n    prep_step = prep_component(data=data_input)\n    train_step = train_component(\n        data=prep_step.outputs.output_data,\n        learning_rate=0.01\n    )\n    return {\"model\": train_step.outputs.model}\n\npipeline = training_pipeline(\n    data_input=Input(type=\"uri_folder\", path=\"azureml:my-dataset:1\")\n)\n\npipeline_job = ml_client.jobs.create_or_update(pipeline)\n```\n\n## Environments\n\n### Create Custom Environment\n\n```python\nfrom azure.ai.ml.entities import Environment\n\nenv = Environment(\n    name=\"my-env\",\n    version=\"1\",\n    image=\"mcr.microsoft.com\u002Fazureml\u002Fopenmpi4.1.0-ubuntu20.04\",\n    conda_file=\".\u002Fenvironment.yml\"\n)\n\nml_client.environments.create_or_update(env)\n```\n\n## Datastores\n\n### List Datastores\n\n```python\nfor ds in ml_client.datastores.list():\n    print(f\"{ds.name}: {ds.type}\")\n```\n\n### Get Default Datastore\n\n```python\ndefault_ds = ml_client.datastores.get_default()\nprint(f\"Default: {default_ds.name}\")\n```\n\n## MLClient Operations\n\n| Property | Operations |\n|----------|------------|\n| `workspaces` | create, get, list, delete |\n| `jobs` | create_or_update, get, list, stream, cancel |\n| `models` | create_or_update, get, list, archive |\n| `data` | create_or_update, get, list |\n| `compute` | begin_create_or_update, get, list, delete |\n| `environments` | create_or_update, get, list |\n| `datastores` | create_or_update, get, list, get_default |\n| `components` | create_or_update, get, list |\n\n## Best Practices\n\n1. **Pick sync OR async and stay consistent.** Do not mix `azure.ai.ml` sync clients with `azure.ai.ml` 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 MLClient(...) as client:` (sync) or `async with MLClient(...) as client:` (async). For async `DefaultAzureCredential` from `azure.identity.aio`, also use `async with credential:` so tokens and transports are cleaned up.\n3. **Use versioning** for data, models, and environments\n4. **Configure idle scale-down** to reduce compute costs\n5. **Use environments** for reproducible training\n6. **Stream job logs** to monitor progress\n7. **Register models** after successful training jobs\n8. **Use pipelines** for multi-step workflows\n9. **Tag resources** for organization and cost tracking\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 Machine Learning SDK v2 for Python\n\nClient library for managing Azure ML resources: workspaces, jobs, models, data, and compute.\n\n## Installation\n\n```bash\npip install azure-ai-ml\n```\n\n## Environment Variables\n\n```bash\nAZURE_SUBSCRIPTION_ID=\u003Cyour-subscription-id>  # Required for all auth methods\nAZURE_RESOURCE_GROUP=\u003Cyour-resource-group>  # Required for all auth methods\nAZURE_ML_WORKSPACE_NAME=\u003Cyour-workspace-name>  # 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\nfrom azure.ai.ml import MLClient\nfrom azure.identity import DefaultAzureCredential, ManagedIdentityCredential\nimport os\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()\nwith MLClient(\n    credential=credential,\n    subscription_id=os.environ[\"AZURE_SUBSCRIPTION_ID\"],\n    resource_group_name=os.environ[\"AZURE_RESOURCE_GROUP\"],\n    workspace_name=os.environ[\"AZURE_ML_WORKSPACE_NAME\"]\n) as ml_client:\n    for ws in ml_client.workspaces.list():\n        print(ws.name)\n```\n\n### From Config File\n\n```python\nfrom azure.ai.ml import MLClient\nfrom azure.identity import DefaultAzureCredential\n\n# Uses config.json in current directory or parent\nwith MLClient.from_config(\n    credential=DefaultAzureCredential()\n) as ml_client:\n    for ws in ml_client.workspaces.list():\n        print(ws.name)\n```\n\n> **Long-lived `ml_client`:** Subsequent examples in this skill assume `ml_client` was created via the pattern above and is alive for the lifetime of your script. In production, wrap your top-level workflow in a single `with MLClient(...) as ml_client:` block so the underlying HTTP transport closes cleanly on exit.\n\n## Workspace Management\n\n### Create Workspace\n\n```python\nfrom azure.ai.ml.entities import Workspace\n\nws = Workspace(\n    name=\"my-workspace\",\n    location=\"eastus\",\n    display_name=\"My Workspace\",\n    description=\"ML workspace for experiments\",\n    tags={\"purpose\": \"demo\"}\n)\n\nml_client.workspaces.begin_create(ws).result()\n```\n\n### List Workspaces\n\n```python\nfor ws in ml_client.workspaces.list():\n    print(f\"{ws.name}: {ws.location}\")\n```\n\n## Data Assets\n\n### Register Data\n\n```python\nfrom azure.ai.ml.entities import Data\nfrom azure.ai.ml.constants import AssetTypes\n\n# Register a file\nmy_data = Data(\n    name=\"my-dataset\",\n    version=\"1\",\n    path=\"azureml:\u002F\u002Fdatastores\u002Fworkspaceblobstore\u002Fpaths\u002Fdata\u002Ftrain.csv\",\n    type=AssetTypes.URI_FILE,\n    description=\"Training data\"\n)\n\nml_client.data.create_or_update(my_data)\n```\n\n### Register Folder\n\n```python\nmy_data = Data(\n    name=\"my-folder-dataset\",\n    version=\"1\",\n    path=\"azureml:\u002F\u002Fdatastores\u002Fworkspaceblobstore\u002Fpaths\u002Fdata\u002F\",\n    type=AssetTypes.URI_FOLDER\n)\n\nml_client.data.create_or_update(my_data)\n```\n\n## Model Registry\n\n### Register Model\n\n```python\nfrom azure.ai.ml.entities import Model\nfrom azure.ai.ml.constants import AssetTypes\n\nmodel = Model(\n    name=\"my-model\",\n    version=\"1\",\n    path=\".\u002Fmodel\u002F\",\n    type=AssetTypes.CUSTOM_MODEL,\n    description=\"My trained model\"\n)\n\nml_client.models.create_or_update(model)\n```\n\n### List Models\n\n```python\nfor model in ml_client.models.list(name=\"my-model\"):\n    print(f\"{model.name} v{model.version}\")\n```\n\n## Compute\n\n### Create Compute Cluster\n\n```python\nfrom azure.ai.ml.entities import AmlCompute\n\ncluster = AmlCompute(\n    name=\"cpu-cluster\",\n    type=\"amlcompute\",\n    size=\"Standard_DS3_v2\",\n    min_instances=0,\n    max_instances=4,\n    idle_time_before_scale_down=120\n)\n\nml_client.compute.begin_create_or_update(cluster).result()\n```\n\n### List Compute\n\n```python\nfor compute in ml_client.compute.list():\n    print(f\"{compute.name}: {compute.type}\")\n```\n\n## Jobs\n\n### Command Job\n\n```python\nfrom azure.ai.ml import command, Input\n\njob = command(\n    code=\".\u002Fsrc\",\n    command=\"python train.py --data ${{inputs.data}} --lr ${{inputs.learning_rate}}\",\n    inputs={\n        \"data\": Input(type=\"uri_folder\", path=\"azureml:my-dataset:1\"),\n        \"learning_rate\": 0.01\n    },\n    environment=\"AzureML-sklearn-1.0-ubuntu20.04-py38-cpu@latest\",\n    compute=\"cpu-cluster\",\n    display_name=\"training-job\"\n)\n\nreturned_job = ml_client.jobs.create_or_update(job)\nprint(f\"Job URL: {returned_job.studio_url}\")\n```\n\n### Monitor Job\n\n```python\nml_client.jobs.stream(returned_job.name)\n```\n\n## Pipelines\n\n```python\nfrom azure.ai.ml import dsl, Input, Output\nfrom azure.ai.ml.entities import Pipeline\n\n@dsl.pipeline(\n    compute=\"cpu-cluster\",\n    description=\"Training pipeline\"\n)\ndef training_pipeline(data_input):\n    prep_step = prep_component(data=data_input)\n    train_step = train_component(\n        data=prep_step.outputs.output_data,\n        learning_rate=0.01\n    )\n    return {\"model\": train_step.outputs.model}\n\npipeline = training_pipeline(\n    data_input=Input(type=\"uri_folder\", path=\"azureml:my-dataset:1\")\n)\n\npipeline_job = ml_client.jobs.create_or_update(pipeline)\n```\n\n## Environments\n\n### Create Custom Environment\n\n```python\nfrom azure.ai.ml.entities import Environment\n\nenv = Environment(\n    name=\"my-env\",\n    version=\"1\",\n    image=\"mcr.microsoft.com\u002Fazureml\u002Fopenmpi4.1.0-ubuntu20.04\",\n    conda_file=\".\u002Fenvironment.yml\"\n)\n\nml_client.environments.create_or_update(env)\n```\n\n## Datastores\n\n### List Datastores\n\n```python\nfor ds in ml_client.datastores.list():\n    print(f\"{ds.name}: {ds.type}\")\n```\n\n### Get Default Datastore\n\n```python\ndefault_ds = ml_client.datastores.get_default()\nprint(f\"Default: {default_ds.name}\")\n```\n\n## MLClient Operations\n\n| Property | Operations |\n|----------|------------|\n| `workspaces` | create, get, list, delete |\n| `jobs` | create_or_update, get, list, stream, cancel |\n| `models` | create_or_update, get, list, archive |\n| `data` | create_or_update, get, list |\n| `compute` | begin_create_or_update, get, list, delete |\n| `environments` | create_or_update, get, list |\n| `datastores` | create_or_update, get, list, get_default |\n| `components` | create_or_update, get, list |\n\n## Best Practices\n\n1. **Pick sync OR async and stay consistent.** Do not mix `azure.ai.ml` sync clients with `azure.ai.ml` 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 MLClient(...) as client:` (sync) or `async with MLClient(...) as client:` (async). For async `DefaultAzureCredential` from `azure.identity.aio`, also use `async with credential:` so tokens and transports are cleaned up.\n3. **Use versioning** for data, models, and environments\n4. **Configure idle scale-down** to reduce compute costs\n5. **Use environments** for reproducible training\n6. **Stream job logs** to monitor progress\n7. **Register models** after successful training jobs\n8. **Use pipelines** for multi-step workflows\n9. **Tag resources** for organization and cost tracking\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":45,"description":48},{"author":12,"package":46,"version":47},"azure-ai-ml","1.0.0","Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines.\nTriggers: \"azure-ai-ml\", \"MLClient\", \"workspace\", \"model registry\", \"training jobs\", \"datasets\".\n","main","3f5b461b2314e01c400564051e92469114c5b68f",".github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-ai-ml-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":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add microsoft\u002Fskills --skill azure-ai-ml-py",{"tool":65,"command":66},"bunx","bunx skills add microsoft\u002Fskills --skill azure-ai-ml-py",{"tool":68,"command":69},"pnpm","pnpm dlx skills add microsoft\u002Fskills --skill azure-ai-ml-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-ml-py\u002FSKILL.md",true,[73,79],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fcapabilities.md","REFERENCE","参考文档",1627,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-ai-ml-py\u002Freferences\u002Fcapabilities.md",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fnon-hero-scenarios.md",2434,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-ai-ml-py\u002Freferences\u002Fnon-hero-scenarios.md",[84,92,119,155,182,202],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":91},"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":103,"publishedAt":40},"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",[98],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[104,105,106,107,9,20,108,109,110,111,26,33,112,113,114,115,116,117,118],"skill creator","creator","ai coding agents","coding agents","foundry","microsoft foundry","coding","guide","Existing","services","new","when","sdks","with","ai coding",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":135,"publishedAt":40},"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",[125,128,131,134],{"categoryNo":126,"categoryName":127,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":129,"categoryName":130,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":132,"categoryName":133,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[136,137,138,139,20,140,141,142,34,143,144,24,145,146,147,115,148,149,150,151,152,153,154],"podcast generation","generation","podcast","frontend","azure openai","realtime","react","Audio","creation","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":40},"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":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[163,9,164,165,166,167,168,20,169,170,171,172,173,174,175,176,26,177,62,178,33,179,180,181],"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":40},"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":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[190,169,191,192,39,9,34,193,194,24,195,115,196,197,198,111,199,200,26,201,33,117],"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":40},"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":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},{"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",[204,20,170,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,26,237,238,239],"analytics","memory","summarize","exploration","parse","project","time","vector","join","log","pipe","datetime","discipline","time series","regex","anomaly","section","tool","geo"]