[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71BKC8NJC35RVPQTVRNTCWQ":3,"skill-same:01M71BKC8NJC35RVPQTVRNTCWQ":81},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":60,"install":61,"resources":74},"01M71BKC8NJC35RVPQTVRNTCWQ","hosted-agents-v2-py",null,"Build hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition.\nUse when creating container-based agents that run custom code in Azure AI Foundry.\nTriggers: \"ImageBasedHostedAgentDefinition\", \"hosted agent\", \"container agent\", \n\"create_version\", \"ProtocolVersionRecord\", \"AgentProtocol.RESPONSES\".","strmt7\u002Fai_skills_collection_benchmarked","strmt7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F28989754?v=4","01M71929P914SWKQ7QJV24NBBY","Stratos","01M71929Q9VGKQ7PWYR95VSQQQ",1,"MIT","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Fofficial-vendor-reference\u002Fhosted-agents-v2-py\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"agents v2 py","hosted agents","hosted agents v2 py","microsoft","sdk","azure ai","build","with","version","use","container","custom","azure","triggers","run","create","code","when","azure ai foundry","projects","2026-11-10 10:12:30",false,"---\nname: hosted-agents-v2-py\ndescription: \"Build hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition.\\nUse when creating container-based agents that run custom code in Azure AI Foundry.\\nTriggers: \\\"ImageBasedHostedAgentDefinition\\\", \\\"hosted agent\\\", \\\"container agent\\\", \\n\\\"create_version\\\", \\\"ProtocolVersionRecord\\\", \\\"AgentProtocol.RESPONSES\\\".\\n\"\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n  package: azure-ai-projects\n---\n\n# Azure AI Hosted Agents (Python)\n\nBuild container-based hosted agents using `ImageBasedHostedAgentDefinition` from the Azure AI Projects SDK.\n\n## Installation\n\n```bash\npip install azure-ai-projects>=2.0.0b3 azure-identity\n```\n\n**Minimum SDK Version:** `2.0.0b3` or later required for hosted agent support.\n\n## Environment Variables\n\n```bash\nAZURE_AI_PROJECT_ENDPOINT=https:\u002F\u002F\u003Cresource>.services.ai.azure.com\u002Fapi\u002Fprojects\u002F\u003Cproject>\n```\n\n## Prerequisites\n\nBefore creating hosted agents:\n\n1. **Container Image** - Build and push to Azure Container Registry (ACR)\n2. **ACR Pull Permissions** - Grant your project's managed identity `AcrPull` role on the ACR\n3. **Capability Host** - Account-level capability host with `enablePublicHostingEnvironment=true`\n4. **SDK Version** - Ensure `azure-ai-projects>=2.0.0b3`\n\n## Authentication\n\nAlways use `DefaultAzureCredential`:\n\n```python\nfrom azure.identity import DefaultAzureCredential\nfrom azure.ai.projects import AIProjectClient\n\ncredential = DefaultAzureCredential()\nclient = AIProjectClient(\n    endpoint=os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n    credential=credential\n)\n```\n\n## Core Workflow\n\n### 1. Imports\n\n```python\nimport os\nfrom azure.identity import DefaultAzureCredential\nfrom azure.ai.projects import AIProjectClient\nfrom azure.ai.projects.models import (\n    ImageBasedHostedAgentDefinition,\n    ProtocolVersionRecord,\n    AgentProtocol,\n)\n```\n\n### 2. Create Hosted Agent\n\n```python\nclient = AIProjectClient(\n    endpoint=os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n    credential=DefaultAzureCredential()\n)\n\nagent = client.agents.create_version(\n    agent_name=\"my-hosted-agent\",\n    definition=ImageBasedHostedAgentDefinition(\n        container_protocol_versions=[\n            ProtocolVersionRecord(protocol=AgentProtocol.RESPONSES, version=\"v1\")\n        ],\n        cpu=\"1\",\n        memory=\"2Gi\",\n        image=\"myregistry.azurecr.io\u002Fmy-agent:latest\",\n        tools=[{\"type\": \"code_interpreter\"}],\n        environment_variables={\n            \"AZURE_AI_PROJECT_ENDPOINT\": os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n            \"MODEL_NAME\": \"gpt-4o-mini\"\n        }\n    )\n)\n\nprint(f\"Created agent: {agent.name} (version: {agent.version})\")\n```\n\n### 3. List Agent Versions\n\n```python\nversions = client.agents.list_versions(agent_name=\"my-hosted-agent\")\nfor version in versions:\n    print(f\"Version: {version.version}, State: {version.state}\")\n```\n\n### 4. Delete Agent Version\n\n```python\nclient.agents.delete_version(\n    agent_name=\"my-hosted-agent\",\n    version=agent.version\n)\n```\n\n## ImageBasedHostedAgentDefinition Parameters\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| `container_protocol_versions` | `list[ProtocolVersionRecord]` | Yes | Protocol versions the agent supports |\n| `image` | `str` | Yes | Full container image path (registry\u002Fimage:tag) |\n| `cpu` | `str` | No | CPU allocation (e.g., \"1\", \"2\") |\n| `memory` | `str` | No | Memory allocation (e.g., \"2Gi\", \"4Gi\") |\n| `tools` | `list[dict]` | No | Tools available to the agent |\n| `environment_variables` | `dict[str, str]` | No | Environment variables for the container |\n\n## Protocol Versions\n\nThe `container_protocol_versions` parameter specifies which protocols your agent supports:\n\n```python\nfrom azure.ai.projects.models import ProtocolVersionRecord, AgentProtocol\n\n# RESPONSES protocol - standard agent responses\ncontainer_protocol_versions=[\n    ProtocolVersionRecord(protocol=AgentProtocol.RESPONSES, version=\"v1\")\n]\n```\n\n**Available Protocols:**\n| Protocol | Description |\n|----------|-------------|\n| `AgentProtocol.RESPONSES` | Standard response protocol for agent interactions |\n\n## Resource Allocation\n\nSpecify CPU and memory for your container:\n\n```python\ndefinition=ImageBasedHostedAgentDefinition(\n    container_protocol_versions=[...],\n    image=\"myregistry.azurecr.io\u002Fmy-agent:latest\",\n    cpu=\"2\",      # 2 CPU cores\n    memory=\"4Gi\"  # 4 GiB memory\n)\n```\n\n**Resource Limits:**\n| Resource | Min | Max | Default |\n|----------|-----|-----|---------|\n| CPU | 0.5 | 4 | 1 |\n| Memory | 1Gi | 8Gi | 2Gi |\n\n## Tools Configuration\n\nAdd tools to your hosted agent:\n\n### Code Interpreter\n\n```python\ntools=[{\"type\": \"code_interpreter\"}]\n```\n\n### MCP Tools\n\n```python\ntools=[\n    {\"type\": \"code_interpreter\"},\n    {\n        \"type\": \"mcp\",\n        \"server_label\": \"my-mcp-server\",\n        \"server_url\": \"https:\u002F\u002Fmy-mcp-server.example.com\"\n    }\n]\n```\n\n### Multiple Tools\n\n```python\ntools=[\n    {\"type\": \"code_interpreter\"},\n    {\"type\": \"file_search\"},\n    {\n        \"type\": \"mcp\",\n        \"server_label\": \"custom-tool\",\n        \"server_url\": \"https:\u002F\u002Fcustom-tool.example.com\"\n    }\n]\n```\n\n## Environment Variables\n\nPass configuration to your container:\n\n```python\nenvironment_variables={\n    \"AZURE_AI_PROJECT_ENDPOINT\": os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n    \"MODEL_NAME\": \"gpt-4o-mini\",\n    \"LOG_LEVEL\": \"INFO\",\n    \"CUSTOM_CONFIG\": \"value\"\n}\n```\n\n**Best Practice:** Never hardcode secrets. Use environment variables or Azure Key Vault.\n\n## Complete Example\n\n```python\nimport os\nfrom azure.identity import DefaultAzureCredential\nfrom azure.ai.projects import AIProjectClient\nfrom azure.ai.projects.models import (\n    ImageBasedHostedAgentDefinition,\n    ProtocolVersionRecord,\n    AgentProtocol,\n)\n\ndef create_hosted_agent():\n    \"\"\"Create a hosted agent with custom container image.\"\"\"\n\n    client = AIProjectClient(\n        endpoint=os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n        credential=DefaultAzureCredential()\n    )\n\n    agent = client.agents.create_version(\n        agent_name=\"data-processor-agent\",\n        definition=ImageBasedHostedAgentDefinition(\n            container_protocol_versions=[\n                ProtocolVersionRecord(\n                    protocol=AgentProtocol.RESPONSES,\n                    version=\"v1\"\n                )\n            ],\n            image=\"myregistry.azurecr.io\u002Fdata-processor:v1.0\",\n            cpu=\"2\",\n            memory=\"4Gi\",\n            tools=[\n                {\"type\": \"code_interpreter\"},\n                {\"type\": \"file_search\"}\n            ],\n            environment_variables={\n                \"AZURE_AI_PROJECT_ENDPOINT\": os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n                \"MODEL_NAME\": \"gpt-4o-mini\",\n                \"MAX_RETRIES\": \"3\"\n            }\n        )\n    )\n\n    print(f\"Created hosted agent: {agent.name}\")\n    print(f\"Version: {agent.version}\")\n    print(f\"State: {agent.state}\")\n\n    return agent\n\nif __name__ == \"__main__\":\n    create_hosted_agent()\n```\n\n## Async Pattern\n\n```python\nimport os\nfrom azure.identity.aio import DefaultAzureCredential\nfrom azure.ai.projects.aio import AIProjectClient\nfrom azure.ai.projects.models import (\n    ImageBasedHostedAgentDefinition,\n    ProtocolVersionRecord,\n    AgentProtocol,\n)\n\nasync def create_hosted_agent_async():\n    \"\"\"Create a hosted agent asynchronously.\"\"\"\n\n    async with DefaultAzureCredential() as credential:\n        async with AIProjectClient(\n            endpoint=os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n            credential=credential\n        ) as client:\n            agent = await client.agents.create_version(\n                agent_name=\"async-agent\",\n                definition=ImageBasedHostedAgentDefinition(\n                    container_protocol_versions=[\n                        ProtocolVersionRecord(\n                            protocol=AgentProtocol.RESPONSES,\n                            version=\"v1\"\n                        )\n                    ],\n                    image=\"myregistry.azurecr.io\u002Fasync-agent:latest\",\n                    cpu=\"1\",\n                    memory=\"2Gi\"\n                )\n            )\n            return agent\n```\n\n## Common Errors\n\n| Error | Cause | Solution |\n|-------|-------|----------|\n| `ImagePullBackOff` | ACR pull permission denied | Grant `AcrPull` role to project's managed identity |\n| `InvalidContainerImage` | Image not found | Verify image path and tag exist in ACR |\n| `CapabilityHostNotFound` | No capability host configured | Create account-level capability host |\n| `ProtocolVersionNotSupported` | Invalid protocol version | Use `AgentProtocol.RESPONSES` with version `\"v1\"` |\n\n## Best Practices\n\n1. **Version Your Images** - Use specific tags, not `latest` in production\n2. **Minimal Resources** - Start with minimum CPU\u002Fmemory, scale up as needed\n3. **Environment Variables** - Use for all configuration, never hardcode\n4. **Error Handling** - Wrap agent creation in try\u002Fexcept blocks\n5. **Cleanup** - Delete unused agent versions to free resources\n\n## Reference Links\n\n- [Azure AI Projects SDK](https:\u002F\u002Fpypi.org\u002Fproject\u002Fazure-ai-projects\u002F)\n- [Hosted Agents Documentation](https:\u002F\u002Flearn.microsoft.com\u002Fazure\u002Fai-services\u002Fagents\u002Fhow-to\u002Fhosted-agents)\n- [Azure Container Registry](https:\u002F\u002Flearn.microsoft.com\u002Fazure\u002Fcontainer-registry\u002F)\n","# Azure AI Hosted Agents (Python)\n\nBuild container-based hosted agents using `ImageBasedHostedAgentDefinition` from the Azure AI Projects SDK.\n\n## Installation\n\n```bash\npip install azure-ai-projects>=2.0.0b3 azure-identity\n```\n\n**Minimum SDK Version:** `2.0.0b3` or later required for hosted agent support.\n\n## Environment Variables\n\n```bash\nAZURE_AI_PROJECT_ENDPOINT=https:\u002F\u002F\u003Cresource>.services.ai.azure.com\u002Fapi\u002Fprojects\u002F\u003Cproject>\n```\n\n## Prerequisites\n\nBefore creating hosted agents:\n\n1. **Container Image** - Build and push to Azure Container Registry (ACR)\n2. **ACR Pull Permissions** - Grant your project's managed identity `AcrPull` role on the ACR\n3. **Capability Host** - Account-level capability host with `enablePublicHostingEnvironment=true`\n4. **SDK Version** - Ensure `azure-ai-projects>=2.0.0b3`\n\n## Authentication\n\nAlways use `DefaultAzureCredential`:\n\n```python\nfrom azure.identity import DefaultAzureCredential\nfrom azure.ai.projects import AIProjectClient\n\ncredential = DefaultAzureCredential()\nclient = AIProjectClient(\n    endpoint=os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n    credential=credential\n)\n```\n\n## Core Workflow\n\n### 1. Imports\n\n```python\nimport os\nfrom azure.identity import DefaultAzureCredential\nfrom azure.ai.projects import AIProjectClient\nfrom azure.ai.projects.models import (\n    ImageBasedHostedAgentDefinition,\n    ProtocolVersionRecord,\n    AgentProtocol,\n)\n```\n\n### 2. Create Hosted Agent\n\n```python\nclient = AIProjectClient(\n    endpoint=os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n    credential=DefaultAzureCredential()\n)\n\nagent = client.agents.create_version(\n    agent_name=\"my-hosted-agent\",\n    definition=ImageBasedHostedAgentDefinition(\n        container_protocol_versions=[\n            ProtocolVersionRecord(protocol=AgentProtocol.RESPONSES, version=\"v1\")\n        ],\n        cpu=\"1\",\n        memory=\"2Gi\",\n        image=\"myregistry.azurecr.io\u002Fmy-agent:latest\",\n        tools=[{\"type\": \"code_interpreter\"}],\n        environment_variables={\n            \"AZURE_AI_PROJECT_ENDPOINT\": os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n            \"MODEL_NAME\": \"gpt-4o-mini\"\n        }\n    )\n)\n\nprint(f\"Created agent: {agent.name} (version: {agent.version})\")\n```\n\n### 3. List Agent Versions\n\n```python\nversions = client.agents.list_versions(agent_name=\"my-hosted-agent\")\nfor version in versions:\n    print(f\"Version: {version.version}, State: {version.state}\")\n```\n\n### 4. Delete Agent Version\n\n```python\nclient.agents.delete_version(\n    agent_name=\"my-hosted-agent\",\n    version=agent.version\n)\n```\n\n## ImageBasedHostedAgentDefinition Parameters\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| `container_protocol_versions` | `list[ProtocolVersionRecord]` | Yes | Protocol versions the agent supports |\n| `image` | `str` | Yes | Full container image path (registry\u002Fimage:tag) |\n| `cpu` | `str` | No | CPU allocation (e.g., \"1\", \"2\") |\n| `memory` | `str` | No | Memory allocation (e.g., \"2Gi\", \"4Gi\") |\n| `tools` | `list[dict]` | No | Tools available to the agent |\n| `environment_variables` | `dict[str, str]` | No | Environment variables for the container |\n\n## Protocol Versions\n\nThe `container_protocol_versions` parameter specifies which protocols your agent supports:\n\n```python\nfrom azure.ai.projects.models import ProtocolVersionRecord, AgentProtocol\n\n# RESPONSES protocol - standard agent responses\ncontainer_protocol_versions=[\n    ProtocolVersionRecord(protocol=AgentProtocol.RESPONSES, version=\"v1\")\n]\n```\n\n**Available Protocols:**\n| Protocol | Description |\n|----------|-------------|\n| `AgentProtocol.RESPONSES` | Standard response protocol for agent interactions |\n\n## Resource Allocation\n\nSpecify CPU and memory for your container:\n\n```python\ndefinition=ImageBasedHostedAgentDefinition(\n    container_protocol_versions=[...],\n    image=\"myregistry.azurecr.io\u002Fmy-agent:latest\",\n    cpu=\"2\",      # 2 CPU cores\n    memory=\"4Gi\"  # 4 GiB memory\n)\n```\n\n**Resource Limits:**\n| Resource | Min | Max | Default |\n|----------|-----|-----|---------|\n| CPU | 0.5 | 4 | 1 |\n| Memory | 1Gi | 8Gi | 2Gi |\n\n## Tools Configuration\n\nAdd tools to your hosted agent:\n\n### Code Interpreter\n\n```python\ntools=[{\"type\": \"code_interpreter\"}]\n```\n\n### MCP Tools\n\n```python\ntools=[\n    {\"type\": \"code_interpreter\"},\n    {\n        \"type\": \"mcp\",\n        \"server_label\": \"my-mcp-server\",\n        \"server_url\": \"https:\u002F\u002Fmy-mcp-server.example.com\"\n    }\n]\n```\n\n### Multiple Tools\n\n```python\ntools=[\n    {\"type\": \"code_interpreter\"},\n    {\"type\": \"file_search\"},\n    {\n        \"type\": \"mcp\",\n        \"server_label\": \"custom-tool\",\n        \"server_url\": \"https:\u002F\u002Fcustom-tool.example.com\"\n    }\n]\n```\n\n## Environment Variables\n\nPass configuration to your container:\n\n```python\nenvironment_variables={\n    \"AZURE_AI_PROJECT_ENDPOINT\": os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n    \"MODEL_NAME\": \"gpt-4o-mini\",\n    \"LOG_LEVEL\": \"INFO\",\n    \"CUSTOM_CONFIG\": \"value\"\n}\n```\n\n**Best Practice:** Never hardcode secrets. Use environment variables or Azure Key Vault.\n\n## Complete Example\n\n```python\nimport os\nfrom azure.identity import DefaultAzureCredential\nfrom azure.ai.projects import AIProjectClient\nfrom azure.ai.projects.models import (\n    ImageBasedHostedAgentDefinition,\n    ProtocolVersionRecord,\n    AgentProtocol,\n)\n\ndef create_hosted_agent():\n    \"\"\"Create a hosted agent with custom container image.\"\"\"\n\n    client = AIProjectClient(\n        endpoint=os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n        credential=DefaultAzureCredential()\n    )\n\n    agent = client.agents.create_version(\n        agent_name=\"data-processor-agent\",\n        definition=ImageBasedHostedAgentDefinition(\n            container_protocol_versions=[\n                ProtocolVersionRecord(\n                    protocol=AgentProtocol.RESPONSES,\n                    version=\"v1\"\n                )\n            ],\n            image=\"myregistry.azurecr.io\u002Fdata-processor:v1.0\",\n            cpu=\"2\",\n            memory=\"4Gi\",\n            tools=[\n                {\"type\": \"code_interpreter\"},\n                {\"type\": \"file_search\"}\n            ],\n            environment_variables={\n                \"AZURE_AI_PROJECT_ENDPOINT\": os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n                \"MODEL_NAME\": \"gpt-4o-mini\",\n                \"MAX_RETRIES\": \"3\"\n            }\n        )\n    )\n\n    print(f\"Created hosted agent: {agent.name}\")\n    print(f\"Version: {agent.version}\")\n    print(f\"State: {agent.state}\")\n\n    return agent\n\nif __name__ == \"__main__\":\n    create_hosted_agent()\n```\n\n## Async Pattern\n\n```python\nimport os\nfrom azure.identity.aio import DefaultAzureCredential\nfrom azure.ai.projects.aio import AIProjectClient\nfrom azure.ai.projects.models import (\n    ImageBasedHostedAgentDefinition,\n    ProtocolVersionRecord,\n    AgentProtocol,\n)\n\nasync def create_hosted_agent_async():\n    \"\"\"Create a hosted agent asynchronously.\"\"\"\n\n    async with DefaultAzureCredential() as credential:\n        async with AIProjectClient(\n            endpoint=os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n            credential=credential\n        ) as client:\n            agent = await client.agents.create_version(\n                agent_name=\"async-agent\",\n                definition=ImageBasedHostedAgentDefinition(\n                    container_protocol_versions=[\n                        ProtocolVersionRecord(\n                            protocol=AgentProtocol.RESPONSES,\n                            version=\"v1\"\n                        )\n                    ],\n                    image=\"myregistry.azurecr.io\u002Fasync-agent:latest\",\n                    cpu=\"1\",\n                    memory=\"2Gi\"\n                )\n            )\n            return agent\n```\n\n## Common Errors\n\n| Error | Cause | Solution |\n|-------|-------|----------|\n| `ImagePullBackOff` | ACR pull permission denied | Grant `AcrPull` role to project's managed identity |\n| `InvalidContainerImage` | Image not found | Verify image path and tag exist in ACR |\n| `CapabilityHostNotFound` | No capability host configured | Create account-level capability host |\n| `ProtocolVersionNotSupported` | Invalid protocol version | Use `AgentProtocol.RESPONSES` with version `\"v1\"` |\n\n## Best Practices\n\n1. **Version Your Images** - Use specific tags, not `latest` in production\n2. **Minimal Resources** - Start with minimum CPU\u002Fmemory, scale up as needed\n3. **Environment Variables** - Use for all configuration, never hardcode\n4. **Error Handling** - Wrap agent creation in try\u002Fexcept blocks\n5. **Cleanup** - Delete unused agent versions to free resources\n\n## Reference Links\n\n- [Azure AI Projects SDK](https:\u002F\u002Fpypi.org\u002Fproject\u002Fazure-ai-projects\u002F)\n- [Hosted Agents Documentation](https:\u002F\u002Flearn.microsoft.com\u002Fazure\u002Fai-services\u002Fagents\u002Fhow-to\u002Fhosted-agents)\n- [Azure Container Registry](https:\u002F\u002Flearn.microsoft.com\u002Fazure\u002Fcontainer-registry\u002F)\n",{"name":5,"license":15,"metadata":49,"description":53},{"author":50,"package":51,"version":52},"Microsoft","azure-ai-projects","1.0.0","Build hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition.\nUse when creating container-based agents that run custom code in Azure AI Foundry.\nTriggers: \"ImageBasedHostedAgentDefinition\", \"hosted agent\", \"container agent\", \n\"create_version\", \"ProtocolVersionRecord\", \"AgentProtocol.RESPONSES\".\n","main","5c95bcac4646c5aed06bd9aed5235cfc7985aafc","included\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Fofficial-vendor-reference\u002Fhosted-agents-v2-py",0,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked","https:\u002F\u002Fgithub.com\u002Fstrmt7","2026-11-11 04:18:12",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add strmt7\u002Fai_skills_collection_benchmarked --skill hosted-agents-v2-py",{"tool":67,"command":68},"bunx","bunx skills add strmt7\u002Fai_skills_collection_benchmarked --skill hosted-agents-v2-py",{"tool":70,"command":71},"pnpm","pnpm dlx skills add strmt7\u002Fai_skills_collection_benchmarked --skill hosted-agents-v2-py","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Fofficial-vendor-reference\u002Fhosted-agents-v2-py\u002FSKILL.md",true,[75],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Facceptance-criteria.md","REFERENCE","参考文档",11295,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Fofficial-vendor-reference\u002Fhosted-agents-v2-py\u002Freferences\u002Facceptance-criteria.md",[82,113,138,163,188,215],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":96,"publishedAt":44},"01M71D4H3T6M57DFKN8HENAWRV","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Fofficial-reference\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Fofficial-reference\u002Fwebapp-testing\u002FSKILL.md",[90,93],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":94,"categoryName":95,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[97,98,99,100,101,102,103,104,105,106,107,31,108,109,110,111,112],"webapp","testing","webapp testing","for","applications","local","frontend","debugging","toolkit","logs","browser","playwright","web","behavior","ui","screenshots",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":117,"sourceHtmlUrl":118,"categories":119,"keywords":121,"publishedAt":44},"01M71D4CQR2A2TB7GASCR5ZBG3","skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Fofficial-reference\u002Fskill-creator-anthropics\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Fofficial-reference\u002Fskill-creator-anthropics\u002FSKILL.md",[120],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[122,123,124,125,126,127,41,128,39,129,130,38,131,132,133,134,135,136,100,137],"skill creator","creator","performance","improve","run evals","new","analysis","optimize","variance analysis","edit","benchmark","a skill","existing skill","evals","modify","accuracy",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":146,"publishedAt":44},"01M71D488XHEZVXXSXFYP8ENMH","playwright-skill","Complete browser automation with Playwright. Auto-detects dev servers, writes reusable test scripts, and supports screenshots, responsive checks, UX validation, login flows, link checks, and arbitrary browser automation. Use when the user wants to test a website, automate browser interactions, validate web functionality, or perform browser-based testing.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Flatest-release-browser-automation\u002Fplaywright-skill\u002FSKILL.md",[144,145],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[108,147,148,149,98,150,151,41,152,107,153,154,155,156,157,158,159,160,161,162],"playwright skill","browser automation","flows","auto","access","Bash","website","ux","login","scripts","read","write","node","install","network","responsive",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":167,"sourceHtmlUrl":168,"categories":169,"keywords":171,"publishedAt":44},"01M71CY25GM939M6RES91QSG3T","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fsearch-retrieval-web-automation\u002Fofficial-reference\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fsearch-retrieval-web-automation\u002Fofficial-reference\u002Fweb-artifacts-builder\u002FSKILL.md",[170],{"categoryNo":94,"categoryName":95,"taxonomyType":21,"taxonomyTypeDesc":22},[172,173,174,109,175,176,177,100,178,179,103,180,33,181,182,183,184,185,186,187],"builder","artifacts builder","artifacts","web artifacts builder","single-file","css","Tailwind","ui components","single","file","components","react","multi","state","routing","state management",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":192,"sourceHtmlUrl":193,"categories":194,"keywords":204,"publishedAt":44},"01M71CXZB60QJJ1H4S3NN94WMZ","frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML\u002FCSS layouts, or when styling\u002Fbeautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fsearch-retrieval-web-automation\u002Fofficial-reference\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fsearch-retrieval-web-automation\u002Fofficial-reference\u002Ffrontend-design\u002FSKILL.md",[195,196,199],{"categoryNo":94,"categoryName":95,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":197,"categoryName":198,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":200,"categoryName":201,"taxonomyType":202,"taxonomyTypeDesc":203},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[103,205,206,177,207,208,209,101,210,211,33,41,174,40,182,212,183,213,214,31],"design","frontend design","ui design","generic","aesthetics","landing","pages","web ui","react components","examples",{"skillNo":216,"name":217,"nameZh":6,"description":218,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":219,"categories":220,"keywords":221,"publishedAt":44},"01M71CVZ54WFBTVA7R16PFY1ZE","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fzarr-python\u002FSKILL.md",[],[222,223,224,225,226,227,228,229,230,100,231,232,233,234,235,236,237,238],"zarr python","python","zarr","arrays","Cloud Storage","scientific","storage","parallel","dask","numpy","gcs","s3","integration","scientific computing","cloud","scale","pipelines"]