Agent skill · software engineering · aiskillstore

hosted-agents-v2-py

Build hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition. Use when creating container-based agents in Azure AI Foundry.

Why this skill is useful

Provides specific commands and patterns for creating and managing Azure AI hosted agents that the AI wouldn't reliably generate on its own.

What it needs

Requires azure-ai-projects, azure-identity installed locally. Requires azure account access. About 4k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.

What this skill does

Azure AI Hosted Agents (Python) Build container-based hosted agents using ImageBasedHostedAgentDefinition from the Azure AI Projects SDK. Installation Minimum SDK Version: 2.0.0b3 or later required for hosted agent support. Environment Variables Prerequisites Before creating hosted agents: 1. Container Image - Build and push to Azure Container Registry (ACR) 2. ACR Pull Permissions - Grant your project's managed identity AcrPull role on the ACR 3. Capability Host - Account-level capability host with enablePublicHostingEnvironment=true 4. SDK Version - Ensure azure-ai-projects>=2.0.0b3 Authentication Always use DefaultAzureCredential: Core Workflow 1. Imports 2. Create Hosted Agent 3. List Agent Versions 4. Delete Agent Version ImageBasedHostedAgentDefinition Parameters Parameter Type Required Description ----------- ------ ---------- ------------- containerprotocolversions list[ProtocolVersionRecord] Yes Protocol versions the agent supports image str Yes Full container image path (registry/image:tag) cpu str No CPU allocation (e.g., "1", "2") memory str No Memory allocation (e.g., "2Gi", "4Gi") tools list[dict] No Tools available to the agent environmentvariables dict[str, str] No Environment variables for the container Protocol Versions The containerprotocolversions parameter specifies which protocols your agent supports: Available Protocols: Protocol Description ---------- ------------- AgentProtocol.RESPONSES Standard response protocol for agent interactions Resource Allocation Specify CPU and memory for your container: Resource Limits: Resource Min Max Default ---------- ----- ----- --------- CPU 0.5 4 1 Memory 1Gi 8Gi 2Gi Tools Configuration Add tools to your hosted agent: Code Interpreter MCP Tools Multiple Tools Environment Variables Pass configuration to your container: Best Practice: Never hardcode secrets. Use environment variables or Azure Key Vault. …

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills aiskillstore/hosted-agents-v2-py

View the source on GitHub

Browse the @skills marketplace