azure-root

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

azure-root

azure-root

Microsoft Azure Agent Framework Integration

Microsoft Azure Agent Framework 集成

This skill delegates all Azure provisioning and operations to the official Microsoft Agent Framework.
bash
undefined
该Skill将所有Azure资源部署与操作任务委托给官方的Microsoft Agent Framework处理。
bash
undefined

Python

Python

pip install semantic-kernel
pip install semantic-kernel

.NET / C#

.NET / C#

dotnet add package Microsoft.SemanticKernel.Agents

**Docs:** https://learn.microsoft.com/en-us/agent-framework/overview/

Use the Microsoft Agent Framework for all Azure provisioning and operational actions. This skill provides architecture guidance, cost modeling, and pre-flight requirements — the framework handles execution.
dotnet add package Microsoft.SemanticKernel.Agents

**文档:** https://learn.microsoft.com/en-us/agent-framework/overview/

所有Azure资源部署与操作行为均使用Microsoft Agent Framework完成。本Skill提供架构指导、成本建模与预检查要求,具体执行由该框架负责。

Architecture Guidance

架构指导

Consult this skill for:
  • Azure service selection and trade-off analysis
  • Cost estimation and optimization strategy
  • Pre-flight Entra ID / RBAC permission requirements
  • IaC approach (Bicep vs ARM vs Terraform AzureRM)
  • Integration patterns with Microsoft 365 and other Azure services
  • Multi-agent workflow design using Agent Framework graph-based runtime
本Skill可提供以下方面的参考:
  • Azure服务选型与权衡分析
  • 成本估算与优化策略
  • 预检查Entra ID / RBAC权限要求
  • 基础设施即代码(IaC)方案对比(Bicep vs ARM vs Terraform AzureRM)
  • 与Microsoft 365及其他Azure服务的集成模式
  • 基于Agent Framework图式运行时的多Agent工作流设计

Agent Framework Capabilities

Agent Framework 功能特性

CapabilityDescription
AgentsIndividual LLM agents with tool + MCP server support
WorkflowsGraph-based multi-agent pipelines with checkpointing
ProvidersAzure OpenAI, OpenAI, Anthropic, Ollama, and more
MCPNative MCP client for external service integration
Human-in-the-loopBuilt-in approval and intervention checkpoints
功能描述
Agents支持工具与MCP服务器的独立LLM代理
Workflows带检查点的图式多Agent流水线
ProvidersAzure OpenAI、OpenAI、Anthropic、Ollama等
MCP用于外部服务集成的原生MCP客户端
Human-in-the-loop内置审批与干预检查点

Reference

参考链接