The Complete Production SOP: How to Deploy and Run Microsoft Semantic Kernel C# AI Orchestrator in Autonomous AI Agents

---
name: "semantic-kernel-csharp-orchestration"
description: "Integrate LLMs, native plugins, and memory into .NET enterprise applications."
metadata:
  author: "Microsoft"
  version: "1.0.0"
  runtime_compatibility:
    - "codex"
    - "claude-code"
    - "cursor"
    - "windsurf"
triggers:
  - "create semantic kernel plugin c#"
  - "setup kernelbuilder dotnet"
  - "enable auto tool calling semantic kernel"
permissions:
  fs_read: true
  fs_write: "workspace"
  shell_exec: false
  net_access: false
---

# Microsoft Semantic Kernel C# AI Orchestrator

Builds enterprise AI solutions using Microsoft Semantic Kernel in C#: KernelBuilder, KernelPluginFactory, PromptTemplateConfig, vector connectors, and automatic function invocation.

## When to Invoke
Invoke this skill whenever you need to:
- create semantic kernel plugin c#
- setup kernelbuilder dotnet
- enable auto tool calling semantic kernel

## Execution SOP & Rules
1. Build kernel instances with Kernel.CreateBuilder().AddOpenAIChatCompletion(...).Build().
2. Decorate native C# methods with [KernelFunction] and [Description] attributes for tool binding.
3. Enable automatic function calling with FunctionChoiceBehavior.Auto().
4. Structure prompts using standard Semantic Kernel template syntax ({{$input}}).

## Verification Checklist
- Run local linting, syntax validation, and type-checks before reporting completion.
- Ensure all created or modified files adhere to workspace boundaries and avoid uncommitted secrets.
- Verify tests or build commands exit cleanly with return code 0.

using Microsoft.Extensions.Configuration;
using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.ChatCompletion;

var config = new ConfigurationBuilder()
    .AddUserSecrets<Program>()
    .AddEnvironmentVariables()
    .Build();

var modelId = config["OpenAI:ModelId"] ?? "gpt-4o";
var apiKey = config["OpenAI:ApiKey"] ?? throw new InvalidOperationException("OpenAI:ApiKey is required.");

var builder = Kernel.CreateBuilder();
builder.AddOpenAIChatCompletion(modelId, apiKey);

var kernel = builder.Build();

using System.ComponentModel;
using Microsoft.SemanticKernel;

public class OrderPlugin
{
    [KernelFunction, Description("Retrieves the status of an order using its identifier.")]
    public string GetOrderStatus(
        [Description("The alphanumeric order ID.")] string orderId)
    {
        // Deterministic mock logic or database lookup
        return $"Order {orderId} is currently Shipped and in transit.";
    }
}