Azure AI Agents Persistent Dotnet
microsoft/skills
Azure AI Agents Persistent SDK for .NET. An agent skill from microsoft/skills.
Build AI-enabled .NET applications with Semantic Kernel using services, plugins, prompts, and function-calling patterns that remain testable and maintainable.
$ npx skills add managedcode/dotnet-skills --skill semantic-kernel -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install managedcode/dotnet-skills semantic-kernel --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/managedcode/dotnet-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel .claude/skills/semantic-kernel && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "semantic-kernel" agent skill from https://github.com/managedcode/dotnet-skills/tree/main/catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel into .claude/skills/semantic-kernel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-kernel", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/managedcode/dotnet-skills/tree/main/catalog/Frameworks/Semantic-Kernel/skills/semantic-kernelType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add managedcode/dotnet-skills --skill semantic-kernel -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install managedcode/dotnet-skills semantic-kernel --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/managedcode/dotnet-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel .agents/skills/semantic-kernel && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "semantic-kernel" agent skill from https://github.com/managedcode/dotnet-skills/tree/main/catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel into .agents/skills/semantic-kernel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-kernel", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add managedcode/dotnet-skills --skill semantic-kernel -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install managedcode/dotnet-skills semantic-kernel --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/managedcode/dotnet-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel .cursor/skills/semantic-kernel && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "semantic-kernel" agent skill from https://github.com/managedcode/dotnet-skills/tree/main/catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel into .cursor/skills/semantic-kernel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-kernel", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/managedcode/dotnet-skills.git --path catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add managedcode/dotnet-skills --skill semantic-kernel -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install managedcode/dotnet-skills semantic-kernel --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/managedcode/dotnet-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel .gemini/skills/semantic-kernel && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "semantic-kernel" agent skill from https://github.com/managedcode/dotnet-skills/tree/main/catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel into .gemini/skills/semantic-kernel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-kernel", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install managedcode/dotnet-skills semantic-kernelInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add managedcode/dotnet-skills --skill semantic-kernel -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/managedcode/dotnet-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel .github/skills/semantic-kernel && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "semantic-kernel" agent skill from https://github.com/managedcode/dotnet-skills/tree/main/catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel into .github/skills/semantic-kernel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-kernel", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add managedcode/dotnet-skills --skill semantic-kernel -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install managedcode/dotnet-skills semantic-kernel --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/managedcode/dotnet-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel .opencode/skills/semantic-kernel && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "semantic-kernel" agent skill from https://github.com/managedcode/dotnet-skills/tree/main/catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel into .opencode/skills/semantic-kernel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-kernel", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
semantic-kernelBuild AI-enabled .NET applications with Semantic Kernel using services, plugins, prompts, and function-calling patterns that remain testable and maintainable.
Semantic Kernel is an agent skill from managedcode/dotnet-skills. Build AI-enabled .NET applications with Semantic Kernel using services, plugins, prompts, and function-calling patterns that remain testable and maintainable. USE FOR: adding AI-driven prompts, plugins, or orchestration to a .NET app; reviewing kernel construction, service registration, or plugin usage; building function-calling. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint…
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `manifest.json`, `references/anti-patterns.md` and `references/patterns.md`). Compatibility notes: Requires Semantic Kernel 1.x packages (.NET 8+).
It sits in AI & LLM Engineering, covering Structured output and tool calling, Codebase knowledge for agents and LLM API integration. It works with .NET and OpenAPI. The repository describes itself as: Installable .NET skill catalog and CLI for Codex, Claude Code, GitHub Copilot, and Gemini. The licence is MIT.
9 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 535dd55. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are csharp).
From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
learn.microsoft.comgithub.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Requires Semantic Kernel 1.x packages (.NET 8+).
From compatibility in the SKILL.md frontmatter.
Semantic Kernel loads about 2.8k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 145 tokens; SKILL.md has 600 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from managedcode/dotnet-skills at commit 535dd55, republished under its MIT licence (© managedcode). 600 words, ~2,758 tokens.
.claude/skills/semantic-kernel/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.| Concept | Description |
|---|---|
| Kernel | Central orchestrator for AI services and plugins |
| Plugin | Collection of functions exposed to the LLM |
| Function | Native C# method or prompt template |
| Chat Completion | LLM service for generating responses |
| Memory | Vector storage for semantic search |
dotnet-1.79.0 and later, keep OpenAPI plugin server URL validation enabled, do not re-enable automatic redirects on the default HttpPlugin or WebFileDownloadPlugin clients without an explicit trusted-host policy, and use the current Microsoft Agent Framework-compatible migration samples when moving SK agent code to Agent Framework.1.79.0. The release fixes the Cosmos vector-store path, rejects mixed-separator UNC paths, URL-encodes OpenAPI server variables, adds Ollama Think, and allows deterministic TimePlugin tests through TimeProvider injection.2.0.0-beta.3 update in 1.79.0 as a breaking dependency change. Re-run prompt-template tests and remove security workarounds that are no longer needed after the vulnerable transitive version is gone.1.80.0, re-test OpenAPI plugin HTTP-client defaults and Gemini calls that restrict FunctionChoiceBehavior to a supplied function list. The migrated .NET MEVD providers are no longer owned by Semantic Kernel; follow their redirect guidance and keep vector-provider package references explicit during upgrades.For 1.80.1, update migrated vector-provider references to the current CommunityToolkit.VectorData package names and re-run connector and OpenAPI plugin tests after the dependency refresh. The release removes retired OpenAI Assistants integration tests; do not interpret that removal as a working Assistants migration path. Use Responses or the current Agent Framework migration guidance for affected integrations.
var builder = Kernel.CreateBuilder();
builder.AddAzureOpenAIChatCompletion(
deploymentName: "gpt-4",
endpoint: config["AzureOpenAI:Endpoint"]!,
apiKey: config["AzureOpenAI:ApiKey"]!);
// Or OpenAI
builder.AddOpenAIChatCompletion(
modelId: "gpt-4",
apiKey: config["OpenAI:ApiKey"]!);
var kernel = builder.Build();builder.Services.AddKernel()
.AddAzureOpenAIChatCompletion(
deploymentName: "gpt-4",
endpoint: config["AzureOpenAI:Endpoint"]!,
apiKey: config["AzureOpenAI:ApiKey"]!);
// Register plugins
builder.Services.AddSingleton<WeatherPlugin>();
builder.Services.AddSingleton<OrderPlugin>();
// In your service
public class AiService(Kernel kernel)
{
public async Task<string> ChatAsync(string message)
{
var response = await kernel.InvokePromptAsync(message);
return response.ToString();
}
}public class WeatherPlugin
{
[KernelFunction]
[Description("Gets the current weather for a specified city")]
public async Task<string> GetWeather(
[Description("The city name, e.g., 'Seattle'")] string city,
[Description("Temperature unit: 'celsius' or 'fahrenheit'")] string unit = "celsius")
{
// Call actual weather API
var weather = await _weatherService.GetCurrentAsync(city);
return $"Weather in {city}: {weather.Temperature}° {unit}, {weather.Condition}";
}
[KernelFunction]
[Description("Gets the weather forecast for the next N days")]
public async Task<string> GetForecast(
[Description("The city name")] string city,
[Description("Number of days (1-7)")] int days = 3)
{
var forecast = await _weatherService.GetForecastAsync(city, days);
return FormatForecast(forecast);
}
}| Practice | Why It Matters |
|---|---|
Clear [Description] | LLM uses this to decide when to call |
| Specific parameter names | Helps LLM map user intent |
| Idempotent functions | Safe to retry on failures |
| Return meaningful strings | LLM needs to understand results |
| Validate inputs | LLM may hallucinate parameters |
var settings = new OpenAIPromptExecutionSettings
{
FunctionChoiceBehavior = FunctionChoiceBehavior.Auto()
};
kernel.Plugins.AddFromObject(new WeatherPlugin(), "Weather");
kernel.Plugins.AddFromObject(new OrderPlugin(), "Orders");
var result = await kernel.InvokePromptAsync(
"What's the weather in Seattle and do I have any pending orders?",
new KernelArguments(settings));var settings = new OpenAIPromptExecutionSettings
{
FunctionChoiceBehavior = FunctionChoiceBehavior.Required(
[kernel.Plugins["Weather"]["GetWeather"]])
};var chatService = kernel.GetRequiredService<IChatCompletionService>();
var history = new ChatHistory();
history.AddSystemMessage("You are a helpful assistant.");
history.AddUserMessage(userMessage);
var response = await chatService.GetChatMessageContentAsync(
history,
executionSettings: new OpenAIPromptExecutionSettings
{
FunctionChoiceBehavior = FunctionChoiceBehavior.Auto()
},
kernel: kernel);
history.AddAssistantMessage(response.Content!);await foreach (var chunk in chatService.GetStreamingChatMessageContentsAsync(
history, executionSettings, kernel))
{
Console.Write(chunk.Content);
}// WRONG - agents share plugins
var sharedKernel = Kernel.CreateBuilder().Build();
sharedKernel.Plugins.AddFromObject(new AllPlugins());
var agent1 = new ChatCompletionAgent { Kernel = sharedKernel };
var agent2 = new ChatCompletionAgent { Kernel = sharedKernel };
// Both agents have same plugins!
// CORRECT - isolated kernels
var kernel1 = CreateKernelForAgent1();
kernel1.Plugins.AddFromObject(new WeatherPlugin());
var kernel2 = CreateKernelForAgent2();
kernel2.Plugins.AddFromObject(new OrderPlugin());
var agent1 = new ChatCompletionAgent { Kernel = kernel1 };
var agent2 = new ChatCompletionAgent { Kernel = kernel2 };| Anti-Pattern | Why It's Bad | Better Approach |
|---|---|---|
Vague [Description] | LLM won't call at right time | Be specific and actionable |
| Sharing kernel across agents | Plugin leakage | Clone or create new kernels |
| No input validation | Hallucinated parameters | Validate and return errors |
| Using deprecated Planners | Removed in favor of function calling | Use FunctionChoiceBehavior |
| Ignoring logging | Can't debug AI decisions | Enable Semantic Kernel logging |
[KernelFunction]
[Description("Places an order for a product")]
public async Task<string> PlaceOrder(
[Description("Product ID")] string productId,
[Description("Quantity (1-100)")] int quantity)
{
// Validate inputs
if (string.IsNullOrEmpty(productId))
return "Error: Product ID is required";
if (quantity < 1 || quantity > 100)
return "Error: Quantity must be between 1 and 100";
try
{
var order = await _orderService.CreateAsync(productId, quantity);
return $"Order {order.Id} placed successfully for {quantity} units";
}
catch (ProductNotFoundException)
{
return $"Error: Product '{productId}' not found";
}
}[Fact]
public async Task GetWeather_ReturnsFormattedWeather()
{
var mockWeatherService = new Mock<IWeatherService>();
mockWeatherService.Setup(w => w.GetCurrentAsync("Seattle"))
.ReturnsAsync(new Weather { Temperature = 20, Condition = "Sunny" });
var plugin = new WeatherPlugin(mockWeatherService.Object);
var result = await plugin.GetWeather("Seattle", "celsius");
Assert.Contains("20°", result);
Assert.Contains("Sunny", result);
}For complex multi-agent scenarios, consider microsoft-agent-framework:
© managedcode, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (references) in catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel of managedcode/dotnet-skills.
Open the folder on GitHubat commit 535dd55
Semantic Kernel next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Semantic Kernel this skillmanagedcode/dotnet-skills | 486 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Azure AI Agents Persistent Dotnetmicrosoft/skills | 3.1k | 6 repos | ~3k | Automated safety check: Pass | MIT | |
| Claude Cookbooks Reference2025Emma/vibe-coding-cn | 23k | 1 repos | ~2.2k | Automated safety check: Pass | MIT | |
| Gemini API Devgoogle-gemini/gemini-skills | 4.3k | — | ~5.1k | Automated safety check: Pass | Apache-2.0 | |
| Azure Openai To Responsesmicrosoft/ai-agents-for-beginners | 77k | — | ~6k | Automated safety check: Notes | MIT | |
| Anthropic Product Knowledgesyahiidkamil/Software-Engineer-AI-Agent-Atlas | 397 | 4 repos | ~651 | Automated safety check: Pass | None |
microsoft/skills
Azure AI Agents Persistent SDK for .NET. An agent skill from microsoft/skills.
2025Emma/vibe-coding-cn
Reference of Claude API examples and guides covering tool use, vision, RAG, classification, summarization, text-to-SQL, prompt caching and agent patterns.
google-gemini/gemini-skills
A skill your agent uses when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, speech generation (TTS), voice…
microsoft/ai-agents-for-beginners
Migrate Python apps from Azure OpenAI Chat Completions to the Responses API.
syahiidkamil/Software-Engineer-AI-Agent-Atlas
Stop and consult this skill whenever your response would include specific facts about Anthropic's products.
scouzi1966/maclocal-api
Maintain and extend AFM (maclocal-api), a Swift OpenAI-compatible local LLM server and CLI for Apple Foundation Models, MLX models, API gateway proxying, and Vision OCR.
managedcode/dotnet-skills
Use a repo-root .editorconfig to configure free .NET analyzer and style rules.
managedcode/dotnet-skills
Use the open-source free ArchUnitNET library for architecture rules in .NET tests.
managedcode/dotnet-skills
Build, upgrade, and operate Aspire 13.5.x C or TypeScript application hosts with the current CLI, AppHost, ServiceDefaults, integrations, dashboard, testing, MCP, and deployment patterns for…
managedcode/dotnet-skills
Build, debug, modernize, or review ASP.NET Core applications with correct hosting, middleware, security, configuration, logging, and deployment patterns on current .NET.
managedcode/dotnet-skills
Use the open-source free Asynkron.Profiler dotnet tool for CLI-first CPU, allocation, exception, contention, and heap profiling of .NET commands or existing trace artifacts.
managedcode/dotnet-skills
Build, review, or migrate Azure Functions in .NET with correct execution model, isolated worker setup, bindings, DI, and Durable Functions patterns.
Categories
Build AI-enabled .NET applications with Semantic Kernel using services, plugins, prompts, and function-calling patterns that remain testable and maintainable. Semantic Kernel is an agent skill from managedcode/dotnet-skills.NET applications with Semantic Kernel using services, plugins, prompts, and function-calling patterns that remain testable and maintainable.
Semantic Kernel fits situations like: : adding AI-driven prompts; orchestration to a .NET app; reviewing kernel construction; service registration.
Run `npx skills add managedcode/dotnet-skills --skill semantic-kernel -a claude-code`. Or copy the skill folder (catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel in managedcode/dotnet-skills) into .claude/skills/semantic-kernel in your project. Claude Code loads it when a task matches its description.
Run `npx skills add managedcode/dotnet-skills --skill semantic-kernel -a codex`. Or copy the skill folder (catalog/Frameworks/Semantic-Kernel/skills/semantic-kernel in managedcode/dotnet-skills) into .agents/skills/semantic-kernel in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add managedcode/dotnet-skills --skill semantic-kernel -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/semantic-kernel, .gemini/skills/semantic-kernel, .github/skills/semantic-kernel and .opencode/skills/semantic-kernel in your project.
SKILL.md names no scripts, command-line tools or credentials: Semantic Kernel is instructions for the agent only. Compatibility (from SKILL.md): Requires Semantic Kernel 1.x packages (.NET 8+)..
SKILL.md names 2 domains. As links in the text: learn.microsoft.com and github.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Semantic Kernel is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.8k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Semantic Kernel: Azure AI Agents Persistent Dotnet (microsoft/skills, 3.1k stars), Claude Cookbooks Reference (2025Emma/vibe-coding-cn, 23k stars), Gemini API Dev (google-gemini/gemini-skills, 4.3k stars) and Azure Openai To Responses (microsoft/ai-agents-for-beginners, 77k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
managedcode (a GitHub organization) maintains it in managedcode/dotnet-skills, which has 486 GitHub stars. The repository holds 81 skills in this directory. The repository was last updated on October 7, 2026.
Source: managedcode/dotnet-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.