Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add khalilbenaz/claude-skills-collection --skill semantic-kernel-guidegit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/semantic-kernel-guide)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/semantic-kernel-guide"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/semantic-kernel-guide/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/semantic-kernel-guide"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/semantic-kernel-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00106 | $0.02812 |
| Opus 5 | $0.00053 | $0.01406 |
| Sonnet 5 | $0.00021 | $0.00562 |
| Haiku 4.5 | $0.00011 | $0.00281 |
Grade A, and why
semantic-kernel-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Kernel Guide — Agents IA Enterprise Microsoft
Quand utiliser ce skill
Utiliser quand l'utilisateur développe des applications IA en .NET/C# ou Python avec un besoin d'architecture structurée : plugins typés, planification automatique, injection de dépendances, tests unitaires, ou intégration Azure (Azure OpenAI, Azure AI Search, Cosmos DB). SK est le choix naturel pour les équipes .NET adoptant l'IA générative en production.
Ne pas utiliser SK si : projet Python pur sans besoin enterprise → LangChain ou LlamaIndex suffisent. Script one-shot sans plugins → appel API direct suffit.
Workflow en étapes
1. Installation et structure de projet
# .NET (recommandé : toujours figer la version)
dotnet add package Microsoft.SemanticKernel --version 1.30.0
dotnet add package Microsoft.SemanticKernel.Agents.Core
dotnet add package Microsoft.SemanticKernel.Plugins.Memory # si RAG
# Python
pip install "semantic-kernel==1.14.0"
Structure .NET recommandée :
MyAIApp/
├── Plugins/
│ ├── WeatherPlugin.cs
│ └── Prompts/
│ └── Summarize/
│ ├── skprompt.txt
│ └── config.json
├── Filters/
│ └── LoggingFilter.cs
├── Program.cs
└── appsettings.json
2. Configuration du Kernel
using Microsoft.SemanticKernel;
var builder = Kernel.CreateBuilder();
// Azure OpenAI avec Managed Identity (recommandé production — pas de clé API en dur)
builder.AddAzureOpenAIChatCompletion(
deploymentName: "gpt-4o",
endpoint: config["AzureOpenAI:Endpoint"]!,
credential: new DefaultAzureCredential() // Managed Identity
);
// Fallback : clé API (dev/test seulement)
// builder.AddOpenAIChatCompletion("gpt-4o", Environment.GetEnvironmentVariable("OPENAI_API_KEY")!);
builder.Services.AddLogging(c => c.AddConsole().SetMinimumLevel(LogLevel.Warning));
var kernel = builder.Build();
ASP.NET Core — ne jamais instancier Kernel manuellement :
// Program.cs
builder.Services.AddKernel()
.AddAzureOpenAIChatCompletion(deploymentName, endpoint, credential);
builder.Services.AddSingleton<WeatherPlugin>();
builder.Services.AddFromType<WeatherPlugin>("Weather");
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 294 lines · 106 tokens per session scan A 8a27ce9d0320
semantic-kernel-guide is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 16d ago), licensed MIT. It adds 106 tokens to every session and 2,812 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
java-patterns
Java: Spring Boot, CompletableFuture, records, sealed types, JPA/Hibernate, virtual threads. Triggers: Java, Spring, JPA, Hibernate, Maven, Gradle, virtual thread, sealed class.
kotlin-patterns
Kotlin: coroutines, Flow, sealed/data classes, null safety, Ktor, Compose, KMP. Triggers: Kotlin, coroutine, Flow, suspend, Ktor, Jetpack Compose, KMP, kotlinx.
rust-patterns
Rust: ownership, lifetimes, async (Tokio), Result/anyhow/thiserror, traits, unsafe. Triggers: Rust, borrow checker, lifetime, Tokio, cargo, trait, impl, Result, unsafe, clippy.
swift-patterns
Swift/iOS: SwiftUI, Combine, async/await, actors, SPM, Core Data, UIKit interop. Triggers: Swift, SwiftUI, Combine, iOS, Xcode, actor, Core Data, @MainActor, @State.
ruby-patterns
Ruby/Rails: blocks, metaprogramming, ActiveRecord, Sidekiq, RSpec, Sorbet, Hanami. Triggers: Ruby, Rails, ActiveRecord, Sidekiq, RSpec, Gemfile, bundler, Hanami, Sorbet.
typescript-patterns
TypeScript types: generics, discriminated unions, Zod, satisfies, branded types. Triggers: TypeScript, TS, generics, Zod, satisfies, strict mode.