El Bruno

⚠️ This blog post was created with the help of AI tools. Yes, I used a bit of magic from language models to organize my thoughts and automate the boring parts, but the geeky fun and the 🤖 in C# are 100% mine.

Hi 👋

If you’re experimenting with AI Agents in .NET, one of the concepts that appears quickly is Agent Skills.

Skills are the mechanism that allows an agent to extend its capabilities: calling prompts, running code, or executing external logic.

To make this easier to understand, we published a small sample repo:

👉 https://github.com/Azure-Samples/agent-skills-dotnet-demo

The goal of the sample is simple: show how to register and execute skills from a .NET agent with minimal setup.

---

The sample app

The repo uses a .NET 10 file-based app, so there’s no project scaffolding required.

Just clone the repo, deploy the Foundry models (if you don't have them) and then run the app. 

The demo runs three prompts, each triggering a different skill with inline sample data:

1. Meeting Notes — Summarizes a standup transcript into key points, decisions, and action items. This is a Prompt based skill.
2. Data Analyzer — Analyzes CSV sales data for trends, top performers, and anomalies. This is a Python based skill.
3. Code Reviewer — Reviews a C# code snippet for bugs, performance issues, and best practices. This is a C# based skill.

The FileAgentSkillsProvider exposes skills as tools — the model reads skill descriptions and automatically picks the best match for each prompt.

Why skills matter

Agent skills are an important building block for real AI applications, because they allow agents to:

• access external systems
• run deterministic code
• integrate with APIs
• orchestrate complex workflows

Instead of a simple prompt-response loop, agents can use tools and capabilities to complete tasks.

---

Try it yourself

Clone the repo and experiment with adding new skills: https://github.com/Azure-Samples/agent-skills-dotnet-demo