Plugins, Skills & Agents lab
Working out what plugins, connectors and MCP actually are
I kept meeting words like plugin, skill, connector, MCP and agent. Instead of nodding along, I stopped and studied each one, then tried to use them in a real project. This is the notebook of that experiment.
Tools I used
How it started
I kept reading about plugins, skills, connectors and MCP servers and understanding none of it. So I stopped reading and started installing.
What actually happened
I installed plugins one at a time and watched what each one actually changed. A skill turned out to be nothing more than written instructions the model loads when the work matches. A connector turned out to be a login plus a set of allowed actions. An MCP server turned out to be the thing sitting behind the connector, defining the tools and enforcing who may call them. None of these were magic. Every one of them was a boring, explainable piece — and that is exactly why they are worth explaining to people who were told they were complicated.
Moments that changed the build
- Me: "What is the difference between a skill and a plugin?" → A plugin is the box; a skill is one thing inside the box.
- Me: "Why did it not use the tool?" → Because I described the tool instead of describing the outcome.
- Me: "Is MCP a product?" → No. It is the protocol tools speak so any assistant can call them.
What broke
A plugin installed but never fired. I had described the tool by name instead of asking for the result I wanted. The moment I asked for the outcome, it ran.
What I learned
Ask for outcomes, not tools. Trust nothing you have not installed and watched behave.
The ebook from this project
- Read it
Deepthi's Reading #001
Plugins, Skills, Connectors, MCP, Agents and Codex — explained while I built with them
Ebook · $10.00