Andy Halliday

And it creates a reusable application that can do what it's focused on

repeatedly for a user.

A skill is a little more atomic in my mind, which is there's going to be a whole bunch of different skills that you might assemble over the course of time.

And the cloud version to stay within their ecosystem, the cloud code or cloud code work version can decide on its own

To look through the skills library and see if there's a skill or get the skill that's requisite to the task that it's going to have.

And there isn't, I don't think in the chat GPT world, there is a way to have the agent, like the chat GPT agent mode,

automatically review all of the custom GPTs that you have in your library and say, which one of these might be helpful here?

And is the knowledge in those helpful?

It doesn't have that mechanism.

And so the, it's the, it's the protocol that skills enables the,

with the agent that's doing the work for you on your computer or in a coding vibe coding session.

It's the, the skill is just this thing that it can call upon to help itself.

And I don't think there's that level of communication and custom GPT.

You basically have to go to the custom GPT or invoke it with the app in the course of a chat.

And then it will,

take on board the knowledge that's built into that custom GPT and the instructions and understand that process.

So there is a similarity there.

I do get that, but I think of them as very different in terms of their fundamental architecture.

Here's another little thing that the skills framework enables, which is a skill can be updated just like a custom GPT could be updated and improved.

But a skill can be updated by the process of using the skill.