Carl Yeh

Yeah, exactly.

And it's actually not hard to set up because, like...

In this case, I'm using subagents, but let's just, for example, ditch the subagents and you're just in a folder and you're just like, you have Claude create a skill.

I don't know what that skill would be for that specific use case.

And then when you engage in that task, just build out, literally ask Claude, hey, I want to build a slash command retrospective.

And it does these three things, review, books out learning failures, update the skill in the folder.

And that's it.

And so now you have a slash command, then you have a skill and it automatically updates every single time.

You can make it as simple or as complex, a little bit more complex how I'm doing here, where every single agent skill gets updated if it's appropriate, if the learning affects them.

So the skill, so we have like a, let's say property value.

Yeah, let's say, let's look at this description extractor here.

So you have the skill, which instructs the agent to what it actually does.

But then the learning is any additional information that doesn't need to be part of the skill, but that the agent will look at before executing the next time.

Yeah.

Every single time.

If I retrospective based on the, you still have to remember to hit retrospective, but I can create a hook that,

when the session's over.

But the thing is, sometimes the sessions are longer or shorter than what I normally do.

So just in case, I have control of the retrospective.

But you can set a hook that it... Trigger that.