JV Jesse Vincent On MLOps.community

“Most skill guidance says the description should say what it is and when to use it. But especially with the newer models, when they can read the description and think, 'oh, I know how to do a code review,' they skip the skill. They don't bother to load it. If the description is just 'use this skill anytime you're about to do a code review,' it doesn't know what's inside, so it has to go look. So the description should only ever include when to use.”

MLOps.community · AI Builders · November 2026

“Most skill guidance says the description should say what it is and when to use it. But especially with the newer models, when they can read the description and think, 'oh, I know how to do a code review,' they skip the skill. They don't bother to load it. If the description is just 'use this skill anytime you're about to do a code review,' it doesn't know what's inside, so it has to go look. So the description should only ever include when to use.” — Jesse Vincent, MLOps.community

Context

Asked how his Superpowers skills trigger so reliably, Jesse Vincent explains his rule for writing agent skill descriptions: tell the model when to use a skill, never what's in it.

Transcript

MLOps.community Around 12:38 into the episode
Speaker 3

Yeah.

Demetrios Brinkmann

Dude, what did you do to make it trigger so easily? Because that's one of my gripes with the skills that I'll build. And even after saying multiple times, like, hey, this skill is called this, I use keywords and sometimes it still doesn't trigger and it's so frustrating.

Jesse Vincent

So there are a couple of things going on. So when superpowers first shipped, I accidentally front ran Anthropic. Superpowers was a skill system for Cloud Code. I didn't know they were putting skills into Cloud Code. I had found skills on cloud.ai. They were using them for Office Docs. And so I had to build everything. So I had to build the system pieces, the triggering pieces, the skill structures. And I had done something pretty different. So the standard front matter for a skill is a name and a description. And in my version of it, before there was a standard, there was name, description, and when to use. And when to use was a separate line that didn't say anything about what the skill did. Just here are the situations in which you should trigger the skill. And the model never saw the skill description. It only saw name and when to use. And that worked really well. And when Anthropic came out with their skill system, so they, you know, they reached out to me and they're like, so these are the docs we're going to ship next week. And, you know, what do you think? And I like sent back this sort of litany of like, should do this, should do this, should this. I think you should name skills in, you know, in Active Voice, like writing…

Demetrios Brinkmann

attention became too much like prompt injection. Right. It was super sensitive. They put

Jesse Vincent

a ton of effort into trying to defend against prompt injection. To their credit, it works much better. It is much harder to trick the model, but it means, you know, it's a constant game of evolution. Yeah. And it's, we also, we don't want superpowers only to work in the highest end frontier models.…

Speaker 3

Well, this is the fascinating piece: that you really have to almost like either build something that you know is going to be kind of universal and you're not going to get as deep as possible for certain models or have evals and pinned skills for pinned models.

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

More from MLOps.community