I also don't know how much to trust the model, but I've had the model tell me specifically that certain aspects of ASD-STE100 are unactionable and will just create more noise.

The OP's own skill even leads with something in a very similar vein:

> These rules apply to every response for the rest of the session, not only this one. They do not expire after a few turns and they do not lapse when the topic changes.

My understanding is that phrases like this are at best a _very_ weak signal to the model. It's simply contradictory to how the model works at a level that can't be overridden by injecting tokens.

> Specific time estimates (minutes, not "a bit").

I actually wish the model would go completely in the opposite direction. Except in the rare circumstances where the model has actually measured something, it is hilariously deficient in its concept of time. It will often output phrases like "this relates to that you did weeks ago", referring to something that happened in the session just a few turns (and hours or a couple of days) ago. Likewise for estimating how long a coding tasks takes, it is hilariously inept. It honestly feels like it rolls two completely independent dice to select a number and a value from (hours | days | weeks) when it needs to attach an estimate to something. I'd much rather read "a bit" than be distracted by these utterly nonsensical times.

The full skill gives this example:

>Bad: "This will take some work." Good: "About 15 minutes if tests already cover this. An afternoon if not."

My experience is that it is very likely that whatever task this is describing takes anywhere from 1 to 30 minutes, consistently. Maybe I just work way faster than the average person.

Separately, from SpaceX's own prospectus, Starlink is only a tiny fraction of the overall conglomerate that went public recently. It "only" needs to support double digit billions of valuation to pull its weight inside of the company.