Cut a feature list down to a real MVP
A feature list only gets smaller when someone's willing to be ruthless about it — left alone, it only grows.
- Use it for
- Anyone with an ambitious feature list who needs it cut down to something actually shippable soon.
A feature list for a new product tends to grow rather than shrink, because every feature on it seemed worth including when it was added — cutting it down requires someone willing to be genuinely ruthless about what's essential versus what merely seems useful. This prompt does that cut explicitly, against a real time constraint, rather than a soft "maybe trim a few things."
When not to use this
If the list is already scoped tightly and realistic for the timeframe, this aggressive cutting isn't needed — this is for a list that's grown past what's actually buildable soon.
Did this work?
The resulting MVP is small enough to actually build in the stated timeframe, with everything else explicitly deferred rather than quietly forgotten.
Tested on claude-opus-5. Evidence status is draft; it moves to battle-tested only on recorded runs, never by hand.