2) Use StockFish to evaluate all the positions
3) Pick a position at random, show it to the user, and ask for their evaluation
4) User gets a score based on the difference b/t their eval and StockFish's.
The idea being that this could allow you to rapidly hone your position-evaluation skill. That might be a faster way to improve at chess than just grinding through many games.
But it takes far more to build something useful for humans than just asking stockfish to give you the best move.
For one thing you don't want to learn to play like machines. Often the moves that machines make are terrible human moves. Machines walk into extremely dangerous positions all the time; positions where you need to make a series of only moves to gain a small advantage. Humans shouldn't be doing this.
Machines also rely on tactics heavily. Unless you understand the tactics in play it will make your play much worse. It might appear to you take a piece can't be taken, but stockfish says it can. Ok? Unless you understand the reason why, you aren't going to gain anything from this exercise.