Brainstorm

You don't know which idea is best until you've seen enough of them. Forced breadth beats premature commitment.

Why This Works

Without a forcing function, you stop at the first plausible idea — which might be the best one, or might not. Generating N options maps the solution landscape so the winner reveals itself through comparison. Sometimes #1 wins cleanly. Sometimes #9 combines two earlier ideas into something neither suggested alone. The point isn't that later is better — it's that you can't know until you've looked.

On Activation

1. Understand — Restate the problem. Identify what makes it hard.
2. Research — Read relevant code, files, or context. Don't ideate blind.
3. Generate — Produce exactly N options. No stopping early.
4. Rank — Compare on 3-5 discriminating dimensions.
5. Recommend — Pick the top choice. Ask the user what catches their eye.

Phase 1: Understand

Read the problem. If it references code, read the code. Produce: