brainstorm
Installation
SKILL.md
Brainstorm
What this skill is — and isn't
| Skill | Question it answers | Output |
|---|---|---|
vd:research |
"Which of these known options should I pick?" | Comparison report with citations |
vd:brainstorm |
"How should I approach this — what are the options?" | Decision brief with 3+ invented/curated approaches |
vd:plan |
"Given the chosen approach, what are the steps?" | Phased implementation plan |
Brainstorm is solution-space exploration. You may end up recommending a known pattern, but the job is to surface paths the user hasn't considered, then converge.
Hard rules
- No code, no scaffolding, no file edits to source. Only the brief gets written. If the user pushes for implementation, point them at
vd:planorvd:cook. - Minimum 3 genuinely divergent options. If all your options share the same architectural assumption (e.g. all are "different ORMs"), you haven't diverged — invent one that violates the shared assumption (e.g. "no ORM, raw SQL").
- Steel-man before strawman. For each option write the strongest case first. If you can't argue for it convincingly, you don't understand it yet.
- Brutal honesty. Name dealbreakers, hidden costs, ops burden, lock-in, hiring market, debugging pain. No marketing language. No symmetric "it's all tradeoffs" hedging — pick one.
- Decomposition first, depth second. If the request spans 3+ independent subsystems, stop and decompose before any deep-dive.