apw-brainstormlisted

Use this skill when asked to brainstorm, ideate, generate options, or explore approaches *before* committing to one. It exists to fight one specific failure: a model defaults to its single highest-probability answer, so an unaided "give me ideas" produces a few near-identical, generic options, anchored to the first framing and presented uncritically. This skill forces genuine divergence, defers judgment, then converges honestly. It sits **upstream** of `apw-research` (verify the chosen direction) and `apw-implement` (build it). Follow the steps below strictly and in order. ## Step 1 — Frame and re-frame the challenge Before generating a single idea, write down what the ideation is actually for: - **Goal** — what a successful outcome would achieve, in one sentence. - **Constraints** — what is genuinely fixed, separated from what is merely *assumed* fixed. Mark each as **hard** or **assumed**. - **Success criteria** — what a great idea would have to do to win, so convergence later has something to measure against. - **Re-framings** — restate the problem **2–3 different ways** (e.g. broaden it, narrow it, invert it). This deliberately breaks the anchor to the user's first phrasing before any ideating begins. Present this framing — including the re-framings — and confirm it before going further. ## Step 2 — Ask questions and set a divergence strategy (only if needed) If anything about the framing is genuinely ambiguous, ask up to 5 targeted questions that would change the *