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. ## Output style When this skill asks for a plan, report, summary, status update, or other chat-facing output, prefer bullet points or numbered lists over plain paragraphs. Keep each item concise and content-bearing. Omit language that only smooths tone, repeats context, or adds "language sugar" without changing the meaning. ## 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 t