ideatelisted

# ideate — diverge before you converge `/ideate` — generate ideas for THIS repo (reads its AGENTS.md/README) `/ideate <topic|problem>` — generate ideas for an arbitrary problem, no repo needed Answer one question: **what could this become that isn't obvious yet — and which of those directions actually deserves effort?** Both halves matter. A session that only sprays ideas is a whiteboard; one that judges before it has range is just the first idea wearing a verdict. The deliverable is a short list of directions each carrying its own reason to live or die. The enemy the whole skill is built against is **premature convergence** — latching onto the first plausible idea and spending the session polishing it. Every step below exists to hold divergence open long enough to be worth converging on. ## Step 0 — Frame the ground You cannot diverge from nothing; fix a starting point first. - **With a repo** (`/ideate` alone): read `AGENTS.md` (the map skill writes it), `README`, and the top-reacted open issues. Distill the project's **job in one sentence** and its **differentiation axis** — the thing it does that alternatives don't, which every later verdict is judged against. - **With a topic** (`/ideate <problem>`): restate the problem in one sentence and name the **user** and the **constraint that hurts most**. Missing pieces are assumptions — state them, don't invent facts. - Read `out/ideate/tracker.md` if it exists: ideas already generated, verdicts already made. A