priorartlisted

# priorart — who built this before me? `/priorart <idea>` — check whether the idea already exists `/priorart` — list ideas already checked (from `out/priorart/checked.md`) Answer one question: **has someone already built this — and what does that mean for whether you should?** The deliverable is one honest verdict with the landscape as its evidence, not a survey. Advisory throughout: it recommends; the human decides what, if anything, gets built. ## Step 0 — Check the memory Read `out/priorart/checked.md` if it exists. If this idea (or a close variant) was checked before, open with **"Since last check"**: re-verify the previous brief's findings (status changes, new arrivals since that date) instead of redoing the whole search. The pipeline below is for ideas not yet in the log. ## Step 1 — Restate before searching Restate the idea in one sentence — what it does, who it's for, and the constraint that makes it distinctive — and confirm it with the user. Too vague to restate → ask exactly **one** clarifying question, offering at most 3 example dimensions (it's a question, not a questionnaire). ## Step 2 — Vocabulary before queries Before any search, write 6–10 framings of the idea from distinct vantage points: the builder's terms, the end-user's terms, the academic field's terms, the infrastructure/implementation terms, and the adjacent discipline that likely solved this first. Map each planned query to a framing — this is what prevents five queries landing in the same s