grillinglisted

# Grilling Interview the user relentlessly until you reach a shared understanding. Map this as a **design tree**: every decision branches into the decisions that hang off it. Source: `mattpocock/skills` `skills/productivity/grilling/SKILL.md` @ `1bb95954ef0d06ba4d64a9c267fb75f57c614a1f`, MIT, scouted 2026-08-19. Tweaked for this system: three boundary sections added at the end, the delegation qualification co-located with the instruction it qualifies, and no change to the mechanism. Prior scout of this repo: `incubator/SCOUT-2026-08-15-mattpocock-skills-summary-derived.md`, pinned at `8b78b531ab965735c5dc74f6f7a219e1e37326df`. The source moved between scouts and neither record cited the other. That record is SUMMARY-DERIVED; its claims are not re-verified here. Work the tree in **rounds**. The **frontier** is every decision whose prerequisites are already settled: the questions you can ask *now* without guessing at answers you have not heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round. Each question is formatted like this: ``` Q1 - <question title>: <question body, may be several paragraphs, including options> -> <your recommended answer> ``` Each round of answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another que