grimepmxgrill-me

Original skill: [grilling](https://github.com/mattpocock/skills/blob/main/skills/productivity/grilling/SKILL.md) — nested copy at [`original/UPSTREAM.md`](original/UPSTREAM.md), with the promoted pack copy at [`../../og/grill-me/SKILL.md`](../../og/grill-me/SKILL.md). Mutation: rounds are capped at 10 questions, and skipped questions accept the recommended answer. 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. 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 haven't heard yet. Ask a pack of **at most 10** frontier questions per round — if the frontier is larger, pick the 10 highest-leverage questions and hold the rest for the next round. Number each question and give your recommended answer. Then wait for the user's answers before the next round. Format a round like so: ``` ❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices> ➡️ <your recommended answer> --- ❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices> ➡️ <your recommended answer> ``` The user answers inline by number, in any order, as many as they want. Any question they skip, treat your recommended answer as accepted and say so in the next round's recap. Each round t...