grill-melisted

> Ported from mattpocock/skills. Upstream splits this in two: a `grill-me` stub that forwards to > a `grilling` skill holding the method. The stub sets the frontmatter flag that opts a skill out > of model invocation, so it can only ever be reached by typing the slash command, which is the > opposite of what it is for here. This ships the method directly, under the name the marketplace > page uses. Upstream's `agents/openai.yaml` is dropped: this bundle targets Claude Code alone. 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 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. 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> ``` Each round the user 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 whos