Files
skills/grilling/SKILL.md
T
2026-09-19 22:25:20 +02:00

2.4 KiB
Raw Blame History

name, description
name description
grilling Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

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 and give your recommended answer for each decision. Then wait for the user's answers before the next round.

Choose the presentation mode once per invocation:

  • Markdown mode when the caller requests it: use numbered Markdown questions with the same options, tradeoffs, and recommendation, even when the ask tool is available.

  • Interactive mode otherwise: when ask is available, present the whole frontier in one ask call:

    • One UI question per frontier decision, with a stable ID and a short title in header.
    • Give 2–5 distinct options. Put consequences and tradeoffs in each option's description; the UI-provided custom answer covers choices you did not anticipate.
    • Set recommended to your recommended option.
    • Set multi: true only when selecting several options is valid.

If ask is unavailable in interactive mode, use Markdown mode.

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 whose answer depends on another question still open in this round belongs to a later round, not this one.

Finding facts is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it; don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The decisions are the user's: put each to them and wait.

The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.