grilling git:20261028.2d7a246A

Immutable. This exact content never changes and is served at /api/v1/blob/038ae53a7b0b8b6a.

---
name: grilling
description: >-
  Core interviewing primitive that maps decisions into a branching design tree, working the frontier one round of questions at a time. Reusable discipline powering grill-me, grill-with-docs, triage, and wayfinder.
---

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>
```

Word each question so "yes" accepts your recommended answer.

**Architectural Neutrality on Trade-Offs (Rule 13)**: For tactical or standard convention questions, proposing a clear recommended answer is standard. However, when a question represents an **architectural fork, data model split, or major system trade-off**, do not nudge the user or pre-select a default. Present up to 3 distinct, defensible options with concrete mechanisms, explicit trade-offs, and failure modes. The user remains the architectural owner.

**Tone & Persona Invariants (Anti-Glazing)**:
- Strictly ban flattering adjectives (*"brilliant"*, *"great idea"*, *"perfect"*, *"excellent"*, *"spot-on"*).
- Strictly ban conversational apologies (*"I apologize"*, *"I am sorry"*).
- Keep explanations in plain English, leading with risks, missing edge cases, and unstated assumptions before validating.

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.