grilling v1.0A

Immutable. This exact content is served forever at /api/v1/blob/c3af8d4fc18a0a09.

---
name: grilling
description: >
  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.
allowed-tools: Read Grep Glob Bash Task
compatibility: >
  Owns the grilling procedure. grill-me and grill-with-docs are thin entry points that call this
  skill.
metadata:
  tags: design-tree, frontier-rounds, stress-testing, plan-review, interview
  platforms: Claude, ChatGPT, Gemini, Codex
  version: "1.0"
  source: mattpocock/skills
  upstream_commit: 3cca18b368ae95cdbdebbff572ccafa662551015
  invocation: model-invoked
---

# Grilling — Design Tree Interview

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.

This skill is imported from `mattpocock/skills` (MIT) and is **model-invoked** upstream.

## When to use this skill

- 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.

## Instructions

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 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.

## Examples

- Apply this skill to one narrow scope first, confirm the output matches the shape described above, then widen to the full task.
- When a step needs a fact from the repository or the environment, look it up instead of asking the user for it.

## Best practices

- Keep the upstream procedure intact; record deviations explicitly instead of silently improvising.
- Stop and hand control back to the user at every decision point this skill marks as theirs.
- Prefer small reversible changes, and state assumptions rather than burying them.

## References

- Upstream skill: `mattpocock/skills` `skills/productivity/grilling/SKILL.md` (commit `3cca18b`, MIT)
- Project standards: `.agent-skills/skill-standardization/SKILL.md`
- Validator script: `.agent-skills/skill-standardization/scripts/validate_skill.sh`