grilling

mattpocock/skills/grilling

The grilling skill is used to relentlessly interview the user about a plan, decision, or idea, helping them stress-test their thinking. It is triggered when the user wants to examine their thoughts or uses any 'grill' trigger phrases. The skill models the decision process as a design tree, where each decision branches into dependent decisions. It works in rounds, asking all questions on the current frontier and providing recommended answers, then waiting for the user's responses before proceeding. The skill finds facts itself rather than asking the user, and continues until the frontier is empty, ensuring no assumptions are left unexamined.

安裝量 · 8,275查看來源

Installation

npx skills add https://github.com/mattpocock/skills --skill grilling

技能檔案

SKILL.md

最近同步 · 2026年10月22日

agents/openai.yaml›

interface:
  display_name: "Grilling"
  short_description: "Stress-test thinking a round of questions at a time"

SKILL.md›

---
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.
---

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.

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.