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.
Installs into .claude/skills of the current project.
Are you the author of Grilling?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/joaoequer-grilling)
---
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.
---
<!-- Fonte: github.com/mattpocock/skills, skills/productivity/grilling/SKILL.md (Matt Pocock). Copiado
verbatim 2026-09-01 após leitura completa. Instalada como dependência direta de
improve-codebase-architecture. Ver Wibi/backlogs/skills-radar.md (seção C). -->
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.), go find it yourself — a direct Grep/Read/Glob for anything a single lookup answers; reserve a sub-agent for a search broad enough to actually need its own context window. 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 it 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.
