Interview the user relentlessly about a plan, design or idea until both sides share one understanding. Use when the user says 'grill me' or wants a plan stress-tested, and whenever plan mode is active, before writing the plan.
Installs into .claude/skills of the current project.
Are you the author of Grill Me?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/nguyenhuy190303-grill-me)
---
name: grill-me
description: "Interview the user relentlessly about a plan, design or idea until both sides share one understanding. Use when the user says 'grill me' or wants a plan stress-tested, and whenever plan mode is active, before writing the plan."
---
# Grill me
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. Write the round in the user's language.
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.
## In plan mode
The EEP plan-mode hook points here whenever plan mode is on. Grill first, then write the plan from the settled tree.
- One session per plan. On later turns, continue the open session instead of starting over.
- The user can stop it at any point ("skip", "enough", "just plan"). Then list the decisions still open as assumptions in the plan.
- A small change with no real decision left needs no rounds. Say so in one line and write the plan.
Source: mattpocock/skills `grill-me` + `grilling` (MIT, see LICENSE).
