# What if the agent asked you the hard questions instead?

Canonical URL: https://bestskillsforclaude.com/en/skills/grill-me
Language: en
Skill: grill-me
Publisher: Matt Pocock (https://github.com/mattpocock)
Source: https://github.com/mattpocock/skills
License as stated by the publisher: MIT
Runtime: Claude Code and agents that support the skills CLI
Category: Engineering discipline
Last reviewed: 2026-08-05

The plan you cannot defend out loud is the plan that will fail in week three.

## Short answer
The grill-me skill reverses the usual direction: instead of answering your questions, it interrogates you about a plan or design until every unresolved branch is either decided or explicitly deferred. It is the fastest way to find the decision you have been quietly avoiding.

Best for: Design decisions, architecture choices and specifications before implementation starts.
Skip it if: The work is mechanical and there is nothing to decide.

## What to remember
- Being questioned surfaces gaps faster than being advised.
- Answers you invent under pressure are the ones to double check afterwards.
- It pairs with brainstorming and writing-plans, which sit on either side of it.
- It cannot supply domain knowledge you do not have. It only finds where it is missing.

## What it changes in practice
Most plans fail on the parts nobody wanted to discuss: migration, error paths, who owns the data, what happens to existing customers. Those are exactly the parts a friendly review skips.
An interrogation surfaces them because it keeps pulling on branches rather than approving the shape. The discomfort is the mechanism, not a side effect.

## Where it disappoints
It can grind. Not every branch deserves resolution before implementation, and deferring some deliberately is a legitimate answer that you have to give explicitly.
It also cannot check facts about your organisation. It will accept a confident answer that happens to be wrong.

## Install and first run
1. Install it with the skills CLI from mattpocock/skills, published under MIT.
2. Bring a real plan, not a topic. It interrogates decisions, not intentions.
3. Write down every answer you had to invent on the spot. Those are the actual gaps.

## Questions
### How is this different from asking for a review?
A review evaluates what you wrote. This questions you until the undecided parts of the plan are visible.

### When should I use it?
Before implementation, on anything where a wrong decision is expensive to reverse.

### Does it need a written plan?
Yes, bring a real plan. A topic produces vague questions and vague answers.

## Sources
- mattpocock/skills on GitHub: https://github.com/mattpocock/skills
- Agent skills directory listing: https://skills.sh

## Other languages
- Spanish: https://bestskillsforclaude.com/es/skills/grill-me
- Brazilian Portuguese: https://bestskillsforclaude.com/pt-br/skills/grill-me
- Japanese: https://bestskillsforclaude.com/ja/skills/grill-me