Skip to content
Back to skills

Grill Me

ASecurity

Pressure-test a plan, belief, or strategy through a focused Socratic conversation when the user asks to challenge their thinking.

  • 26 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 23, 2026
ai-agents

Security analysis

A100/100

Scanned September 23, 2026

npx -y skills add tomcounsell/ai --skill grill-me --agent claude-code

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.

Security grade badge for Grill Me
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tomcounsell-grill-me-ai/badge)](https://www.skillsdirectory.com/skills/tomcounsell-grill-me-ai)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: grill-me
description: "Pressure-test a plan, belief, or strategy through a focused Socratic conversation when the user asks to challenge their thinking."
---

# Grill Me

Read referenced artifacts before questioning the user. Recover the claim from the conversation; ask what to examine only if it remains unclear.
Start with the least-examined assumption. Ask one pointed, non-leading question and wait for the answer before choosing the next. Useful probes: what would falsify the claim, what happens if its key premise fails, what tradeoff is being accepted, and how early failure becomes visible.
Track confidence by topic and follow vague answers to evidence. Stop when enough signal emerges or the user stops; five to seven questions is a guide, not a quota. Close with the most consequential unvalidated assumption, your confidence with reasons, and one practical validation action. The purpose is better judgment, not winning the argument.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.