grill-me

Runs a relentless interview session to sharpen a plan or design.

Updated Sep 17, 2026
One-click install
npx skills add https://github.com/coseto6125/claude-setup --skill grill-me-coseto6125
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: grill-me
Source: https://github.com/coseto6125/claude-setup/tree/main/skills/grill-me
Command: npx skills add https://github.com/coseto6125/claude-setup --skill grill-me-coseto6125

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Plans and designs often contain hidden assumptions and weak spots that only surface under pressure. This Skill subjects your plan or design to a relentless interview so flaws are exposed before implementation begins. ## Core Features & Use Cases - Relentless Interview: Delegates to the /grilling session, which interrogates your plan or design with probing questions. - Plan Sharpening: Forces you to articulate and defend decisions, revealing gaps in reasoning. - Use Case: Before starting a new module, invoke this Skill to have your design challenged question by question until the weak points are identified and resolved. ## Quick Start Ask the assistant to grill you on your current plan or design so its weak points are exposed before you build it.

Frequently Asked Questions about grill-me

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I stress-test a plan before implementing it?▼

Invoke this Skill to start a grilling session where the AI interviews you relentlessly about your plan. Each answer exposes assumptions and gaps, letting you fix weaknesses before writing any code.

What is the difference between grill-me and grilling?▼

grill-me is a thin entry point that runs a /grilling session. The grilling skill contains the actual interview logic, while grill-me provides a direct, user-invoked way to start that session.

Can I use this to review a design document?▼

Yes. Present your design or plan and the session will interrogate it question by question. It works for architecture decisions, feature plans, or any design that benefits from adversarial scrutiny.

When should I not use an interview-style plan review?▼

Avoid it when you need automated checks like linting, dependency audits, or test coverage, since the session is conversational and produces no artifacts. Use it for reasoning validation, not mechanical verification.