grill-me

Interviews the user question-by-question to stress-test plans and design decisions.

Updated May 7, 2026
One-click install
npx skills add https://github.com/Pieter-1337/Euricom-tsz --skill grill-me-pieter-1337
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grill-me
Source: https://github.com/Pieter-1337/Euricom-tsz/tree/main/.claude/skills/matt-grill-me
Command: npx skills add https://github.com/Pieter-1337/Euricom-tsz --skill grill-me-pieter-1337

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Plans and designs often contain hidden assumptions, unresolved dependencies, and unexplored branches that only surface during implementation. This Skill systematically interrogates every aspect of a plan so gaps and weak decisions are exposed before work begins. ## Core Features & Use Cases - Relentless one-at-a-time questioning: Walks down each branch of the design decision tree, resolving dependencies between decisions sequentially. - Recommended answers: For each question asked, it provides its own recommended answer so the user can accept, reject, or refine it. - Codebase grounding: When a question can be answered by exploring the codebase, it investigates the code directly instead of asking. - Use Case: Before implementing a new feature architecture, ask to be grilled on the design so every trade-off, dependency, and edge case is explicitly decided. ## Quick Start Ask the assistant to grill you on your current plan or design document until every decision is resolved.

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 design plan with an AI assistant?

Invoke the grill-me skill and present your plan or design. The assistant interviews you one question at a time, walking each branch of the decision tree and offering recommended answers until every dependency is resolved.

How does the grill-me skill answer questions about my codebase?

When a question can be answered by exploring the codebase, the skill investigates the code directly instead of asking you. This keeps the interview focused on genuine decisions rather than discoverable facts.

When should I use design interrogation instead of a standard code review?

Use it before implementation begins, when decisions are still cheap to change. It targets plan-level assumptions and decision dependencies, whereas code review evaluates already-written implementation.

What are the limitations of AI-driven plan interrogation?

The quality of questioning depends on the context provided about the plan and codebase. It cannot validate business constraints or stakeholder requirements that exist only outside the repository and conversation.