grill-me

Interview users one question at a time to clarify plans and resolve decision branches.

Updated Jul 11, 2022
One-click install
npx skills add https://github.com/zhengfran/dotconfig --skill grill-me-zhengfran
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grill-me
Source: https://github.com/zhengfran/dotconfig/tree/main/tools/ai/agents/skills/grill-me
Command: npx skills add https://github.com/zhengfran/dotconfig --skill grill-me-zhengfran

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you uncover hidden assumptions, resolve ambiguities, and reach shared understanding of a plan or design by forcing the discussion down every branch of the decision tree.

Core Features & Use Cases

  • Relentless interview: Questions are asked one at a time to iteratively clarify intent, constraints, and tradeoffs.
  • Branch-by-branch decision resolution: Each dependency between decisions is resolved before moving forward.
  • Codebase-backed answers: When applicable, it explores the codebase to ground answers in actual implementation details.
  • Use Case: You have a proposed system design, and you want confidence that requirements, dependencies, and failure modes are fully understood and agreed upon before implementation.

Quick Start

Ask an AI to run the grill-me interview by saying: "Grill me on this plan until we reach shared understanding: [paste your plan/design here]."

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 system design to uncover hidden assumptions and dependencies?

A relentless interview asks questions one at a time to iteratively clarify intent, constraints, and tradeoffs. This branch-by-branch resolution ensures all stakeholders reach shared understanding before implementation begins.

How do I resolve ambiguities and achieve stakeholder alignment for a proposed plan?

Achieve stakeholder alignment by conducting a relentless, one-question-at-a-time interrogation that forces branch-by-branch decision resolution. This uncovers hidden assumptions and validates scenarios iteratively until shared understanding is reached.

Can I use codebase exploration to ground design review answers in actual implementation details?

Yes, codebase exploration can be applied during design review to ground answers in actual implementation details. This ensures dependency resolution and scenario validation are accurately contextualized within the existing system architecture.

What is the best way to perform tradeoff analysis for complex system designs?

The best way to perform tradeoff analysis is driving an in-depth interview that explores every decision-tree branch. By resolving dependencies and clarifying constraints one question at a time, you validate complex scenarios thoroughly.

When do I need a decision tree for requirements clarification and scenario validation?

You need a decision tree for requirements clarification when your proposed system design has complex dependencies and failure modes. It forces branch-by-branch resolution to ensure all ambiguities are uncovered before implementation.