grill-me

Clarify ambiguous plans through structured one-at-a-time decision-tree questions.

Updated May 3, 2026
One-click install
npx skills add https://github.com/tykhoncode/dicekit --skill grill-me-tykhoncode
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grill-me
Source: https://github.com/tykhoncode/dicekit/tree/main/.claude/skills/grill-me
Command: npx skills add https://github.com/tykhoncode/dicekit --skill grill-me-tykhoncode

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you resolve ambiguity in a plan or design by forcing clear tradeoffs and surfacing hidden dependencies until you and the user share the same understanding.

Core Features & Use Cases

  • Relentless decision-tree interrogation: Asks follow-up questions one at a time and walks through each branch of the design.
  • Dependency resolution: Identifies and clarifies how earlier decisions constrain later ones.
  • Codebase-aware answers: If a question can be answered by inspecting the repository, it checks the codebase to ground recommendations in reality.
  • Recommended outcome per step: For each question, it provides the recommended answer to move the plan forward.

Quick Start

Tell the AI: "Grill me on this plan: [paste your plan/design], and probe each assumption until we converge on a clear, implementable decision set."

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 an architecture design to surface hidden tradeoffs and dependencies?

Stress-testing a design involves driving a structured, question-by-question decision-tree interrogation that surfaces hidden dependencies and tradeoffs until a shared understanding is reached. Each decision node produces a recommended answer to resolve ambiguity and move the plan forward.

What is a decision tree approach for requirements clarification during a design review?

A decision tree approach for requirements clarification asks follow-up questions one at a time, walking through each branch of a design review. It resolves ambiguity by identifying how earlier decisions constrain later ones, ensuring every outcome aligns with the plan.

How do I resolve ambiguous plan tradeoffs using a structured interview process?

You resolve ambiguous plan tradeoffs using a structured interview process that forces clear choices at each step. It recommends an answer per question node while optionally inspecting the codebase to ground recommendations in reality and resolve dependencies.

Can I use codebase grounding to validate assumptions during an architecture discussion?

Yes, you can use codebase grounding to validate assumptions during an architecture discussion. When a question can be answered by inspecting the repository, the process checks the codebase to ground its recommended answers in reality rather than relying on assumptions.

Does design review interrogation work for evaluating constraints in early-stage planning?

Yes, design review interrogation works for early-stage planning by clarifying ambiguous plans and forcing clear tradeoffs. It drives a relentless decision-tree process until you and your team converge on a clear, implementable decision set.

What are the limitations of using a decision tree for tradeoff analysis?

The limitation of using a decision tree for tradeoff analysis is that it requires sequential, one-at-a-time interrogation, which may not suit rapid-fire brainstorming. It is built for resolving dependencies and aligning decisions, not generating initial concepts.