grill-me

Stress-test plans through iterative questioning to expose assumptions and decision gaps.

Updated Apr 30, 2026
One-click install
npx skills add https://github.com/jnlanahan/Product-Agents-and-Skills --skill grill-me-jnlanahan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grill-me
Source: https://github.com/jnlanahan/Product-Agents-and-Skills/tree/main/skills/2-Define-Grill-Me
Command: npx skills add https://github.com/jnlanahan/Product-Agents-and-Skills --skill grill-me-jnlanahan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents vague or unvalidated plans from moving forward by forcing a structured, one-branch-at-a-time review until decisions and assumptions align.

Core Features & Use Cases

  • Relentless decision-tree interviews: Walks through the design plan one question at a time to surface hidden dependencies between decisions.
  • Shared-understanding convergence: Turns ambiguous areas into explicit choices by resolving assumptions interactively.
  • Codebase-guided answers: When a question can be answered by inspecting the repository, it prioritizes exploring the codebase over guessing.
  • Operational logging: Records key outcomes into .claude/progress.md and suggests the next step based on remaining gaps.
  • Use case: Before implementation, you can stress-test a PRD or architecture/design so you don’t discover mismatches during build or review.

Quick Start

Ask the assistant to run the /grill-me flow on your plan and interview you relentlessly until every unresolved assumption is identified.

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 product design to expose hidden assumptions before implementation?

Relentless decision-tree interviews stress-test a plan by asking one question at a time, forcing ambiguous areas into explicit choices to expose assumptions and dependencies before implementation begins.

What is the best way to review a PRD for unresolved dependencies and decision gaps?

Reviewing a PRD for decision gaps requires iterative questioning that traverses a single-question decision tree, ensuring every unresolved assumption is identified and aligned prior to build or review.

Can I use assumption testing to validate architecture design against my existing codebase?

Yes, assumption testing can validate architecture design by exploring the codebase to answer factual questions about your repository, preventing the interview process from relying on guesses.

How do I log plan review outcomes and track remaining gaps after a design critique?

You can log plan review outcomes by recording key decisions and remaining gaps into a progress file, which then provides a clear recommendation for your next operational step based on unresolved areas.

Does scenario planning work with single-question-at-a-time decision tree traversal?

Scenario planning works effectively with single-question-at-a-time decision tree traversal because it systematically forces answers to converge into shared understanding by resolving dependencies one branch at a time.