grilling

Interviews users in structured rounds to stress-test plans and decisions.

1|Updated Nov 9, 2025
One-click install
npx skills add https://github.com/akashjpal/question-generator --skill grilling-akashjpal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grilling
Source: https://github.com/akashjpal/question-generator/tree/main/.agents/skills/grilling
Command: npx skills add https://github.com/akashjpal/question-generator --skill grilling-akashjpal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Plans and decisions often contain hidden assumptions and unresolved dependencies that only surface after execution begins. This Skill systematically interrogates a plan, decision, or idea until every open question is answered and a shared understanding is reached. ## Core Features & Use Cases - Design Tree Mapping: Models every decision as a tree where each choice branches into dependent sub-decisions. - Frontier-Based Rounds: Asks only the questions whose prerequisites are settled, numbering each one and providing a recommended answer. - Autonomous Fact-Finding: Dispatches sub-agents to look up facts from the environment instead of asking the user for information it can find itself. - Use Case: Before starting a major refactor, have the AI grill you on architecture choices, migration strategy, and rollback plans so gaps in your thinking surface before you write code. ## Quick Start Ask the AI to grill you on your plan for an upcoming project or decision and answer each numbered round of questions until the frontier is empty.

Frequently Asked Questions about grilling

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

FAQPage Schema
How do I stress-test a plan with an AI assistant?

Ask the AI to grill you on your plan. It maps your decisions into a tree, then asks numbered questions in rounds, giving a recommended answer for each, until every open decision is resolved.

What is a design tree in decision-making?

A design tree models each decision as a node whose answer unlocks dependent sub-decisions. The frontier is the set of questions answerable right now, and each answered round pushes the frontier outward.

Can the AI look up facts instead of asking me during an interview?

Yes. When a question needs a fact from the filesystem or tools, the Skill dispatches a sub-agent to find it rather than asking you. Only genuine decisions are put to the user.

When should I use structured interrogation instead of a simple review?

Use it when a plan has many interdependent decisions and hidden assumptions, such as architecture choices or product launches. A simple review suits small, self-contained decisions with few dependencies.

When does a grilling session end?

The session ends when the frontier is empty, meaning every branch of the design tree has been visited and nothing remains silently assumed. The AI waits for your confirmation before acting on the outcome.