grilling

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

1|Updated Mar 7, 2025
One-click install
npx skills add https://github.com/carmonalab/ECODA_paper --skill grilling-carmonalab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: grilling
Source: https://github.com/carmonalab/ECODA_paper/tree/main/.agents/skills/grilling
Command: npx skills add https://github.com/carmonalab/ECODA_paper --skill grilling-carmonalab

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Plans and design decisions often contain hidden assumptions and unexplored branches that only surface after implementation begins. This Skill stress-tests an idea by relentlessly interviewing the user, mapping every decision as a design tree so nothing is left silently assumed. ## Core Features & Use Cases - Design Tree Mapping: Models the plan as a tree where every decision branches into dependent sub-decisions. - Frontier-Based Rounds: Asks only the questions whose prerequisites are settled, numbering each question and providing a recommended answer per round. - Fact Delegation: Dispatches sub-agents to look up environmental facts instead of asking the user for information that can be retrieved directly. - Use Case: Before starting a migration project, have the AI grill you on the plan so every architectural choice, dependency, and risk is explicitly decided and confirmed before any code is written. ## Quick Start Grill me on my plan to migrate our monolith to microservices until we reach a shared understanding.

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 or idea with an AI assistant?▼

Ask the AI to grill you on your plan. It maps your decisions as a design tree and interviews you in rounds, asking every question whose prerequisites are settled until no assumptions remain unexplored.

What is a design tree in decision planning?▼

A design tree models every decision as a node whose branches are the sub-decisions that depend on it. The frontier is the set of questions answerable now, and each answered round pushes the frontier outward to unblock dependent questions.

How does the grilling interview format work?▼

Each round presents numbered questions with a title, detailed body, and a recommended answer marked with an arrow. You answer all questions in the round, then the next round of newly unblocked questions is computed and asked.

Does the AI ask me for facts it could look up itself?▼

No. When a question needs a fact from the filesystem or tools, a sub-agent is dispatched to find it. Only downstream questions wait for that result; the rest of the frontier is asked immediately.

When is the grilling session finished?▼

The session ends when the frontier is empty, meaning every branch of the design tree has been visited and nothing is silently assumed. The AI does not act on the plan until you confirm shared understanding.