grilling

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

Updated Sep 16, 2022
One-click install
npx skills add https://github.com/ryuya-matsunawa/dotfiles --skill grilling-ryuya-matsunawa
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: grilling
Source: https://github.com/ryuya-matsunawa/dotfiles/tree/main/agents/.agents/skills/grilling
Command: npx skills add https://github.com/ryuya-matsunawa/dotfiles --skill grilling-ryuya-matsunawa

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Plans and decisions often contain hidden assumptions and unexplored branches. This Skill stress-tests your thinking by relentlessly interviewing you until every decision in your plan has been explicitly examined and settled. ## Core Features & Use Cases - Design Tree Mapping: Models your plan as a tree of decisions where each choice branches into dependent sub-decisions. - Frontier-Based Rounds: Asks all currently answerable questions in numbered rounds, each with a recommended answer, then recomputes the frontier based on your replies. - Autonomous Fact-Finding: Dispatches sub-agents to look up facts from the environment instead of asking you for information it can find itself. - Use Case: Before starting a major refactor, use this Skill to grill yourself on architecture choices, migration strategy, and rollback plans until no assumption remains unexamined. ## Quick Start Ask the AI to grill you about your plan for an upcoming project or decision you want to stress-test.

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 decision with AI?▼

Ask the AI to grill you about your plan. It maps your decisions as a tree, then interviews you in numbered rounds of questions with recommended answers until every branch has been examined and no assumptions remain.

What is a design tree in decision planning?▼

A design tree models a plan as decisions that branch into dependent sub-decisions. The frontier is the set of questions answerable now; settled answers push the frontier outward and unblock dependent questions in later rounds.

Does the grilling skill ask users for facts it could look up?▼

No. Fact-finding is delegated to sub-agents that inspect the environment such as the filesystem or tools. Only decisions are put to the user, and questions depending on pending facts wait for the sub-agent to report.

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 is silently assumed. The AI will not act on the plan until you confirm a shared understanding.

When should I not use a question-round interview approach?▼

Avoid it for trivial decisions with no downstream dependencies or when you need immediate execution rather than deliberation. The multi-round format is designed for consequential plans where unexamined assumptions carry real risk.