grilling

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

1|Updated Aug 24, 2026
One-click install
npx skills add https://github.com/yamcodes/the-hat --skill grilling-yamcodes
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: grilling
Source: https://github.com/yamcodes/the-hat/tree/main/skills/grilling
Command: npx skills add https://github.com/yamcodes/the-hat --skill grilling-yamcodes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Plans and design decisions often contain hidden assumptions and unresolved dependencies that surface too late. This Skill stress-tests your thinking by relentlessly interviewing you until every decision in your plan is explicitly 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 only the questions whose prerequisites are already settled, numbering each question and providing a recommended answer. - Autonomous Fact-Finding: Dispatches sub-agents to look up facts from the environment instead of asking you for anything it could find itself. - Use Case: Before implementing a new caching layer, use this Skill to be grilled on eviction policy, invalidation triggers, storage backend, and failure modes until no assumption remains silently made. ## Quick Start Ask the AI to grill you about your plan or decision, for example by saying "grill me on my database migration plan".

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 design decision with an AI assistant?▼

Use the grilling skill to be interviewed about your plan in structured rounds. The AI maps your decision as a tree, asks all currently answerable questions with recommended answers, and continues until every branch is settled.

How does the grilling skill decide which questions to ask?▼

It computes a frontier of decisions whose prerequisites are already settled and asks that entire frontier in one numbered round. Questions depending on still-open answers are deferred to later rounds.

Can the AI look up facts itself during a grilling session?▼

Yes. When a question needs a fact from the filesystem or tools, the skill dispatches a sub-agent to find it rather than asking the user. Only questions downstream of that fact 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 remains silently assumed. The AI will not act on the plan until you confirm shared understanding.

When should I not use the grilling approach?▼

Avoid it for trivial or time-sensitive decisions where exhaustive questioning adds no value. It is designed for consequential plans and ideas where unexamined assumptions carry real risk.