grilling

Stress-tests plans and decisions through structured rounds of interview questions.

4|Updated May 26, 2026
One-click install
npx skills add https://github.com/YYG501/PM-AI-Harness --skill grilling-yyg501
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grilling
Source: https://github.com/YYG501/PM-AI-Harness/tree/main/vendor/mattpocock-skills/skills/productivity/grilling
Command: npx skills add https://github.com/YYG501/PM-AI-Harness --skill grilling-yyg501

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Plans and decisions often contain hidden assumptions and unexplored branches that only surface after execution begins. This Skill interviews you relentlessly about a plan, decision, or idea, mapping it as a design tree so every dependent decision is examined before you commit. ## Core Features & Use Cases - Design Tree Mapping: Models your plan as a tree where every decision branches into the decisions that depend on it. - Frontier-Based Rounds: Asks only the questions whose prerequisites are already settled, numbering each question and providing a recommended answer per round. - Fact-Finding via Sub-Agents: Dispatches sub-agents to look up facts from the filesystem or tools instead of asking you for information it can find itself. - Use Case: Before starting a migration project, use this Skill to grill yourself on the plan; it will surface unanswered questions about rollback strategy, data validation, and sequencing across multiple rounds until nothing is silently assumed. ## Quick Start Ask the AI to grill you on your plan for the upcoming product launch 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 before executing it?

Use a structured interview approach that maps your plan as a design tree of dependent decisions. Each round asks only the questions whose prerequisites are settled, with recommended answers, until every branch has been examined and nothing is silently assumed.

What is a design tree for decision making?

A design tree models a plan where every decision branches into the decisions that depend on it. The frontier is the set of questions answerable now; answering them pushes the frontier outward and unblocks dependent questions in later rounds.

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

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 questions downstream of that fact wait; the rest of the frontier is asked immediately.

When should I not use a grilling-style interview process?

Avoid it for trivial or fully reversible decisions where the cost of multi-round questioning exceeds the risk of a wrong choice. It is designed for plans and decisions where hidden assumptions carry real consequences.

How does the interview know when the plan is fully explored?

The session ends when the frontier is empty, meaning every branch of the design tree has been visited and no decision remains silently assumed. The AI waits for your confirmation of shared understanding before any action is taken.