grilling

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

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/Fatih0234/mattpocock-skills-pi --skill grilling-fatih0234
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: grilling
Source: https://github.com/Fatih0234/mattpocock-skills-pi/tree/main/skills/productivity/grilling
Command: npx skills add https://github.com/Fatih0234/mattpocock-skills-pi --skill grilling-fatih0234

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Plans and decisions often contain hidden assumptions and unexplored branches that only surface after implementation begins. This Skill forces every decision into the open by relentlessly interviewing the user until a shared understanding is reached. ## Core Features & Use Cases - Design Tree Mapping: Models a plan as a tree of decisions where each choice 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 Investigation: Delegates codebase exploration to a repo-scout subagent so factual questions are answered by investigation, not by the user. - Use Case: Before starting a migration, have the agent grill you on scope, rollback strategy, and data handling so every assumption is explicitly decided before any code changes. ## Quick Start Ask the agent to grill you on your plan for an upcoming feature or architectural decision.

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 agent?▼

Ask the agent to grill you on your plan. It maps your decisions as a tree, then asks numbered questions in rounds with recommended answers, continuing until every branch is settled 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 whose prerequisites are already answered, so only those are asked in each round.

Can the agent investigate the codebase during a grilling session?▼

Yes. When a question requires substantial codebase exploration, the skill dispatches a repo-scout subagent to gather facts, grouping independent investigations into parallel dispatches before asking the current round.

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 agent waits for explicit user confirmation before acting on the outcome.

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

Avoid it for trivial decisions with no downstream dependencies or when requirements are already fully specified. The multi-round format adds overhead that only pays off for plans with branching, interdependent decisions.