grilling

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

Updated Aug 22, 2026
One-click install
npx skills add https://github.com/falentio/cimi --skill grilling-falentio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grilling
Source: https://github.com/falentio/cimi/tree/main/.agents/skills/skills/grilling
Command: npx skills add https://github.com/falentio/cimi --skill grilling-falentio

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 systematically interrogates an idea through structured rounds of questions until every decision is explicitly settled. ## 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 already settled, numbering each one and providing a recommended answer. - Autonomous Fact-Finding: Dispatches sub-agents to look up facts from the environment instead of asking the user for information it can find itself. - Use Case: Before starting a migration project, use this Skill to be grilled on scope, rollback strategy, and data handling so no critical decision is left silently assumed. ## Quick Start Ask the AI to grill you on your plan for an upcoming project or decision and answer each numbered round of questions.

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?

Present your plan and ask to be grilled on it. The Skill maps your decisions as a tree and asks numbered questions in rounds, giving recommended answers, until every branch is explicitly settled and confirmed.

What is a design tree in decision making?

A design tree models a plan where every decision branches into the sub-decisions that depend on it. The frontier is the set of questions whose prerequisites are already answered, so they can be asked immediately without guessing.

How does the round-based questioning format work?

Each round asks the entire current frontier at once: numbered questions with a title, body, and a recommended answer. Your answers settle decisions, push the frontier outward, and unblock dependent questions for the next round.

Does the grilling process require me to research facts myself?

No. When a question needs a fact from the filesystem or environment, a sub-agent is dispatched to find it. You only make decisions; fact-gathering never blocks questions that do not depend on the pending research.

When is the grilling session considered complete?

The session ends when the frontier is empty, meaning every branch of the design tree has been visited and nothing remains silently assumed. No action is taken until you confirm a shared understanding has been reached.