grilling

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

Updated Aug 20, 2026
One-click install
npx skills add https://github.com/bittlinkm/claude-setup --skill grilling-bittlinkm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grilling
Source: https://github.com/bittlinkm/claude-setup/tree/main/skills/grilling
Command: npx skills add https://github.com/bittlinkm/claude-setup --skill grilling-bittlinkm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Plans and decisions often contain hidden assumptions and unexplored branches that only surface after execution fails. This Skill systematically interrogates an idea through structured rounds of questions until every decision in the design tree 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 question and providing a recommended answer. - Autonomous Fact-Finding: Dispatches sub-agents to look up facts from the environment instead of burdening the user with research questions. - Use Case: Before starting a migration project, use this Skill to be grilled on scope, rollback strategy, and dependencies until no assumption remains unexamined. ## Quick Start Ask the assistant to grill you on your plan for launching a new feature until you reach a shared understanding.

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?

Stress-test a plan by having it interrogated as a design tree of decisions. Each round surfaces the frontier of questions whose prerequisites are settled, with recommended answers, until every branch is explicitly decided and nothing is silently assumed.

What is a design tree for decision making?

A design tree maps a plan as decisions branching into dependent sub-decisions. The frontier is the set of questions answerable now; answering them pushes the frontier outward until the entire tree is visited.

How does the grilling process handle questions that need external facts?

Fact-finding is delegated to sub-agents that look up information from the filesystem or tools, never the user. Questions downstream of a running exploration wait, while the rest of the frontier is asked immediately.

When does a grilling session end?

A session ends when the frontier is empty, meaning every branch of the design tree has been visited and no assumption remains unexamined. The user must confirm shared understanding before any action is taken.

When should I not use round-based grilling for decisions?

Avoid it for trivial or time-critical decisions where exhaustive exploration costs more than the risk of a wrong call. It is designed for consequential plans where hidden assumptions carry real downside.