grilling

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

3|1|Updated Jul 12, 2026
One-click install
npx skills add https://github.com/DuckKota/my-opencode-setup --skill grilling-duckkota
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: grilling
Source: https://github.com/DuckKota/my-opencode-setup/tree/main/src/skills/grilling
Command: npx skills add https://github.com/DuckKota/my-opencode-setup --skill grilling-duckkota

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 an idea by relentlessly interviewing the user 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 per round. - Autonomous Fact-Finding: Dispatches sub-agents to look up facts from the filesystem or tools instead of asking the user for information it can find itself. - Use Case: Before implementing a new architecture, have the AI grill you on data models, failure modes, and integration points round by round until no assumption remains unexamined. ## Quick Start Ask the AI to grill you on your plan for the upcoming 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 or design decision with AI?▼

Ask the AI to grill you on your plan. It maps your decisions as a tree, then interviews you in rounds, asking only the questions whose prerequisites are settled and recommending an answer for each until nothing is left assumed.

What is a design tree in decision planning?▼

A design tree models every decision as a node branching into the sub-decisions that depend on it. The frontier is the set of questions answerable now; settled answers push the frontier outward and unblock dependent questions.

Does the grilling skill answer its own questions using the environment?▼

Yes. When a question needs a fact from the filesystem or tools, it dispatches a sub-agent to find it rather than asking the user. Only the decisions themselves are left to the user.

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 no assumption remains silent. The AI will not act on the outcome until the user confirms shared understanding.

When should I not use round-based grilling for a decision?▼

Avoid it for trivial or time-critical decisions where exhaustive questioning adds no value. It is designed for consequential plans where hidden assumptions carry real risk, not quick everyday choices.