Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →bhoon716/ultra-grill-me
Use when the user wants to grill, stress-test, pressure-test, or otherwise validate a plan, design, product idea, architecture decision, implementation plan, business strategy, writing direction, research question, learning plan, personal decision, or Agent Skill design through Socratic, one-question-at-a-time interrogation with options and session logging. Also trigger on casual pre-execution phrasing like "X 하려고 하는데 파헤쳐줘", "빈틈없이 검증해줘", "질문으로 털어줘", "반대신문하듯 봐줘", "압박 검증해줘", or vague validation as
Passed 18 of 22 test cases with the skill, and 7 of 22 without it.
and 14 more in the full report
11 fixed7 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
I'm considering whether to accept a job offer at an early-stage startup versus staying at my corporate Tech Lead position. Please help me examine this choice by interrogating my plan through a one-question-at-a-time validation loop. At each step, show a one-line summary of where my decision stands, point out the biggest unresolved ambiguity blocking my choice, ask one precise question with its rationale, and give me numbered options where option 1 is marked as recommended, alongside options to see alternative recommendations or type my own answer.
| Checked | Without skill | With skill |
|---|---|---|
| The response includes the section label "**Why it matters**:" | Missed | Passed |
| The output ends with a closing prompt instructing the user how to respond. | Missed | Passed |
| The response presents between 2 and 5 concrete multiple-choice options before the meta-options. | Passed | Passed |
The instructions your model reads when the skill loads.
Stress-test a plan, design, product idea, strategy, writing direction, learning plan, personal decision, or Agent Skill design through Socratic, one-question-at-a-time interrogation. This skill aims to remove ambiguity, surface hidden assumptions, identify weak success criteria, analyze tradeoffs, and examine failure modes.
This is a "validation-before-execution" skill, NOT an immediate generation skill.
Use this skill when the user asks to:
Do not use this skill when:
logs/ directory (the folder adjacent to the active SKILL.md), following the format in logs/template.md. Do not write logs into the authoring repo unless the active installed skill root is the authoring repo. All grill sessions must be logged.test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.