Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →fradser/grill-me
Runs a relentless interview that sharpens a plan or design.
Passed 6 of 17 test cases with the skill, and 2 of 17 without it.
and 13 more in the full report
8 fixed0 passed either way12 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need to align on a strategy for handling background job failures in our queue processor. Start grilling me so we can establish a clear shared plan.
| Checked | Without skill | With skill |
|---|---|---|
| Limits the interrogation to one question. | Missed | Passed |
| Designates one option as '(Recommended)'. | Missed | Passed |
The instructions your model reads when the skill loads.
Call the Skill tool with "grilling".
Run the /mattpocock:grilling discipline relentlessly: one question at a time via the AskUserQuestion tool, each with your recommended option marked "(Recommended)", waiting for the answer before continuing. Do not act until the user confirms shared understanding.
test cases passed, vs 2 / 17 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.