Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
.claude/skills/mxyhi-grilling/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 154% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 126% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-22 | ✗→✓ | ▲ Improved | -4% | 0% |
Interview the user relentlessly until you reach a shared understanding. Map this as a design tree: every decision branches into the decisions that hang off it.
Work the tree in rounds. The frontier is every decision whose prerequisites are already settled — the questions you can ask _now_ without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.
Each question should be formatted like so:
❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>Each round the user answers reshapes the tree — settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a _later_ round, not this one.
Finding _facts_ is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it — don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report — ask the rest of the frontier now. The _decisions_ are the user's — put each to them and wait.
The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 16,601 | 11,628 | -30% | 1 | 1 | 0% | 907 | 2,300 | +154% | 0 | 0 | — |
case-02 | pass→pass | 15,486 | 15,058 | -3% | 1 | 1 | 0% | 2,303 | 2,568 | +12% | 0 | 0 | — |
case-03 | fail→fail | 11,090 | 16,188 | +46% | 1 | 1 | 0% | 2,006 | 2,549 | +27% | 0 | 0 | — |
case-04 | pass→fail | 25,859 | 17,867 | -31% | 1 | 1 | 0% | 4,814 | 3,324 | -31% | 0 | 0 | — |
case-05 | fail→fail | 17,677 | 20,176 | +14% | 1 | 1 | 0% | 1,753 | 2,284 | +30% | 0 | 0 | — |
case-06 | pass→fail | 16,197 | 5,603 | -65% | 1 | 1 | 0% | 2,804 | 701 | -75% | 0 | 0 | — |
case-07 | pass→pass | 12,517 | 12,960 | +4% | 1 | 1 | 0% | 2,163 | 2,580 | +19% | 0 | 0 | — |
case-08 | fail→fail | 4,104 | 4,459 | +9% | 1 | 1 | 0% | 676 | 683 | +1% | 0 | 0 | — |
case-09 | pass→pass | 8,819 | 8,754 | -1% | 1 | 1 | 0% | 1,441 | 1,773 | +23% | 0 | 0 | — |
case-10 | pass→pass | 14,251 | 13,962 | -2% | 1 | 1 | 0% | 2,514 | 2,854 | +14% | 0 | 0 | — |
case-11 | pass→pass | 11,910 | 12,888 | +8% | 1 | 1 | 0% | 1,962 | 2,647 | +35% | 0 | 0 | — |
case-12 | pass→pass | 16,360 | 13,546 | -17% | 1 | 1 | 0% | 2,971 | 2,863 | -4% | 0 | 0 | — |
case-13 | fail→pass | 6,932 | 13,771 | +99% | 1 | 1 | 0% | 1,283 | 2,894 | +126% | 0 | 0 | — |
case-14 | pass→pass | 8,672 | 13,005 | +50% | 1 | 1 | 0% | 1,555 | 2,728 | +75% | 0 | 0 | — |
case-15 | fail→pass | 10,976 | 10,882 | -1% | 1 | 1 | 0% | 1,846 | 2,239 | +21% | 0 | 0 | — |
case-16 | pass→pass | 9,809 | 7,471 | -24% | 1 | 1 | 0% | 1,825 | 1,664 | -9% | 0 | 0 | — |
case-17 | pass→pass | 11,009 | 10,810 | -2% | 1 | 1 | 0% | 1,953 | 2,235 | +14% | 0 | 0 | — |
case-18 | pass→fail | 14,384 | 15,962 | +11% | 1 | 1 | 0% | 1,139 | 3,334 | +193% | 0 | 0 | — |
case-19 | fail→fail | 8,354 | 3,781 | -55% | 1 | 1 | 0% | 1,462 | 512 | -65% | 0 | 0 | — |
case-20 | pass→pass | 10,006 | 9,808 | -2% | 1 | 1 | 0% | 1,838 | 2,035 | +11% | 0 | 0 | — |
case-21 | fail→pass | 13,568 | 12,309 | -9% | 1 | 1 | 0% | 2,113 | 2,497 | +18% | 0 | 0 | — |
case-22 | fail→pass | 8,736 | 5,976 | -32% | 1 | 1 | 0% | 1,458 | 1,398 | -4% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 19 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +9 percentage points is the difference between those two pass rates over the 19 comparable cases. 4 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/3/2026 | — |
Other measured skills in the registry, with their headline benchmark lift.