Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Interview the user one question at a time to resolve remaining ambiguity before implementation. Use when planning or brainstorming is done but unknowns remain, or when the user asks to be interviewed about a task or spec.
.claude/skills/neeeophytee-interview-me/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 260% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -34% | 0% |
Brainstorming is over and there are still gaps between the user's map and the territory. Close them by asking, one question at a time, starting with the questions whose answers would change the most.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 8,222 | 15,462 | +88% | 1 | 1 | 0% | 1,253 | 1,329 | +6% | 0 | 0 | — |
case-02 | pass→pass | 5,493 | 6,288 | +14% | 1 | 1 | 0% | 927 | 1,291 | +39% | 0 | 0 | — |
case-03 | fail→fail | 5,424 | 6,786 | +25% | 1 | 1 | 0% | 864 | 1,385 | +60% | 0 | 0 | — |
case-04 | pass→pass | 11,511 | 8,605 | -25% | 1 | 1 | 0% | 1,761 | 1,604 | -9% | 0 | 0 | — |
case-05 | pass→pass | 8,899 | 6,225 | -30% | 1 | 1 | 0% | 1,236 | 1,181 | -4% | 0 | 0 | — |
case-06 | pass→pass | 10,223 | 5,167 | -49% | 1 | 1 | 0% | 1,713 | 1,164 | -32% | 0 | 0 | — |
case-07 | fail→pass | 5,804 | 6,186 | +7% | 1 | 1 | 0% | 1,050 | 1,229 | +17% | 0 | 0 | — |
case-13 | pass→pass | 9,271 | 5,725 | -38% | 1 | 1 | 0% | 1,422 | 1,122 | -21% | 0 | 0 | — |
case-08 | fail→pass | 2,383 | 6,260 | +163% | 1 | 1 | 0% | 371 | 1,336 | +260% | 0 | 0 | — |
case-09 | fail→pass | 9,993 | 7,331 | -27% | 1 | 1 | 0% | 1,620 | 1,694 | +5% | 0 | 0 | — |
case-10 | pass→pass | 6,913 | 6,141 | -11% | 1 | 1 | 0% | 1,168 | 1,368 | +17% | 0 | 0 | — |
case-11 | fail→pass | 13,534 | 7,463 | -45% | 1 | 1 | 0% | 2,201 | 1,463 | -34% | 0 | 0 | — |
case-12 | pass→pass | 12,484 | 9,661 | -23% | 1 | 1 | 0% | 1,764 | 1,683 | -5% | 0 | 0 | — |
case-14 | fail→fail | 4,538 | 5,525 | +22% | 1 | 1 | 0% | 677 | 1,224 | +81% | 0 | 0 | — |
case-15 | fail→fail | 4,907 | 5,278 | +8% | 1 | 1 | 0% | 755 | 1,118 | +48% | 0 | 0 | — |
case-16 | fail→pass | 14,366 | 6,972 | -51% | 1 | 1 | 0% | 2,134 | 1,395 | -35% | 0 | 0 | — |
case-17 | pass→pass | 9,128 | 8,025 | -12% | 1 | 1 | 0% | 1,336 | 1,469 | +10% | 0 | 0 | — |
case-18 | fail→fail | 2,987 | 7,528 | +152% | 1 | 1 | 0% | 498 | 1,544 | +210% | 0 | 0 | — |
case-19 | pass→pass | 14,189 | 9,536 | -33% | 1 | 1 | 0% | 2,097 | 1,740 | -17% | 0 | 0 | — |
case-20 | pass→fail | 29,331 | 7,334 | -75% | 1 | 1 | 0% | 4,937 | 1,412 | -71% | 0 | 0 | — |
case-21 | pass→fail | 22,578 | 6,675 | -70% | 1 | 1 | 0% | 3,941 | 1,310 | -67% | 0 | 0 | — |
case-22 | pass→fail | 21,174 | 5,803 | -73% | 1 | 1 | 0% | 3,293 | 1,066 | -68% | 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. The headline lift of +14 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 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.
Other measured skills in the registry, with their headline benchmark lift.