Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →이 스킬은 moai-commerce:marketplace-coupang-ads로 이름이 변경되었습니다. 쿠팡 광고 풀세트 최적화(캠페인 분류·검색/비검색 분리·엔드 ROAS·자동규칙)는 새 이름으로 호출하세요. 다음과 같은 요청 시 사용하세요: "쿠팡 광고 분석해줘", "쿠팡 AI스마트광고 세팅", "쿠팡 캠페인 분리", "목표 ROAS 설정" 별칭(alias) 유지용 스텁 — 실제 기능은 moai-commerce:marketplace-coupang-ads로 위임됩니다.
.claude/skills/modu-ai-coupang-ad-optimizer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -62% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -75% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -58% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -62% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -65% | 0% |
이 스킬은 moai-commerce:marketplace-coupang-ads로 이름이 변경되었습니다 (marketplace- 패밀리 편입). 쿠팡 광고 최적화 작업은 moai-commerce:marketplace-coupang-ads를 사용하세요. 이 스텁은 기존 호출 호환을 위해 유지됩니다.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-20 | pass→pass | 13,311 | 10,050 | -24% | 1 | 1 | 0% | 2,206 | 1,804 | -18% | 0 | 0 | — |
case-21 | pass→pass | 16,878 | 13,988 | -17% | 1 | 1 | 0% | 2,831 | 2,526 | -11% | 0 | 0 | — |
case-01 | pass→pass | 7,619 | 2,881 | -62% | 1 | 1 | 0% | 1,233 | 659 | -47% | 0 | 0 | — |
case-02 | fail→pass | 6,056 | 1,999 | -67% | 1 | 1 | 0% | 1,049 | 394 | -62% | 0 | 0 | — |
case-03 | fail→pass | 12,101 | 2,017 | -83% | 1 | 1 | 0% | 1,766 | 442 | -75% | 0 | 0 | — |
case-04 | fail→pass | 8,614 | 2,565 | -70% | 1 | 1 | 0% | 1,263 | 526 | -58% | 0 | 0 | — |
case-05 | fail→pass | 6,740 | 1,990 | -70% | 1 | 1 | 0% | 1,153 | 433 | -62% | 0 | 0 | — |
case-06 | fail→pass | 7,013 | 1,479 | -79% | 1 | 1 | 0% | 1,019 | 357 | -65% | 0 | 0 | — |
case-07 | fail→pass | 7,641 | 1,666 | -78% | 1 | 1 | 0% | 1,144 | 355 | -69% | 0 | 0 | — |
case-08 | fail→pass | 13,558 | 2,645 | -80% | 1 | 1 | 0% | 2,279 | 530 | -77% | 0 | 0 | — |
case-09 | fail→pass | 10,092 | 2,313 | -77% | 1 | 1 | 0% | 1,604 | 430 | -73% | 0 | 0 | — |
case-10 | fail→pass | 7,966 | 2,260 | -72% | 1 | 1 | 0% | 1,288 | 445 | -65% | 0 | 0 | — |
case-19 | fail→pass | 9,734 | 2,611 | -73% | 1 | 1 | 0% | 1,515 | 559 | -63% | 0 | 0 | — |
case-11 | fail→pass | 9,648 | 1,858 | -81% | 1 | 1 | 0% | 1,533 | 424 | -72% | 0 | 0 | — |
case-12 | fail→pass | 9,172 | 2,844 | -69% | 1 | 1 | 0% | 1,463 | 336 | -77% | 0 | 0 | — |
case-13 | fail→pass | 9,322 | 1,828 | -80% | 1 | 1 | 0% | 1,468 | 386 | -74% | 0 | 0 | — |
case-14 | fail→pass | 10,787 | 3,442 | -68% | 1 | 1 | 0% | 1,782 | 726 | -59% | 0 | 0 | — |
case-15 | fail→pass | 7,558 | 1,720 | -77% | 1 | 1 | 0% | 1,231 | 386 | -69% | 0 | 0 | — |
case-16 | fail→pass | 9,720 | 2,177 | -78% | 1 | 1 | 0% | 1,643 | 432 | -74% | 0 | 0 | — |
case-17 | fail→pass | 9,823 | 1,845 | -81% | 1 | 1 | 0% | 1,575 | 401 | -75% | 0 | 0 | — |
case-18 | pass→pass | 11,060 | 1,879 | -83% | 1 | 1 | 0% | 1,700 | 379 | -78% | 0 | 0 | — |
case-22 | pass→pass | 12,561 | 7,620 | -39% | 1 | 1 | 0% | 2,065 | 1,282 | -38% | 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 +77 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.