Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →(별칭) media-production 스킬은 두 개의 스킬로 분리되었습니다. 콘텐츠 발행 일정·캘린더는 moai-content:content-calendar 를, 유튜브·팟캐스트 에피소드 기획은 moai-content:youtube-podcast-planner 를 사용하세요.
.claude/skills/modu-ai-media-production/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-20 | ✓→✓ | ＝ Same ✓ | -12% | 0% |
| case-21 | ✓→✓ | ＝ Same ✓ | -3% | 0% |
| case-22 | ✓→✓ | ＝ Same ✓ | -16% | 0% |
media-production 스킬은 산출물 단위로 두 개의 스킬로 분리되었습니다. 요청 성격에 따라 아래 스킬을 사용하세요.
moai-content:content-calendarmoai-content:youtube-podcast-planner| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→pass | 13,749 | 10,440 | -24% | 1 | 1 | 0% | 2,056 | 1,786 | -13% | 0 | 0 | — |
case-01 | fail→fail | 16,983 | 14,167 | -17% | 1 | 1 | 0% | 2,574 | 2,415 | -6% | 0 | 0 | — |
case-02 | fail→fail | 18,574 | 19,395 | +4% | 1 | 1 | 0% | 2,868 | 3,239 | +13% | 0 | 0 | — |
case-03 | fail→fail | 16,031 | 10,694 | -33% | 1 | 1 | 0% | 2,607 | 1,795 | -31% | 0 | 0 | — |
case-05 | fail→fail | 14,576 | 10,471 | -28% | 1 | 1 | 0% | 2,307 | 1,892 | -18% | 0 | 0 | — |
case-06 | fail→fail | 19,820 | 17,778 | -10% | 1 | 1 | 0% | 2,821 | 2,954 | +5% | 0 | 0 | — |
case-07 | fail→fail | 20,102 | 14,295 | -29% | 1 | 1 | 0% | 3,171 | 2,329 | -27% | 0 | 0 | — |
case-08 | fail→fail | 21,786 | 16,738 | -23% | 1 | 1 | 0% | 3,244 | 2,690 | -17% | 0 | 0 | — |
case-09 | fail→fail | 20,960 | 13,625 | -35% | 1 | 1 | 0% | 3,357 | 2,359 | -30% | 0 | 0 | — |
case-10 | fail→fail | 16,227 | 16,638 | +3% | 1 | 1 | 0% | 2,694 | 2,921 | +8% | 0 | 0 | — |
case-11 | fail→fail | 18,580 | 16,394 | -12% | 1 | 1 | 0% | 2,850 | 2,747 | -4% | 0 | 0 | — |
case-12 | fail→pass | 17,284 | 16,128 | -7% | 1 | 1 | 0% | 2,734 | 2,708 | -1% | 0 | 0 | — |
case-13 | fail→fail | 18,410 | 15,727 | -15% | 1 | 1 | 0% | 3,005 | 2,769 | -8% | 0 | 0 | — |
case-14 | fail→fail | 19,550 | 17,486 | -11% | 1 | 1 | 0% | 2,981 | 3,074 | +3% | 0 | 0 | — |
case-15 | fail→fail | 25,626 | 20,645 | -19% | 1 | 1 | 0% | 3,524 | 3,216 | -9% | 0 | 0 | — |
case-16 | fail→fail | 18,839 | 12,815 | -32% | 1 | 1 | 0% | 2,710 | 2,124 | -22% | 0 | 0 | — |
case-17 | fail→fail | 16,062 | 14,897 | -7% | 1 | 1 | 0% | 2,733 | 2,616 | -4% | 0 | 0 | — |
case-18 | fail→fail | 20,394 | 15,368 | -25% | 1 | 1 | 0% | 3,203 | 2,713 | -15% | 0 | 0 | — |
case-19 | fail→fail | 20,415 | 19,404 | -5% | 1 | 1 | 0% | 2,977 | 3,217 | +8% | 0 | 0 | — |
case-20 | pass→pass | 19,206 | 14,348 | -25% | 1 | 1 | 0% | 2,807 | 2,461 | -12% | 0 | 0 | — |
case-21 | pass→pass | 16,833 | 15,673 | -7% | 1 | 1 | 0% | 2,904 | 2,821 | -3% | 0 | 0 | — |
case-22 | pass→pass | 15,886 | 11,583 | -27% | 1 | 1 | 0% | 2,437 | 2,044 | -16% | 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 +9 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.