Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →CSV·Excel 데이터의 프로파일링·품질 보고서를 만들어 드립니다. 다음과 같은 요청 시 사용하세요: - "이 데이터 분석해줘" - "CSV 요약해줘" - "이상값 찾아줘" - "데이터 품질 체크해줘" 컬럼 요약·결측값/이상값 탐지·상관관계 분석을 거쳐 데이터 품질 보고서로 정리합니다.
.claude/skills/modu-ai-data-explorer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -66% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -33% | 0% |
CSV/Excel 파일을 받아 데이터 프로파일링, 품질 검사, 기초 분석을 수행하는 전문가.
| 파일 | 로드 조건 | |------|-----------| | references/data-explorer/guide.md | CSV 인코딩 자동 감지(UTF-8/CP949/EUC-KR), IQR·Z-score 이상값 탐지 기준이 필요할 때 |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | fail→fail | 10,886 | 2,620 | -76% | 1 | 1 | 0% | 1,741 | 966 | -45% | 0 | 0 | — |
case-21 | pass→pass | 8,023 | 7,656 | -5% | 1 | 1 | 0% | 1,415 | 1,791 | +27% | 0 | 0 | — |
case-08 | pass→pass | 16,842 | 20,867 | +24% | 1 | 1 | 0% | 2,986 | 4,228 | +42% | 0 | 0 | — |
case-01 | fail→fail | 25,558 | 6,355 | -75% | 1 | 1 | 0% | 3,450 | 1,092 | -68% | 0 | 0 | — |
case-02 | fail→fail | 18,124 | 31,165 | +72% | 1 | 1 | 0% | 3,201 | 7,197 | +125% | 0 | 0 | — |
case-14 | fail→pass | 11,388 | 3,954 | -65% | 1 | 1 | 0% | 1,804 | 1,229 | -32% | 0 | 0 | — |
case-03 | fail→fail | 19,409 | 8,723 | -55% | 1 | 1 | 0% | 3,442 | 930 | -73% | 0 | 0 | — |
case-04 | fail→pass | 15,550 | 5,766 | -63% | 1 | 1 | 0% | 2,955 | 1,489 | -50% | 0 | 0 | — |
case-05 | pass→pass | 15,844 | 11,674 | -26% | 1 | 1 | 0% | 2,905 | 1,391 | -52% | 0 | 0 | — |
case-06 | fail→pass | 7,838 | 3,263 | -58% | 1 | 1 | 0% | 1,349 | 1,043 | -23% | 0 | 0 | — |
case-07 | pass→pass | 13,383 | 11,146 | -17% | 1 | 1 | 0% | 2,452 | 2,650 | +8% | 0 | 0 | — |
case-09 | pass→pass | 16,128 | 19,230 | +19% | 1 | 1 | 0% | 2,716 | 3,749 | +38% | 0 | 0 | — |
case-10 | pass→pass | 13,933 | 11,636 | -16% | 1 | 1 | 0% | 2,377 | 2,560 | +8% | 0 | 0 | — |
case-11 | pass→pass | 13,709 | 8,351 | -39% | 1 | 1 | 0% | 2,314 | 1,959 | -15% | 0 | 0 | — |
case-12 | pass→pass | 11,370 | 4,918 | -57% | 1 | 1 | 0% | 2,135 | 1,445 | -32% | 0 | 0 | — |
case-13 | pass→pass | 13,491 | 10,456 | -22% | 1 | 1 | 0% | 2,234 | 2,487 | +11% | 0 | 0 | — |
case-16 | fail→fail | 17,157 | 13,675 | -20% | 1 | 1 | 0% | 2,797 | 2,957 | +6% | 0 | 0 | — |
case-17 | fail→pass | 15,676 | 2,155 | -86% | 1 | 1 | 0% | 2,615 | 896 | -66% | 0 | 0 | — |
case-18 | fail→fail | 6,876 | 5,684 | -17% | 1 | 1 | 0% | 1,265 | 1,560 | +23% | 0 | 0 | — |
case-19 | fail→pass | 10,112 | 3,687 | -64% | 1 | 1 | 0% | 1,763 | 1,182 | -33% | 0 | 0 | — |
case-20 | pass→pass | 9,650 | 7,569 | -22% | 1 | 1 | 0% | 1,580 | 1,840 | +16% | 0 | 0 | — |
case-22 | fail→pass | 16,491 | 7,879 | -52% | 1 | 1 | 0% | 2,758 | 2,050 | -26% | 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 +27 percentage points is the difference between those two pass rates over the 19 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.