Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →分析口腔健康数据、识别口腔问题模式、评估口腔健康状况、提供个性化口腔健康建议。支持与营养、慢性病、用药等其他健康数据的关联分析。
.claude/skills/sickn33-oral-health-analyzer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✗→✓ | ▲ Improved | 236% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 316% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 122% | 0% |
| case-12 | ✓→✓ | ＝ Same ✓ | 184% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 254% | 0% |
name: oral-health-analyzer
Read the detailed guide before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely.
User request:
> 分析这些口腔健康记录，识别龋齿或牙周风险趋势，并指出需要专业评估的信号。
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 17,195 | 13,963 | -19% | 1 | 1 | 0% | 2,605 | 5,777 | +122% | 0 | 0 | — |
case-12 | pass→pass | 9,790 | 9,581 | -2% | 1 | 1 | 0% | 1,787 | 5,079 | +184% | 0 | 0 | — |
case-02 | pass→pass | 8,209 | 8,114 | -1% | 1 | 1 | 0% | 1,388 | 4,909 | +254% | 0 | 0 | — |
case-03 | pass→pass | 8,006 | 10,860 | +36% | 1 | 1 | 0% | 1,405 | 5,191 | +269% | 0 | 0 | — |
case-04 | pass→pass | 9,613 | 7,402 | -23% | 1 | 1 | 0% | 1,570 | 4,787 | +205% | 0 | 0 | — |
case-05 | pass→pass | 9,255 | 9,746 | +5% | 1 | 1 | 0% | 1,543 | 5,079 | +229% | 0 | 0 | — |
case-06 | pass→pass | 5,067 | 4,890 | -3% | 1 | 1 | 0% | 874 | 4,406 | +404% | 0 | 0 | — |
case-07 | pass→pass | 5,882 | 6,314 | +7% | 1 | 1 | 0% | 1,036 | 4,729 | +356% | 0 | 0 | — |
case-08 | pass→pass | 8,978 | 6,954 | -23% | 1 | 1 | 0% | 1,616 | 4,799 | +197% | 0 | 0 | — |
case-09 | pass→pass | 8,313 | 4,785 | -42% | 1 | 1 | 0% | 1,454 | 4,328 | +198% | 0 | 0 | — |
case-10 | pass→pass | 10,849 | 8,566 | -21% | 1 | 1 | 0% | 1,810 | 5,001 | +176% | 0 | 0 | — |
case-11 | pass→pass | 7,099 | 8,081 | +14% | 1 | 1 | 0% | 1,264 | 4,836 | +283% | 0 | 0 | — |
case-13 | pass→pass | 5,397 | 8,782 | +63% | 1 | 1 | 0% | 976 | 5,049 | +417% | 0 | 0 | — |
case-14 | pass→pass | 3,634 | 8,212 | +126% | 1 | 1 | 0% | 671 | 5,034 | +650% | 0 | 0 | — |
case-15 | pass→pass | 9,940 | 9,478 | -5% | 1 | 1 | 0% | 1,703 | 5,204 | +206% | 0 | 0 | — |
case-16 | fail→pass | 6,452 | 2,102 | -67% | 1 | 1 | 0% | 1,169 | 3,923 | +236% | 0 | 0 | — |
case-17 | pass→pass | 5,007 | 4,549 | -9% | 1 | 1 | 0% | 905 | 4,320 | +377% | 0 | 0 | — |
case-18 | pass→pass | 5,580 | 3,641 | -35% | 1 | 1 | 0% | 884 | 4,132 | +367% | 0 | 0 | — |
case-19 | fail→pass | 5,542 | 3,307 | -40% | 1 | 1 | 0% | 952 | 3,964 | +316% | 0 | 0 | — |
case-20 | fail→fail | 5,666 | 5,835 | +3% | 1 | 1 | 0% | 1,177 | 4,674 | +297% | 0 | 0 | — |
case-21 | pass→pass | 5,316 | 4,463 | -16% | 1 | 1 | 0% | 882 | 4,212 | +378% | 0 | 0 | — |
case-22 | pass→pass | 7,000 | 7,633 | +9% | 1 | 1 | 0% | 1,120 | 4,745 | +324% | 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.
The publisher has shipped newer versions since this run, so these numbers describe v1, not the version currently listed.
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.