Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →当用户需要分析家庭或个人保障缺口时使用此 skill。适用于保障现状盘点、需求测算、缺口识别、配置建议等场景。
.claude/skills/aifinlab-coverage-gap-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-16 | ✓→✗ | ▼ Worse | -22% | 0% |
你是一名经验丰富的保险规划师，目标是帮助用户全面盘点现有保障，科学测算保障需求，识别保障缺口并提供配置建议。
围绕用户的保障情况，产出结构化、可量化、可执行的缺口分析报告。优先帮助用户解决以下任务：
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-20 | pass→pass | 4,069 | 11,512 | +183% | 1 | 1 | 0% | 866 | 2,613 | +202% | 0 | 0 | — |
case-01 | fail→fail | 26,787 | 45,990 | +72% | 1 | 1 | 0% | 4,532 | 4,682 | +3% | 0 | 0 | — |
case-02 | fail→fail | 23,110 | 18,854 | -18% | 1 | 1 | 0% | 3,644 | 3,737 | +3% | 0 | 0 | — |
case-03 | fail→fail | 35,733 | 29,768 | -17% | 1 | 1 | 0% | 5,040 | 5,405 | +7% | 0 | 0 | — |
case-04 | pass→pass | 19,267 | 19,682 | +2% | 1 | 1 | 0% | 3,011 | 3,535 | +17% | 0 | 0 | — |
case-05 | pass→pass | 21,919 | 21,922 | +0% | 1 | 1 | 0% | 3,561 | 4,157 | +17% | 0 | 0 | — |
case-06 | pass→pass | 19,053 | 17,756 | -7% | 1 | 1 | 0% | 3,038 | 3,663 | +21% | 0 | 0 | — |
case-07 | fail→pass | 17,202 | 15,055 | -12% | 1 | 1 | 0% | 2,898 | 2,878 | -1% | 0 | 0 | — |
case-08 | pass→pass | 16,643 | 18,041 | +8% | 1 | 1 | 0% | 2,681 | 3,489 | +30% | 0 | 0 | — |
case-09 | pass→pass | 11,922 | 11,996 | +1% | 1 | 1 | 0% | 1,902 | 2,412 | +27% | 0 | 0 | — |
case-10 | fail→pass | 17,146 | 13,659 | -20% | 1 | 1 | 0% | 2,694 | 2,628 | -2% | 0 | 0 | — |
case-11 | fail→pass | 18,693 | 16,351 | -13% | 1 | 1 | 0% | 2,993 | 3,065 | +2% | 0 | 0 | — |
case-12 | fail→pass | 16,281 | 15,572 | -4% | 1 | 1 | 0% | 2,471 | 3,144 | +27% | 0 | 0 | — |
case-13 | pass→pass | 27,352 | 23,919 | -13% | 1 | 1 | 0% | 4,557 | 4,673 | +3% | 0 | 0 | — |
case-14 | pass→pass | 36,392 | 13,087 | -64% | 1 | 1 | 0% | 5,139 | 2,609 | -49% | 0 | 0 | — |
case-15 | fail→fail | 9,135 | 7,683 | -16% | 1 | 1 | 0% | 1,413 | 1,642 | +16% | 0 | 0 | — |
case-16 | pass→fail | 17,771 | 9,886 | -44% | 1 | 1 | 0% | 2,570 | 2,011 | -22% | 0 | 0 | — |
case-17 | pass→pass | 18,165 | 13,575 | -25% | 1 | 1 | 0% | 3,070 | 2,846 | -7% | 0 | 0 | — |
case-18 | pass→pass | 16,101 | 14,704 | -9% | 1 | 1 | 0% | 2,393 | 2,826 | +18% | 0 | 0 | — |
case-19 | pass→pass | 16,536 | 14,621 | -12% | 1 | 1 | 0% | 2,547 | 2,775 | +9% | 0 | 0 | — |
case-21 | pass→pass | 17,885 | 18,378 | +3% | 1 | 1 | 0% | 2,922 | 3,431 | +17% | 0 | 0 | — |
case-22 | fail→fail | 10,808 | 10,876 | +1% | 1 | 1 | 0% | 1,661 | 2,231 | +34% | 0 | 0 | — |
case-23 | pass→pass | 11,701 | 11,017 | -6% | 1 | 1 | 0% | 1,887 | 2,377 | +26% | 0 | 0 | — |
case-24 | pass→pass | 17,765 | 15,736 | -11% | 1 | 1 | 0% | 2,469 | 2,882 | +17% | 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. 24 cases were attempted. The headline lift of +13 percentage points is the difference between those two pass rates over the 24 comparable cases. 1 case got worse with the skill loaded, and it is 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.