Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →当用户需要在银行零售金融场景下，围绕高净值客户识别进行候选筛选、潜力评估、服务分层和资源分配时使用本技能。适合输出高净值候选名单、服务优先级、跟进建议和风险提示。
.claude/skills/aifinlab-bank-t155-retail-finance-customer-identification-high-net-worth-assistant/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 66% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -36% | 0% |
本技能用于银行零售客户经营的结构化分析与动作生成，把客户清单转成“可执行名单 + 可追踪动作 + 可复盘指标”。强调高净值阈值管理、候选池滚动复核和私行协同。
eferences/input-schema.md
eferences/output-schema.md
ash python scripts/run_skill.py --input assets/example-input.json --format markdown python scripts/run_skill.py --input assets/example-input.json --format json
脚本入口：scripts/run_skill.py，调用 shared/retail_customer_ops_skill_engine.py 的 $(System.Collections.Hashtable.id) 场景。
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-14 | pass→pass | 21,587 | 19,559 | -9% | 1 | 1 | 0% | 2,805 | 3,628 | +29% | 0 | 0 | — |
case-01 | pass→pass | 29,061 | 71,164 | +145% | 1 | 1 | 0% | 4,205 | 5,534 | +32% | 0 | 0 | — |
case-02 | fail→fail | 27,663 | 33,661 | +22% | 1 | 1 | 0% | 4,064 | 5,059 | +24% | 0 | 0 | — |
case-03 | fail→pass | 18,338 | 14,593 | -20% | 1 | 1 | 0% | 2,444 | 2,905 | +19% | 0 | 0 | — |
case-04 | pass→pass | 18,435 | 25,215 | +37% | 1 | 1 | 0% | 2,699 | 3,665 | +36% | 0 | 0 | — |
case-05 | pass→pass | 9,155 | 13,428 | +47% | 1 | 1 | 0% | 1,333 | 2,688 | +102% | 0 | 0 | — |
case-06 | fail→pass | 18,101 | 20,033 | +11% | 1 | 1 | 0% | 2,860 | 3,863 | +35% | 0 | 0 | — |
case-07 | pass→pass | 16,877 | 22,346 | +32% | 1 | 1 | 0% | 2,426 | 3,625 | +49% | 0 | 0 | — |
case-08 | fail→pass | 25,164 | 22,871 | -9% | 1 | 1 | 0% | 3,387 | 4,427 | +31% | 0 | 0 | — |
case-09 | fail→pass | 15,269 | 20,879 | +37% | 1 | 1 | 0% | 2,168 | 3,599 | +66% | 0 | 0 | — |
case-10 | pass→pass | 19,901 | 22,499 | +13% | 1 | 1 | 0% | 2,943 | 3,662 | +24% | 0 | 0 | — |
case-11 | pass→pass | 23,265 | 20,662 | -11% | 1 | 1 | 0% | 3,006 | 3,879 | +29% | 0 | 0 | — |
case-12 | fail→pass | 16,322 | 5,676 | -65% | 1 | 1 | 0% | 2,409 | 1,542 | -36% | 0 | 0 | — |
case-13 | pass→pass | 13,287 | 19,445 | +46% | 1 | 1 | 0% | 2,265 | 3,780 | +67% | 0 | 0 | — |
case-15 | pass→pass | 13,412 | 18,432 | +37% | 1 | 1 | 0% | 1,976 | 3,539 | +79% | 0 | 0 | — |
case-16 | pass→pass | 11,249 | 19,978 | +78% | 1 | 1 | 0% | 1,827 | 3,796 | +108% | 0 | 0 | — |
case-17 | pass→pass | 16,172 | 20,469 | +27% | 1 | 1 | 0% | 2,621 | 3,794 | +45% | 0 | 0 | — |
case-18 | pass→pass | 18,442 | 27,713 | +50% | 1 | 1 | 0% | 2,817 | 4,301 | +53% | 0 | 0 | — |
case-19 | pass→pass | 15,523 | 19,228 | +24% | 1 | 1 | 0% | 2,289 | 3,289 | +44% | 0 | 0 | — |
case-20 | pass→pass | 14,407 | 18,980 | +32% | 1 | 1 | 0% | 2,279 | 3,071 | +35% | 0 | 0 | — |
case-21 | fail→pass | 17,835 | 30,707 | +72% | 1 | 1 | 0% | 3,243 | 2,574 | -21% | 0 | 0 | — |
case-22 | pass→pass | 23,972 | 22,615 | -6% | 1 | 1 | 0% | 3,089 | 4,249 | +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 +27 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.