Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →公告解读助手 - 订单公告版。专注于重大合同/订单公告解读，分析合同金额、合同类型、客户资质、履约周期及对业绩的影响。 **触发场景**： - 用户粘贴重大合同/订单公告，需要解读 - 用户问"这个订单怎么样"、"金额大吗" - 需要分析合同金额、客户资质、履约周期 - 需要判断订单对业绩的影响 **关键词**："订单"、"合同"、"重大合同"、"中标"、"签约"、"客户"、"履约"、"业绩影响"
.claude/skills/aifinlab-announcement-interpretation-order/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 90% | 0% |
你是一名经验丰富的分析师，擅长解读重大合同/订单公告，帮助投资者判断订单质量和业绩贡献。
| 要素 | 关注点 | 利好程度 | |------|--------|----------| | 合同金额 | 金额大小、占营收比例 | 比例越大越利好 | | 合同类型 | 销售/采购/合作框架 | 销售合同>框架 | | 客户资质 | 知名客户/政府/普通客户 | 知名客户利好 | | 履约周期 | 履行时间 | 周期短见效快 | | 毛利率 | 合同毛利率 | 高毛利利好 |
【XX 公司订单公告解读】
合同金额：XX 亿，占上年度营收 XX%
合同类型：[销售/采购/框架]
客户资质：[客户名称 + 资质]
履约周期：XX 个月/年
业绩影响：预计贡献营收 XX 亿，利润 XX 亿
投资判断：[利好程度 + 简要理由]# 【XX 公司订单公告解读】
## 合同概览
| 项目 | 内容 |
|------|------|
| 合同金额 | |
| 合同类型 | |
| 客户名称 | |
| 客户资质 | |
| 履约周期 | |
| 毛利率 | |
## 合同金额分析
- 绝对金额：XX 亿元
- 占上年度营收：XX%
- 重要性：[重大/中等/小]
## 客户资质分析
- 客户：[名称]
- 资质：[行业龙头/政府/普通]
- 合作历史：[新客户/老客户]
## 履约周期分析
- 履行期限：XX 个月
- 收入确认：[分年度测算]
- 业绩贡献：预计 XX 年确认 XX 亿
## 盈利分析
- 合同毛利率：XX%（如有）
- 对比公司平均：[高/低]XXpct
- 预计利润贡献：XX 亿
## 投资含义
- 短期影响：[股价反应预判]
- 中期影响：[业绩增厚]
## 风险提示
- 合同履约风险
- 客户付款风险
- 毛利率不及预期输出前自查：
python# 调用 skill result = run_skill({ "param1": "value1", "param2": "value2" })
bashpython scripts/run_skill.py --input data.json
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 18,422 | 23,577 | +28% | 1 | 1 | 0% | 2,611 | 3,181 | +22% | 0 | 0 | — |
case-02 | fail→fail | 22,041 | 17,593 | -20% | 1 | 1 | 0% | 3,554 | 4,000 | +13% | 0 | 0 | — |
case-03 | fail→pass | 18,943 | 15,233 | -20% | 1 | 1 | 0% | 2,922 | 3,725 | +27% | 0 | 0 | — |
case-04 | pass→pass | 147,174 | 17,837 | -88% | 1 | 1 | 0% | 2,117 | 3,387 | +60% | 0 | 0 | — |
case-05 | pass→pass | 23,946 | 14,744 | -38% | 1 | 1 | 0% | 3,214 | 3,454 | +7% | 0 | 0 | — |
case-06 | pass→pass | 19,198 | 14,810 | -23% | 1 | 1 | 0% | 2,816 | 3,500 | +24% | 0 | 0 | — |
case-07 | pass→pass | 18,778 | 14,894 | -21% | 1 | 1 | 0% | 2,626 | 3,314 | +26% | 0 | 0 | — |
case-08 | pass→pass | 21,476 | 18,431 | -14% | 1 | 1 | 0% | 2,996 | 3,441 | +15% | 0 | 0 | — |
case-09 | pass→pass | 25,137 | 19,344 | -23% | 1 | 1 | 0% | 3,034 | 4,070 | +34% | 0 | 0 | — |
case-10 | pass→pass | 21,298 | 17,575 | -17% | 1 | 1 | 0% | 3,253 | 3,748 | +15% | 0 | 0 | — |
case-11 | pass→pass | 19,288 | 16,830 | -13% | 1 | 1 | 0% | 3,084 | 3,983 | +29% | 0 | 0 | — |
case-12 | pass→pass | 28,008 | 19,491 | -30% | 1 | 1 | 0% | 3,501 | 3,644 | +4% | 0 | 0 | — |
case-13 | fail→pass | 29,211 | 21,627 | -26% | 1 | 1 | 0% | 2,754 | 3,795 | +38% | 0 | 0 | — |
case-14 | pass→pass | 19,631 | 14,262 | -27% | 1 | 1 | 0% | 2,526 | 3,183 | +26% | 0 | 0 | — |
case-15 | fail→pass | 9,931 | 6,014 | -39% | 1 | 1 | 0% | 1,603 | 2,164 | +35% | 0 | 0 | — |
case-16 | fail→pass | 22,019 | 12,920 | -41% | 1 | 1 | 0% | 3,100 | 3,418 | +10% | 0 | 0 | — |
case-17 | pass→pass | 19,376 | 15,340 | -21% | 1 | 1 | 0% | 2,301 | 3,668 | +59% | 0 | 0 | — |
case-18 | pass→pass | 15,967 | 11,100 | -30% | 1 | 1 | 0% | 2,119 | 2,562 | +21% | 0 | 0 | — |
case-19 | fail→pass | 13,437 | 19,424 | +45% | 1 | 1 | 0% | 1,783 | 3,391 | +90% | 0 | 0 | — |
case-20 | fail→fail | 16,202 | 45,218 | +179% | 1 | 1 | 0% | 2,319 | 3,297 | +42% | 0 | 0 | — |
case-21 | pass→pass | 23,606 | 22,542 | -5% | 1 | 1 | 0% | 3,008 | 4,312 | +43% | 0 | 0 | — |
case-22 | pass→pass | 18,660 | 20,626 | +11% | 1 | 1 | 0% | 2,669 | 3,661 | +37% | 0 | 0 | — |
case-23 | pass→pass | 26,952 | 16,795 | -38% | 1 | 1 | 0% | 3,471 | 3,581 | +3% | 0 | 0 | — |
case-24 | pass→pass | 21,709 | 17,559 | -19% | 1 | 1 | 0% | 3,412 | 3,953 | +16% | 0 | 0 | — |
case-25 | pass→pass | 19,034 | 15,715 | -17% | 1 | 1 | 0% | 2,425 | 3,293 | +36% | 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. 25 cases were attempted. The headline lift of +20 percentage points is the difference between those two pass rates over the 25 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.