Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A股日内动量/分时趋势策略。当用户说"日内动量"、"分时趋势"、"intraday momentum"、"盘中趋势"、"日内追涨"、"分时动量"时触发。基于 cn-stock-data 获取数据，分析日内动量效应、分时趋势信号、最优交易时段。支持 formal/brief 两种输出风格。
.claude/skills/aifinlab-a-share-intraday-momentum/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 14% | 0% |
通过 cn-stock-data skill 获取数据：
# [标的/市场] 日内动量分析报告
## 一、日内动量效应
| 时段 | 自相关 | 延续概率 | 信号强度 |
|------|--------|---------|----------|
## 二、分时趋势信号
[当前信号状态、VWAP位置]
## 三、最优时段
[各时段收益特征、推荐交易窗口]
## 四、策略表现
[回测结果、风险指标]
## 五、今日操作建议## [标的] 日内动量速览
- 开盘30分钟涨 +1.2%，动量延续概率 62%
- 当前价格在VWAP上方，趋势偏多
- 最优交易窗口：10:00-11:00
- 建议：顺势持有，止损设在VWAP下方参考 references/intraday-momentum-guide.md 获取详细方法论与 A股实证研究。
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-20 | pass→pass | 26,644 | 49,471 | +86% | 1 | 1 | 0% | 4,738 | 9,492 | +100% | 0 | 0 | — |
case-01 | fail→fail | 28,963 | 44,010 | +52% | 1 | 1 | 0% | 4,139 | 6,131 | +48% | 0 | 0 | — |
case-02 | fail→pass | 17,520 | 27,479 | +57% | 1 | 1 | 0% | 2,538 | 3,549 | +40% | 0 | 0 | — |
case-03 | fail→pass | 40,669 | 35,532 | -13% | 1 | 1 | 0% | 5,969 | 7,094 | +19% | 0 | 0 | — |
case-04 | fail→fail | 32,259 | 34,084 | +6% | 1 | 1 | 0% | 4,784 | 6,557 | +37% | 0 | 0 | — |
case-05 | pass→pass | 23,488 | 20,175 | -14% | 1 | 1 | 0% | 3,422 | 3,955 | +16% | 0 | 0 | — |
case-06 | fail→fail | 21,187 | 22,815 | +8% | 1 | 1 | 0% | 3,285 | 4,287 | +31% | 0 | 0 | — |
case-07 | fail→pass | 24,864 | 26,741 | +8% | 1 | 1 | 0% | 3,762 | 4,378 | +16% | 0 | 0 | — |
case-08 | pass→pass | 22,003 | 22,879 | +4% | 1 | 1 | 0% | 3,177 | 4,241 | +33% | 0 | 0 | — |
case-09 | pass→pass | 22,276 | 24,274 | +9% | 1 | 1 | 0% | 3,360 | 4,559 | +36% | 0 | 0 | — |
case-10 | fail→pass | 23,145 | 22,942 | -1% | 1 | 1 | 0% | 3,389 | 4,444 | +31% | 0 | 0 | — |
case-11 | pass→pass | 27,362 | 25,111 | -8% | 1 | 1 | 0% | 3,561 | 4,879 | +37% | 0 | 0 | — |
case-12 | fail→pass | 15,571 | 10,569 | -32% | 1 | 1 | 0% | 2,079 | 2,377 | +14% | 0 | 0 | — |
case-13 | fail→fail | 21,938 | 21,637 | -1% | 1 | 1 | 0% | 3,154 | 3,803 | +21% | 0 | 0 | — |
case-14 | fail→pass | 23,887 | 16,323 | -32% | 1 | 1 | 0% | 3,278 | 3,553 | +8% | 0 | 0 | — |
case-15 | fail→pass | 20,795 | 15,440 | -26% | 1 | 1 | 0% | 3,488 | 3,366 | -3% | 0 | 0 | — |
case-16 | pass→pass | 22,998 | 17,591 | -24% | 1 | 1 | 0% | 3,532 | 3,422 | -3% | 0 | 0 | — |
case-17 | pass→pass | 18,325 | 16,746 | -9% | 1 | 1 | 0% | 2,871 | 3,489 | +22% | 0 | 0 | — |
case-18 | fail→pass | 15,408 | 6,527 | -58% | 1 | 1 | 0% | 2,476 | 1,847 | -25% | 0 | 0 | — |
case-19 | pass→pass | 15,239 | 11,985 | -21% | 1 | 1 | 0% | 2,246 | 2,765 | +23% | 0 | 0 | — |
case-21 | pass→pass | 25,054 | 36,971 | +48% | 1 | 1 | 0% | 4,299 | 7,848 | +83% | 0 | 0 | — |
case-22 | pass→pass | 25,346 | 25,385 | +0% | 1 | 1 | 0% | 3,798 | 4,774 | +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. The headline lift of +36 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.