Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A股量价关系量化分析。当用户说"量价"、"volume price"、"缩量"、"放量"、"量价背离"、"天量天价"、"地量地价"、"换手率分析"、"成交量异常"时触发。基于 cn-stock-data 获取K线数据，量化分析量价关系模式，识别异常量价信号。支持研报风格（formal）和快速分析风格（brief）。
.claude/skills/aifinlab-a-share-volume-price/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -12% | 0% |
bashSCRIPTS="$SKILLS_ROOT/cn-stock-data/scripts" python "$SCRIPTS/cn_stock_data.py" kline --code [CODE] --freq daily --start [日期] python "$SCRIPTS/cn_stock_data.py" quote --code [CODE]
量化计算：
bashQSCRIPTS="$SKILLS_ROOT/a-share-volume-price/scripts" python "$QSCRIPTS/volume_price_analyzer.py" --data kline.json --window 20
获取包含 OHLCV（开高低收量）的K线数据。
8 种经典量价关系：量增价升/量增价跌/量缩价升/量缩价跌/量增价平/量缩价平/量平价升/量平价跌
| 维度 | formal | brief | |------|--------|-------| | 指标 | 全部量价指标 | VR+OBV方向 | | 模式 | 近期模式序列分析 | 当日模式 | | 异常 | 历史异常回测 | 有/无异常 |
默认风格：brief。
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 | 33,773 | 28,750 | -15% | 1 | 1 | 0% | 5,493 | 1,161 | -79% | 0 | 0 | — |
case-02 | fail→fail | 16,200 | 19,424 | +20% | 1 | 1 | 0% | 2,386 | 3,455 | +45% | 0 | 0 | — |
case-03 | fail→fail | 21,672 | 26,114 | +20% | 1 | 1 | 0% | 4,029 | 4,413 | +10% | 0 | 0 | — |
case-04 | pass→fail | 18,585 | 13,532 | -27% | 1 | 1 | 0% | 3,657 | 1,462 | -60% | 0 | 0 | — |
case-05 | fail→fail | 16,911 | 19,958 | +18% | 1 | 1 | 0% | 2,501 | 3,594 | +44% | 0 | 0 | — |
case-06 | fail→pass | 14,277 | 2,748 | -81% | 1 | 1 | 0% | 2,019 | 1,144 | -43% | 0 | 0 | — |
case-07 | fail→fail | 14,816 | 7,797 | -47% | 1 | 1 | 0% | 2,517 | 1,182 | -53% | 0 | 0 | — |
case-08 | pass→pass | 19,568 | 15,746 | -20% | 1 | 1 | 0% | 3,024 | 3,273 | +8% | 0 | 0 | — |
case-09 | fail→pass | 13,719 | 2,649 | -81% | 1 | 1 | 0% | 1,790 | 1,050 | -41% | 0 | 0 | — |
case-10 | fail→pass | 17,161 | 6,151 | -64% | 1 | 1 | 0% | 2,399 | 1,725 | -28% | 0 | 0 | — |
case-11 | pass→pass | 26,412 | 14,070 | -47% | 1 | 1 | 0% | 3,349 | 3,013 | -10% | 0 | 0 | — |
case-12 | fail→pass | 15,861 | 7,528 | -53% | 1 | 1 | 0% | 1,965 | 1,908 | -3% | 0 | 0 | — |
case-13 | pass→pass | 19,984 | 23,758 | +19% | 1 | 1 | 0% | 2,911 | 4,040 | +39% | 0 | 0 | — |
case-14 | pass→pass | 25,885 | 20,528 | -21% | 1 | 1 | 0% | 3,206 | 3,645 | +14% | 0 | 0 | — |
case-15 | pass→pass | 17,876 | 15,508 | -13% | 1 | 1 | 0% | 2,241 | 2,664 | +19% | 0 | 0 | — |
case-16 | pass→pass | 17,602 | 9,576 | -46% | 1 | 1 | 0% | 2,246 | 2,014 | -10% | 0 | 0 | — |
case-17 | pass→pass | 8,988 | 5,306 | -41% | 1 | 1 | 0% | 1,181 | 1,408 | +19% | 0 | 0 | — |
case-18 | fail→pass | 11,140 | 6,582 | -41% | 1 | 1 | 0% | 1,754 | 1,535 | -12% | 0 | 0 | — |
case-19 | pass→pass | 11,586 | 7,262 | -37% | 1 | 1 | 0% | 1,585 | 1,833 | +16% | 0 | 0 | — |
case-20 | fail→pass | 11,771 | 6,707 | -43% | 1 | 1 | 0% | 1,635 | 1,639 | +0% | 0 | 0 | — |
case-21 | pass→pass | 6,336 | 5,150 | -19% | 1 | 1 | 0% | 996 | 1,434 | +44% | 0 | 0 | — |
case-22 | pass→pass | 16,061 | 7,593 | -53% | 1 | 1 | 0% | 2,460 | 1,899 | -23% | 0 | 0 | — |
case-23 | pass→pass | 10,767 | 12,092 | +12% | 1 | 1 | 0% | 1,682 | 2,412 | +43% | 0 | 0 | — |
case-24 | pass→pass | 8,465 | 2,725 | -68% | 1 | 1 | 0% | 1,500 | 1,084 | -28% | 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, and 21 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +21 percentage points is the difference between those two pass rates over the 21 comparable cases. 3 cases got worse with the skill loaded, and they are 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.