Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A股因子择时/风格轮动量化/大小盘价值成长风格切换。当用户说"因子择时"、"factor timing"、"风格轮动"、"什么风格在涨"、"大盘还是小盘"、"价值还是成长"、"风格切换"、"因子轮动"、"大盘小盘占优"、"价值成长占优"、"风格择时"时触发。MUST USE when user asks about factor timing, style rotation between value/growth or large/small cap, or which investment style is currently outperforming. 基于 cn-stock-data 获取数据，量化分析因子/风格的轮动节奏。支持研报风格（formal）和快速分析风格（brief）。
.claude/skills/aifinlab-a-share-factor-timing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -48% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -53% | 0% |
bashSCRIPTS="$SKILLS_ROOT/cn-stock-data/scripts" python "$SCRIPTS/cn_stock_data.py" kline --code [CODE] --freq daily --start [日期] python "$SCRIPTS/cn_stock_data.py" quote --code [CODE] python "$SCRIPTS/cn_stock_data.py" finance --code [CODE]
获取大盘/小盘、价值/成长、高波/低波等风格指数K线。
| 维度 | formal | brief | |------|--------|-------| | 因子表现 | 各因子收益+IC | 当前强势因子 | | 轮动信号 | 多维度择时评分 | 推荐风格 | | 历史规律 | 因子轮动周期分析 | 无 |
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 | 33,918 | 36,554 | +8% | 1 | 1 | 0% | 4,846 | 5,449 | +12% | 0 | 0 | — |
case-02 | fail→fail | 22,371 | 15,347 | -31% | 1 | 1 | 0% | 3,300 | 1,545 | -53% | 0 | 0 | — |
case-03 | pass→pass | 25,804 | 26,840 | +4% | 1 | 1 | 0% | 4,576 | 4,676 | +2% | 0 | 0 | — |
case-04 | pass→pass | 20,096 | 22,194 | +10% | 1 | 1 | 0% | 3,463 | 4,643 | +34% | 0 | 0 | — |
case-05 | pass→pass | 22,911 | 34,092 | +49% | 1 | 1 | 0% | 4,646 | 5,928 | +28% | 0 | 0 | — |
case-06 | fail→pass | 24,220 | 7,138 | -71% | 1 | 1 | 0% | 3,782 | 1,971 | -48% | 0 | 0 | — |
case-07 | fail→pass | 17,236 | 6,153 | -64% | 1 | 1 | 0% | 2,928 | 1,544 | -47% | 0 | 0 | — |
case-08 | pass→pass | 20,527 | 18,529 | -10% | 1 | 1 | 0% | 3,251 | 3,337 | +3% | 0 | 0 | — |
case-09 | pass→pass | 16,726 | 13,960 | -17% | 1 | 1 | 0% | 2,630 | 2,693 | +2% | 0 | 0 | — |
case-10 | fail→fail | 12,577 | 12,105 | -4% | 1 | 1 | 0% | 2,556 | 2,397 | -6% | 0 | 0 | — |
case-11 | fail→fail | 25,635 | 22,853 | -11% | 1 | 1 | 0% | 4,501 | 4,442 | -1% | 0 | 0 | — |
case-12 | pass→pass | 19,545 | 14,300 | -27% | 1 | 1 | 0% | 2,463 | 2,677 | +9% | 0 | 0 | — |
case-13 | pass→pass | 22,301 | 21,422 | -4% | 1 | 1 | 0% | 3,131 | 3,951 | +26% | 0 | 0 | — |
case-14 | pass→pass | 18,111 | 17,017 | -6% | 1 | 1 | 0% | 2,811 | 3,311 | +18% | 0 | 0 | — |
case-15 | pass→pass | 15,722 | 10,752 | -32% | 1 | 1 | 0% | 2,294 | 1,456 | -37% | 0 | 0 | — |
case-16 | fail→pass | 11,244 | 3,073 | -73% | 1 | 1 | 0% | 1,673 | 995 | -41% | 0 | 0 | — |
case-17 | fail→pass | 11,632 | 2,671 | -77% | 1 | 1 | 0% | 1,786 | 901 | -50% | 0 | 0 | — |
case-18 | fail→pass | 15,635 | 3,951 | -75% | 1 | 1 | 0% | 2,284 | 1,083 | -53% | 0 | 0 | — |
case-19 | fail→pass | 20,058 | 16,689 | -17% | 1 | 1 | 0% | 2,755 | 3,251 | +18% | 0 | 0 | — |
case-20 | pass→pass | 22,412 | 15,666 | -30% | 1 | 1 | 0% | 3,161 | 2,936 | -7% | 0 | 0 | — |
case-21 | pass→pass | 18,965 | 16,731 | -12% | 1 | 1 | 0% | 2,799 | 2,891 | +3% | 0 | 0 | — |
case-22 | fail→pass | 19,504 | 14,101 | -28% | 1 | 1 | 0% | 2,624 | 2,708 | +3% | 0 | 0 | — |
case-23 | pass→pass | 24,982 | 22,834 | -9% | 1 | 1 | 0% | 3,545 | 3,421 | -3% | 0 | 0 | — |
case-24 | pass→pass | 20,472 | 16,429 | -20% | 1 | 1 | 0% | 2,544 | 2,601 | +2% | 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 23 counted toward the lift figure. The other 1 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 +29 percentage points is the difference between those two pass rates over the 23 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/28/2026 | +27% |
Other measured skills in the registry, with their headline benchmark lift.