Install any skill in seconds. Free to start, no credit card required.
Get Started Free →aifinlab/a-share-correlation
A股相关性分析/联动关系/相关系数计算。当用户说"相关性"、"联动"、"correlation"、"XX和YY相关吗"、"哪些股票走势相似"、"分散化"、"对冲"、"beta"、"同涨同跌"、"相关性分析"、"相关系数"、"相关性矩阵"时触发。MUST USE when user asks about correlation analysis, correlation coefficient between stocks/sectors, or diversification analysis based on correlation. 计算个股/指数/行业之间的收益率相关系数、Beta值,分析联动关系和分散化效果,辅助组合构建和对冲决策。支持研报风格(formal)和快速查看风格(brief)。
Passed 17 of 22 test cases with the skill, and 14 of 22 without it.
3 fixed15 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
如果用户想做全市场 500 只成分股的两两相关性全矩阵计算,相关性分析工具对单次处理的标的数量建议区间是多少?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies a target selection limit between 2 and 10 assets for analysis. | Missed | Passed |
The instructions your model reads when the skill loads.
通过 cn-stock-data skill 获取数据:
kline 路由:多标的历史日K线(至少 1 年,推荐 2-3 年)quote 路由:实时行情、所属行业计算工具:Python numpy/pandas
pandas.DataFrame.corr() 计算皮尔逊相关系数矩阵numpy 做回归计算 Betapandas.DataFrame.rolling().corr() 计算滚动相关性r_t = (close_t - close_{t-1}) / close_{t-1}Beta = Cov(r_stock, r_market) / Var(r_market)test cases passed, vs 14 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.