Menu
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/aifinlab/FinClaw --skill style-factor-calculationThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
A股逆向选择/信息不对称分析。当用户说"逆向选择"、"adverse selection"、"信息不对称"、"知情交易者"、"逆向选择成本"、"信息劣势"时触发。基于 cn-stock-data 获取数据，度量逆向选择与信息不对称程度。支持 formal/brief 两种输出风格。
A股量价异常检测/异动监控。当用户说"异常检测"、"异动"、"anomaly"、"量价异常"、"异常波动"、"XX有异动"时触发。量化检测股价和成交量异常。支持formal和brief风格。
A股自相关/序列相关性/收益率自相关结构分析。当用户说"自相关"、"autocorrelation"、"序列相关"、"收益率预测性"、"动量还是反转"、"自相关系数"、"ACF"、"PACF"、"Ljung-Box"、"收益率是否可预测"、"随机游走检验"时触发。MUST USE when user asks about return autocorrelation, serial correlation tests, or whether a stock's returns are predictable. 量化分析收益率的自相关结构（ACF/PACF、Ljung-Box检验、随机游走检验）。支持formal和brief风格。
Based on SOC occupation classification
Showing SKILL.md
| name | style-factor-calculation |
| description | 用于因子暴露的风格因子计算原子 skill，适用于通用行业金融计算场景。 |
本 Skill 支持多种金融数据输入格式，核心数据来源包括：
说明：本 Skill 不包含数据采集功能，需要用户提供清洗后的价格和财务数据。建议数据时间跨度不少于1年，以便进行准确的风格因子计算。
本 Skill 提供全面的风格因子计算能力，涵盖多种风格因子：
{
"symbol": "000001.SZ",
"date": "2024-12-31",
"style_factors": {
"value_factors": {
"pe": 15.2,
"pe_percentile": 45.3,
"pb": 2.1,
"pb_percentile": 52.8,
"ps": 3.5,
"ps_percentile": 48.2
},
"growth_factors": {
"revenue_growth": 12.5,
"revenue_growth_percentile": 65.8,
"net_income_growth": 18.3,
"net_income_growth_percentile":
LICENSE 文件requirements.txt 为准