菜单
Use when tasks need reusable research pipeline templates, factor screening, parameter sensitivity sweeps, or strategy comparison.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when tasks need factor diagnostics, IC/grouped return analysis, attribution, robustness checks, or time-series distribution and stationarity checks.
Use when tasks need vectorized strategy execution, portfolio weighting, portfolio-level filters, transaction cost helpers, exit A/B analysis, overlay metrics, or multi-strategy return blending.
Use when tasks need strategy-agnostic OHLCV indicators, math utilities, generic factor examples, regime slicing, resampling, or label makers.
Use when tasks need optional PyCaret model training, ML factor generation, inference wrappers, feature importance, or sparse LASSO weight generation.
Use when tasks need PandaData/PandaAI market data, reference data, adjustment factors, futures tick downloads, or symbol conversion.
Use when tasks need HTML reports, Markdown strategy reports, PNG chart helpers, or report files under the research reports directory.
| name | research |
| description | Use when tasks need reusable research pipeline templates, factor screening, parameter sensitivity sweeps, or strategy comparison. |
| Function | Module | Description |
|---|---|---|
screen_all_indicators | factor_screening.py | Batch-compute all indicators on a pool, run full_stat, return IC/IR ranking |
param_sweep | param_sensitivity.py | Grid-sweep a factor parameter, return IC/IR vs parameter table |
compare_strategies | strategy_comparison.py | Run multiple factor configs through ModularBacktester, compare Sharpe/MaxDD/Calmar |
from skills.research.factor_screening import screen_all_indicators
from skills.research.param_sensitivity import param_sweep
from skills.research.strategy_comparison import compare_strategies