From agi-super-team
Computes all 101 WorldQuant formulaic alphas in Python/Pandas for factor IC testing and single-factor backtesting.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agi-super-team:alpha101This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Zura Kakushadze 论文《101 Formulaic Alphas》(arXiv:1601.00991) 的完整Python实现。
Zura Kakushadze 论文《101 Formulaic Alphas》(arXiv:1601.00991) 的完整Python实现。 101个真实量化交易alpha因子,公式即代码。
skills/alpha101/
├── SKILL.md ← 本文件
├── scripts/
│ ├── alpha101.py ← 101个因子函数 + 基础函数库
│ ├── compute_ic.py ← 因子IC/IR计算
│ └── backtest_alpha.py ← 单因子回测
└── references/
└── paper_notes.md ← 论文笔记与函数定义
from scripts.alpha101 import compute_alphas, alpha101
# 输入: date x ticker DataFrame
data = {
'open': df_open, 'close': df_close, 'high': df_high, 'low': df_low,
'volume': df_vol, 'vwap': df_vwap, 'returns': df_returns
}
# 计算所有可用因子
alphas = compute_alphas(data) # dict of alpha_name -> DataFrame
# 单独计算
from scripts.alpha101 import alpha101
a101 = alpha101(df_open, df_close, df_high, df_low)
python scripts/compute_ic.py --data <path> --output results/
python scripts/backtest_alpha.py --alpha 101 --data <path>
| 类别 | 因子 | 输入 |
|---|---|---|
| 纯价量 | #1-#47, #49-#55, #60, #61, #71-#74, #84, #88, #101 | OHLCV + VWAP |
| 行业中性化 | #48, #56, #58-#59, #63, #67, #69-#70, #76, #79-#82, #87, #89-#91, #93, #97, #100 | + 行业分类 |
| 复杂参数 | #57-#99 | 非整数窗口, 混合权重 |
rank(x) 截面排名 [0,1]
delay(x,d) d天前的值
delta(x,d) 当期 - d天前
correlation(x,y,d) d天滚动相关
scale(x,a=1) 缩放使sum(abs(x))=a
decay_linear(x,d) 线性衰减加权均值
ts_min/ts_max(x,d) 滚动最小/最大
ts_rank(x,d) 时间序列排名
ts_sum/ts_std(x,d) 滚动求和/标准差
adv{d} d天平均成交额
IndNeutralize(x,ind) 行业中性化
因子计算 → IC/IR筛选(>0.03) → 样本外验证 → 组合构建(低相关等权) → 回测扣费 → 实盘
npx claudepluginhub aaaaqwq/agi-super-team --plugin agi-super-teamRuns the FactorMiner research engine to discover alpha factors from validated datasets via Ralph or Helix loops with causal validation, regime conditioning, and debate generation.
Guides writing JoinQuant (聚宽) Python strategies for backtesting, simulation, and research. Covers data APIs, trading functions, technical indicators, and Alpha factors.
Builds financial models, backtests trading strategies, and analyzes market data with risk metrics, portfolio optimization, and statistical arbitrage.