Agent Skills
› NeverSight/learn-skills.dev
› hft-quant-expert
hft-quant-expert
GitHub专为DeFi和加密衍生品设计的高频量化交易专家，提供策略构建、信号生成、风险管理及仓位计算支持。涵盖回测验证、成本考量（Gas/滑点）及常用公式实现，确保策略稳健性。
Trigger Scenarios
信号分析
策略回测
Alpha因子挖掘
夏普比率计算
波动率评估
相关性分析
仓位规模确定
风险控制
Install
npx skills add NeverSight/learn-skills.dev --skill hft-quant-expert -g -y
SKILL.md
Frontmatter
{
"name": "hft-quant-expert",
"description": "Quantitative trading expertise for DeFi and crypto derivatives. Use when building trading strategies, signals, risk management. Triggers on signal, backtest, alpha, sharpe, volatility, correlation, position size, risk."
}
HFT Quant Expert
Quantitative trading expertise for DeFi and crypto derivatives.
When to Use
- Building trading strategies and signals
- Implementing risk management
- Calculating position sizes
- Backtesting strategies
- Analyzing volatility and correlations
Workflow
Step 1: Define Signal
Calculate z-score or other entry signal.
Step 2: Size Position
Use Kelly Criterion (0.25x) for position sizing.
Step 3: Validate Backtest
Check for lookahead bias, survivorship bias, overfitting.
Step 4: Account for Costs
Include gas + slippage in profit calculations.
Quick Formulas
# Z-score
zscore = (value - rolling_mean) / rolling_std
# Sharpe (annualized)
sharpe = np.sqrt(252) * returns.mean() / returns.std()
# Kelly fraction (use 0.25x)
kelly = (win_prob * win_loss_ratio - (1 - win_prob)) / win_loss_ratio
# Half-life of mean reversion
half_life = -np.log(2) / lambda_coef
Common Pitfalls
- Lookahead bias - Using future data
- Survivorship bias - Only existing assets
- Overfitting - Too many parameters
- Ignoring costs - Gas + slippage
- Wrong annualization - 252 daily, 365*24 hourly
Version History
- e0220ca Current 2026-07-05 21:54
