quantitative-trading 插件 backtesting-frameworks Skill 实战构建抗偏差的量化回测系统【免费下载链接】agentsMulti-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity项目地址: https://gitcode.com/GitHub_Trending/agents24/agents导读本文讲解 GitHub 推荐项目精选 agents24 仓库中quantitative-trading插件内backtesting-frameworksAgent Skill 的核心内容如何构建稳健、可上生产环境的量化交易策略回测系统。你将掌握回测五大偏差前视偏差、幸存者偏差、过拟合、选择偏差、交易成本偏差的识别与规避方法理解 Train/Validation/Test 三段式回测结构与 Walk-Forward 前向分析并通过事件驱动回测器、向量化回测器、Walk-Forward 优化器与 Monte Carlo 分析四个可运行 Python 模式搭建一套能输出可靠策略绩效估计的回测基础设施。该 Skill 在本仓库中定位为quantitative-trading插件的领域技能之一与 quant-analyst.md策略开发与回测及 risk-metrics-calculationVaR/CVaR/回撤指标技能互补本技能解决如何正确地回测风险指标技能解决如何度量回测结果的风险。其核心定义见 SKILL.md全部可运行代码模式集中在 references/details.md。一、何时使用该 SkillSKILL.md 的 frontmatter 声明了明确的激活条件description 中的 Use when 语义开发交易策略回测Developing trading strategy backtests构建回测基础设施Building backtesting infrastructure验证策略绩效Validating strategy performance规避常见回测偏差Avoiding common backtesting biases实现 Walk-Forward 前向分析Implementing walk-forward analysis比较候选策略Comparing strategy alternatives这与 quant-analyst.md 中 Robust backtesting with transaction costs and slippage含交易成本与滑点的稳健回测、Out-of-sample testing to avoid overfitting样本外测试避免过拟合两条方法论一一对应Skill 是 Agent 在执行回测任务时加载的领域知识包。二、核心概念五大回测偏差SKILL.md 用一张表系统归纳了回测中最常见的五种偏差及其缓解手段这是本技能的理论基石Bias 偏差Description 描述Mitigation 缓解手段Look-ahead 前视偏差使用了未来信息Point-in-time data 时点数据Survivorship 幸存者偏差只在幸存标的上测试Use delisted securities 纳入退市标的Overfitting 过拟合对历史曲线拟合过头Out-of-sample testing 样本外测试Selection 选择偏差挑选有利策略cherry-pickingPre-registration 预先注册Transaction 交易成本偏差忽略交易成本Realistic cost models 真实成本模型关键解读前视偏差是最隐蔽也最常见的错误典型来源包括用当日收盘价计算信号却在当日开盘成交、信号未做 shift(1) 延迟一 bar、财务数据使用事后重述版本。在 details.md 的向量化回测器中专门用一行signals signal_func(prices).shift(1).fillna(0)并通过注释 shifted to avoid look-ahead 明确示范了规避手段。幸存者偏差要求数据集中包含已退市标的否则回测收益会被系统性高估。选择偏差要求策略在数据探索之前预先注册避免先看数据、再编故事。交易成本偏差要求回测引擎内置佣金与滑点模型这正是 quant-analyst.md 强调的 Include realistic assumptions about market microstructure包含现实的市场微观结构假设。三、正确的回测结构Training / Validation / Test 三段式SKILL.md 给出了标准的回测数据划分结构Historical Data │ ▼ ┌─────────────────────────────────────────┐ │ Training Set │ │ (Strategy Development Optimization) │ └─────────────────────────────────────────┘ │ ▼ ┌─────────────────────────────────────────┐ │ Validation Set │ │ (Parameter Selection, No Peeking) │ └─────────────────────────────────────────┘ │ ▼ ┌─────────────────────────────────────────┐ │ Test Set │ │ (Final Performance Evaluation) │ └─────────────────────────────────────────┘三段职责边界Training Set训练集只用于策略开发与参数优化。所有基于历史数据的学习都必须发生在这里。Validation Set验证集用于参数选择与模型调优严禁偷看No Peeking。如果验证集被反复用于调参它会退化为训练集的一部分最终 Test Set 也会被污染。Test Set测试集仅在最终阶段运行一次用于最终绩效评估。SKILL.md 的 Donts 明确警告Dont optimize on full history - Reserve test set不要在全部历史上优化必须保留测试集。四、Walk-Forward Analysis 前向分析仅做一次 train/test 划分不足以评估策略的时间稳定性SKILL.md 推荐使用滚动窗口的前向分析Window 1: [Train──────][Test] Window 2: [Train──────][Test] Window 3: [Train──────][Test] Window 4: [Train──────][Test] ─────▶ Time核心思想在每个窗口内仅在 Train 段上优化参数再把最优参数应用到紧随其后的 Test 段评估然后窗口向前滚动重复。这与在全部历史上优化一次截然不同能暴露参数随市场状态漂移导致的过拟合问题。SKILL.md 的 Dos 中 Use walk-forward - Not just train/test 正是指这一点。五、实现模式一事件驱动回测器Event-Driven Backtesterdetails.md 的 Pattern 1 提供了完整的、可直接运行的事件驱动回测器适合策略依赖成交回报回调、订单类型多样市价/限价/止损的场景。其核心抽象如下5.1 订单与成交的数据结构from abc import ABC, abstractmethod from dataclasses import dataclass, field from datetime import datetime from decimal import Decimal from enum import Enum from typing import Dict, List, Optional import pandas as pd import numpy as np class OrderSide(Enum): BUY buy SELL sell class OrderType(Enum): MARKET market LIMIT limit STOP stop dataclass class Order: symbol: str side: OrderSide quantity: Decimal order_type: OrderType limit_price: Optional[Decimal] None stop_price: Optional[Decimal] None timestamp: Optional[datetime] None dataclass class Fill: order: Order fill_price: Decimal fill_quantity: Decimal commission: Decimal slippage: Decimal timestamp: datetime实现细节值得注意全部金额字段使用decimal.Decimal而非 float避免资金计算中的浮点误差累积——这正是生产级回测与快速原型的关键差异之一。Order将交易方向side、订单类型order_type、限价/止损价分离建模为后续接入限价单与止损单的撮合逻辑预留了扩展点。5.2 持仓与组合账本dataclass class Position: symbol: str quantity: Decimal Decimal(0) avg_cost: Decimal Decimal(0) realized_pnl: Decimal Decimal(0) def update(self, fill: Fill) - None: if fill.order.side OrderSide.BUY: new_quantity self.quantity fill.fill_quantity if new_quantity ! 0: self.avg_cost ( (self.quantity * self.avg_cost fill.fill_quantity * fill.fill_price) / new_quantity ) self.quantity new_quantity else: self.realized_pnl fill.fill_quantity * (fill.fill_price - self.avg_cost) self.quantity - fill.fill_quantity dataclass class Portfolio: cash: Decimal positions: Dict[str, Position] field(default_factorydict) def get_position(self, symbol: str) - Position: if symbol not in self.positions: self.positions[symbol] Position(symbolsymbol) return self.positions[symbol] def process_fill(self, fill: Fill) - None: position self.get_position(fill.order.symbol) position.update(fill) if fill.order.side OrderSide.BUY: self.cash - fill.fill_price * fill.fill_quantity fill.commission else: self.cash fill.fill_price * fill.fill_quantity - fill.commission def get_equity(self, prices: Dict[str, Decimal]) - Decimal: equity self.cash for symbol, position in self.positions.items(): if position.quantity ! 0 and symbol in prices: equity position.quantity * prices[symbol] return equity要点买入时用加权平均成本法更新avg_cost卖出时按fill_price - avg_cost累积已实现盈亏符合期货/股票多头仓位的标准记账方式。process_fill中现金变化显式扣除commission佣金把交易成本真实写入账本而非事后粗略折算。get_equity用持仓数量 × 当前价格估算组合净值供逐 bar 绘制权益曲线。5.3 策略与执行模型的抽象class Strategy(ABC): abstractmethod def on_bar(self, timestamp: datetime, data: pd.DataFrame) - List[Order]: pass abstractmethod def on_fill(self, fill: Fill) - None: pass class ExecutionModel(ABC): abstractmethod def execute(self, order: Order, bar: pd.Series) - Optional[Fill]: pass class SimpleExecutionModel(ExecutionModel): def __init__(self, slippage_bps: float 10, commission_per_share: float 0.01): self.slippage_bps slippage_bps self.commission_per_share commission_per_share def execute(self, order: Order, bar: pd.Series) - Optional[Fill]: if order.order_type OrderType.MARKET: base_price Decimal(str(bar[open])) # Apply slippage slippage_mult 1 (self.slippage_bps / 10000) if order.side OrderSide.BUY: fill_price base_price * Decimal(str(slippage_mult)) else: fill_price base_price / Decimal(str(slippage_mult)) commission order.quantity * Decimal(str(self.commission_per_share)) slippage abs(fill_price - base_price) * order.quantity return Fill( orderorder, fill_pricefill_price, fill_quantityorder.quantity, commissioncommission, slippageslippage, timestampbar.name ) return NoneStrategy用抽象方法把信号生成与成交回报处理分离ExecutionModel把订单如何变成成交独立出来。SimpleExecutionModel演示了滑点slippage默认 10 bps基点买入在基准价上浮、卖出在基准价下浮即slippage_mult 1 slippage_bps/10000佣金commission默认每股0.01按成交数量线性计算以 bar 的开盘价bar[open]作为成交基准价模拟下一根 bar 开盘执行的时序天然规避收盘价信号与开盘价成交的前视偏差。5.4 主循环Backtesterclass Backtester: def __init__( self, strategy: Strategy, execution_model: ExecutionModel, initial_capital: Decimal Decimal(100000) ): self.strategy strategy self.execution_model execution_model self.portfolio Portfolio(cashinitial_capital) self.equity_curve: List[tuple] [] self.trades: List[Fill] [] def run(self, data: pd.DataFrame) - pd.DataFrame: Run backtest on OHLCV data with DatetimeIndex. pending_orders: List[Order] [] for timestamp, bar in data.iterrows(): # Execute pending orders at todays prices for order in pending_orders: fill self.execution_model.execute(order, bar) if fill: self.portfolio.process_fill(fill) self.strategy.on_fill(fill) self.trades.append(fill) pending_orders.clear() # Get current prices for equity calculation prices {data.index.name or default: Decimal(str(bar[close]))} equity self.portfolio.get_equity(prices) self.equity_curve.append((timestamp, float(equity))) # Generate new orders for next bar new_orders self.strategy.on_bar(timestamp, data.loc[:timestamp]) pending_orders.extend(new_orders) return self._create_results() def _create_results(self) - pd.DataFrame: equity_df pd.DataFrame(self.equity_curve, columns[timestamp, equity]) equity_df.set_index(timestamp, inplaceTrue) equity_df[returns] equity_df[equity].pct_change() return equity_df主循环的时序纪律值得反复强调它同时规避了前视偏差与交易成本偏差先执行昨日挂单pending_orders上一 bar 收盘生成的订单在今日价格上成交再记录今日净值用今日close计算权益写入权益曲线最后生成明日新订单策略基于截至当前的data.loc[:timestamp]生成订单加入pending_orders留待下一根 bar 执行。输出为标准 DataFrame以时间戳为索引的equity权益曲线与returns由pct_change()计算的收益率序列可直接喂给后文 5.7 的指标计算函数。六、实现模式二向量化回测器Vectorized Backtester当策略逻辑简单、只需要验证想法时逐 bar 事件循环性能不足。Pattern 2 提供了基于 pandas 数组运算的向量化回测器适合动量、均线交叉这类信号型策略的大规模快速扫描import pandas as pd import numpy as np from typing import Callable, Dict, Any class VectorizedBacktester: Fast vectorized backtester for simple strategies. def __init__( self, initial_capital: float 100000, commission: float 0.001, # 0.1% slippage: float 0.0005 # 0.05% ): self.initial_capital initial_capital self.commission commission self.slippage slippage def run( self, prices: pd.DataFrame, signal_func: Callable[[pd.DataFrame], pd.Series] ) - Dict[str, Any]: Run backtest with signal function. Args: prices: DataFrame with close column signal_func: Function that returns position signals (-1, 0, 1) Returns: Dictionary with results # Generate signals (shifted to avoid look-ahead) signals signal_func(prices).shift(1).fillna(0) # Calculate returns returns prices[close].pct_change() # Calculate strategy returns with costs position_changes signals.diff().abs() trading_costs position_changes * (self.commission self.slippage) strategy_returns signals * returns - trading_costs # Build equity curve equity (1 strategy_returns).cumprod() * self.initial_capital # Calculate metrics results { equity: equity, returns: strategy_returns, signals: signals, metrics: self._calculate_metrics(strategy_returns, equity) } return results def _calculate_metrics( self, returns: pd.Series, equity: pd.Series ) - Dict[str, float]: Calculate performance metrics. total_return (equity.iloc[-1] / self.initial_capital) - 1 annual_return (1 total_return) ** (252 / len(returns)) - 1 annual_vol returns.std() * np.sqrt(252) sharpe annual_return / annual_vol if annual_vol 0 else 0 # Drawdown rolling_max equity.cummax() drawdown (equity - rolling_max) / rolling_max max_drawdown drawdown.min() # Win rate winning_days (returns 0).sum() total_days (returns ! 0).sum() win_rate winning_days / total_days if total_days 0 else 0 return { total_return: total_return, annual_return: annual_return, annual_volatility: annual_vol, sharpe_ratio: sharpe, max_drawdown: max_drawdown, win_rate: win_rate, num_trades: int((returns ! 0).sum()) }几个实现要点前视偏差的天然防御signals signal_func(prices).shift(1).fillna(0)——信号整体后移一根 bar确保第 t 天的持仓决策只使用第 t-1 天及之前的信息signals.diff().abs()计算换仓位置变化仅对发生调仓的 bar 计收交易成本。成本建模trading_costs position_changes * (commission slippage)把 0.1% 佣金与 0.05% 滑点合并为单次换仓成本strategy_returns signals * returns - trading_costs显式扣除。年化约定按 252 个交易日年化np.sqrt(252)这与 risk-metrics-calculation 中ann_factor 252的约定一致便于两个技能产出的指标直接互相引用。使用示例momentum_signal演示了 20 日均线动量信号收盘价高于 SMA 持多头否则空仓调用方式为backtester.run(price_data, lambda p: momentum_signal(p, 50))。七、实现模式三Walk-Forward Optimization 前向优化Pattern 3 把第 4 节的 Walk-Forward 方法论落成代码支持anchored锚定/扩展窗口与rolling滚动窗口两种模式并通过网格搜索在每段训练窗口内选择最优参数from typing import Callable, Dict, List, Tuple, Any import pandas as pd import numpy as np from itertools import product class WalkForwardOptimizer: Walk-forward analysis with anchored or rolling windows. def __init__( self, train_period: int, test_period: int, anchored: bool False, n_splits: int None ): Args: train_period: Number of bars in training window test_period: Number of bars in test window anchored: If True, training always starts from beginning n_splits: Number of train/test splits (auto-calculated if None) self.train_period train_period self.test_period test_period self.anchored anchored self.n_splits n_splits def generate_splits( self, data: pd.DataFrame ) - List[Tuple[pd.DataFrame, pd.DataFrame]]: Generate train/test splits. splits [] n len(data) if self.n_splits: step (n - self.train_period) // self.n_splits else: step self.test_period start 0 while start self.train_period self.test_period n: if self.anchored: train_start 0 else: train_start start train_end start self.train_period test_end min(train_end self.test_period, n) train_data data.iloc[train_start:train_end] test_data data.iloc[train_end:test_end] splits.append((train_data, test_data)) start step return splits def optimize( self, data: pd.DataFrame, strategy_func: Callable, param_grid: Dict[str, List], metric: str sharpe_ratio ) - Dict[str, Any]: Run walk-forward optimization. Args: data: Full dataset strategy_func: Function(data, **params) - results dict param_grid: Parameter combinations to test metric: Metric to optimize Returns: Combined results from all test periods splits self.generate_splits(data) all_results [] optimal_params_history [] for i, (train_data, test_data) in enumerate(splits): # Optimize on training data best_params, best_metric self._grid_search( train_data, strategy_func, param_grid, metric ) optimal_params_history.append(best_params) # Test with optimal params test_results strategy_func(test_data, **best_params) test_results[split] i test_results[params] best_params all_results.append(test_results) print(fSplit {i1}/{len(splits)}: fBest {metric}{best_metric:.4f}, params{best_params}) return { split_results: all_results, param_history: optimal_params_history, combined_equity: self._combine_equity_curves(all_results) } def _grid_search( self, data: pd.DataFrame, strategy_func: Callable, param_grid: Dict[str, List], metric: str ) - Tuple[Dict, float]: Grid search for best parameters. best_params None best_metric -np.inf # Generate all parameter combinations param_names list(param_grid.keys()) param_values list(param_grid.values()) for values in product(*param_values): params dict(zip(param_names, values)) results strategy_func(data, **params) if results[metrics][metric] best_metric: best_metric results[metrics][metric] best_params params return best_params, best_metric def _combine_equity_curves( self, results: List[Dict] ) - pd.Series: Combine equity curves from all test periods. combined pd.concat([r[equity] for r in results]) return combined设计解读切分逻辑generate_splits默认以test_period为步长滚动指定n_splits时自动计算步长。anchoredTrue时训练起点始终为 0扩展窗口否则训练窗口随起点滚动滚动窗口。优化闭环每个 split 内_grid_search用itertools.product对param_grid做笛卡尔积网格搜索在训练段上按目标指标默认sharpe_ratio选出最优参数再把该参数应用到紧随其后的测试段——训练与测试严格分离杜绝在测试段上偷看调参。产出split_results各段测试结果、param_history参数漂移历史可观察最优参数是否随市场环境剧烈变化——若剧烈变化往往意味着过拟合、combined_equity拼接全部测试段的权益曲线用于评估整体样本外表现。八、实现模式四Monte Carlo 分析Pattern 4 通过自助重采样bootstrap with replacement量化策略的不确定性。SKILL.md 的 Dos 中 Monte Carlo analysis - Understand uncertainty 即是本模式的入口import numpy as np import pandas as pd from typing import Dict, List class MonteCarloAnalyzer: Monte Carlo simulation for strategy robustness. def __init__(self, n_simulations: int 1000, confidence: float 0.95): self.n_simulations n_simulations self.confidence confidence def bootstrap_returns( self, returns: pd.Series, n_periods: int None ) - np.ndarray: Bootstrap simulation by resampling returns. Args: returns: Historical returns series n_periods: Length of each simulation (default: same as input) Returns: Array of shape (n_simulations, n_periods) if n_periods is None: n_periods len(returns) simulations np.zeros((self.n_simulations, n_periods)) for i in range(self.n_simulations): # Resample with replacement simulated_returns np.random.choice( returns.values, sizen_periods, replaceTrue ) simulations[i] simulated_returns return simulations def analyze_drawdowns( self, returns: pd.Series ) - Dict[str, float]: Analyze drawdown distribution via simulation. simulations self.bootstrap_returns(returns) max_drawdowns [] for sim_returns in simulations: equity (1 sim_returns).cumprod() rolling_max np.maximum.accumulate(equity) drawdowns (equity - rolling_max) / rolling_max max_drawdowns.append(drawdowns.min()) max_drawdowns np.array(max_drawdowns) return { expected_max_dd: np.mean(max_drawdowns), median_max_dd: np.median(max_drawdowns), fworst_{int(self.confidence*100)}pct: np.percentile( max_drawdowns, (1 - self.confidence) * 100 ), worst_case: max_drawdowns.min() } def probability_of_loss( self, returns: pd.Series, holding_periods: List[int] [21, 63, 126, 252] ) - Dict[int, float]: Calculate probability of loss over various holding periods. results {} for period in holding_periods: if period len(returns): continue simulations self.bootstrap_returns(returns, period) total_returns (1 simulations).prod(axis1) - 1 prob_loss (total_returns 0).mean() results[period] prob_loss return results def confidence_interval( self, returns: pd.Series, periods: int 252 ) - Dict[str, float]: Calculate confidence interval for future returns. simulations self.bootstrap_returns(returns, periods) total_returns (1 simulations).prod(axis1) - 1 lower (1 - self.confidence) / 2 upper 1 - lower return { expected: total_returns.mean(), lower_bound: np.percentile(total_returns, lower * 100), upper_bound: np.percentile(total_returns, upper * 100), std: total_returns.std() }三个核心分析维度analyze_drawdowns对历史收益率做 1000 次有放回重采样每次模拟一条权益曲线并计算最大回撤输出期望最大回撤、中位数最大回撤、95% 分位最差回撤与最坏情形回答这个策略的最大回撤有多稳定。probability_of_loss默认考察 21/63/126/252约 1/3/6/12 个月持有期下亏损的概率用于资金管理与持有期决策。confidence_interval对 252 个周期一年的累计收益给出置信区间默认 95%lower_bound/upper_bound直接量化策略收益的不确定性范围。九、性能指标体系details.md 末尾提供了统一的绩效指标计算函数可直接对接事件驱动回测器与向量化回测器产出的returns序列def calculate_metrics(returns: pd.Series, rf_rate: float 0.02) - Dict[str, float]: Calculate comprehensive performance metrics. # Annualization factor (assuming daily returns) ann_factor 252 # Basic metrics total_return (1 returns).prod() - 1 annual_return (1 total_return) ** (ann_factor / len(returns)) - 1 annual_vol returns.std() * np.sqrt(ann_factor) # Risk-adjusted returns sharpe (annual_return - rf_rate) / annual_vol if annual_vol 0 else 0 # Sortino (downside deviation) downside_returns returns[returns 0] downside_vol downside_returns.std() * np.sqrt(ann_factor) sortino (annual_return - rf_rate) / downside_vol if downside_vol 0 else 0 # Calmar ratio equity (1 returns).cumprod() rolling_max equity.cummax() drawdowns (equity - rolling_max) / rolling_max max_drawdown drawdowns.min() calmar annual_return / abs(max_drawdown) if max_drawdown ! 0 else 0 # Win rate and profit factor wins returns[returns 0] losses returns[returns 0] win_rate len(wins) / len(returns[returns ! 0]) if len(returns[returns ! 0]) 0 else 0 profit_factor wins.sum() / abs(losses.sum()) if losses.sum() ! 0 else np.inf return { total_return: total_return, annual_return: annual_return, annual_volatility: annual_vol, sharpe_ratio: sharpe, sortino_ratio: sortino, calmar_ratio: calmar, max_drawdown: max_drawdown, win_rate: win_rate, profit_factor: profit_factor, num_trades: int((returns ! 0).sum()) }各指标含义与计算口径指标含义计算口径total_return累计总收益(1returns).prod()-1annual_return年化收益按 252 交易日几何年化annual_volatility年化波动率日收益标准差 × √252sharpe_ratio夏普比率(年化收益 - 无风险利率) / 年化波动率默认rf_rate0.02sortino_ratio索提诺比率分母换为下行波动仅亏损日标准差calmar_ratio卡玛比率年化收益 / 最大回撤绝对值max_drawdown最大回撤权益曲线峰值到谷底的最大跌幅win_rate胜率盈利周期数 / 非零周期数profit_factor盈亏比总盈利 / 总亏损绝对值无亏损时为infnum_trades交易次数非零收益周期计数风险调整后收益指标Sharpe/Sortino/Calmar与回撤指标正是 risk-manager.md 中 Risk-adjusted performance metrics、Maximum drawdown analysis 所依赖的度量基础若需要更细化的 VaR、CVaR、下行偏差等风险指标可进一步引用同插件下的 risk-metrics-calculation Skill。十、Best PracticesDos 与 DontsSKILL.md 末尾以清单形式总结了可操作的最佳实践这是本技能最浓缩的实战守则应该做DosUse point-in-time data—— 使用时点数据规避前视偏差Include transaction costs—— 计入交易成本获得现实估计Test out-of-sample—— 始终预留样本外数据Use walk-forward—— 使用前向分析而非仅一次 train/testMonte Carlo analysis—— 用蒙特卡洛理解不确定性不该做DontsDont overfit—— 限制参数数量避免对历史曲线过度拟合Dont ignore survivorship—— 数据必须包含退市标的Dont use adjusted data carelessly—— 谨慎使用复权数据理解复权方式对信号的影响Dont optimize on full history—— 不在全历史上优化必须保留测试集Dont ignore capacity—— 不要忽略资金容量市场冲击market impact会影响真实收益十一、在本仓库中的使用方式本 Skill 遵循 Agent Skills 规范采用元数据 → 指令 → 资源的三层渐进式披露progressive disclosure结构SKILL.md的 frontmatter 承载名称与激活条件始终加载正文为导航级核心概念与最佳实践激活后加载references/details.md存放完整代码模式按需读取。安装方式有两种# 方式一通过插件安装加载 quantitative-trading 插件的 agents skills commands /plugin install quantitative-trading # 方式二仅安装单个 Skill 到任意 Agent使用 Agent Skills 安装器 gh skill install wshobson/agents backtesting-frameworks # GitHub CLI 2.90 npx skills add wshobson/agents --skill backtesting-frameworks # vercel-labs/skills在实际使用中Agent 的典型协作链路为quant-analystAgent 负责设计策略与搭建回测调用本 Skill 的事件驱动/向量化模式risk-managerAgent 负责用 Monte Carlo 与风险指标评估回测结果的稳健性两者共享本 Skill 产出的权益曲线与收益序列。该插件在 docs/plugins.md 中被归类为 Finance 类目Algorithmic trading and risk management共提供 backtesting-frameworks 与 risk-metrics-calculation 两个技能形成先正确回测、再度量风险的完整闭环。结语backtesting-frameworks Skill 的价值不在于提供某一个回测框架而在于把回测中最容易被忽视、也最致命的偏差问题系统化、工程化前视偏差靠时序纪律与shift(1)防御幸存者偏差靠数据完整性过拟合靠样本外与前向分析交易成本靠显式成本模型选择偏差靠预先注册。配合事件驱动与向量化两套回测引擎、Walk-Forward 优化器、Monte Carlo 分析器以及统一的绩效指标函数你可以直接在本仓库提供的代码模式之上搭建属于自己的、可上生产环境的量化回测基础设施。【免费下载链接】agentsMulti-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity项目地址: https://gitcode.com/GitHub_Trending/agents24/agents创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考