Vibeship-spawner-skills algorithmic-trading

id: algorithmic-trading name: Algorithmic Trading category: finance description: Use when building trading systems, backtesting strategies, implementing execution algorithms, or analyzing market microstructure - covers strategy development, risk management, and production deployment

patterns: golden_rules: - rule: "Never optimize on all data" reason: "Out-of-sample testing prevents overfitting" - rule: "Include realistic costs" reason: "Slippage and commissions kill edge" - rule: "Use event-driven backtests" reason: "Time-based sampling creates look-ahead bias" - rule: "Version everything" reason: "Data, code, models, and parameters" - rule: "Paper trade before live" reason: "Exposes slippage and execution bugs"

framework_8_step: steps: - "HYPOTHESIS - Define market inefficiency" - "DATA - Collect clean, adjusted data" - "SIGNAL - Generate trading signals" - "BACKTEST - Event-driven with realistic costs" - "OPTIMIZE - Walk-forward optimization" - "VALIDATE - Out-of-sample testing" - "DEPLOY - Paper trade first" - "MONITOR - Track performance, drift"

inefficiency_types: microstructure: "Order flow imbalances, bid-ask dynamics" behavioral: "Overreaction, anchoring, herding" fundamental: "Earnings surprises, value anomalies" technical: "Momentum, mean reversion, breakouts" statistical: "Pairs trading, factor arbitrage" event: "Corporate actions, economic releases"

execution_algorithms: twap: "Time-Weighted Average Price" vwap: "Volume-Weighted Average Price" is: "Implementation Shortfall" pov: "Percentage of Volume"

anti_patterns:

• pattern: "Optimizing on full dataset" problem: "Massive overfitting" solution: "Walk-forward validation"
• pattern: "Ignoring transaction costs" problem: "Strategy unprofitable live" solution: "Include realistic cost model"
• pattern: "Single market testing" problem: "Regime-dependent strategy" solution: "Test across multiple periods"
• pattern: "No position limits" problem: "Catastrophic losses" solution: "Max position and drawdown limits"
• pattern: "Hardcoded parameters" problem: "Fails on regime change" solution: "Adaptive or robust parameters"
• pattern: "Looking at P&L first" problem: "Curve fitting" solution: "Focus on process, not results"

implementation_checklist: strategy_development: - "Define clear hypothesis based on market inefficiency" - "Collect clean, adjusted data (splits, dividends)" - "Implement signal generation with proper lookback" - "Build event-driven backtest with realistic costs" - "Perform walk-forward optimization" risk_management: - "Calculate risk-adjusted metrics (Sharpe, Sortino, Calmar)" - "Implement position sizing based on risk" - "Set maximum drawdown limits" - "Define position concentration limits" deployment: - "Paper trade for minimum 2 weeks" - "Set up monitoring and alerting" - "Document strategy logic and parameters" - "Implement kill switch for emergencies"

handoffs:

• skill: risk-modeling trigger: "VaR and risk metrics for portfolio"
• skill: portfolio-optimization trigger: "asset allocation decisions"
• skill: derivatives-pricing trigger: "options strategies and hedging"

ecosystem: backtesting: - "backtesting.py - Fast strategy backtesting" - "vectorbt - Vectorized backtesting" - "zipline - Event-driven backtesting" analysis: - "pyfolio - Performance analysis" - "quantstats - Trading statistics" brokers: - "alpaca-py - Alpaca API" - "ib_insync - Interactive Brokers" - "ccxt - Crypto exchanges"

sources: tutorials: - "PyQuant 8-Step Framework" - "Backtesting.py Documentation" books: - "Advances in Financial Machine Learning - Lopez de Prado"