Backtest Reality Stress Tester

The problem

Most backtests suffer from survival bias, lookahead errors, and unrealistic execution assumptions. Developers often find that strategies with stellar historical results collapse immediately when faced with real-world slippage, fees, or unseen market regimes.

What it does

• Identifies hidden data leakage, lookahead bias, and repainting indicators in Pine Script or Python code.
• Calculates break-even friction levels to determine at what cost-per-trade the strategy edge disappears.
• Stress-tests performance against parameter sensitivity, trade concentration, and regime shifts.
• Evaluates the integrity of out-of-sample data and research chronology to detect search-bias and overfitting.
• Produces a tiered robustness score constrained by the quality of available evidence.

Frameworks & tools

Works with Pine Script (TradingView), Python (Pandas/Backtrader), CSV trade logs, and standard brokerage backtest reports.

Why this beats prompting it yourself

This skill enforces a two-stage scoring rubric that prevents "absence of evidence" from being mistaken for "robustness." It uses specialized failure-pattern recognition to catch subtle timing errors that generic LLM prompts typically overlook.

Use cases

• Auditing a Pine Script strategy before committing capital to a live bot.
• Validating third-party backtest claims before purchasing a trading signal or algorithm.
• Determining if a strategy edge is a result of over-optimization or genuine market inefficiency.
• Quantifying the impact of realistic slippage and borrow fees on high-turnover strategies.

Known limitations

Does not provide financial advice or guarantee future profits. Requires strategy code or detailed trade logs for high-confidence leakage detection.