Find your next open-source project

Search by name, purpose, or keyword — or paste a GitHub repository URL
All skills

backtest-expert

Stress-test a trading strategy's backtest and return a scored Deploy, Refine, or Abandon decision.

When to use it

You have backtest metrics for a rule-based strategy and need to know whether it survives pessimistic costs, parameter changes, and out-of-sample periods before risking money.

For example

You say

Use backtest-expert to evaluate my gap-up mean-reversion strategy: 150 trades, 62% win rate, 1.8% average win, 1.2% average loss, 15% max drawdown, 8 years tested, 3 parameters, slippage tested.

You get
  • Scored evaluation report
  • Deploy/Refine/Abandon decision
  • Blocking reasons list

How it works

  • Parameter sensitivity is checked by varying stops and targets around the baseline to find stable plateaus rather than narrow peaks.
  • Walk-forward analysis compares in-sample and out-of-sample results to flag over-optimization.
  • Results that look too good, such as over 90% win rate with tiny drawdowns, trigger a look-ahead bias audit.

Before installing

The evaluation script needs Python 3.9+; no API keys or external data are required.

This skill includes 3 scripts your assistant may run on your computer.