Optimize

This lets you brute force parameter combinations for VectorBT strategies and see what actually works on historical data. It tests ranges like EMA crossover periods or RSI thresholds, tracks return, Sharpe, drawdown, and trade count for each combo, then spits out heatmaps and top performers. The setup handles Indian market specifics like NSE delivery fees and lot sizes for futures, pulls benchmark comparisons against NIFTY, and explains results without jargon. It's opinionated about using TA-Lib over VectorBT's built-ins and applies exrem signal cleaning by default. If you're tweaking strategies and want to know which parameters survive real slippage and costs, this gives you the full grid search with visual output.

skills.sh installs: 2.4K
GitHub stars: 223
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add marketcalls/vectorbt-backtesting-skills --skill optimize --agent claude-code

Installs into .claude/skills of the current project.

Files

Create a parameter optimization script for a VectorBT strategy.

Arguments

Parse $ARGUMENTS as: strategy symbol exchange interval

$0 = strategy name (e.g., ema-crossover, rsi, donchian). Default: ema-crossover
$1 = symbol (e.g., SBIN, RELIANCE, NIFTY). Default: SBIN
$2 = exchange (e.g., NSE, NFO). Default: NSE
$3 = interval (e.g., D, 1h, 5m). Default: D

If no arguments, ask the user which strategy to optimize.