Backtest

If you're backtesting Indian equities or futures with VectorBT, this generates complete Python scripts instead of making you wire up data fetching, signal generation, and plotting from scratch every time. It pulls data from OpenAlgo or DuckDB, uses TA-Lib for standard indicators and OpenAlgo's ta library for specialty ones like Supertrend, runs the backtest with proper Indian delivery fees (0.111% plus fixed costs) or F&O rates, and spits out stats, a benchmark comparison table, trade CSVs, and Plotly charts. It includes templates for common strategies like EMA crossover, RSI, MACD, and Donchian channels. The lot size logic for NIFTY and BANKNIFTY futures is built in, which saves you from getting sizing wrong on leveraged products.

skills.sh installs: 3.5K
GitHub stars: 223
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Create a complete VectorBT backtest script for the user.

Arguments

Parse $ARGUMENTS as: strategy symbol exchange interval

$0 = strategy name (e.g., ema-crossover, rsi, donchian, supertrend, macd, sda2, momentum)
$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 they want.