Quick Stats

A backtest runner that keeps things inline and focused on Indian equities. You give it a symbol like SBIN or RELIANCE, it pulls data from OpenAlgo or yfinance, runs an EMA 10/20 crossover using TA-Lib, and prints stats with proper Indian delivery fees baked in. It benchmarks against NIFTY automatically and explains metrics in plain language, which is helpful if you're not steeped in quant jargon. The whole thing outputs code you paste into a Jupyter cell or run as a script, no file juggling required. Good for quick sanity checks on a strategy before you build something heavier, though you're locked into that one EMA crossover setup.

skills.sh installs: 2.1K
GitHub stars: 223
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Generate a quick inline backtest and print stats. Do NOT create a file - output code directly for the user to run or execute in a notebook.

Arguments

$0 = symbol (e.g., SBIN, RELIANCE). Default: SBIN
$1 = exchange. Default: NSE
$2 = interval. Default: D

Instructions

Generate a single code block the user can paste into a Jupyter cell or run as a script. The code must:

Fetch data from OpenAlgo (or DuckDB if user provides a DB path, or yfinance as fallback)
Use OpenAlgo ta for EMA 10/20 crossover by default (never VectorBT built-in); only use TA-Lib if the user explicitly says "talib"/"TA-Lib"
Clean signals with ta.exrem() (always .fillna(False) before exrem)
Use Indian delivery fees: fees=0.00111, fixed_fees=20
Fetch NIFTY benchmark via OpenAlgo (symbol="NIFTY", exchange="NSE_INDEX")
Print a compact results summary: