VectorBT Backtesting

VectorBT Backtesting is an AI Engineering skill for Claude Code, published by marketcalls in vectorbt-backtesting-skills.

200 stars43 forkson marketcalls/vectorbt-backtesting-skillsAdded 2026/09/05Repository updated 2026/07/12

View source on GitHub Download repo ZIP

agent-skillsbacktestingmonte-carlooptimizationpythonquantstatsrobustnesstearsheetsvectorbtwalk-forward

Install in seconds

Install VectorBT Backtesting

Copy VectorBT Backtesting into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/marketcalls/vectorbt-backtesting-skills/tree/master/.claude/skills/backtest ~/.claude/skills/backtest

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/marketcalls/vectorbt-backtesting-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .claude/skills/backtest/SKILL.md in marketcalls/vectorbt-backtesting-skills
Installs to: ~/.claude/skills/backtest
Collection: One of 6 skills cataloged from this repository
Category: AI Engineering — 3101 skills

What VectorBT Backtesting does

VectorBT Backtesting creates a complete Python backtest script for a named strategy and symbol. It is used to fetch data, generate signals, run a portfolio test, compare against a benchmark, and export plots and trades.

VectorBT Backtesting is cataloged under AI Engineering on DirSkills. VectorBT Backtesting comes from a repository tagged agent-skills, backtesting, monte-carlo, optimization and python.

Documentation

README

Excerpt

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.

Instructions

This is the opening of the README. Read the full README on GitHub.

Commands VectorBT Backtesting provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/backtest

Frequently asked about VectorBT Backtesting

What else does marketcalls publish alongside VectorBT Backtesting?
VectorBT Backtesting is one of 6 skills that DirSkills catalogs from marketcalls/vectorbt-backtesting-skills, the repository it ships in. Its siblings there include Optimize, Quick Stats and Setup. Each one is a separate skill with its own page in this directory, installs the same way VectorBT Backtesting does, and is maintained by marketcalls in that same repository. The rest of the collection is listed on the marketcalls/vectorbt-backtesting-skills page.
How does VectorBT Backtesting compare to other AI Engineering skills?
VectorBT Backtesting ranks #2858 by stars among the 3101 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of VectorBT Backtesting against them. Open each page to compare what they document and how they install.