vectorbt-backtesting-skills

marketcalls/vectorbt-backtesting-skills

Agentic coding skills for backtesting trading strategies using VectorBT. Supports Indian, US, and Crypto markets with realistic transaction cost modeling, TA-Lib indicators, QuantStats tearsheets, and 12 ready-made strategy templates.

124 stars

30 forks

Python

84 views

View on GitHub Add to Favorites

Installation

Option 1: Use slash command in Claude Code

/install-skill https://github.com/marketcalls/vectorbt-backtesting-skills

Option 2: Clone to skills directory

# Global (all projects)

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

# Project-specific

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

Add MCP server to .cursor/mcp.json:

{
  "mcpServers": {
    "skillz": {
      "command": "npx",
      "args": ["-y", "skillz-mcp", "https://github.com/marketcalls/vectorbt-backtesting-skills"]
    }
  }
}

Restart Cursor after adding the configuration.

Option 1: Use Gemini CLI command

gemini extensions install https://github.com/marketcalls/vectorbt-backtesting-skills

Option 2: Clone to extensions directory

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

Topics

agent-skills backtesting monte-carlo optimization python quantstats robustness tearsheets vectorbt walk-forward