Skip to content
Get packs

Cross-Market Strategy Builder

Writes a multi-market trading signal engine for backtests mixing stocks, crypto and forex

Source Download skill
Repository
HKUDS/Vibe-Trading
Stars
37,433
Licence
MIT
Files
2 files

What it does

This skill teaches an AI agent how to write a trading strategy file (signal_engine.py) for backtests that combine assets from different markets, such as Chinese A-shares with crypto or US stocks with forex. It explains how to group symbols by market, apply market-specific moving-average and volatility settings, and scale positions by volatility so that a volatile asset like Bitcoin does not dominate the portfolio. The bundled example script shows a complete version of this approach.

Great for

  • Quantitative traders or analysts testing strategies across several markets at once
  • Developers building backtests in the Vibe-Trading framework who need a starting template
  • Students learning how volatility-adjusted position sizing works in practice

Skip it if

  • Anyone wanting live trading advice: the skill only produces backtest code and parameters, and past backtest results do not predict returns
  • Users without programming or backtesting experience, since the output is Python code that must be understood and checked before use
  • Anyone expecting the skill to verify market rules or data accuracy; the file says the engine handles calendars, fees and T+1 rules automatically, which the user should confirm

Try asking

  • “Write a signal_engine.py that backtests 000001.SZ alongside BTC-USDT with volatility-adjusted weights”
  • “Create a cross-market strategy combining AAPL.US, EUR/USD and 600519.SH with per-market moving-average settings”
  • “Set up a config.json for a daily backtest of mixed A-share and crypto codes from 2024 to 2025”
  • “Build a correlation-regime strategy that reduces exposure when cross-market correlation is high”
Step-by-step guide: how to use Cross-Market Strategy BuilderInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    cross-market-strategy.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip cross-market-strategy.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip cross-market-strategy.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Review the generated signal_engine.py before running it, since the agent will execute code in your environment and the example is only a template
  • Check the per-market parameter table and volatility estimates against your own data before trusting the backtest
  • Keep the date range and initial cash in config.json realistic, and treat backtest output as a hypothesis to test rather than a forecast

What's inside

  • example_signal_engine.py
  • SKILL.md

Redistributed unmodified from HKUDS/Vibe-Trading under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.