Backtest trading strategies and analyze quantitative factors across global markets.
npx skills add https://github.com/hxhyyy/Vibe-Trading --skill vibe-trading-hxhyyy
Please help me install this Agent Skill. Skill: vibe-trading Source: https://github.com/hxhyyy/Vibe-Trading/tree/main/agent Command: npx skills add https://github.com/hxhyyy/Vibe-Trading --skill vibe-trading-hxhyyy
This Skill solves the complexity of quantitative finance research by providing a unified interface for backtesting, factor analysis, and multi-agent strategy development without requiring manual data wrangling.
Use the vibe-trading skill to run a backtest on AAPL with a MACD strategy for the year 2024.
High-intent search queries and answers about installing and using this skill.
Backtesting equities without manual data wrangling is achieved through a unified quantitative research environment that automates data sourcing. You can run a strategy test by specifying the asset, indicator, and timeframe to generate performance results directly.
Pre-built quantitative factors for alpha benchmarking include an Alpha Zoo of 452 quantitative signals. These factors enable one-line benchmarking and signal generation to evaluate investment theses without coding custom mathematical models.
Multi-agent swarm orchestration can automate investment thesis analysis by deploying specialized research teams. These agents debate strategies, perform risk audits, and analyze global market regimes across equities, crypto, and futures.
Shadow account diagnostics extract trading rules from a broker journal by automatically parsing your personal trading history. It uses this extracted logic to backtest and optimize your specific strategy without requiring manual rule coding.
Performing quantitative factor analysis and automated alpha benchmarking requires the vibe-trading-ai dependency. This underlying AI integration provides the advanced financial modeling tools needed for shadow account diagnostics and multi-agent orchestration.
Global quantitative research supports diverse market data sources including equities, crypto, and futures. This coverage spans global exchanges to provide comprehensive inputs for backtesting and multi-agent strategy orchestration.
loanntcConvert trading journals and research hypotheses into measurable performance via multi-market backtests and Alpha Zoo benchmarking.
PoorRicanAnalyze Jupyter notebook backtest results and generate a structured Markdown report.
dreamineeringAutomates risk-aware position sizing and portfolio risk management for meme-trading systems.
day18708433173-cryptoRun quantitative backtests and factor analysis across 18 global market-data sources.
