vibe-trading

Run quantitative backtests and factor analysis across 18 global market-data sources.

Updated Jul 10, 2026

Search Tags:#finance #swarm #backtesting #trading #quantitative #alpha

Ready to run

npx skills add https://github.com/day18708433173-crypto/TradingAgents-Pro --skill vibe-trading-day18708433173-crypto

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: vibe-trading
Source: https://github.com/day18708433173-crypto/TradingAgents-Pro/tree/main/agent
Command: npx skills add https://github.com/day18708433173-crypto/TradingAgents-Pro --skill vibe-trading-day18708433173-crypto

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires vibe-trading-ai, pandas, numpy, scikit-learn, fastapi, fastmcp, and includes scripts (resource) components.

What problem does it solve?

This Skill addresses the complexity of quantitative finance research by providing a unified, automated environment for backtesting, factor analysis, and multi-agent strategy evaluation.

Core Features & Use Cases

Quantitative Backtesting: Run vectorized strategies across 7 engines and 18 market-data sources including A-shares, US/HK equities, and crypto.
Alpha Zoo: Access 452 pre-built quantitative factors for one-line benchmarking and signal generation.
Multi-Agent Swarm: Deploy specialized teams like the Investment Committee to conduct bull/bear debates and risk reviews.
Shadow Account: Analyze trade journals to extract implicit trading rules and backtest them against real-market data.

Quick Start

Use the vibe-trading skill to run an investment committee review for NVDA.US with the investment_committee preset.

Frequently Asked Questions about vibe-trading

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I run quantitative backtesting across multiple global market data sources?▼

Quantitative backtesting is executed through vectorized strategies across 7 engines and 18 global data sources, including A-shares, US/HK equities, and crypto, to validate your trading models.

Can I use multi-agent swarms for investment committee reviews and strategy generation?▼

Multi-agent swarms deploy specialized teams like the Investment Committee to conduct bull/bear debates and risk reviews, enabling automated strategy generation and evaluation.

What quantitative factors are available for signal generation and benchmarking?▼

An Alpha Zoo provides 452 pre-built quantitative factors for one-line benchmarking and signal generation, streamlining the factor analysis process for your research.

Does fastmcp integrate with external AI agents to expose trading research capabilities?▼

Fastmcp integration exposes research capabilities and trading connector data to external AI agents, allowing seamless orchestration of your quantitative finance tools.

How do I extract implicit trading rules from a trade journal for backtesting?▼

The Shadow Account feature analyzes trade journals to extract implicit trading rules, which are then backtested against real-market data to validate your strategies.

What is the best way to orchestrate quantitative finance research with pandas and numpy?▼

Orchestrate quantitative finance research by leveraging pandas and numpy within a unified environment that automates backtesting, factor analysis, and multi-agent strategy evaluation.