vibe-trading

Orchestrate AI-powered backtesting and multi-agent research for finance professionals.

Updated Aug 23, 2026

Search Tags:#analytics #ai #data #finance #swarm #backtesting

Ready to run

npx skills add https://github.com/prinzeval/Vibe-Trading --skill vibe-trading-prinzeval

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: vibe-trading
Source: https://github.com/prinzeval/Vibe-Trading/tree/main/VALENDATA/agent
Command: npx skills add https://github.com/prinzeval/Vibe-Trading --skill vibe-trading-prinzeval

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Streamline complex finance research workflows by providing an AI-powered, all-in-one toolkit for backtesting, multi-agent collaboration, and rule extraction from trading journals.

Core Features & Use Cases

Backtesting across seven engines, 71 specialized skills, and multiple data sources to evaluate strategies and surface actionable insights.
Shadow Account loop to extract and test implicit trading rules from journal data, enabling data-driven refinement and performance visualization.
29 pre-built swarm teams for end-to-end research, debate, risk review, and PM decision support across asset classes (A股/港股/美股/crypto).

Quick Start

Install vibe-trading-ai and start the interactive vibe-trading CLI to explore backtests and swarm workflows.

Frequently Asked Questions about vibe-trading

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

FAQPage Schema

How do I backtest trading strategies across multiple asset classes like A-shares and crypto?▼

Backtesting trading strategies across A-shares, HK/US equities, and crypto relies on seven backtesting engines and five data sources to evaluate performance and surface actionable insights.

What is a multi-agent swarm workflow for finance research?▼

Multi-agent swarm workflows for finance research orchestrate 29 pre-built AI teams to execute end-to-end research, debate strategies, review risk, and support portfolio management decisions.

How do I extract and evaluate implicit trading rules from my trading journal?▼

Extracting and evaluating implicit trading rules from trading journals uses the Shadow Account loop to enable data-driven refinement and performance visualization of extracted strategies.

Do I need Python 3.11 to use AI-powered finance research and backtesting tools?▼

AI-powered finance research and backtesting tools require Python 3.11 or higher, the vibe-trading-ai package, and environment settings for data providers and LLMs to function correctly.

Can I use a multi-agent swarm for portfolio management risk review?▼

Multi-agent swarms support portfolio management risk review through 29 pre-built teams designed for end-to-end research, strategy debate, and decision support across multiple asset classes.

What is the best way to automate finance research with a multi-agent AI toolkit?▼

Automating finance research with a multi-agent AI toolkit involves orchestrating 71 specialized skills and 29 swarm teams to evaluate strategies and extract rules from trading journals.