skills.rest
Liangwei-zhang
Liangwei-zhangCOMMUNITY
Explore all skills by this author →
GitHub

vibe-trading

Orchestrate quantitative finance research with backtesting, analytics, and swarm collaboration.

Updated Apr 14, 2026
Search Tags:#ai#finance#swarm#data-analytics#backtesting#multiengine
One-click install
npx skills add https://github.com/Liangwei-zhang/six-stock --skill vibe-trading-liangwei-zhang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vibe-trading
Source: https://github.com/Liangwei-zhang/six-stock/tree/main/Vibe-Trading/agent
Command: npx skills add https://github.com/Liangwei-zhang/six-stock --skill vibe-trading-liangwei-zhang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires vibe-trading-ai.

What problem does it solve?

Vibe-Trading consolidates finance research workflows into a single AI-assisted platform, enabling backtesting, factor analysis, options pricing, and multi-agent swarm experiments across multiple data sources.

Core Features & Use Cases

  • Backtesting across 6 engines and 5 data sources to compare strategies consistently.
  • Factor analysis, options pricing, and multi-agent swarm presets for collaborative research.
  • Use Case: a team iterates a trading idea, validates risk with a swarm, and exports actionable insights.

Quick Start

Install vibe-trading-ai and run a starter workflow to backtest a simple strategy and view the results.

Frequently Asked Questions about vibe-trading

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

FAQPage Schema
How do I run backtests across multiple data sources using Python?▼

Backtesting across multiple data sources is executed by installing the vibe-trading-ai package in a Python 3.11+ environment. This orchestrates data loading and strategy testing across 5 data sources and 6 engines to compare performance consistently.

What is multi-agent swarm collaboration in quantitative finance research?▼

Multi-agent swarm collaboration in quantitative finance uses 29 presets for team-based analysis across research domains. It enables teams to iterate trading ideas, validate risk collaboratively, and generate actionable insights within a single AI-assisted environment.

Do I need Python 3.11 to run vibe-trading-ai backtesting workflows?▼

Yes, Python 3.11+ is required to run vibe-trading-ai backtesting workflows. This environment is necessary to execute backtests, run swarm teams, and generate reports for end-to-end quantitative finance research.

Can I perform options pricing and factor analysis in a single environment?▼

Yes, factor analysis and options pricing can be performed in a single environment. The platform consolidates finance research workflows, supporting multi-agent swarm experiments and backtesting across multiple data sources simultaneously.

What's the best way to validate trading risk with multi-agent swarms?▼

Validating trading risk with multi-agent swarms involves using the 29 swarm presets for team-based analysis. This allows teams to iterate trading ideas, validate risk collaboratively, and export actionable insights.

Related Skills

Explore More Data & Analytics Skills→
ajithkumar31082004-bitajithkumar31082004-bit

vibe-trading

Run backtesting, factor analysis, options pricing, and swarm workflows for HK/US equities, crypto, and derivatives.

Community
Advanced
0xZKnw0xZKnw

vibe-trading

Backtest quantitative strategies across global equities, crypto, and futures markets.

Community
Advanced
ebrahim-saniebrahim-sani

vibe-trading

Orchestrate automated backtesting and multi-agent swarm research across multiple data sources.

Community
Advanced
alexhegitalexhegit
4

quant-strategy

Write and backtest Python quantitative trading strategies with factor analysis.

Community
Intermediate