Orchestrate multi-agent finance research workflows with backtesting across equities, ETFs, and crypto markets.
npx skills add https://github.com/GGwujun/SigmX --skill vibe-trading-ggwujun
Please help me install this Agent Skill. Skill: vibe-trading Source: https://github.com/GGwujun/SigmX/tree/main/agent Command: npx skills add https://github.com/GGwujun/SigmX --skill vibe-trading-ggwujun
This Skill coordinates AI-powered finance research workflows using multi-agent teams and backtesting across multiple data sources.
Install vibe-trading-ai, start the API, and then load a skill with load_skill to begin exploring
High-intent search queries and answers about installing and using this skill.
You can backtest alpha factors using the Alpha Zoo, which provides 452 pre-built alphas across qlib158, alpha101, gtja191, and academic frameworks. It supports equities, ETFs, and crypto markets via 7 backtesting engines.
Multi-agent finance research workflows support 7 data sources: tushare, yfinance, okx, akshare, mootdx, ccxt, and futu. The Shadow Account extracts data from these sources to run backtests and render performance reports.
Yes, Python 3.11 or higher is required. You also need to install the vibe-trading-ai package and start its API before loading finance skills and deploying the 29 multi-agent swarm teams for collaborative research.
Yes, AI multi-agent teams orchestrate end-to-end strategy research from ideation to backtested performance. You can assign strategies to 29 swarm teams, apply 77 finance skills, and review the resulting benchmark comparison reports.
The built-in Trade Journal analyzer evaluates trading records across equities, ETFs, and crypto markets. It integrates with the Shadow Account to extract data, run backtests, and render comprehensive analytics reports.
Using 7 backtesting engines allows you to cross-validate strategy performance across different methodologies. The benchmark comparison panel aggregates results from qlib158, alpha101, gtja191, and academic alphas to ensure robustness.
644408071-designAutomate quantitative trading strategy development and backtesting with Python.
wudyeConvert trade journals into if-then shadow rules and backtest them across markets.
644408071-designBacktest trading strategies across markets using Python and multi-agent swarm teams.
20YN04Backtests quantitative strategies across multiple engines and market-data sources with built-in alpha factors.
