vibe-trading
Vibe-Trading equips your agent with backtesting across equities, crypto, futures, and forex using 8 specialized engines and 23 market-data sources. Extract trading rules from your journal, backtest them against historical data, and deploy 30 pre-built multi-agent teams for research workflows. The Alpha Zoo bundles 462 quantitative factors ready to benchmark.
Vibe-Trading backtests quantitative strategies across 8 engines and 23 market-data sources with 462 pre-built alphas.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-27
Vibe-Trading backtests quantitative strategies across 8 engines and 23 market-data sources with 462 pre-built alphas. Vibe-Trading equips your agent with backtesting across equities, crypto, futures, and forex using 8 specialized engines and 23 market-data sources. Extract trading rules from your journal, backtest them against historical data, and deploy 30 pre-built multi-agent teams for research workflows. The Alpha Zoo bundles 462 quantitative factors ready to benchmark.
Use it when
- Vibe-Trading's trade journal analyzer extracts trading rules from your journal entries and measures performance deltas to identify what.
- Vibe-Trading's Alpha Zoo bundles 462 pre-built quantitative factors ready for immediate use.
Verify before relying
Read SKILL.md below before installing (60 files). Open directory: indexed for reading, not audited.
Similar skills
Install
HKUDS/Vibe-Trading/agent · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What backtesting platform with multiple engines does Vibe-Trading offer?
Vibe-Trading provides a backtesting platform equipped with 8 specialized engines that support equities, crypto, futures, and forex across multiple markets and asset classes. The platform integrates 23 market-data sources to ensure comprehensive historical data coverage for strategy validation.
How does Vibe-Trading analyze personal trade journals?
Vibe-Trading's trade journal analyzer extracts trading rules from your journal entries and measures performance deltas to identify what works. The system profiles your trading behavior and automatically generates testable rules that you can backtest against historical data to validate their effectiveness.
What alpha factors are available in Vibe-Trading's factor library?
Vibe-Trading's Alpha Zoo bundles 462 pre-built quantitative factors ready for immediate use. These factors support comprehensive factor analysis with IC/IR metrics, allowing you to benchmark alpha generation across different market conditions and asset classes.
Can Vibe-Trading run multi-agent AI teams for investment research?
Yes, Vibe-Trading deploys 30 pre-built multi-agent teams designed for collaborative investment research and decision-making workflows. These AI-powered agent swarms automate complex research tasks and enable coordinated analysis across multiple data sources and strategies.
Does Vibe-Trading support options pricing and global market data?
Vibe-Trading fetches market data from 23 sources covering crypto, stocks, and other assets globally. The platform includes options pricing capabilities and supports analysis across China A-shares, HK, US, and crypto markets with integrated Black-Scholes calculations.
What is Vibe-Trading's license and deployment model?
Vibe-Trading is released under the MIT license, making it freely available for commercial and personal use. It functions as a professional quantitative research platform and MCP server agent, enabling seamless integration into your existing trading infrastructure.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
name: vibe-trading version: 0.1.12 description: Professional finance research toolkit — backtesting (8 engines + benchmark comparison panel), factor analysis, Alpha Zoo (462 pre-built alphas across qlib158/alpha101/gtja191/academic/fundamental), options pricing, 88 finance skills, 30 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest → render) across 23 market-data sources (tushare, yfinance, okx, binance, akshare, baostock, tencent, mootdx, ccxt, futu, mt5, local, eastmoney, sina, stooq, yahoo, india_broker, qveris, longbridge, plus optional-key finnhub/alphavantage/tiingo/fmp). dependencies: python: ">=3.11" pip: - vibe-trading-ai env: - name: TUSHARE_TOKEN description: "Tushare API token for China A-share data (optional — HK/US/crypto work without any key)" required: false - name: OPENAI_API_KEY description: "OpenAI-compatible API key — only needed for run_swarm (multi-agent teams). All other tools work without it." required: false - name: LANGCHAIN_MODEL_NAME description: "LLM model name for run_swarm (e.g. deepseek/deepseek-v4-pro). Only needed if using run_swarm." required: false mcp: command:
(truncated - see the full file via the links below)
File tree — 15 files
agent/.editorconfig
agent/.env.example
agent/.gitignore
agent/SKILL.md
agent/api_server.py
agent/backtest/__init__.py
agent/backtest/benchmark.py
agent/backtest/constraints.py
agent/backtest/correlation.py
agent/backtest/metrics.py
agent/backtest/models.py
agent/backtest/perpetual_risk.py
agent/backtest/rebalance_notes.py
agent/backtest/regime.py
agent/backtest/risk_xray.py
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Backtest quantitative trading strategies across multiple markets and asset classes”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Multi-factor ranks stocks by computing and standardizing multiple factors—momentum, reversal, volatility, and volume—then combines them into a composite score to select top performers for equal-weight portfolios. Built-in support for value metrics like PE and ROE on supported markets. The newer ZooSignalEngine integrates 450+ pre-built alphas from the registry for flexible long-only, short-only, or long-short strategies.
Factor Research systematically validates whether factors predict future returns using information coefficient and information ratio metrics, plus quantile-based backtests across instrument groups. Apply it to momentum, value, quality, volatility, or custom factors—then combine validated signals with equal or IC-weighted averaging.
strategy-generate lets you design trading strategies by defining entry/exit logic, then automatically backtests them across stocks, crypto, and other instruments. Write your signal engine in Python, configure your parameters, and the skill handles data loading and performance analysis—no boilerplate required.
Your unified trading partner across options, stocks, crypto, commodities, and forex. Combines five technical methodologies with regime detection, 25+ options strategies, Greeks analysis, and sentiment signals to generate high-conviction trade ideas with educational reasoning behind every signal.
options-strategy lets you backtest complex option portfolios—from covered calls and protective puts to iron condors and butterflies—by synthesizing theoretical prices via Black-Scholes and tracking Greeks exposure across time. The engine accepts daily underlying data, applies historical volatility, and outputs trade-by-trade records, daily Greeks aggregates, and performance metrics for strategy validation.
Test trading strategies against historical data with built-in performance metrics including Sharpe, Sortino, and max drawdown calculations. Includes 8 pre-built strategies and parameter optimization via grid search to find the best-performing configurations.
More skills tradingview-mcp (MIT) · Stock 美股基础数据 (unlicensed)