ai_quant_trade

券商研报分析助手，聚焦"研报获取→结构化提取→多机构观点对比→风险识别→决策辅助"。使用时机：汇总个股券商研报、追踪行业研报、对比多机构观点、识别卖方利益冲突、验证研报时效性。默认数据源为东方财富研报中心公开接口（无需 API Key）。

yfinance global market data interface — retrieve OHLCV, financials, insider transactions, and institutional holdings for US stocks, HK stocks, ETFs, and indices via Yahoo Finance. Free, no API key required.

Read web pages, articles, and document links by converting URLs into Markdown text. Use the `read_url` tool directly, without bash.

tushare是一个财经数据接口包，拥有丰富的数据内容，如股票、基金、期货、数字货币等行情数据，公司财务、基金经理等基本面数据。该模块通过标准化API方式统一了数据资产的对外服务方式，以帮助有需要的技术用户更实时、简洁、轻量的使用相关数据。

Create, modify, and optimize quantitative trading strategies, then backtest and evaluate them.

Perpetual futures funding rate analysis and cash-carry basis trading — funding rate regimes, annualized basis signals, carry trade construction, and funding rate arbitrage between exchanges.

OKX cryptocurrency market data interface. Uses the OKX V5 REST API to retrieve spot, derivatives, index, and other crypto market data, including real-time prices, candlesticks, funding rates, open interest, and more. No authentication required, free to use.

Multi-factor cross-sectional stock ranking. Combines factor standardization, equal-weight or IC-weighted scoring, and TopN portfolio construction. Suitable for multi-instrument portfolio strategies.

Harmonic Patterns signal engine. Identifies XABCD five-point structures such as Gartley/Bat/Butterfly/Crab based on Fibonacci geometry, and generates trading signals in the PRZ (Potential Reversal Zone).

Fundamental factor screening — filter stocks by PE/PB/ROE and other financial metrics for value or growth selection. Supports A-shares (via tushare extra_fields) and HK/US stocks (via yfinance Ticker info).

Factor research framework with IC/IR analysis, quantile backtesting, and factor combination. Suitable for cross-sectional factor evaluation across multiple instruments.

Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the `read_document` tool.

Data source selection decision tree. Load this skill BEFORE any backtest or data-fetching task to choose the best available data source.

Correlation and cointegration analysis — co-movement discovery, deep return-correlation analysis, sector clustering, realized correlation, Engle-Granger / Johansen cointegration, half-life, Kalman dynamic hedge ratio, cross-market linkage analysis, and pair-trading signal generation

Asset allocation theory and optimizer usage — MPT / Black-Litterman / risk budgeting / all-weather strategy, including guides for 4 optimizers and rebalancing rules.