菜单
Data source selection decision tree. Load this skill BEFORE any backtest or data-fetching task to choose the best available data source.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | data-routing |
| category | data-source |
| description | Data source selection decision tree. Load this skill BEFORE any backtest or data-fetching task to choose the best available data source. |
| Source | Markets | Auth Required | Network | Skill |
|---|---|---|---|---|
| tushare | A-shares, funds, futures, macro | Yes (TUSHARE_TOKEN) | China network | tushare |
| akshare | A-shares, US, HK, futures, macro, forex | No | Unrestricted | akshare |
| yfinance | US stocks, HK stocks, ETFs | No | Needs Yahoo Finance access | yfinance |
| okx | Crypto (OKX exchange) | No | Needs okx.com access | okx-market |
| ccxt | Crypto (100+ exchanges) | No | Needs exchange access | ccxt |
Use source: "auto" — the runner automatically routes by symbol pattern and falls back to alternative sources if the primary one is unavailable.
You do NOT need to specify a concrete data source in config.json unless the user explicitly asks for one.
A-shares: tushare (if TUSHARE_TOKEN is set) > akshare (free fallback) US stocks: yfinance > akshare HK stocks: yfinance > akshare Crypto: okx (single exchange) > ccxt (multi-exchange) Futures: tushare > akshare Macro / economics: akshare > tushare Forex: akshare > yfinance
load_skill("akshare")TUSHARE_TOKEN environment variable exists| Market | Format | Examples |
|---|---|---|
| A-shares | NNNNNN.SZ/SH/BJ | 000001.SZ, 600000.SH |
| US stocks | TICKER.US | AAPL.US, MSFT.US |
| HK stocks | NNN(N).HK | 700.HK, 9988.HK |
| Crypto | SYMBOL-USDT | BTC-USDT, ETH-USDT |
| Futures | XXNNNN.EXCHANGE | CU2406.SHFE |
| Forex | XXX/YYY | USD/CNY, EUR/USD |
The backtest runner implements automatic fallback at the market level:
User requests 000001.SZ (A-share)
-> detect market: a_share
-> try tushare: TUSHARE_TOKEN missing -> skip
-> try akshare: available -> use akshare
-> success (zero config required)
This is transparent to the user — they just see results.
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）。
Asset allocation theory and optimizer usage — MPT / Black-Litterman / risk budgeting / all-weather strategy, including guides for 4 optimizers and rebalancing rules.
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
Event-driven strategy based on sentiment-scored signals from news, announcements, and macro events. The LLM acts as the NLP engine, and event data follows a CSV schema.
Factor research framework with IC/IR analysis, quantile backtesting, and factor combination. Suitable for cross-sectional factor evaluation across multiple instruments.
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).