菜单
Core technical indicator collection (trend EMA/ADX + mean-reversion BB/RSI + volume-price OBV/volume ratio), generates a composite signal via three-dimensional voting. Pure pandas implementation for any OHLCV data.
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。
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).
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.
Paid capability marketplace for global multi-asset data; use it when free Vibe-Trading sources lack coverage, depth, or provider quality, and keep free sources as the default for routine OHLCV.
Correlation-regime detection and crisis attribution — edge-density regime states with hysteresis, causal (no look-ahead) smoothing, regime-aware exposure context, first-mover crisis attribution with honest NAME / MACRO / AMBIGUOUS / ABSTAIN verdicts, and a correlation-rewiring leaderboard that catches slow bleed-outs
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.
Strategy Development Manager: convert academic papers and research reports into validated factors and strategies with automated backtesting, persistent storage, and decay monitoring.
| name | technical-basic |
| description | Core technical indicator collection (trend EMA/ADX + mean-reversion BB/RSI + volume-price OBV/volume ratio), generates a composite signal via three-dimensional voting. Pure pandas implementation for any OHLCV data. |
| category | strategy |
Combines three classic Western technical analysis approaches into one composite signal engine:
| Dimension | Indicators | Purpose |
|---|---|---|
| Trend | EMA(12/26) + ADX(14) | Determine direction and trend strength |
| Mean reversion | Bollinger Bands(20,2) + RSI(14) | Detect overbought and oversold conditions |
| Volume-price | OBV + volume ratio | Confirm volume participation |
Three-dimensional voting mechanism:
ewm(alpha=1/period)), not a rolling mean(volume * sign(close.diff())).cumsum()All parameters have default values and can be overridden at instantiation time:
| Parameter | Default | Description |
|---|---|---|
| ema_fast | 12 | Fast EMA period |
| ema_slow | 26 | Slow EMA period |
| adx_period | 14 | ADX calculation period |
| adx_threshold | 25.0 | ADX trend-strength threshold |
| bb_window | 20 | Bollinger Band window |
| bb_std | 2.0 | Bollinger Band standard deviation multiplier |
| rsi_period | 14 | RSI period |
| rsi_oversold | 30 | RSI oversold threshold |
| rsi_overbought | 70 | RSI overbought threshold |
| vol_ma_period | 20 | Volume moving-average period |
| obv_ma_period | 20 | OBV moving-average period |
pip install pandas numpy requests
1 = long, -1 = short, 0 = stand aside