菜单
Data source selection — VN-only. All data comes from vnstock (fundamentals + OHLCV) and VietFin DNSE (OHLCV fallback).
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 — VN-only. All data comes from vnstock (fundamentals + OHLCV) and VietFin DNSE (OHLCV fallback). |
| Source | Markets | Auth Required | How |
|---|---|---|---|
| vnstock | VN equities, indices, ETFs, futures | Optional (VN_STOCK_KEY in .env) | Tool: vn_stock_analyze, vn_factor_data, alpha_bench(universe="vn-index") |
| VietFin DNSE | VN OHLCV | No | Backend fallback for OHLCV (used automatically by loaders) |
| DNSE REST API | VN equities intraday | DNSE_API_KEY + DNSE_API_SECRET | Direct REST call — independent of WebSocket; supports 1m/5m/15m/30m/1H/1D |
| Use Case | Tool | Example |
|---|---|---|
| Single stock analysis | vn_stock_analyze(symbol="VCB", days=365) | Price + profile + ratios + financials |
| Multi-stock factor data | vn_factor_data(universe="vn-index", factor="pe", period="2024-2025") | Factor CSV + return CSV → factor_analysis |
| VN factor benchmark | python run_ic_test.py | Bench 31 VN-core factors on HOSE → IC/IR report |
| Backtest | backtest(run_dir=...) with config.json source: "vietfin" or "auto" | Backtest signal engine on VN stocks |
| Market index | vn_index(symbol="VNINDEX", days=365) | Index OHLCV |
| Mutual funds | vn_fund_search() + vn_fund_history() | Fund NAV data |
| Intraday OHLCV | GET /api/stock/intraday/{symbol}?resolution=5&start=...&end=... | Direct REST: DNSE REST API, resolutions: 1, 5, 15, 30, 1H, 1D |
| Minute analysis | vn_intraday_analysis(symbol="VIC", resolution="5m", days=5) | Intraday VWAP/TWAP/volume profile via DNSE REST |
For backtest config.json:
"source": "vietfin" — VietFin data (vnstock fundamentals fallback)"source": "dnse" — DNSE broker data (supports intraday intervals: "interval": "5m")"source": "auto" — automatic routing (recommended)For minute-level backtests, use "interval" in config.json:
{
"source": "dnse",
"codes": ["VIC"],
"start_date": "2026-05-25",
"end_date": "2026-06-02",
"interval": "5m",
"initial_cash": 100000000,
"commission": 0.00025
}
Do NOT use tushare, akshare, or okx — they are not available.
Candlestick pattern recognition engine, pure pandas vectorized implementation of 15 classic candlestick patterns (5 single-candle + 5 double-candle + 4 triple-candle + 1 trend confirmation), generating a composite signal from bullish/bearish pattern scores.
基于缠论（缠中说禅）的形态识别引擎，使用czsc库自动检测K线分型、笔、中枢，并生成一买/一卖/二买/二卖/三买/三卖等买卖点信号。支持多周期分析和形态分类（3/5/7/9/11笔形态）。
A股可转债分析——转股/纯债/期权三维估值、下修/强赎/回售博弈、双低策略与转债轮动选债框架
公司事件驱动分析：并购套利价差计算、大股东增减持信号、股权激励解读、定增配股影响评估、A股ST/退市预警
Elliott Wave Theory signal engine. Detects swing points through Zigzag, matches 5-wave impulse and 3-wave corrective structures, validates them with Fibonacci wave relationships, and generates trend-top / correction-complete signals. Pure in-house pandas implementation.
ETF分析：产品筛选、费率对比、跟踪误差、流动性评估、策略应用与中国市场ETF量化配置框架。