# Minute Analysis

Minute-level data analysis and backtesting.

- Repository: https://github.com/HKUDS/Vibe-Trading (37375 stars)
- Category: Data and ML
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add HKUDS/Vibe-Trading --skill minute-analysis -g -a claude-code -y`
Codex: `npx skills add HKUDS/Vibe-Trading --skill minute-analysis -g -a codex -y`
Cursor: `npx skills add HKUDS/Vibe-Trading --skill minute-analysis -g -a cursor -y`
Gemini CLI: `npx skills add HKUDS/Vibe-Trading --skill minute-analysis -g -a gemini-cli -y`

## Description

Minute-level data analysis and backtesting. Retrieves minute candlesticks through OKX/Tushare/yfinance and can be used both for analysis and as input to the backtest engine.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Minute-Level Data Analysis and Backtesting

## Purpose

Retrieve minute-level candlestick data through data-source APIs and calculate intraday indicators (VWAP, TWAP, volume distribution, and more).
Supports minute-level backtesting: set `"interval": "5m"` in `config.json` and use the `backtest` tool to run intraday strategies.

## Backtest Configuration

For minute-level backtests, simply add the `interval` field in `config.json`:

```json
{
  "source": "okx",
  "codes": ["BTC-USDT"],
  "start_date": "2026-03-01",
  "end_date": "2026-03-15",
  "interval": "5m",
  "initial_cash": 1000000,
  "commission": 0.0005
}
```

- The annualization factor is inferred automatically from `source + interval` (`OKX 5m = 365 x 288 = 105120`)
- Minute-level datasets are large. Recommended time limits: no more than 7 days for `1m`, no more than 30 days for `5m`, and no more than 1 year for `1H`

## Supported Data Sources and Intervals

| Data Source | Supported Intervals | Notes |
|--------|---------|------|
| OKX | 1m/5m/15m/30m/1H/4H | Cryptocurrency, trades 7x24 |
| Tushare | 1m/5m/15m/30m/1H | China A-shares, requires score >= 2000 |
| yfinance | 1m/5m/15m/30m/1H | Hong Kong / US equities (free, no key required) |

## OKX Minute Candlestick API

```python
import requests
import pandas as pd

resp = requests.get("https://www.okx.com/api/v5/market/candles", params={
    "instId": "BTC-USDT",
    "bar": "1m",       # 1m/5m/15m/30m/1H/4H
    "limit": "300",    # At most 300 rows per request
})
data = resp.json()["data"]
columns = ["ts", "open", "high", "low", "close", "vol", "volCcy", "volCcyQuote", "confirm"]
df = pd.DataFrame(reversed(data), columns=columns)
df["ts"] = pd.to_datetime(df["ts"].astype("int64"), unit="ms")
for col in ["open", "high", "low", "close", "vol"]:
    df[col] = df[col].astype(float)
```

## Indicator Calculation Templates

### VWAP (Volume-Weighted Average Price)

The rest: https://github.com/HKUDS/Vibe-Trading/blob/HEAD/agent/src/skills/minute-analysis/SKILL.md