Skip to main content
ClaudeWave
Skill12k estrellas del repoactualizado today

ccxt

CCXT is a unified Python library for accessing public market data from 100+ cryptocurrency exchanges without authentication. Use it to fetch OHLCV candles, tickers, order books, and trade history across Binance, Bybit, OKX, Coinbase, Kraken, and other exchanges with a consistent interface. The project includes a built-in CCXT DataLoader that automatically handles pagination and serves as a fallback when primary data sources are unavailable.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/HKUDS/Vibe-Trading /tmp/ccxt && cp -r /tmp/ccxt/agent/src/skills/ccxt ~/.claude/skills/ccxt
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

## Overview

CCXT is a unified cryptocurrency exchange trading library supporting 100+ exchanges including Binance, Bybit, OKX, Coinbase, Kraken, and more. Public market data (OHLCV, tickers, order books) requires no API key.

- GitHub: https://github.com/ccxt/ccxt (35k+ stars)
- Install: `pip install ccxt`

## Quick Start

```python
import ccxt

exchange = ccxt.binance({"enableRateLimit": True})

# Fetch daily OHLCV
ohlcv = exchange.fetch_ohlcv("BTC/USDT", "1d", limit=100)
# Returns: [[timestamp, open, high, low, close, volume], ...]

# Fetch ticker
ticker = exchange.fetch_ticker("ETH/USDT")
print(f"ETH price: {ticker['last']}")
```

## Key Methods

| Method | Description | Returns |
|--------|-------------|---------|
| `fetch_ohlcv(symbol, timeframe, since, limit)` | Historical candles | `[[ts, o, h, l, c, v], ...]` |
| `fetch_ticker(symbol)` | Latest quote | `{last, bid, ask, volume, ...}` |
| `fetch_tickers(symbols)` | Batch quotes | `{symbol: ticker}` |
| `fetch_order_book(symbol, limit)` | Order book | `{bids, asks, timestamp}` |
| `fetch_trades(symbol, since, limit)` | Recent trades | `[{price, amount, side, timestamp}, ...]` |

## Timeframes

`1m`, `3m`, `5m`, `15m`, `30m`, `1h`, `2h`, `4h`, `6h`, `12h`, `1d`, `1w`, `1M`

Note: not all exchanges support all timeframes. Use `exchange.timeframes` to check.

## Symbol Format

CCXT uses slash format: `BTC/USDT`, `ETH/BTC`, `SOL/USDT`

The project's DataLoader automatically converts `BTC-USDT` (hyphen) to `BTC/USDT` (slash).

## Exchange Selection

Set via environment variable: `CCXT_EXCHANGE=binance` (default)

Popular exchanges: `binance`, `bybit`, `okx`, `coinbase`, `kraken`, `bitget`, `gate`

## Built-in Loader

The project has a built-in CCXT DataLoader at `backtest/loaders/ccxt_loader.py`. It serves as a fallback when the OKX loader is unavailable.

## Pagination

For long history, CCXT paginates via the `since` parameter (millisecond timestamp). The built-in loader handles this automatically (up to 200 pages).
vibe-tradingSkill

Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, Alpha Zoo (452 pre-built alphas across qlib158/alpha101/gtja191/academic), options pricing, 77 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest → render) across 7 data sources (tushare, yfinance, okx, akshare, mootdx, ccxt, futu).

adr-hshareSkill

ADR/H-share/A-share cross-listing premium analysis — track pricing gaps between US-listed ADRs, HK-listed H-shares, and A-shares for arbitrage signals, dual-listing valuation, and delisting risk assessment.

akshareSkill

AKShare financial data aggregator (18k+ stars). Free, no API key. Covers A-shares, US, HK, futures, macro, forex. Primary fallback for tushare and yfinance.

alpha-zooSkill

Browse and bench the bundled alpha zoos — prebuilt cross-sectional factor libraries (Kakushadze 101, GTJA 191, Qlib 158, Fama-French / Carhart). Use when the user asks "which alphas exist", wants metadata on a named alpha, or wants to run IC/IR on a whole zoo over a universe.

ashare-pre-st-filterSkill

A 股 ST/*ST 风险预测框架 — 基于最新中报/三季报或业绩预告/快报,预测下一财年是否会因营收、利润、净资产、分红不达标而被风险警示,并将新浪监管处罚记录作为独立证据面纳入风险等级。仅适用于 A 股,不预测财务造假。

asset-allocationSkill

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

backtest-diagnoseSkill

Diagnose failed or underperforming backtests, locate the root cause, and fix the issue

behavioral-financeSkill

Behavioral finance applications: theories of overreaction and underreaction, behavioral explanations for momentum and reversal, investor sentiment cycles, cognitive-bias checklists, and debiasing quantitative strategies.