Rqalpha logo

Rqalpha

Organization
lzwme
rqalpha

RQAlpha 米筐开源事件驱动回测框架。支持A股和期货,模块化架构,可自由扩展;当用户需要快速回测A股/期货策略、使用内置数据(download-bundle)、开发Mod插件,或提及 rqalpha、米筐时使用。与 backtrader 相比,rqalpha 内置A股日线数据、安装更简便,适合快速验证;backtrader 更灵活、社区更大。若用户仅需数据获取而无回测需求,引导使用 baostock/akshare/tushare 等数据 Skill。

Overview

Publisherlzwme
Repositoryfinance-quant-skills
Skill namerqalpha
Stars
461
Forks
85
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by lzwme on GitHub. Read the source before you install it.

Installation

Install the Rqalpha AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/lzwme/finance-quant-skills/tree/main/skills/rqalpha
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/lzwme/finance-quant-skills.git /tmp/finance-quant-skills
mkdir -p .claude/skills
cp -r /tmp/finance-quant-skills/skills/rqalpha .claude/skills/rqalpha
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Rqalpha in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Rqalpha on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Rqalpha is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

RQAlpha(米筐开源回测框架)

RQAlpha 是 米筐科技 开发的开源事件驱动回测框架。提供A股和期货市场的策略开发、回测和模拟交易完整解决方案。高度模块化,支持插件(Mod)系统扩展。

文档:https://rqalpha.readthedocs.io

安装

bash
pip install rqalpha

# 下载内置数据包(A股日线数据)
rqalpha download-bundle

# 验证安装
python -c "import rqalpha; print(rqalpha.__version__)"

策略结构

python
from rqalpha.api import *  # 导入所有 API 函数(含 logger)

def init(context):
    """策略启动时调用一次 — 设置订阅和参数"""
    context.stock = '000001.XSHE'
    context.fired = False

def handle_bar(context, bar_dict):
    """每根K线调用 — 主要交易逻辑"""
    if not context.fired:
        order_shares(context.stock, 1000)
        context.fired = True
        logger.info('买入完成')  # logger 通过 from rqalpha.api import * 自动可用

def before_trading(context):
    """每个交易日开盘前调用"""
    pass

def after_trading(context):
    """每个交易日收盘后调用"""
    pass

注意:from rqalpha.api import * 会自动导入 logger,可直接使用 logger.info()、logger.warn()、logger.error() 输出日志。

运行回测

命令行

bash
rqalpha run \
    -f strategy.py \
    -s 2024-01-01 \
    -e 2024-06-30 \
    --account stock 100000 \
    --benchmark 000300.XSHG \
    --plot

Python API

python
from rqalpha.api import *
from rqalpha import run_func

config = {
    "base": {
        "start_date": "2024-01-01",
        "end_date": "2024-06-30",
        "accounts": {"stock": 100000},
        "benchmark": "000300.XSHG",
        "frequency": "1d",
    },
    "extra": {
        "log_level": "warning",
    },
    "mod": {
        "sys_analyser": {"enabled": True, "plot": True},
    },
}

result = run_func(init=init, handle_bar=handle_bar, config=config)
print(result)

代码格式

市场后缀示例
上海A股.XSHG600000.XSHG(浦发银行)
深圳A股.XSHE000001.XSHE(平安银行)
指数.XSHG/.XSHE000300.XSHG(沪深300)
期货.XSGE/.XDCE/.XZCE/.CCFXIF2401.CCFX(沪深300期货)

下单函数

股票下单

python
# 按股数买卖
order_shares('000001.XSHE', 1000)       # 买入1000股
order_shares('000001.XSHE', -500)       # 卖出500股

# 按手买入(1手=100股)
order_lots('000001.XSHE', 10)           # 买入10手(1000股)

# 按金额买入
order_value('000001.XSHE', 50000)       # 买入5万元

# 按组合比例买入
order_percent('000001.XSHE', 0.5)       # 买入组合值50%的仓位

# 目标仓位
order_target_value('000001.XSHE', 100000)   # 调整到10万元
order_target_percent('000001.XSHE', 0.3)    # 调整到组合的30%

# 撤单
cancel_order(order_id)

期货下单

python
# 开仓
buy_open('IF2401.CCFX', 1)              # 买入开多1手
sell_open('IF2401.CCFX', 1)             # 卖出开空1手

# 平仓
sell_close('IF2401.CCFX', 1)            # 卖出平多1手
buy_close('IF2401.CCFX', 1)             # 买入平空1手

数据查询函数

python
def handle_bar(context, bar_dict):
    # 当前K线数据
    bar = bar_dict['000001.XSHE']
    price = bar.close
    volume = bar.volume
    dt = bar.datetime

    # 历史数据(返回DataFrame)
    prices = history_bars('000001.XSHE', bar_count=20, frequency='1d',
                          fields=['close', 'volume', 'open', 'high', 'low'])

    # 检查股票是否可交易
    tradable = is_valid_price(bar.close)

    # 检查是否停牌
    suspended = is_suspended('000001.XSHE')

投资组合与持仓

python
def handle_bar(context, bar_dict):
    # 组合信息
    cash = context.portfolio.cash                    # 可用资金
    total = context.portfolio.total_value            # 总资产
    market_value = context.portfolio.market_value    # 持仓市值
    pnl = context.portfolio.pnl                      # 总盈亏
    returns = context.portfolio.daily_returns        # 日收益率

    # 持仓信息
    positions = context.portfolio.positions
    for stock, pos in positions.items():
        print(f'{stock}: quantity={pos.quantity}, '
              f'sellable={pos.sellable}, '
              f'avg_price={pos.avg_price:.2f}, '
              f'market_value={pos.market_value:.2f}, '
              f'pnl={pos.pnl:.2f}')

定时调度

python
from rqalpha.api import *

def init(context):
    # 每个交易日指定时间运行函数
    scheduler.run_daily(rebalance, time_rule=market_open(minute=5))
    # 每周运行(每周一)
    scheduler.run_weekly(weekly_task, tradingday=1, time_rule=market_open(minute=5))
    # 每月运行(首个交易日)
    scheduler.run_monthly(monthly_task, tradingday=1, time_rule=market_open(minute=5))

def rebalance(context, bar_dict):
    pass

Mod系统(插件)

RQAlpha的模块化架构允许通过Mod扩展功能:

python
config = {
    "mod": {
        "sys_analyser": {
            "enabled": True,
            "plot": True,
            "benchmark": "000300.XSHG",
        },
        "sys_simulation": {
            "enabled": True,
            "matching_type": "current_bar",    # 撮合方式:current_bar(当前Bar)或 next_bar(下一Bar)
            "slippage": 0.01,                  # 滑点(元)
        },
        "sys_transaction_cost": {
            "enabled": True,
            "commission_rate": 0.0003,         # 手续费率
            "tax_rate": 0.001,                 # 印花税(仅卖出)
            "min_commission": 5,               # 最低手续费
        },
    },
}

可用内置Mod

Mod说明
sys_analyser绩效分析和图表绘制
sys_simulation撮合模拟
sys_transaction_cost手续费和税费计算
sys_accounts账户管理
sys_benchmark基准追踪
sys_progress进度条显示
sys_risk风险管理检查

进阶示例

更多完整策略示例(双均线、多股等权、RSI均值回归、止损止盈、期货CTA)见 references/advanced-strategies.md。

绩效分析输出

运行回测后,sys_analyser Mod会输出以下指标:

指标说明
total_returns总收益率
annualized_returns年化收益率
benchmark_total_returns基准总收益率
alphaAlpha值
betaBeta值
sharpe夏普比率
sortinoSortino比率
max_drawdown最大回撤
tracking_error跟踪误差
information_ratio信息比率
volatility波动率

常见错误处理

错误原因解决方法
Bundle not found未下载数据包运行 rqalpha download-bundle
Insufficient cash可用资金不足检查 context.portfolio.cash
Order Creation Failed: suspended股票停牌用 is_suspended() 提前检查
No data for instrument股票代码错误检查代码格式(如 .XSHG / .XSHE)
logger 未定义未导入 API确保 from rqalpha.api import * 在文件顶部

使用技巧

  • RQAlpha 是纯本地框架,无云端依赖,适合离线研究。
  • 使用 rqalpha download-bundle 获取免费内置A股日线数据。
  • Mod 系统允许插入自定义数据源、券商接口和风控模块。
  • 实盘交易可通过 rqalpha-mod-vnpy 连接 vn.py 的券商网关。
  • 支持日线和分钟级回测。
  • 文档:https://rqalpha.readthedocs.io/

资源索引

  • references/advanced-strategies.md — 完整策略示例(双均线、多股等权、RSI均值回归、止损止盈、期货CTA)。需要参考进阶策略实现时读取。

规则

  • 使用此 Skill 前,确认用户明确需要 rqalpha 框架进行策略回测。若用户仅需数据获取,引导使用 baostock/pywencai 等数据 Skill。
  • 策略文件顶部必须包含 from rqalpha.api import *,以确保所有下单函数和 logger 可用。
  • 期货策略必须使用 buy_open/sell_open/buy_close/sell_close,不能使用股票的 order_shares 等函数。
  • 下单前应使用 is_suspended() 检查停牌状态,避免订单失败。
  • 股票代码必须带后缀(.XSHG/.XSHE/.CCFX 等),不能使用纯数字代码。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Rqalpha AI skill do?

RQAlpha 米筐开源事件驱动回测框架。支持A股和期货,模块化架构,可自由扩展;当用户需要快速回测A股/期货策略、使用内置数据(download-bundle)、开发Mod插件,或提及 rqalpha、米筐时使用。与 backtrader 相比,rqalpha 内置A股日线数据、安装更简便,适合快速验证;backtrader 更灵活、社区更大。若用户仅需数据获取而无回测需求,引导使用 baostock/akshare/tushare 等数据 Skill。

Why use Rqalpha on TypingMind?

Because you install it once and use it with any model. Rqalpha is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Rqalpha in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lzwme/finance-quant-skills/tree/main/skills/rqalpha. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Rqalpha?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Rqalpha?

As many as you like. As long as a model supports skills, you can use Rqalpha with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Rqalpha AI skill free?

It is published on GitHub by lzwme. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇