- name
SKILL.md
O arquivo da skill permanece no repositório do publicador.
Cole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add lzwme/finance-quant-skills --skill joinquant-strategy -a cursor -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add lzwme/finance-quant-skills --skill joinquant-strategy -a claude-code -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add lzwme/finance-quant-skills --skill joinquant-strategy -a codex -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add lzwme/finance-quant-skills --skill joinquant-strategy -a grok -yEnvie a mensagem copiada em um chat do Grok Bot. O Bot busca este SKILL.md no GitHub e o adiciona às skills que todos os seus Bots compartilham.
Install this skill: https://github.com/lzwme/finance-quant-skills/tree/HEAD/skills/joinquant-strategyDo publicador
基于本目录离线文档,为聚宽官网(回测 / 模拟 / 研究)编写 Python 策略。回答 API 问题时必须先查阅本地文档,不得凭记忆编造函数签名或参数。查不到时明确说「本地文档未覆盖」,附官网链接 https://www.joinquant.com/help/api/help,不要推测参数默认值。
与 jqdatasdk 的区别:
jqdata在官网策略环境使用;jqdatasdk是本地 Python 库,API 略有不同,且不能在官网回测/模拟/研究中使用。
get_price、order_target、市盈率)api.md,字段/表结构查 data/*.md,踩坑查 faq.mdapi.md 或 data/*.md 中找到出处from jqdata import *),可直接粘贴运行date=,确认未引入未来数据最小可运行结构:
# 导入聚宽函数库
import jqdata
def initialize(context):
g.security = '000001.XSHE'
set_benchmark('000300.XSHG')
set_option('use_real_price', True) # 开启动态复权(真实价格),建议开启
run_daily(trade, time='open') # 或 time='every_bar' / '9:30'
def trade(context):
security = g.security
close_data = attribute_history(security, 5, '1d', ['close'])
MA5 = close_data['close'].mean()
current_price = close_data['close'][-1]
cash = context.portfolio.available_cash
if current_price > 1.01 * MA5:
order_value(security, cash)
elif current_price < MA5 and context.portfolio.positions[security].closeable_amount > 0:
order_target(security, 0)
完整可运行骨架(配置集中、盘前选池、先卖后买、热更新入口)见 strategy_template.md;模拟盘热更新机制见 simulation.md。
jqdata 模块在研究与回测环境均可使用。
期货策略需将 run_daily 的 reference_security 设为对应主力合约(如 IF9999.CCFX),以匹配夜盘开盘时间。
get_price(security, start_date, end_date, frequency='daily', fields=None, fq='pre')
attribute_history(security, count, unit, fields) # 回测环境,不含当天
history(count, unit, field, security_list, df=True)
get_bars(security, count, unit, fields, include_now=True)
get_all_securities(types=['stock'], date=None) # date 防未来函数
get_index_stocks('000300.XSHG', date=None)
get_industry_stocks('C15', date=None)
get_concept_stocks('GN036', date=None)
set_universe([...]) # 设置后 history 可不传 security_list
from jqdata import *
q = query(valuation).filter(valuation.code == '000001.XSHE')
df = get_fundamentals(q, date='2015-10-15')
# 或 run_query(单次最多 4000 行,不可连表)
df = finance.run_query(query(finance.STK_XXX).filter(...).limit(4000))
order(security, amount) # 按股数,正买负卖
order_value(security, value) # 按金额
order_target(security, amount) # 调到目标股数
order_target_value(security, value) # 调到目标市值
order_target_percent(security, percent) # 调到目标仓位比例
A 股买入数量须为 100 整数倍(科创板 200 股起);卖光持仓时不受限。每日最多 10000 笔订单。
from jqlib.technical_analysis import *
# check_date 策略中建议用 context.current_dt,避免盘中取当日收盘指标产生未来数据
result = MACD(security_list, check_date=context.current_dt, SHORT=12, LONG=26, MID=9)
from jqfactor import Factor, calc_factors
class MyFactor(Factor):
name = 'my_factor'
max_window = 5
dependencies = ['close']
def calc(self, data):
return data['close'].mean()
factors = calc_factors(securities, [MyFactor()], start_date, end_date)
详见 factor.md 与 data/Alpha101.md、data/Alpha191.md。
get_all_securities(date=...)、get_index_stocks(..., date=...) 等必须传入历史时点的 date,不能用未来日期history / attribute_history 取天数据时不包含当天;要当天数据需取分钟级check_date 只精确到日期时返回收盘值,盘中调用当天会产生未来数据get_fundamentals 的 date 参数含义run_daily,避免与 handle_data 混用run_daily(func, time='every_bar') 频率与回测设置一致run_weekly/monthly 的 force=False 可避免晚注册时的就近执行模拟盘持有独立的代码副本、initialize 不会重跑,回测里正常的改动常在模拟盘失效。回答此类问题前先读 simulation.md:内含断点定位、apply_settings 迁移模板、诊断模板与误判清单。
run_query / get_fundamentals 单次最多返回 4000 行run_query 不支持连表查询fq=None 为不复权完整示例见 api.md 末尾「策略示例」:均线策略、多股票持仓、追涨策略、万圣节效应等。
api.md 章节索引、文档同步脚本用法:reference.md
api.md/faq.md/data/*.md由脚本从官网同步,切勿手改;reference.md、simulation.md、strategy_template.md手工维护。
聚宽(JoinQuant)官网策略开发指南,涵盖回测、模拟交易、数据 API、交易函数、因子与技术指标。当用户编写聚宽策略、回测、模拟盘,排查模拟盘改代码不生效/替换代码,查询聚宽 API、get_price/order/run_daily、Alpha 因子、技术指标,或提及 joinquant、聚宽、jqdata 策略时使用。本地数据获取请用 jqdatasdk 技能。
---name: joinquant-strategydescription: 聚宽(JoinQuant)官网策略开发指南,涵盖回测、模拟交易、数据 API、交易函数、因子与技术指标。当用户编写聚宽策略、回测、模拟盘,排查模拟盘改代码不生效/替换代码,查询聚宽…---# skills/joinquant-strategy/SKILL.mdPerguntas frequentes
Baixe skills/joinquant-strategy/SKILL.md do publicador ou copie o caminho e abra o repositório. O PlugMCP lista a skill e não hospeda o arquivo.
O publicador o mantém em https://github.com/lzwme/finance-quant-skills.
Claude, Cursor, Codex e Grok Build conseguem ler um SKILL.md que você adiciona a partir do repositório do publicador. O Grok Bot o instala quando você envia em um chat o link da pasta da skill no GitHub.