qmt-strategy-autopilot

一句话需求自动生成并执行国金QMT策略(封闭式澄清 + 双源数据 + 实盘语义)

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "qmt-strategy-autopilot" with this command: npx skills add listolany/qmt-strategy-autopilot

国金QMT Strategy Autopilot

将自然语言需求转换为 StrategySpec,按依赖顺序调用国金QMT skills 执行策略。

功能

  • 一句话解析策略需求
  • 1-5 个封闭式澄清问题
  • 统一 StrategySpec 生成
  • 步骤幂等执行(request_id + step_state
  • 数据双源(xtdata 主源 + qgdata 补源)

命令

# 1) 生成策略计划(可能返回澄清问题)
python3 {baseDir}/scripts/qmt_autopilot.py plan "我持仓的股票里,60分钟5日线下穿10日线则卖出"

# 2) 提交澄清回答
python3 {baseDir}/scripts/qmt_autopilot.py clarify "我持仓的股票里,60分钟5日线下穿10日线则卖出" '{"confirm_mode":"收盘确认","price_mode":"买一价"}'

# 3) 执行StrategySpec
python3 {baseDir}/scripts/qmt_autopilot.py run '{"strategy_name":"demo","symbol_scope":"portfolio","symbols":[],"signal":{"period":"60m","type":"ma_cross","fast":5,"slow":10,"direction":"bearish"},"trigger":{"confirm_mode":"bar_close","cooldown_sec":0,"once_per_day":true},"execution":{"side":"SELL","qty_mode":"all","qty_ratio":1.0,"price_mode":"bid1","max_retries":1},"risk":{"max_order_count":20,"daily_loss_limit":0.05,"dup_signal_block":true},"runtime":{"interval_sec":3,"session":"trade_hours","broker_env":"sim"},"meta":{}}'

环境变量

  • BROKER_ENV=sim|live:柜台环境切换(策略语义不变)
  • QGDATA_TOKEN:启用历史分钟/资讯补源
  • CONNECTION_MANAGER_PATHREALTIME_DATA_PATHTRADING_EXECUTION_PATH:可选自定义路径

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

Vnpy Futures Trading

VeighNa(原vnpy)支持中国期货自动交易执行,集成日盘/夜盘交易时段管理,并提供CSI300成分股数据下载及Alpha101/LightGBM等因子研究工作流。。

Registry SourceRecently Updated
1660Profile unavailable
General

Nautilus Algo Trading

使用 NautilusTrader 配置驱动的 BacktestNode 运行高性能多市场回测,支持 Parquet 数据目录和外部 CSV 数据导入,策略可直接过渡到实盘交易。。

Registry SourceRecently Updated
1950Profile unavailable
General

Ml4t Book Notebooks

基于《Machine Learning for Trading》第二版配套 notebooks 实现量化交易策略开发与回测,涵盖多市场金融数据的时间序列机器学习分析。

Registry SourceRecently Updated
1730Profile unavailable
General

Finrl Rl Trading

Use ensemble deep reinforcement learning (A2C, DDPG, PPO, TD3, SAC) to execute automated multi-market stock trading with

Registry SourceRecently Updated
1780Profile unavailable