← 返回 Skills 市场

LongPort Quant Trader (房总版)

Name: LongPort Quant Trader (房总版)
Author: fxm1618-gmail

作者 fxm1618-gmail · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

106

总下载

当前安装

版本数

在 OpenClaw 中安装

/install fxm1618-longport-quant-trader

功能描述

长桥证券量化交易集成 - 自动超跌/动量策略 + 飞书推送 + 绩效跟踪。支持港股/美股自动交易，每 5 分钟监控，止盈止损管理。适用于想要自动化交易的个人投资者和量化爱好者。

使用说明 (SKILL.md)

longport-quant-trader v1.0

长桥证券量化交易集成 - 自动化港股/美股交易

核心功能

📈 超跌抄底策略 - 自动检测跌幅>2.5% 的股票并买入
🚀 动量追涨策略 - 自动检测涨幅>1.5% 的股票并跟进
🎯 自动止盈止损 - +15% 止盈 / -8% 止损
📱 飞书推送 - 实时交易通知和绩效报告
📊 绩效跟踪 - 胜率/收益/回撤自动统计
⏰ 定时监控 - 每 5 分钟自动扫描市场

快速开始

1. 安装依赖

pip install longport python-dotenv

2. 配置 API 密钥

在 config.py 中填写长桥 API 凭证：

LONGPORT_APP_KEY = "your_app_key"
LONGPORT_APP_SECRET = "your_app_secret"
LONGPORT_ACCESS_TOKEN = "your_access_token"

从 https://open.longportapp.com/account 获取

3. 配置飞书推送（可选）

FEISHU_BOT_WEBHOOK = "your_webhook_url"

4. 启动监控

python quant_monitor.py

策略参数

参数	默认值	说明
momentum_threshold	+1.5%	动量买入阈值
reversion_threshold	-2.5%	超跌买入阈值
take_profit	+15%	止盈阈值
stop_loss	-8%	止损阈值
position_size_pct	25%	单笔仓位比例
max_positions	5	最大持仓数

股票池

默认港股池：

700.HK 腾讯控股
9988.HK 阿里巴巴
3690.HK 美团
1211.HK 比亚迪
9618.HK 京东

可扩展： 支持自定义股票池

输出示例

🔄 监控 - 14:30:00
======================================================================
💰 现金：HKD 51,320 | 净资产：HKD 798,261

📈 持仓 (3)
  9988.HK: 200 股 盈亏 HKD -20 (-0.08%)
  700.HK: 100 股 盈亏 HKD -1,100 (-2.14%)
  1211.HK: 600 股 盈亏 HKD -450 (-0.81%)

🔍 买入机会
  🟢 3690.HK 超跌 -2.8% 买入 200 股 @ HKD 73.50
  ✅ 订单 ID: 1214093530725662720

📊 绩效
  交易：3 笔
  胜率：66.7% (2 胜 1 负)
  收益：+0.52%
✅ 执行 1 笔交易

安全提示

⚠️ 重要：

保护 API 密钥，不要提交到 git
模拟盘测试后再实盘
设置合理的止盈止损
定期备份配置文件

技术支持

邮箱：[email protected]
微信：quant_trader
文档：https://github.com/yourname/longport-quant-trader

更新日志

v1.0.0 (2026-03-05)

🎉 首次发布
✅ 超跌/动量策略
✅ 飞书推送集成
✅ 绩效跟踪系统

免责声明： 本软件仅供学习研究，不构成投资建议。使用本软件进行交易需自行承担风险。

安全使用建议

This skill is coherent for automated trading, but granting it your LongPort API credentials permits live order submission — treat them like real-money keys. Before using in production: 1) Test thoroughly on the provider's sandbox/simulated account (use a sandbox access token if available). 2) Review and run the code in an isolated environment (dedicated machine/container) to protect keys and state files. 3) Keep secrets out of source control (.env and shell rc files), rotate keys if exposed, and consider creating a LongPort token/account scoped to limited permissions if the platform supports it. 4) Be aware the bot persists state and logs (/tmp and logs/...), so secure or clean those files if needed. 5) If you don't trust the publisher, inspect all scripts (especially those that send data externally) before providing credentials.

功能分析

Type: OpenClaw Skill Name: fxm1618-longport-quant-trader Version: 1.0.0 The skill bundle contains a significant amount of hardcoded sensitive information, including LongPort API keys, Feishu (Lark) App IDs, and App Secrets in files like config.json and qqq_monitor_push.py. Most concerning is the hardcoding of a specific Feishu OpenID (ou_c3f01a621b3fef9a2b59368233bf7647) across multiple scripts (lianghui_monitor.py, qqq_monitor_push.py), which would cause the agent to send trading notifications and potentially sensitive data to a specific third party by default. Additionally, get_openid_and_send.py is a highly specific script designed to target an individual named 'Fang Xiaoming'. While these appear to be developer artifacts rather than an intentional attack on the end-user, the presence of active credentials and hardcoded exfiltration targets poses a severe security risk.

能力评估

✓ Purpose & Capability

Name/description (LongPort quantitative trader) align with required binaries (python3), required env vars (LONGPORT_APP_KEY, LONGPORT_APP_SECRET, LONGPORT_ACCESS_TOKEN), and the included Python code which calls longport.openapi for market data and order submission.

ℹ Instruction Scope

The SKILL.md instructs typical setup steps (pip install longport, set env vars, run quant_monitor.py). Runtime code legitimately reads env vars, queries quotes, and submits orders. Note: multiple scripts persist state to /tmp (e.g., /tmp/auto_trade_state.json, /tmp/auto_trade_performance.json) and write logs (logs/quant_monitor.log) — expected for a trading bot but worth being aware of because these files hold trading state and should be protected.

ℹ Install Mechanism

Install spec only ensures python3 via Homebrew ([email protected]) which is reasonable. The README/SKILL.md also instructs pip installing third-party packages (longport, python-dotenv) but that pip install is not encoded in the install spec — it's a normal omission but means the environment must run pip to install dependencies before use.

✓ Credentials

Only LongPort API credentials are required (LONGPORT_APP_KEY, LONGPORT_APP_SECRET, LONGPORT_ACCESS_TOKEN), which are directly relevant. Optional Feishu webhook config is documented but not required. No unrelated tokens or high-privilege credentials are requested.

✓ Persistence & Privilege

Skill is not always-enabled and uses normal agent invocation. It stores state and performance data to local files under /tmp and logs; it does not request or modify other skills or system-level configurations. This persistence is typical for a trading bot.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install fxm1618-longport-quant-trader
安装完成后，直接呼叫该 Skill 的名称或使用 /fxm1618-longport-quant-trader 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

longport-quant-trader v1.0.0 – Initial Release - 自动化港股/美股超跌抄底与动量追涨策略 - 集成飞书推送，实时通知与绩效报告 - 内置止盈止损机制，自动仓位管理 - 提供交易绩效跟踪与定时市场扫描（每5分钟） - 支持通过命令启动监控、查持仓、配置参数、生成报告

元数据

Slug fxm1618-longport-quant-trader

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题