← 返回 Skills 市场

LongPort Quant Trader

Name: LongPort Quant Trader
Author: fxm1618-gmail

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

cross-platform ⚠ suspicious

113

总下载

当前安装

版本数

在 OpenClaw 中安装

/install 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 appears to be what it says: an automated LongPort trading toolkit that will read market data and can submit real orders if given your LongPort credentials. Before installing, consider: 1) Use a sandbox or simulated account to validate behavior (do not use real money until tested). 2) Do NOT commit API keys to source control — prefer environment variables or a secrets manager; if you follow the config.py suggestion, delete keys from disk afterward. 3) Limit the credentials' permissions if LongPort supports scoped tokens; use a read-only token or a test token where possible and rotate/revoke keys after testing. 4) Review the 'longport' Python package source (PyPI/GitHub) and examine any network calls if you require stronger assurance. 5) If you enable Feishu webhook notifications, treat webhooks as secrets. 6) Because the skill can place trades, run it on a dedicated device and monitor logs and order history closely to detect unexpected activity.

功能分析

Type: OpenClaw Skill Name: longport-quant-trader Version: 1.0.0 The skill bundle contains several high-risk security issues, most notably the inclusion of hardcoded API credentials and secrets. Specifically, 'config.json' contains LongPort API keys, and 'qqq_monitor_push.py' contains a hardcoded Feishu (Lark) App ID and Secret. Furthermore, 'get_openid_and_send.py' includes logic specifically designed to search for and target an individual named '房晓明' (Fang Xiaoming) within a Feishu tenant to send automated messages. While these may be remnants of a specific development or testing environment, the presence of hardcoded secrets and targeted messaging logic is highly irregular for a general-purpose skill and poses a significant risk of credential exposure and unauthorized communication.

能力评估

✓ Purpose & Capability

Name/description (LongPort quantitative trader) align with the code and requirements: code imports longport.openapi, submits orders, monitors quotes, and sends Feishu notifications. Required env vars are LongPort credentials which are expected for this purpose. Required binary (python3) and pip dependencies (longport, python-dotenv) are appropriate.

ℹ Instruction Scope

SKILL.md and SETUP_GUIDE instruct running monitoring/trading scripts (e.g., quant_monitor.py, hk_scanner_full.py) and storing API keys either as env vars or in a config.py/.env. The runtime instructions and code do perform account queries and order submission (expected), and write local state files (e.g., /tmp/auto_trade_state.json). Minor inconsistency: SKILL.md shows editing config.py while most code uses Config.from_env() and dotenv — this may lead users to store secrets on disk if they follow the config.py guidance. No instructions request unrelated files, credentials, or external endpoints beyond LongPort and optional Feishu.

✓ Install Mechanism

Install spec only bootstraps Python via Homebrew ([email protected]). SKILL.md also instructs pip installing 'longport' and 'python-dotenv' (expected). There are no downloads from untrusted URLs or archive extraction in the install spec. Overall install approach is proportionate.

ℹ Credentials

Declared required env vars are LONGPORT_APP_KEY, LONGPORT_APP_SECRET, LONGPORT_ACCESS_TOKEN — these map directly to the trading API and are necessary for automated trading. No unrelated credentials are requested. Note: those credentials allow placing real trades; the skill's access is powerful and should be limited to appropriate accounts (use sandbox/test keys if available). Feishu webhook is optional and not listed as required.

✓ Persistence & Privilege

Skill is not marked always:true and uses normal autonomous invocation. It creates/writes small local state and performance files under /tmp (and suggests local config/.env). It does not request system-wide configuration changes or modify other skills. Autonomous invocation combined with trading credentials implies high potential impact (financial) but that impact is coherent with the stated purpose.

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 longport-quant-trader
安装完成后，直接呼叫该 Skill 的名称或使用 /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 - 首次发布版本，集成港股/美股自动量化交易。 - 支持超跌抄底与动量追涨策略，内置止盈止损管理。 - 提供飞书推送功能，监控结果和绩效实时推送。 - 每 5 分钟自动市场扫描，智能捕捉买卖机会。 - 支持绩效跟踪、个性化参数配置和自定义股票池。

元数据

Slug 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