Stock Monitor Pro

专业级智能股票监控预警系统 V2.1。支持收盘日报自动生成、反爬虫优化(Session级UA、多数据源冗余)、成本百分比预警、均线金叉死叉、RSI超买超卖、成交量异动监控、智能错误提醒。符合中国投资者习惯（红涨绿跌）。Use when user needs stock market monitoring, pri...

Security Scan

The skill's code and runtime instructions generally match a stock-monitoring tool, but there are several packaging and consistency issues (missing referenced files, hard-coded user paths, test assumptions) that make the bundle unreliable and warrant caution before installing or running it.

Purpose & Capability

The name/description (stock monitoring, alerts, daily reports) aligns with the included Python scripts: monitor/monitor_v2 implement data fetching, indicator calculation, alert rules, and a daemon. The anti-scraping measures, multi-source fetching and alert logic are coherent with the stated purpose.

Instruction Scope

SKILL.md tells the user to start a background daemon (control.sh start -> launches monitor_v2.py) which is consistent with a long-running monitor. However SKILL.md/README reference files that are not present (config.example.py, RULE_REVIEW_REPORT.md). The included test suite and some code expect particular symbols (e.g., '600362', 'XAU') and contain hard-coded absolute paths (/home/wesley/...), which are out-of-band assumptions and likely to fail or mislead. The runtime instructions do not request unrelated secrets, but they do instruct long-running network access to multiple external endpoints.

Install Mechanism

There is no install spec — this is instruction/code-only. No downloads, package installs, or extraction-from-URL operations are present in the manifest. That lowers installation risk; the skill just contains Python and shell scripts.

Credentials

The skill declares no required env vars, credentials, or config paths. The code does perform many outgoing HTTP requests to public finance APIs (eastmoney, sina, qt.gtimg, etc.), which is expected for a market-monitoring tool. There are no requests for unrelated credentials or keys in the package.

Persistence & Privilege

The control.sh and monitor_daemon start a persistent background process and write logs/pid to $HOME/.stock_monitor. This is typical for a monitor but does create persistent presence on the host. always is false (normal). The skill does not attempt to modify other skills or system-wide settings.

What to consider before installing

What to consider before installing/running: - Packaging inconsistencies: README and SKILL.md mention config.example.py and RULE_REVIEW_REPORT.md that are not present. The included test suite also references specific symbols and a hard-coded user path (/home/wesley/...), so the bundle appears incompletely packaged or adapted from a different developer environment. Expect runtime errors unless you fix or supply the missing files. - Tests are brittle: test_suite asserts the presence of stock codes and gold data that the WATCHLIST in the monitors may not contain. Don't assume the tests will pass on your machine; review and adapt tests before running. - Persistent daemon behavior: control.sh launches a background Python process and writes logs/pid under $HOME/.stock_monitor. If you install, the process will run continuously (as intended) — run it in a sandbox or container first, and inspect the log file for unexpected behavior. Use the provided stop/status commands to manage it. - Network activity: the code fetches market data from multiple public endpoints and uses anti-scraping headers (rotating UA, fingerprint headers, randomized delays). This is consistent with scraping market data but be aware of potential rate-limiting and the ethics/legality of aggressive scraping for some data providers. No evidence of exfiltration to private endpoints, but all network traffic is external — review firewall/network policies if needed. - Hard-coded paths and assumptions: the bundle contains developer-era hard-coded paths and assumptions (user home paths, specific symbol expectations). Before running with your real holdings, inspect and/or edit WATCHLIST and any configuration to ensure it matches your assets and risk tolerances. Recommended actions: 1. Inspect the scripts (monitor_v2.py, monitor.py, analyser.py) locally; grep for any URLs or destinations you don’t recognize (there are only public finance APIs in the package). 2. Run the code in an isolated environment (container or VM) first. 3. Provide or adapt a config (the README suggests config.example.py — create a small config or edit WATCHLIST inline). 4. Remove or fix hard-coded absolute paths in test_suite or run tests only after adapting them to your environment. 5. If you will run the daemon long-term, limit its filesystem permissions and monitor outbound connections. Given the coherence with the claimed functionality but the packaging and test inconsistencies, proceed cautiously rather than trusting it as-is.

Stock Monitor Pro V2 - 全功能智能投顾系统

🎯 核心特色

1. 七大预警规则 (全都要!)

规则	触发条件	权重
成本百分比	盈利+15% / 亏损-12%	⭐⭐⭐
日内涨跌幅	个股±4% / ETF±2% / 黄金±2.5%	⭐⭐
成交量异动	放量>2倍均量 / 缩量<0.5倍	⭐⭐
均线金叉/死叉	MA5上穿/下穿MA10	⭐⭐⭐
RSI超买超卖	RSI>70超买 / RSI<30超卖	⭐⭐
跳空缺口	向上/向下跳空>1%	⭐⭐
动态止盈	盈利10%+后回撤5%/10%	⭐⭐⭐

2. 分级预警系统

• 🚨 紧急级: 多条件共振 (如: 放量+均线金叉+突破成本)
• ⚠️ 警告级: 2个条件触发 (如: RSI超卖+放量)
• 📢 提醒级: 单一条件触发

3. 中国习惯

• 🔴 红色 = 上涨 / 盈利
• 🟢 绿色 = 下跌 / 亏损

📋 监控配置

完整预警规则示例

{
    "code": "600362",
    "name": "江西铜业",
    "type": "individual",  # 个股
    "market": "sh",
    "cost": 57.00,          # 持仓成本
    "alerts": {
        # 1. 成本百分比
        "cost_pct_above": 15.0,    # 盈利15%提醒 (¥65.55)
        "cost_pct_below": -12.0,   # 亏损12%提醒 (¥50.16)
        
        # 2. 日内涨跌幅 (个股±4%)
        "change_pct_above": 4.0,
        "change_pct_below": -4.0,
        
        # 3. 成交量异动
        "volume_surge": 2.0,       # 放量>2倍5日均量
        
        # 4-7. 技术指标 (默认开启)
        "ma_monitor": True,        # 均线金叉死叉
        "rsi_monitor": True,       # RSI超买超卖
        "gap_monitor": True,       # 跳空缺口
        "trailing_stop": True      # 动态止盈
    }
}

标的类型差异化

类型	日内异动阈值	成交量阈值	适用标的
individual (个股)	±4%	2倍	江西铜业、中国平安
etf (ETF)	±2%	1.8倍	恒生医疗、创50等
gold (黄金)	±2.5%	无	伦敦金

🚀 运行方式

后台常驻进程

cd ~/workspace/skills/stock-monitor/scripts
./control.sh start    # 启动
./control.sh status   # 查看状态
./control.sh log      # 查看日志
./control.sh stop     # 停止

⚡ 智能频率 (北京时间)

时间段	频率	监控标的
交易时间 9:30-15:00	每5分钟	全部+技术指标
午休 11:30-13:00	每10分钟	全部
收盘后 15:00-24:00	每30分钟	全部 (日线数据)
凌晨 0:00-9:30	每1小时	仅伦敦金
周末	每1小时	仅伦敦金

🔔 预警消息示例

多条件共振 (紧急级)

🚨【紧急】🔴 江西铜业 (600362)
━━━━━━━━━━━━━━━━━━━━
💰 当前价格: ¥65.50 (+15.0%)
📊 持仓成本: ¥57.00 | 盈亏: 🔴+14.9%

🎯 触发预警 (3项):
  • 🎯 盈利 15% (目标价 ¥65.55)
  • 🌟 均线金叉 (MA5¥63.2上穿MA10¥62.8)
  • 📊 放量 2.5倍 (5日均量)

📊 江西铜业 深度分析
💰 价格异动:
• 当前: 65.5 (+15.0%)
• MA趋势: MA5>MA10>MA20 [多头排列]
• RSI: 68 [接近超买]

💡 Kimi建议:
🚀 多条件共振，趋势强劲，可考虑继续持有或分批减仓。

RSI超卖 (警告级)

⚠️【警告】🟢 恒生医疗 (159892)
━━━━━━━━━━━━━━━━━━━━
💰 当前价格: ¥0.72 (-10.0%)
📊 持仓成本: ¥0.80 | 盈亏: 🟢-10.0%

🎯 触发预警 (2项):
  • 📉 日内大跌 -10.0%
  • ❄️ RSI超卖 (28.5)，可能反弹

💡 Kimi建议:
🔍 短期超跌严重，RSI进入超卖区，关注反弹机会但勿急于抄底。

动态止盈提醒

📢【提醒】🔴 中国平安 (601318)
━━━━━━━━━━━━━━━━━━━━
💰 当前价格: ¥70.50 (+6.8%)
📊 持仓成本: ¥66.00 | 盈亏: 🔴+6.8%

🎯 触发预警:
  • 📉 利润回撤 5.2%，建议减仓保护利润
  (最高盈利12%已回撤)

🛠️ 文件结构

stock-monitor/
├── SKILL.md                    # 本文档
├── RULE_REVIEW_REPORT.md       # 规则审核报告
└── scripts/
    ├── monitor.py              # 核心监控 (7大规则)
    ├── monitor_daemon.py       # 后台常驻进程
    ├── analyser.py             # 智能分析引擎
    └── control.sh              # 一键控制脚本

⚙️ 自定义配置

修改成本价

"cost": 55.50,  # 改成你的实际成本

调整预警阈值

"cost_pct_above": 20.0,     # 盈利20%提醒
"cost_pct_below": -15.0,    # 亏损15%提醒
"change_pct_above": 5.0,    # 日内异动±5%
"volume_surge": 3.0,        # 放量3倍提醒

开关技术指标

"ma_monitor": False,     # 关闭均线
"rsi_monitor": True,     # 开启RSI
"gap_monitor": True,     # 开启跳空

📝 更新日志

• v3.0 全功能版: 完成7大预警规则 (成本/涨跌幅/成交量/均线/RSI/跳空/动态止盈)
• v2.4 成本百分比版: 支持基于持仓成本的百分比预警
• v2.3 中国版: 红涨绿跌颜色习惯
• v2.2 常驻进程版: 后台常驻进程支持
• v2.1 智能频率版: 智能频率控制
• v2.0 Pro版: 新闻舆情分析

⚠️ 使用提示

1. 技术指标有滞后性: 均线、MACD等都是滞后指标，用于确认趋势而非预测
2. 避免过度交易: 预警只是参考，不要每个信号都操作
3. 多条件共振更可靠: 单一指标容易假信号，多条件共振更准确
4. 动态止盈要灵活: 回撤5%减仓、10%清仓是建议，根据市场灵活调整

---

核心原则:

预警系统目标是"不错过大机会，不犯大错误"，不是"抓住每一个波动"。