← 返回 Skills 市场
232
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install stock-monitor-skill-0-1-0-custom
功能描述
全功能智能股票监控预警系统。支持成本百分比、均线金叉死叉、RSI超买超卖、成交量异动、跳空缺口、动态止盈等7大预警规则。符合中国投资者习惯(红涨绿跌)。
安全使用建议
This package appears to be a coherent self-hosted stock-monitoring tool, but please consider the following before installing/running it:
- Run in a sandbox or VM first. The package runs a persistent daemon (control.sh -> monitor_daemon.py) that will continuously make outbound HTTP requests to finance/news APIs and create logs under $HOME/.stock_monitor.
- Review the code locally. The network endpoints used (eastmoney, sina, push2.eastmoney.com, search.sina.com.cn) are public finance data sources and expected for this tool; confirm you are comfortable granting the runtime outbound access to them.
- Missing/misaligned files and paths: README mentions config.example.py which is not in the bundle; test_suite.py inserts an absolute developer path (/home/wesley/...) — if you run tests, either run them after adjusting paths or inspect/modify test_suite.py to avoid referencing your filesystem unexpectedly.
- Ownership/metadata mismatch: _meta.json ownerId differs from the registry metadata. This could be an innocuous packaging oversight, but if provenance matters to you, ask the publisher for clarification.
- Resource usage and rate limits: the daemon's schedule can be frequent (every 5 minutes during market hours) and may hit rate limits of public APIs. Consider throttling, adding caching, or running with limited network egress if you want to control usage.
- Permissions: do not run the scripts as root. They are intended for user-level operation and write only to the user's home directory.
If you decide to proceed, run the code in an isolated environment first, verify the exact network calls (e.g., via a proxy or firewall), and confirm the logging/ PID behavior meets your expectations.
功能分析
Type: OpenClaw Skill
Name: stock-monitor-skill-0-1-0-custom
Version: 0.1.0
The skill bundle is a functional stock monitoring and alerting system tailored for the Chinese market. It implements technical analysis (RSI, Moving Averages), news sentiment analysis, and a background daemon for persistent monitoring. The code uses the 'requests' library to fetch public financial data from legitimate sources like Sina Finance and EastMoney, and no evidence of data exfiltration, malicious execution, or harmful prompt injection was found. A hardcoded path in 'test_suite.py' appears to be a developer oversight rather than a malicious indicator.
能力评估
Purpose & Capability
Name/description (stock monitoring and alerts) align with the code and runtime instructions: the scripts query public finance/news endpoints (Eastmoney, Sina), compute indicators, and emit alerts. There are minor documentation mismatches (README suggests copying config.example.py but no such file exists in the bundle) and an inconsistent ownerId in _meta.json versus registry metadata, but these are likely bookkeeping issues rather than functional mismatches.
Instruction Scope
SKILL.md and control.sh limit the agent to starting/stopping a local daemon and editing local config; the runtime instructions do not ask the agent to read unrelated system files or environment secrets. Notable points: (1) README mentions a config.example.py that is not present in the package; (2) the included tests (test_suite.py) insert an absolute developer path (/home/wesley/...) which is odd and could try to reference a developer-local path if tests are executed as-is. These are scope/robustness concerns but not evidence of exfiltration.
Install Mechanism
No install spec (instruction-only install) and no external archive downloads. Code is provided in the skill bundle; nothing in the files attempts to fetch or run arbitrary installers from unknown hosts. Risk remains that the packaged Python will be run on the host (daemon and scripts), which is expected for this type of skill.
Credentials
The skill declares no required environment variables or credentials and the code uses only public web APIs. It writes logs and a PID file under $HOME/.stock_monitor (control.sh and monitor_daemon.py). No credentials or secret access is requested; network access to public finance/news endpoints is necessary for the stated purpose.
Persistence & Privilege
always:false (no forced inclusion). The skill runs a user-level background process (via control.sh -> nohup python3 monitor_daemon.py) and creates files in the user's home directory. This is a standard behavior for a self-hosted monitor but worth noting because it results in continuous outbound network traffic and persistent local files until the user stops it.
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 stock-monitor-skill-0-1-0-custom - 安装完成后,直接呼叫该 Skill 的名称或使用
/stock-monitor-skill-0-1-0-custom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
v0.1.0
Stock Monitor 0.1.0 初始版本上线。
- 支持7大核心预警规则:成本百分比、日内涨跌幅、成交量异动、均线金叉死叉、RSI超买超卖、跳空缺口、动态止盈
- 预警系统分为紧急级、警告级、提醒级,细分信号共振
- 完全符合中国红涨绿跌习惯
- 支持个股、ETF、黄金差异化监控
- 集成后台常驻进程和一键控制脚本
- 灵活自定义阈值和预警规则,提升个性化策略能力
元数据
常见问题
Stock Monitor Skill 0.1.0 是什么?
全功能智能股票监控预警系统。支持成本百分比、均线金叉死叉、RSI超买超卖、成交量异动、跳空缺口、动态止盈等7大预警规则。符合中国投资者习惯(红涨绿跌)。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 232 次。
如何安装 Stock Monitor Skill 0.1.0?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install stock-monitor-skill-0-1-0-custom」即可一键安装,无需额外配置。
Stock Monitor Skill 0.1.0 是免费的吗?
是的,Stock Monitor Skill 0.1.0 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Stock Monitor Skill 0.1.0 支持哪些平台?
Stock Monitor Skill 0.1.0 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Stock Monitor Skill 0.1.0?
由 aiden-fan(@aiden-fan)开发并维护,当前版本 v0.1.0。
推荐 Skills