← 返回 Skills 市场
115
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install stock-advisor
功能描述
你的私人 AI 投顾。提供 A 股个股深度多维分析、持仓管理。
安全使用建议
Before installing or running: (1) Resolve the metadata mismatch — SKILL.md and scripts expect STOCK_ADVISOR_API_URL and STOCK_ADVISOR_API_KEY even though registry metadata lists none. (2) Verify and trust the backend: by default the skill will contact https://api.daas.ai (or the URL you set). If you don't trust that service, run your own local backend and set STOCK_ADVISOR_API_URL to http://localhost:8000. (3) Inspect any remote install script before running it — README recommends curl | sh from astral.sh to install 'uv'; avoid executing that blindly. (4) The portfolio data is stored locally in data/portfolio.json, but a sample file contains a user path — replace or remove sample data. (5) If you need strong privacy, run the skill in a sandboxed environment and/or host the API backend yourself so scans don't go to an external server.
功能分析
Type: OpenClaw Skill
Name: stock-advisor
Version: 1.0.0
The stock-advisor skill bundle provides legitimate stock analysis and local portfolio management functionality. It interacts with an external API (defaulting to api.daas.ai) to fetch market data and uses a local JSON file (data/portfolio.json) for storing user holdings. While the code contains a minor information leak by storing the local Python environment path (sys.prefix) in the portfolio data, there is no evidence of malicious intent, data exfiltration, or unauthorized command execution. The scripts (scan.py, portfolio.py) and instructions (SKILL.md) are well-aligned with the stated purpose.
能力评估
Purpose & Capability
The name/description (A股深度分析 + 持仓管理) match included scripts: scan.py calls a cloud API and portfolio.py reads/writes local data. However registry metadata stated no required env vars/credentials while SKILL.md and scripts rely on STOCK_ADVISOR_API_URL and STOCK_ADVISOR_API_KEY — this inconsistency should be resolved.
Instruction Scope
SKILL.md instructs running the included scripts (expected). It claims '所有持仓和预警数据均保存在本地' which is true for portfolio operations, but scan.py performs network calls to the configured cloud backend (symbol queries via /api/scan). The skill does not exfiltrate portfolio data in code, but the privacy claim is misleading because scan requests go to an external service. README also suggests running a remote install curl | sh (astral.sh) which broadens runtime scope and risk.
Install Mechanism
There is no formal install spec in the registry (lowest risk), but README recommends installing 'uv' via curl -LsSf https://astral.sh/uv/install.sh | sh. That is a remote install script from a third-party domain; running it without inspection is risky. The package_files themselves are plain Python scripts (no packaged binary downloads).
Credentials
The code and SKILL.md legitimately use two env vars (STOCK_ADVISOR_API_URL, STOCK_ADVISOR_API_KEY) for contacting a cloud backend — proportional to the cloud-scan function. However, registry metadata claimed no required env vars/primary credential, which is inconsistent. The default API key in config.py ('demo-key-123456') and default base URL (https://api.daas.ai) mean the skill can run without you supplying secrets, but will contact that default service unless you override it.
Persistence & Privilege
The skill does not request always:true and will not be force-included. It writes only its own local portfolio.json file via LocalStore; it does not modify other skills or system-wide settings. Autonomous invocation is enabled (default) but not combined with other high-risk requests.
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-advisor - 安装完成后,直接呼叫该 Skill 的名称或使用
/stock-advisor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
Initial release of Stock Advisor Pro for OpenClaw.
元数据
常见问题
Stock Advisor Pro 是什么?
你的私人 AI 投顾。提供 A 股个股深度多维分析、持仓管理。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 115 次。
如何安装 Stock Advisor Pro?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install stock-advisor」即可一键安装,无需额外配置。
Stock Advisor Pro 是免费的吗?
是的,Stock Advisor Pro 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Stock Advisor Pro 支持哪些平台?
Stock Advisor Pro 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 Advisor Pro?
由 daas.ai(@daasai)开发并维护,当前版本 v1.0.0。
推荐 Skills