← 返回 Skills 市场
xuxuclassmate

Trading Assistant Core

作者 XuXu · GitHub ↗ · v4.0.0 · MIT-0
cross-platform ✓ 安全检测通过
139
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install trading-assistant-core
功能描述
Market data analysis toolkit with technical indicators and portfolio tracking. Educational use only.
安全使用建议
This package appears internally consistent for an educational trading-analysis tool, but before installing or running it: 1) Inspect requirements.txt and the remaining (omitted) Python files (trading_signals.py, support_resistance.py, any notification modules) for network calls, webhooks, or hardcoded remote endpoints (Feishu/DingTalk/email integrations are mentioned in README). 2) Run it in an isolated environment/container and only provide the minimal API keys needed (rotate keys after testing if concerned). 3) Be aware the tool will create/write local files (data/, logs/, portfolio/holdings.json, accuracy_log.json); if you have sensitive data in your environment, avoid mounting sensitive directories. 4) Do not supply brokerage credentials — this skill claims 'no trade execution' and there is no declared brokerage credential requirement; supplying broker keys would be unnecessary and risky. 5) If you plan to trust outputs for real trading, validate indicator logic and test thoroughly; the repository is labelled educational and 'not financial advice.' Finally, if you want higher assurance, provide the omitted source files (or examine them yourself) so they can be checked for any outbound notification code or unexpected behavior — I rated confidence medium because a few files were truncated/omitted in the listing.
功能分析
Type: OpenClaw Skill Name: trading-assistant-core Version: 4.0.0 The skill bundle is a comprehensive trading assistant for technical analysis and portfolio management. It fetches market data from legitimate sources (Twelve Data, Alpha Vantage, and Sina Finance) and performs calculations for indicators like RSI and MACD. The code follows security best practices mentioned in its documentation, such as avoiding 'eval()', 'subprocess', and automatic '.env' loading to prevent secret exposure. While 'config.py' contains a default Feishu 'chat_id', it appears to be a placeholder for the notification feature rather than a malicious exfiltration vector.
能力评估
Purpose & Capability
Name/description (market data, indicators, portfolio tracking) align with what is requested: python/pip and API keys for Twelve Data and Alpha Vantage. Primary credential (TWELVE_DATA_API_KEY) is appropriate. Required binaries and declared env vars are directly relevant to the stated functionality.
Instruction Scope
SKILL.md instructs the agent to install dependencies, export the two API keys, and run the Python scripts. The files shown perform read-only data fetches (urllib/requests), indicator calculations, portfolio bookkeeping (local JSON files), and logging. SKILL.md's claim of 'no subprocess, no shell, no eval/exec' appears accurate in the reviewed files. The agent is instructed only to use the declared API keys and local files; there is no broad or vague permissioning in the instructions.
Install Mechanism
No external binary download/install spec in the registry entry. The repository contains Python modules and a requirements.txt; installation is via pip -r requirements.txt as documented in SKILL.md. This is a common, low-risk install mechanism — but you should review requirements.txt before installing to ensure there are no unexpected third-party packages.
Credentials
Only two API keys are required (TWELVE_DATA_API_KEY, ALPHA_VANTAGE_API_KEY), which match the data sources referenced in code and README. The code reads TRADING_ASSISTANT_LANG optionally (i18n), and the modules read/write local JSON files for persistence — no unrelated secrets or cloud credentials are requested. No evidence that environment variables beyond those declared are accessed in the inspected files.
Persistence & Privilege
The skill does create and write local files/directories (data/, logs/, portfolio/holdings.json, accuracy_log.json). always:false and normal model invocation settings (autonomy allowed) are used. Writing local JSON logs/config is expected for this app, but you should be aware it will persist portfolio/accuracy data in the skill's directory. There is no indication it modifies other skills or system-wide agent config.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install trading-assistant-core
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /trading-assistant-core 触发
  4. 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
v4.0.0
Version 4.0.0 — Major Update - Updated SKILL.md with detailed security, installation, and usage information. - Expanded documentation to emphasize educational use and clarify safety guarantees. - Added environment variable and dependency requirements. - Improved feature descriptions and provided direct resource links. - Reaffirmed read-only, non-trading nature of the toolkit.
元数据
Slug trading-assistant-core
版本 4.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Trading Assistant Core 是什么?

Market data analysis toolkit with technical indicators and portfolio tracking. Educational use only. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 139 次。

如何安装 Trading Assistant Core?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install trading-assistant-core」即可一键安装,无需额外配置。

Trading Assistant Core 是免费的吗?

是的,Trading Assistant Core 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Trading Assistant Core 支持哪些平台?

Trading Assistant Core 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 Trading Assistant Core?

由 XuXu(@xuxuclassmate)开发并维护,当前版本 v4.0.0。

💬 留言讨论