← 返回 Skills 市场
wtjjacobj

trading-log

作者 wtjjacobj · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
92
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install trading-log
功能描述
交易日志记录系统——记录所有买卖交易、计算持仓盈亏、自动刷实时行情。When the user mentions buying/selling stocks, recording trades, checking positions, or calculating profit/loss.
安全使用建议
This skill appears to implement a local trading log and fetches realtime prices from Tencent (qt.gtimg.cn), which matches its description — but there are inconsistencies you should resolve before using it. Specifically: (1) the documentation and manifest reference different filenames than the shipped script, and the script uses a hardcoded path (/home/jocob/Desktop/...) rather than the ~/Desktop path described; confirm and correct the file locations so it reads/writes where you expect. (2) The skill will create persistent JSON files containing your trades; if you care about privacy or retention, inspect the save/load functions and change paths or add deletion/backup policies. (3) It makes outbound HTTP requests only to a known public price API (qt.gtimg.cn) — if you require stricter network controls, run it in a sandboxed environment or block network access. (4) Because SKILL.md mentions automatic Cron triggers but provides no installer for scheduling, verify how your agent will schedule runs before enabling autonomous invocation. If you want to proceed, run the script locally in a controlled folder (not someone else's /home), review the code yourself (or have a developer do so), and fix the path/filename inconsistencies.
功能分析
Type: OpenClaw Skill Name: trading-log Version: 1.0.0 The trading-log skill is a legitimate utility for tracking stock trades and calculating profit/loss. It fetches real-time market data from a public Tencent Finance API (qt.gtimg.cn) and manages local JSON data files. While it contains hardcoded file paths for a specific user ('jocob') in scripts/trading_log.py, there is no evidence of data exfiltration, malicious execution, or prompt injection.
能力评估
Purpose & Capability
The skill claims to record trades, compute P/L, and fetch realtime prices — the included Python script and SKILL.md implement that functionality. However, the SKILL.md and file manifest reference filenames like '交易日志.py' and files expected on ~/Desktop, while the actual code lives at scripts/trading_log.py and uses hardcoded paths under /home/jocob/Desktop. This discrepancy is unexpected and suggests the package was not packaged consistently.
Instruction Scope
SKILL.md instructs the agent to run commands from ~/Desktop and refers to a mainAgent Cron that will trigger daily updates, but the shipped script reads/writes a hardcoded LOG_FILE at /home/jocob/Desktop/交易日志_持仓记录.json and the code path differs from the documented file names. The instructions also assert '记录永久保存,不可删除' (permanently saved) without any mechanism to enforce or manage retention. These mismatches create a risk that the agent will read/write unexpected filesystem locations or fail silently.
Install Mechanism
There is no install spec (instruction-only plus an included script). That minimizes supply-chain risk; nothing is downloaded at install time and no external packages are automatically pulled.
Credentials
The skill requests no environment variables or credentials, which is appropriate for a local trading log. However, it does access the user's filesystem (hardcoded /home/jocob Desktop paths). While not a secret-exfiltration pattern, hardcoded user paths are brittle and could unintentionally access another user's files on multi-user systems or fail to store data where the user expects.
Persistence & Privilege
The skill is not marked always:true and does not request elevated privileges, but it writes persistent JSON trade logs and claims they are permanent. It also references being triggered by a '主Agent的Cron系统' without providing installation or scheduling steps — if the agent is allowed to schedule recurring tasks, this will create long-lived data on disk. Autonomous invocation is allowed by default; combine that with persistent storage if you need to limit continuous background activity.
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-log
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /trading-log 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
v1.0.0
trading-log 1.0.0 - 首次发布:推出A股/港股交易日志记录系统 - 支持实时行情刷新、持仓/盈亏自动计算 - 通过自然语言或命令行记录买卖、查询持仓、生成盈亏报表 - 日志、持仓、盈亏等功能一站式管理 - 自动对接腾讯行情接口,15:30自动刷新价格并持久化数据
元数据
Slug trading-log
版本 1.0.0
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-log 是什么?

交易日志记录系统——记录所有买卖交易、计算持仓盈亏、自动刷实时行情。When the user mentions buying/selling stocks, recording trades, checking positions, or calculating profit/loss. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 92 次。

如何安装 trading-log?

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

trading-log 是免费的吗?

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

trading-log 支持哪些平台?

trading-log 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-log?

由 wtjjacobj(@wtjjacobj)开发并维护,当前版本 v1.0.0。

💬 留言讨论