agentleFS
ishenliishenli/investment-agent/skills/transaction-management/SKILL.md

transaction-management

Skill10 starsChanged 6 months agoMITView on GitHub

查询与记录用户的交易:入金、出金、买入、卖出,以及交易历史、按日期范围查询、交易摘要。 当用户说"记一笔买入"、"帮我记录今天卖了 XX"、"查一下最近的交易"、"这个月的交易流水"、 "买卖记录"、"入金了多少",或要求基于交易记录做统计时,**务必使用此技能**。

The file

Files
SKILL.md

交易记录管理

记录新交易:addTransactionTool

用户委托记交易("记一笔"、"帮我记录")时调用 addTransactionTool。参数规则:

参数必填条件说明
account_id必填账户 ID(字符串)。不确定时先用 dbQueryTool 查 accounts 确认,禁止猜 ID
type必填deposit 入金 / withdrawal 出金 / buy 买入 / sell 卖出
amountdeposit / withdrawal 必填金额(数值,不带货币单位符号)
symbolbuy / sell 必填标的代码,如 AAPL、600519、0700.HK
quantitybuy / sell 必填数量
pricebuy / sell 必填单价
sector可选stock / etf / fund / crypto,默认 stock
market可选US / CN / HK
description可选交易描述
trade_time可选ISO 格式;用户没说时间就不要编造,留空用默认

流程:确认账户 → 确认关键字段取值 → 执行 → 向用户复述记录内容。写入操作必须复述确认的数据再返回,字段不清楚就问,不要代填。

查询

  • 最近交易:transactionHistoryTool(limit 默认 50,offset 翻页)。
  • 日期范围:transactionHistoryByDateTool,参数 start_date / end_date(YYYY-MM-DD)。相对日期("这个月"、"上周")必须先换算成具体日期。
  • 交易摘要(Markdown 汇总):transactionSummaryTool。
  • 资金余额变化:配合 accountBalanceTool。

统计口径

  • 盈亏、平均成本等派生指标由交易记录计算时,注明计算窗口(时间范围、账户、标的)。
  • buy/sell 金额 = quantity × price;如果两笔字段可疑(数量或价格异常),指出并把原始数据贴出来,不要静默纠正。

限制

  • 修改、删除已有交易记录没有对应工具;发现错误记录时明确告知用户到应用界面处理。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.