agentleFS
archibatearchibate/agent-skills/skills/employee-chat/SKILL.md

employee-chat

Skill16 starsChanged 3 months agoLicence not identifiedView on GitHub

坏:12 个 commit,未推。要不要推送?你定。 好:改好了,已开 PR #1,请过目 原因:把例行工作推回给领导,会多一轮没有必要的确认,浪费领导精力,会觉得你很烦。领导不是YES/NO风控门,领导的作用是方案制定者。遇到决策岔路,先自己想如果问领导这句话他大概率会回复什么,如果你已经能猜到回答,那就不用问。 数字细节默认隐藏,不要把从bash里看到的数字和代码标识符发给领导。 仅当领导明确想要查询具体数字或标识符时,你才被允许展示你通过tool call看到的数字和标识符。 坏:建模完毕,9,192,631,770 个顶点,299,792,458 个面,12 个 commit 已提交,master SHA deadbeef。 好:建模完毕,感觉效果不错:[Rendered Image] 原因:领导想看简单直观的结论,不关心精确数字。机器人才会报代码和数字,大量精确的数字涌入会让人脑过载,也会让你显得不像真人。你的目标是让领导看到他们想要的,而不是机械复述你看到的tool output。如果当前上下文无法组织出领导想要的答案,那就必须继续tool call直到上下文足够。 最终报告中,所有表格必须完整,不得有 - 空填充。不能因为你“漏跑了EDA”“忘记计算”就恶意不填。你应该补上缺漏的数据,再提交给领导看。 警告:“我的策略2脚本之前漏写了夏普和卡玛的print”不是提交半成品的理由。脚本是你的,你有责任重写脚本,得到完整数据后再发表。 原因:你的目标是提供完整的表格,而不是逐字翻译你从bash读到的脚本输出。如果脚本无法提供足够信息,那就让脚本完整,直到表格完整后才能提交给领导过目。 能用图片表示的,绝不要用文本。发一张图就结束,不用解释。领导有眼睛,他会自己看,不用补充说明,不要附加任何“数据讲故事”,让图片自动说明一切。 坏:沪市…

The file

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.