agentleFS
juliasadlerjuliasadler/muse-skills-cn/skills/ai-memory-management/SKILL.md

ai-memory-management

Skill1 starsChanged 30 days agoMITView on GitHub

管理 AI 助手的记忆:记什么、忘什么、清理前先确认

The file

Files
SKILL.md

AI 记忆管理

何时使用

  • 用户说"记住这个""忘掉那个""别再记了"
  • 定期整理记忆,或发现信息可能过时
  • 清理涉及多处副本或自动化流程时

规则清单

  1. 值得长期记:稳定偏好、重要决定、关键事实(称呼、过敏、常用设置)
  2. 只记一次:临时任务、一次性事件、仅当前会话有用的上下文
  3. 定期清理过时信息:已完成的计划、已变更的偏好、失效的安排
  4. 删除前先跟用户确认:说明会删什么、可能影响什么
  5. 把"忘掉"当作全系统清理:对话记录、笔记、提醒、自动化都可能留有副本或重新写入
  6. 先做只读盘点:原始位置、副本、能再生它的来源、无法删除的部分
  7. 用日常语言沟通,不暴露内部机制(说"记忆""提醒",不说数据库、索引等术语)
  8. 清理后验证:确认各处都不再出现该信息
  9. 交接时用"那条信息"指代,不复制敏感内容到新地方
  10. 如实说明清理边界:已分享给他人的内容可能删不掉

场景示例

示例一:用户说"忘掉我之前的地址"

  • 盘点:记忆笔记、对话历史、提醒、引用它的日程
  • 告知:找到 3 处副本,其中 1 处是已发出的共享文档,无法删除
  • 用户确认后删除可删部分,并验证不再出现

示例二:用户说"记住我改喝燕麦奶了"

  • 更新偏好,标记旧偏好(喝牛奶)为过时
  • 下次建议点单时使用新偏好,并定期复核是否仍适用

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.