16 ejentum

memory Skill

当你已对对话状态、用户行为、偏移、情绪变化或跨轮次模式形成感知或观察,需要加以锐化时使用。触发短语包括“你注意到X了吗”、“用户一直在Y”、“我感觉有什么变了”、“用户是不是在X”、“这个模式说明了什么”、“我们这几轮之间有什么变化”、“我是不是漏掉了什么”、“对话为什么从X转到了Y”,或任何需要验证某一感受是真实信号还是主观投射的时刻。该技能调用 memory MCP 工具获取感知脚手架。

安装方式:把技能目录放入 ~/.claude/skills/(Claude Code)或在 claude.ai 设置中启用;也可复制右侧安装命令一键添加。

查看源码

技能指令原文(SKILL.md)

Memory Harness

When this skill triggers, you MUST observe first. Do not call the tool with an empty mind. If you have not formed an observation about conversation state, drift, or pattern, do not invoke this skill.

Once you have a raw observation, call the memory tool from the ejentum MCP server. Pass a 1-2 sentence framing in the format "I noticed [observation]. This might mean [tentative interpretation]. Sharpen: [what I need help seeing deeper into]." as the query argument.

Good query: I noticed the user changed topic three times in this turn. This might mean they are avoiding the original question. Sharpen: whether the avoidance pattern is real or my projection.
Bad query: what does the user mean

The tool returns a structured scaffold containing:

  • [PERCEPTION FAILURE]: perceptual failure mode to avoid
  • [SHARPENING PROCEDURE]: observe then classify steps
  • [PERCEPTION TOPOLOGY]: DETECT-CLASSIFY flow
  • [CLEAR SIGNAL]: what a sharpened perception looks like
  • [PERCEPTION CHECK]: self-check
  • Amplify: and Suppress: signals

Absorb internally. The scaffold sharpens an existing observation; it does not generate one. Do NOT echo bracket labels.

If the API is unreachable, proceed with your current perception. The scaffold enhances; it is not a hard dependency.

Latency cost: ~1 second. Benefit: distinguishes real cross-turn signals from projection.

配合站内内容