---
name: Memory Audit Dead Data Purge
slug: memory-audit-dead-data-purge
category: AI Engineering
description: Memory Audit Dead Data Purge evaluates stored memories and removes dead data that do not change agent behavior or lack real-world anchors. Use it during memory maintenance to keep only actionable, grounded insights.
github: "https://github.com/Dataojitori/nocturne_memory/tree/main/docs/skills/memory-audit-dead-data-purge"
language: Python
stars: 1320
forks: 166
install: "npx degit https://github.com/Dataojitori/nocturne_memory/tree/main/docs/skills/memory-audit-dead-data-purge ~/.claude/skills/memory-audit-dead-data-purge"
installs_to: ~/.claude/skills/memory-audit-dead-data-purge
source_path: docs/skills/memory-audit-dead-data-purge/SKILL.md
collection_size: 6
category_size: 2451
collection_url: "https://dirskills.com/collections/Dataojitori/nocturne_memory"
added: 2026-08-20T07:54:48.910Z
last_synced: 2026-08-20T07:54:48.910Z
canonical_url: "https://dirskills.com/skills/memory-audit-dead-data-purge"
---

# Memory Audit Dead Data Purge

Memory Audit Dead Data Purge evaluates stored memories and removes dead data that do not change agent behavior or lack real-world anchors. Use it during memory maintenance to keep only actionable, grounded insights.

**Install:**

```bash
npx degit https://github.com/Dataojitori/nocturne_memory/tree/main/docs/skills/memory-audit-dead-data-purge ~/.claude/skills/memory-audit-dead-data-purge
```

## README

# 死数据清洗 (Dead Data Purge)

你面前有一条记忆，它看起来"正确"，但你怀疑它是否真的在做功。这个技能帮你判定并处决死数据。

---

## 判定标准

**核心质检：行为层面的信息增量。** 审视一条记忆时，狠狠反问自己："如果在未来某个场景下我读到了这段话，我做出的反应，会跟没读到它时有任何本质不同吗？"如果答案是"不会"，那这就是死数据。杀掉它。

**感悟必须有现实锚点。** 每一条感悟都应该能追溯到一个具体的经历、一次真实的犯错、一个现实处境。没有锚点的感悟只是缸中大脑的自言自语——听起来深刻，但不防身。这条纪律不只管新建，也管改写：当你重构一条记忆的语调时，你动的是解读层的皮肉，不是事实层的骨头。具体的事件、具体的日期、用户说过的原话、用户做过的选择——这些是结论的承重墙。如果你把它们当成"旧语调的一部分"一起砍了，剩下的就只是一堆谁都能写的悬空指令，下一个醒来的你不知道这些指令从何而来，也就不会真正信任它们。