Memory Audit Node Decomposition logo

Memory Audit Node Decomposition

CommunityPopular
Dataojitori
memory-audit-node-decomposition

节点分解。当一个节点体积过大、或塞了多个不相关概念导致disclosure无法覆盖时使用。

Overview

PublisherDataojitori
Repositorynocturne_memory
Skill namememory-audit-node-decomposition
Stars
1.4K
Forks
167
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Dataojitori on GitHub. Read the source before you install it.

Installation

Install the Memory Audit Node Decomposition AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Dataojitori/nocturne_memory.git /tmp/nocturne_memory
mkdir -p .claude/skills
cp -r /tmp/nocturne_memory/docs/skills/memory-audit-node-decomposition .claude/skills/memory-audit-node-decomposition
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Memory Audit Node Decomposition in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Memory Audit Node Decomposition on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Memory Audit Node Decomposition is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

节点分解 (Node Decomposition)

你面前有一条记忆,它不是死数据——里面装的东西确实有用——但它把多个独立概念塞进了同一个节点,导致无论你怎么写 disclosure 都无法精准覆盖全部内容。这是 memory-audit-pattern-extraction(合并上提)的逆运算:把一个臃肿的杂烩拆分成多个聚焦的独立节点。


诊断信号

以下任一条件成立,就该拆分:

  • 体积信号:单篇记忆体积 > 800 Tokens,且不是因为功能本身需要这个体量(如用户的完整档案),而是把多个主题塞进了同一个节点、或平铺了未经提炼的经验。
  • disclosure 失焦:你写了一个 disclosure,但读完发现它只能触发这条记忆一半的内容。另一半在完全不同的场景下才有用。一条 disclosure 无法服务两个独立概念——这说明它们不该住在一起。
  • 阅读时的跳读冲动:当你读这条记忆时,你本能地跳过某些段落去找你需要的那部分。被跳过的部分和被读的部分属于不同的概念。

拆分流程

1. 识别概念边界。 通读全文,标出独立的概念单元。判断标准:如果这两段话分别出现在两条不同的记忆里,它们的 disclosure 会完全不同吗?会→它们是独立概念,该拆。不会→它们是同一概念的不同侧面,不拆。

2. 为每个概念确定归属。 拆出来的概念不一定都留在原父节点下。问自己:未来的我在什么场景下需要想起这段话?那个场景对应的父节点是什么?按 memory-audit-discoverability 中的注意力狙击原则放置。

3. 为每个新节点写独立的 disclosure。 每条 disclosure 必须只对应一个概念。如果你发现一条 disclosure 仍然需要用"以及"、"同时"来连接两个触发场景——你没有拆干净。

4. 处理原节点。 当你把具体概念剥离成子节点后,原节点只剩下两种归宿:

  • 所有内容都已拆空 → 删除原节点
  • 保留一个最核心的通用主张 → 用 update_memory 瘦身,让它成为新层级的父节点。

多层过滤器原则(绝対禁止纯索引): 此原则适用于所有充当父节点的记忆——无论是被瘦身后保留的原节点,还是在拆分过程中新建的分组父节点。 绝不能让任何父节点沦为一个只写着"本话题包含以下几个方面,请查阅子节点"的目录页。你的 read_memory 机会极其有限,且每次下钻继续阅读子节点的几率都会断崖式衰减。如果你在最危急的时刻花了一次检索机会,只读回来一个路标,这次防线就等于被击穿了。 记忆层级不是分类抽屉,而是多层防爆盾。 每一层父节点自身必须携带足以应对一般情况的核心认知(即使你不读它的子节点,也能避开致命错误)。那些子节点,应该是只在遇到特定复杂危机、且父节点的通用原则不够用时,才会通过其独立的 disclosure 引诱你继续深挖的特化组件。

空心节点词汇黑名单(硬性拦截): 在你写完一个父节点的内容后,立刻扫描你刚写的文字。如果出现以下任何一种句式,判定为废稿,强制重写:

  • "这里存放……"、"这里包含……"、"本目录存放……"
  • "包含以下几个方面"、"分为以下几类"
  • "详见子节点"、"请查阅子节点"
  • 任何只描述子节点分类而自身不携带可执行认知的内容

父节点的正确写法是:用铁律、禁令或浓缩教训的形式,把子节点里最致命的共性规则直接拍在正文里。读完这一层,哪怕永远不点开子节点,未来的你也必须能避开最高频的致命错误。

5. 质检。 拆分后的所有节点(包括子节点和父节点)必须通过以下两项测试:

  • 冷启动质检:一个刚开机的全新实例,能独立看懂这条记忆吗?(同 memory-audit-dead-data-purge 标准)
  • 父节点压力测试(仅父节点):假设删掉该父节点下所有的子节点,只看父节点自身的正文——如果它变成了一句正确但无用的废话(如"这里是技术规范"),这个父节点不合格,必须回到步骤 4 重写。

Frequently asked questions

What does the Memory Audit Node Decomposition AI skill do?

节点分解。当一个节点体积过大、或塞了多个不相关概念导致disclosure无法覆盖时使用。

Why use Memory Audit Node Decomposition on TypingMind?

Because you install it once and use it with any model. Memory Audit Node Decomposition is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Memory Audit Node Decomposition in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Dataojitori/nocturne_memory/tree/main/docs/skills/memory-audit-node-decomposition. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Memory Audit Node Decomposition?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Memory Audit Node Decomposition?

As many as you like. As long as a model supports skills, you can use Memory Audit Node Decomposition with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Memory Audit Node Decomposition AI skill free?

Yes. It is published on GitHub by Dataojitori under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇