Dialysis Prism logo

Dialysis Prism

Community
kangarooking
dialysis-prism

用"透析三棱镜"框架穿透问题表象找到本质原因,通过校准目标B、重构方法A、消除变量C三步解决反复出现的顽固问题。适用于面对同一个问题反复出现、用了各种方法都治不好的场景,以及需要精准定义问题后再解决的分析型场景。当你发现"打补丁式"的解决方案无效时使用此skill。不适用于全新领域没有历史方法可回溯的场景,也不适用于纯不确定性事件(那是概率域/风险域,应使用mirror-world)。关键触发信号:"这个问题怎么又出现了"、"为什么总是解决不了"、"试了好多方法都没用"、"问题的根源到底是什么"。

Overview

Publisherkangarooking
Repositorycognitive-dividend-skill
Skill namedialysis-prism
Stars
54
Forks
13
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Dialysis Prism 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.
    https://github.com/kangarooking/cognitive-dividend-skill/tree/main/dialysis-prism
  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/kangarooking/cognitive-dividend-skill.git /tmp/cognitive-dividend-skill
mkdir -p .claude/skills
cp -r /tmp/cognitive-dividend-skill/dialysis-prism .claude/skills/dialysis-prism
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dialysis Prism 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 Dialysis Prism 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 Dialysis Prism 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.

透析三棱镜

R — 原文 (Reading)

"问题"就是:期望与现状的落差部分。假设某件事的期望值是B,现状是B′,那么这个落差部分(B′→B),就是问题。……要解决这个问题,不能盯着B′→B看,而是要透过B′去看ABC,我称之为"透析三棱镜"。……第一步,校准目标B:目标要符合SMART原则,同时要避免把手段当成目标。第二步,重构方法A:想要改变现状,不是从现状出发添加一个新的解决方案,而是要回过头,重构原来的方法系统。第三步,消除变量C:通过"象、数、理"这个基本框架来寻找它,并通过5Why的提问方法,挖掘真正的原因。 —— 第17章《透析三棱镜》

I — 方法论骨架 (Interpretation)

  1. 问题的定义:问题 = 期望(B) - 现状(B')。找不到落差就找不到问题,"没有问题"往往是不知道目标也不知道现状
  2. 表面问题是症状B'→B,本质原因藏在ABC三个因素中:A(方法)、B(目标)、C(变量)
  3. 三棱镜B(校准目标):首先检查目标本身是否正确。常见错误——目标模糊(如"幸福"无法衡量)、把手段当目标(如"赚到100万"可能是手段不是目标)
  4. 三棱镜A(重构方法):现状B'是由原有方法A导致的。治标是再找一条从B'到B的新路径;治本是重构原来的方法系统本身
  5. 三棱镜C(消除变量):如果A和B都没问题但B'依然存在,一定有隐藏变量C。用"象数理"框架找:现象→数据→道理。用5Why连续追问挖掘根因
  6. 关键原则:不要给建议太早——"我们太喜欢给建议,却往往还没弄清楚问题到底是什么"
  7. 方法论的本质区别:洋务运动是在旧系统上打补丁(治标),明治维新是重构整个系统(治本)

A1 — 书中应用 (Past Application)

  • 洋务运动 vs 明治维新:清政府在封建体制不变的前提下只学西方技术(在旧方法A上打补丁),最终失败;日本同时改革体制和技术(重构整个方法A),一举跻身列强——同样的问题,治标vs治本的天壤之别
  • 世界杯期间的工厂产能下降:现象是产能下降(象),数据是夜班次品率飙升3倍(数),用5Why追问发现:工人熬夜看球→精神差→操作失误→次品增加(理)。改善行动落在"自己可以改变的事":禁止携带手机进工厂
  • 投诉率上升分析:不用"我感觉投诉多了"这种主观表述,而是用数据——"上月2‰ vs 本月6.7‰,提高3倍",从感性认知转为理性分析
  • "幸福"作为目标的错误:幸福无法衡量→找不到落差→连问题是什么都不知道→无法开始解决

A2 — 触发场景 (Future Trigger)

何时使用:

  • 同一个问题反复出现,每次"解决"后过段时间又冒出来
  • 试了多种解决方案都无效,开始怀疑是不是问题定义本身有误
  • 需要做根因分析(复盘、事故调查、绩效改进)
  • 制定改进计划时,想确保抓住的是本质而非表象
  • 团队讨论陷入"头痛医头脚痛医脚"的循环

语言信号:

  • "这个问题怎么又出现了?"
  • "为什么总是解决不了?"
  • "试了好多方法都没用"
  • "问题的根源到底是什么?"
  • "到底是哪里出了问题?"
  • "我们是不是一直在治标不治本?"

与相邻skill区分:

  • vs. brain-unseal:大脑封印是恢复大脑运转能力的前置步骤,透析三棱镜是大脑运转起来之后的问题分析工具。顺序:先解封印 → 再用三棱镜
  • vs. structured-thinking:结构化思维是拆解和分类的工具,透析三棱镜是穿透表象找根因的工具。可以先用结构化把要素拆全,再用三棱镜逐一排查
  • vs. mirror-world:三棱镜适用于确定性问题(可以找到ABC),镜像世界适用于不确定性问题(ABC本身不可控)

E — 可执行步骤 (Execution)

步骤1:校准目标B——先确认问题定义是否正确

  • 写下你当前面对的问题,用"B - B' = 问题"的格式表述:期望是什么(B)?现状是什么(B')?落差在哪里?
  • 检查目标B是否符合SMART原则:具体的(S)、可衡量的(M)、可达成的(A)、相关的(R)、有时限的(T)
  • 检查是否把"手段"当成了"目标":问自己"实现B之后我会得到什么?"如果答案才是真正的目标,那就替换B
  • 完成标准:目标B可以用一个具体的数字或明确的可验证状态来表述,且不是中间手段而是最终目的

步骤2:重构方法A——回溯现有系统,而非打补丁

  • 梳理导致当前现状B'的原有方法A包含哪些环节(人、流程、工具、规则)
  • 不要从B'出发新加一个解决方案,而是回到A本身,问"原有方法中的哪个环节导致了B'偏离B?"
  • 对该环节做系统重构而非增量修补:是替换而非叠加
  • 完成标准:能画出"重构前的方法A"和"重构后的方法A'"的对比图,且A'不是在A上叠加补丁,而是改变了一个核心环节

步骤3:消除变量C——用象数理+5Why找到隐藏变量

  • 如果A重构后问题仍在,启动变量排查:
    • 象(现象):具体观察到的异常表现是什么?列出所有异常现象
    • 数(数据):找到量化数据来替代"我感觉"——数据是什么?变动幅度多大?
    • 理(道理):数据变动的背后原因是什么?用5Why连续追问至少5层,直到找到你可以改变的根因
  • 把改善行动落在"自己可以改变的事情上",而不是外部不可控因素
  • 完成标准:产出一份数据化的问题分析报告(现象→数据→5Why链条→根因→可执行的改善行动),且改善行动100%在自己可控范围内

B — 边界 (Boundary)

不要用的场景:

  • 全新领域没有历史方法A可回溯——无旧方法可重构,需要从零设计
  • 纯不确定性事件(股市暴跌、突发灾害)——ABC模型不适用,应切换到mirror-world的四域策略
  • 紧急事故需要立即行动——来不及做深度分析,先止血再复盘
  • 问题本身足够简单,一眼就能看到原因——过度分析浪费时间

失败模式:

  • 跳过B直接找A:目标本身就错了,后面所有分析都是在错误的基础上空转
  • 在A上打补丁而非重构:每次出问题就加一条规则/流程,系统越来越臃肿但问题依然存在
  • 5Why停在第一层:如"产能下降→工人失误→完",没有追问为什么工人会失误
  • 找到根因但不可控:如"因为世界杯在举行"——分析正确但无法行动,等于白分析
  • 用"我感觉"代替数据:没有量化分析,三棱镜就退化为拍脑袋

作者盲点:

  • 对"如何判断问题该从B、A还是C开始排查"缺乏优先级指导,实际操作中三个方向都可能,需要大量时间和资源逐一排查
  • 5Why方法依赖提问者的经验,同一现象不同人可能问出完全不同的因果链——没有校准机制
  • "重构方法A"在实践中可能涉及组织架构调整、利益重新分配等复杂因素,远比书中描述的困难
  • 象数理框架来自《易经》但被简化为"现象→数据→道理",实际分析中"理"的确定往往需要领域专业知识支撑

相关 skills

本 skill 与以下 skill 存在关联:

  • structured-thinking(前置依赖):透析三棱镜的分析过程(校准B、重构A、消除C)需要结构化思维作为基础工具,先用MECE原则把问题要素拆全,再用三棱镜逐一排查根因。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Dialysis Prism AI skill do?

用"透析三棱镜"框架穿透问题表象找到本质原因,通过校准目标B、重构方法A、消除变量C三步解决反复出现的顽固问题。适用于面对同一个问题反复出现、用了各种方法都治不好的场景,以及需要精准定义问题后再解决的分析型场景。当你发现"打补丁式"的解决方案无效时使用此skill。不适用于全新领域没有历史方法可回溯的场景,也不适用于纯不确定性事件(那是概率域/风险域,应使用mirror-world)。关键触发信号:"这个问题怎么又出现了"、"为什么总是解决不了"、"试了好多方法都没用"、"问题的根源到底是什么"。

Why use Dialysis Prism on TypingMind?

Because you install it once and use it with any model. Dialysis Prism 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 Dialysis Prism in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kangarooking/cognitive-dividend-skill/tree/main/dialysis-prism. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Dialysis Prism?

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 Dialysis Prism?

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

Is the Dialysis Prism AI skill free?

Yes. It is published on GitHub by kangarooking 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 👇