Cognitive Contrast logo

Cognitive Contrast

Community
kangarooking
cognitive-contrast

当用户需要放大产品相对于竞品的优势时,调用此 skill。核心操作是先描述竞品差+利益少,再描述自己好+利益大,利用心理学对比原理制造心理落差。特别适用于成熟品类中"在某些方面更好"的产品。不适用于全新品类(没有竞品可对比)、也不适用于品牌形象广告(对比显得格局低)。关键触发信号:用户提到"产品比竞品好但读者感知不到""怎么突出差异化优势""卖点太平淡想放大效果"。

Overview

Publisherkangarooking
Repositoryviral-copywriting-skill
Skill namecognitive-contrast
Stars
80
Forks
12
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 Cognitive Contrast 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/viral-copywriting-skill/tree/main/cognitive-contrast
  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/viral-copywriting-skill.git /tmp/viral-copywriting-skill
mkdir -p .claude/skills
cp -r /tmp/viral-copywriting-skill/cognitive-contrast .claude/skills/cognitive-contrast
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cognitive Contrast 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 Cognitive Contrast 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 Cognitive Contrast 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.

认知对比写作法

R — 原文 (Reading)

我们先指出竞品的差,再展示我们产品的好,我们的产品就会显得格外好!1.描述竞品:产品差+利益少。2.描述我们:产品好+利益大。批评竞品时要有理有据,不能乱骂。

— 关健明, 第一章 1.3 认知对比


I — 方法论骨架 (Interpretation)

认知对比写作法利用心理学"对比原理"——当两件东西差异大时,人们会认为差异比实际的更大。操作分两步:

第一步"描述竞品":指出竞品/旧方案在设计和功能上的具体缺点(产品差),以及给消费者带来的不好体验(利益少)。批评必须"有理有据",基于可验证的事实,而非恶意贬低或空洞的"竞品很差"。

第二步"描述自己":展示自己的产品在对应方面的优势(产品好),以及给消费者带来的更大好处(利益大)。自己的优势必须精确对应竞品的缺点——竞品差在哪里,自己就好在哪里,形成一一对应的对比关系。

四个组件(竞品差、利益少、自己好、利益大)缺一不可:只说竞品差不说是自己好,是抱怨不是对比;只说自己好不说竞品差,是自夸不是对比。自夸之所以"平淡无奇",是因为没有参照物——读者无法判断"更静音"是好还是不好,直到你告诉他竞品有多吵。

关键约束:批评竞品时不能乱骂,否则引起读者反感。对比的目的是放大自己的优势,而非贬低对手。适用于成熟品类中"在某些方面更好"的产品。全新品类没有竞品可对比,不适合用此方法。


A1 — 书中的应用 (Past Application)

案例 1: HeyJuice冷榨果汁(工艺对比)

  • 问题: 冷榨果汁需要让读者理解HPP超高压灭菌和传统高温灭菌的本质区别,但技术术语读者看不懂。
  • 方法论的使用: 描述竞品差——传统高温灭菌"烫死"细菌的同时也破坏了维生素B1、C、B12、叶酸,"鲜果汁进去,熟果汤出来"。描述自己好——HPP超高压灭菌"压死"细菌,多元酚100%保留,维生素C保留85%(高温只有40%)。把技术对比翻译成"鲜果汁vs熟果汤"的直觉对比。
  • 结论: "鲜果汁进去,熟果汤出来"是认知对比的典范——把工艺差异翻译成任何人都能秒懂的利益差异。
  • 结果: 读者反应强烈,大量自发传播。"难怪超市果汁那么难喝""以后再也不买果汤了"。

案例 2: 棉柔巾(使用体验对比)

  • 问题: 棉柔巾作为新产品,读者不理解为什么要从毛巾换到棉柔巾。
  • 方法论的使用: 描述竞品差——南方气候潮湿,毛巾不易干、会发臭、滋生螨虫,对皮肤二次污染、毛孔变大,浪费了昂贵的护肤品(产品差+利益少)。描述自己好——棉柔巾用完即弃,每一片崭新,对皮肤0污染(产品好+利益大)。竞品差的描写击中了潮湿地区女性的真实痛点。
  • 结论: 把"螨虫""毛孔变大""浪费护肤品"串联成一条完整的"损失链",让读者感到换掉的代价远大于保持现状。
  • 结果: 由毕业仅两年的文案新人撰写,ROI达到惊人的1:7(投1元广告费赚7元营业额)。

案例 3: 灭蚊灯(感官化对比)

  • 问题: 灭蚊灯功能"采用轴承风扇,更静音,实测仅40分贝"——读者对40分贝无感,觉得"更静音"平淡无奇。
  • 方法论的使用: 描述竞品差——普通灭蚊灯用廉价风扇,嗡嗡响,放在卧室吵得睡不好(产品差+利益少)。描述自己好——轴承风扇,40分贝,最大噪音来自电子钟(产品好+利益大)。用"电子钟的声音"把40分贝翻译成了具体的感官体验。
  • 结论: 认知对比的"利益"部分必须具体可感,"更静音"是抽象自夸,"最大噪音来自电子钟"是可感知的对比。
  • 结果: 作者指出单纯自夸"感觉太平淡",加入对比后产品优势被显著放大。

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

  1. 用户的产品在成熟品类中"某些方面更好",但读者感知不到差异——需要通过对比放大优势。
  2. 用户的卖点写成"更X""比X好",读者觉得"听起来还行但也没什么了不起"——需要具体对比参照物。
  3. 用户的产品功能参数优于竞品,但技术术语读者看不懂——需要把参数差异翻译成体验差异。

语言信号

  • "产品比竞品好但读者感知不到"
  • "怎么突出差异化优势"
  • "卖点太平淡想放大效果"
  • "参数比竞品好但不会表达"
  • "读者觉得我和竞品差不多"

与相邻 skill 的区分

  • 与 fear-appeal 的区别: 认知对比制造的是"选谁"的判断(竞品vs我),恐惧诉求制造的是"解不解决"的紧迫(不解决会怎样)。两者经常组合使用——先用恐惧诉求放大痛点,再用认知对比展示为什么选我。
  • 与 fact-proof 的区别: 事实证明用数据和实验证明自己的性能("生鸡蛋压入床垫不破"),认知对比用参照物放大自己的优势("竞品差→我好")。事实证明回答"真的能做到吗",认知对比回答"为什么选你而不是别人"。

E — 可执行步骤 (Execution)

  1. 锁定对比维度

    • 操作:找出产品相对于竞品/旧方案最突出的优势维度(如噪音、营养保留率、体积、价格等)。选择读者最关心的1-3个维度,不要面面俱到。
    • 完成标准:选定维度既能展示产品最大优势,又是读者决策的关键因素。
  2. 描写竞品的差和利益少

    • 操作:描述竞品/旧方案在选定维度上的具体缺点——要写具体事实而非泛泛的"不好"。如不说"高温灭菌不好",而说"鲜果汁进去,熟果汤出来"。批评必须有理有据,不能恶意贬低。
    • 完成标准:竞品的缺点描述是可验证的具体事实,且读者能直接感知到"利益少"对自己意味着什么。
  3. 描写自己的好和利益大

    • 操作:精确对应竞品缺点,展示自己在同一维度上的优势,以及这个优势给消费者带来的具体好处。优势描述也要具体——不说"更静音",而说"最大噪音来自电子钟"。
    • 完成标准:自己的优势和利益与竞品的缺点形成一一对应关系,读者能清晰感知"选我比选竞品多获得了什么"。
  4. 检查对比的公正性和力度

    • 操作:确认(1)批评竞品是基于事实而非恶意攻击;(2)技术术语已翻译成读者可感知的体验语言;(3)对比前后的落差足够大,制造了明显的心理冲击。
    • 完成标准:读者看完对比后产生"差距真大"的感觉,而非"差不多"或"你在贬低别人"。

B — 边界 (Boundary) ★

不要在以下情况使用此 skill

  • 全新品类(没有竞品可对比)——读者对品类本身没有认知基础,对比无从展开。应先用感官占领或使用场景帮助读者建立品类认知。
  • 品牌形象广告——对比显得格局低,暗示你的品牌需要靠踩别人来凸显自己。
  • 2B场景中直接点名竞品——可能引发法律纠纷或商业关系问题,应改为对比"传统方案"而非具体竞品。

作者在书中警告的失败模式

  • 单纯自夸平淡无奇:直接陈述"更静音""更有营养""更柔和",没有对比参照物,读者无法感知"更"的程度(ce04)。
  • 技术名词写成"天书":把"上下双层发热管,360度立体加热"直接搬进文案,读者看不懂也不想了解(ce16)。必须翻译成日常可感知的利益。
  • 只说产品差不链接到利益少:罗列竞品的技术缺陷但不说明"这对消费者意味着什么",读者觉得"这跟我有什么关系"。

作者的盲点 / 时代局限

  • 没有讨论"竞品也在进步"的动态场景——当竞品也在快速迭代时,认知对比的内容很快过时。
  • 没有讨论"对比公正性"的边界——有些对比虽然基于事实,但选择了对竞品最不利的维度,本质上是不公平的比较,可能引发消费者反感或法律风险。
  • 案例全是实体产品,对服务类产品(如SaaS、咨询)的对比写法缺乏示范——服务对比的核心是"决策过程透明度"和"服务过程可控感",而非物理参数。

相关 skills (阶段 3 填充)

  • depends-on: copywriting-four-step-system
  • contrasts-with: fear-appeal
  • composes-with: sensory-occupation

审计信息

  • 验证通过: V1 (跨域验证) / V2 (预测力) / V3 (独特性) 均通过
  • 测试通过率: 待测
  • 蒸馏时间: 2026-05-02

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 Cognitive Contrast AI skill do?

当用户需要放大产品相对于竞品的优势时,调用此 skill。核心操作是先描述竞品差+利益少,再描述自己好+利益大,利用心理学对比原理制造心理落差。特别适用于成熟品类中"在某些方面更好"的产品。不适用于全新品类(没有竞品可对比)、也不适用于品牌形象广告(对比显得格局低)。关键触发信号:用户提到"产品比竞品好但读者感知不到""怎么突出差异化优势""卖点太平淡想放大效果"。

Why use Cognitive Contrast on TypingMind?

Because you install it once and use it with any model. Cognitive Contrast 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 Cognitive Contrast in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kangarooking/viral-copywriting-skill/tree/main/cognitive-contrast. 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 Cognitive Contrast?

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 Cognitive Contrast?

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

Is the Cognitive Contrast 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 👇