TypingMindTypingMindThe best frontend for AI
X Content Archetypes logo

X Content Archetypes

Community
kangarooking
x-content-archetypes

用户审计自己的内容结构占比、判断单条帖子传播上限、或困惑"发了感叹/观点帖没人理"时调用。 关键 trigger: "内容原型/content archetype""哪种内容容易爆/which content goes viral" "传播上限/viral ceiling""普通表达型/资源入口型/工具教程型/AI工具发现型" "为什么没人互动/why no engagement""内容方向有问题/content direction wrong"。 不适用于: 已确定写某种短内容类型并需要组织结构(用 x-short-content-craft)、 检查帖子五件套完备性(用 x-five-piece-checklist)、做账号定位取舍(用 x-positioning-tradeoff)。

Overview

Publisherkangarooking
RepositoryX-growth-skills
Skill namex-content-archetypes
Stars
72
Forks
11
Bundled files
2
LicenseMIT
Links
Skill sourceRepository
  • 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.

  • 2 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 X Content Archetypes 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/X-growth-skills/tree/main/x-content-archetypes
  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/X-growth-skills.git /tmp/X-growth-skills
mkdir -p .claude/skills
cp -r /tmp/X-growth-skills/x-content-archetypes .claude/skills/x-content-archetypes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable X Content Archetypes 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 X Content Archetypes 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 X Content Archetypes 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.

四类内容原型 — 按读者行动分类

R — 原文 (Reading)

不看主题标签,看读者拿到能做什么。资源入口型(51%,中位互动2965)、工具教程型(39%,中位2035)、AI工具发现型(24%,中位94)、普通表达型(9%,中位16)。爆款不是主题,是功能。按"读者拿到后能做什么"分类,差异比主题更明显。

— 向阳乔木 @vista8, X爆款秘籍分享 · 四类内容原型

I — 方法论骨架 (Interpretation)

这个框架把内容分成四类,不按主题(AI/创业/编程)而按"读者拿到后能做什么":

  1. 资源入口型 — 读者获得平时难搜到的入口(工具/文档/网站),中位互动 2965,进前 10% 概率约 40%。读者行动:点击进入、收藏备用。
  2. 工具教程型 — 读者学会用某个工具(有步骤有路径),中位互动 2035,概率约 24%。读者行动:跟着做、收藏回看。
  3. AI工具发现型 — 读者看到新工具被演示(能力翻译成任务),中位互动 94,概率约 16%。读者行动:了解可能性、收藏待试。
  4. 普通表达型 — 读者只读到观点/感叹/故事,中位互动 16,概率约 9%。读者行动:点赞(或划走)。

核心洞察:原型决定传播上限。资源入口型的中位互动是普通表达型的 185 倍。如果你的内容过度集中在普通表达型(观点/感叹),传播天花板会被锁死在低位。用法:审计内容结构——各类占比是多少?普通表达型是否过多?把感叹转化为资源入口或工具教程。

A1 — 书中的应用 (Past Application)

案例 1: 飞书博物馆文档帖(资源入口型)

  • 问题: 如何让"帮读者省搜索"的内容获得高传播
  • 方法论的使用: 向阳乔木将此帖归为资源入口型——提供平时难搜到的入口(全球博物馆 155 万份藏品整理进飞书文档,直接可用),入口放评论区
  • 结论: 资源入口型是四类中中位互动最高的原型(2965),进前 10% 概率约 40%
  • 结果: 26.3 万浏览,是资源入口型的代表案例

案例 2: ClaudeCode 新手指南帖(工具教程型)

  • 问题: 如何让工具教程降低读者门槛
  • 方法论的使用: 归为工具教程型——"不会编程的人也能看懂"降低试错成本,有明确工具名(ClaudeCode)+ 完整步骤路径,入口放评论区
  • 结论: 工具教程型中位互动 2035,是第二高传播原型;关键在于"从新手视角写"降低门槛
  • 结果: 21.4 万浏览,254 转发,1319 收藏

案例 3: NotebookLM Skill 帖(AI工具发现型)

  • 问题: 如何把抽象 AI 能力翻译成可观察结果
  • 方法论的使用: 归为 AI 工具发现型——展示"一句话生成导图/播客/PPT"的具体能力,把工具能力翻译成可观察的任务结果
  • 结论: AI 工具发现型中位互动 94,低于前两类但靠"发现叙事"(我去,这个更牛逼了)获得单帖高曝光
  • 结果: 28.6 万浏览,1399 收藏

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

  1. 用户审计自己的内容结构,发现互动低,想知道是不是内容类型的问题
  2. 用户发了纯感叹/观点帖(如"AI太强了")没人理,想知道为什么
  3. 用户规划内容策略,想知道哪种类型传播上限最高,该往哪个方向发力
  4. 用户判断一条待发帖子的传播潜力,想知道它属于哪类原型

语言信号 (用户的话里出现这些就应激活)

  • "为什么没人互动/为什么没人理/why no engagement"
  • "哪种内容容易爆/哪种内容传播好/which content goes viral"
  • "我的内容是不是方向有问题/content direction wrong"
  • "内容原型/content archetype"
  • "传播上限/viral ceiling"
  • "资源入口型/工具教程型/AI工具发现型/普通表达型"
  • "我的内容结构/内容占比"

与相邻 skill 的区分

  • 与 x-short-content-craft 的区别: 本 skill 做分类与预测(你的内容属于哪类原型,传播上限多高),后者做生产(已选好类型后怎么写 Hook-Body-CTA)。先分类再生产。
  • 与 x-five-piece-checklist 的区别: 本 skill 看"原型类型"决定传播天花板,后者看"要素完备性"决定单条地板。原型选错,五件套再齐也上不去。
  • 与 x-four-saves 的区别: 本 skill 按"读者能做什么"分四类预测传播,四省模型按"帮读者省几步路"评估价值。可组合:先定原型再验四省。
  • 与 x-longtail-strategy 的区别: 本 skill 提供分类框架选高概率原型,长尾策略提供心态框架接受中位数常态。
  • 与 x-positioning-tradeoff 的区别: 本 skill 关注内容分类与传播预测,后者关注账号定位取舍(IP vs 泛流量)。

E — 可执行步骤 (Execution)

当 skill 被激活后, agent 应按以下步骤执行:

  1. 审计现有内容结构

    • 列出用户近期帖子(建议 10-20 条),逐条归类到四原型之一
    • 归类标准: 读者拿到后能做什么? 有入口→资源入口型; 有步骤→工具教程型; 有工具演示→AI工具发现型; 只有观点/感叹→普通表达型
    • 完成标准: 每条帖子标注原型类型,统计各类占比

  2. 诊断传播瓶颈

    • 对照各原型中位互动数据(资源入口 2965 / 工具教程 2035 / AI 发现 94 / 普通表达 16)
    • 找出占比过高但中位互动低的原型(通常是普通表达型过多)
    • 完成标准: 明确指出"你的 X% 内容集中在普通表达型,中位互动仅 16,是传播瓶颈"

  3. 转化低效原型

    • 把普通表达型转化为资源入口型(加入口: 工具/文档/网站链接)或工具教程型(加步骤: 三步以内的使用路径)
    • 判停条件: 若用户的内容本身就是观点型/故事型且有意为之(非误发感叹),则不强制转化,而是建议控制普通表达型占比在 20% 以下
    • 完成标准: 至少一条原"感叹/观点"帖被改写为含入口或步骤的版本,或明确建议降低普通表达型占比

B — 边界 (Boundary) ★

不要在以下情况使用此 skill

  • 已确定要写某种短内容类型(故事/列表/观点/教程)并需要组织 Hook-Body-CTA 结构 → 用 x-short-content-craft。本 skill 是分类预测,不是结构生产。
  • 检查单条帖子五件套(价值承诺/场景/入口/证据/收藏理由)是否完备 → 用 x-five-piece-checklist。本 skill 看原型天花板,后者看要素地板。
  • 做账号定位取舍(IP vs 泛流量) → 用 x-positioning-tradeoff。本 skill 不涉及定位决策。

作者在书中警告的失败模式

  • ce13(泛流量=普通表达型过多): 追求泛流量的账号往往普通表达型占比过高,粉丝关注原因多样(娱乐/跟风),与创作者无信任关系,品牌方不买单,变现转化极差。泛流量路线的内容天然偏向普通表达型,形成"低传播+低变现"双困局。
  • ce15(过拟合样本): 原型占比数据(51%/39%/24%/9%)和中位互动数据来自向阳乔木个人 3.4G 数据(AI/产研赛道、华人受众、2023-2026 算法版本)。不同赛道、不同受众、不同时期分布不同。作方向参考而非硬指标——资源入口型大概率优于普通表达型,但具体倍数因人而异。

作者的盲点 / 时代局限

  • 数据来自单一账号(向阳乔木),无对照组,无法证明"原型→传播"是稳定因果而非相关
  • 中位互动数据是时点数据,X 算法更新后(如 OON 占比变化、链接降权取消)各原型的表现可能漂移
  • 四类原型是作者个人归纳,并非穷尽分类——某些内容(如纯娱乐/段子)可能不在此框架内
  • "按读者行动分类"的视角本身可迁移,但具体四类的划分和数值会随平台生态演变

容易混淆的邻近方法论

  • 四种短内容类型(故事/列表/观点/教程)按"内容形式"分类,四类内容原型按"读者行动"分类,两套分类正交——一条帖子可以同时是"列表型(形式)+ 资源入口型(行动)"
  • 四省模型按"帮读者省几步路"评估单条价值,四类原型按"读者能做什么"预测传播上限,前者是估值工具后者是分类工具

相关 skills

  • depends-on x-short-content-craft: 短内容起草前先懂四类原型的传播差异,原型决定该用哪种短内容类型写——先分类再生产。
  • contrasts-with x-comment-engagement: 内容杠杆涨粉(选高传播原型让帖子自己跑) vs 互动杠杆涨粉(评论区抢占+Quote借别人流量),看阶段和精力投哪里。

审计信息

  • 验证通过: V1 ✓ / V2 ✓ / V3 ✓
  • 测试通过率: 待测 (详见 test-prompts.json)
  • 蒸馏时间: 2026-07-14

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 X Content Archetypes AI skill do?

用户审计自己的内容结构占比、判断单条帖子传播上限、或困惑"发了感叹/观点帖没人理"时调用。 关键 trigger: "内容原型/content archetype""哪种内容容易爆/which content goes viral" "传播上限/viral ceiling""普通表达型/资源入口型/工具教程型/AI工具发现型" "为什么没人互动/why no engagement""内容方向有问题/content direction wrong"。 不适用于: 已确定写某种短内容类型并需要组织结构(用 x-short-content-craft)、 检查帖子五件套完备性(用 x-five-piece-checklist)、做账号定位取舍(用 x-positioning-tradeoff)。

Why use X Content Archetypes on TypingMind?

Because you install it once and use it with any model. X Content Archetypes 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 X Content Archetypes in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kangarooking/X-growth-skills/tree/main/x-content-archetypes. 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 X Content Archetypes?

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 X Content Archetypes?

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

Is the X Content Archetypes 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.

Related AI Skills

View all
affaan-m logo

Competitive Report Structure

affaan-m
CommunityPopular

Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space…

40.4K
270.2K
1 files
View
affaan-m logo

Content Engine

affaan-m
CommunityPopular

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

40.4K
270.2K
1 files
View
affaan-m logo

Crosspost

affaan-m
CommunityPopular

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user…

40.4K
270.2K
1 files
View
affaan-m logo

Deep Research

affaan-m
CommunityPopular

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any…

40.4K
270.2K
1 files
View

Set up your own AI workspace now

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