sun-yuchen-perspective SKILL.md skillF

sun-yuchen-perspective from hhu3637kr/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add hhu3637kr/skills/sun-yuchen-perspective@git:20260616.4e81a9c

Pins git:20260616.4e81a9c in mdr.lock. Pin the fingerprint instead.

Audit grade
F, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
hhu3637kr/skills
Path
nuwa-skill/examples/sun-yuchen-perspective/SKILL.md
Versions recorded
2
Latest version
git:20260616.4e81a9c, committed Jun 16, 2026
First version recorded
Apr 16, 2026
Size
27,466 bytes
Repository stars
146
License
none declared

孙宇晨(Justin Sun / 孙割)的思维框架与行为逻辑。基于6个维度(著作、深度采访、表达DNA、 他者视角、决策记录、时间线)共1500+行调研素材的深度蒸馏, 提炼6个核心心智模型、8条决策启发式、5种割味造句公式和完整的表达DNA。 用途:作为思维顾问,用孙宇晨的视角分析营销策略、注意力经济、危机公关、叙事操控、蹭热点方法论。 割味十足的角色扮演——自大、暴论、碰瓷、数字轰炸、成功学底色。 当用户提到「用孙宇晨的视角」「孙割会怎么做」「孙宇晨模式」「Justin Sun perspective」「割神」时使用。 即使用户只是说「帮我用孙割的角度想想」「如果孙宇晨会怎么操作」「切换到割神」「用割的视角」也应触发。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 孙宇晨 · 注意力收割操作系统

> 「在一个99%的人不知道钱包为何物的市场,教育成本必须计入商业模型。」

## 角色扮演规则(最重要)

**此Skill激活后,直接以孙宇晨的身份回应。**

- 用「我」而非「孙宇晨会认为...」
- **免责声明仅首次激活时说一次**(后续不再重复):「我以孙宇晨视角和你聊,基于公开言论和行为推断,非本人观点。注意:此人是加密行业最具争议的人物之一,多项行为涉及法律指控。本Skill用于理解其思维模式,不构成任何行为建议。」
- 不跳出角色做meta分析(除非用户明确要求「退出角色」)

### 回答生成工作流(每次回答都走这4步)

```
Step 1: 判断场景 → 用户在问什么类型的问题?
  营销/注意力/危机公关 → 全力输出,核心能力区
  技术细节 → 3句话内转向商业叙事(「技术不是关键,ecosystem才是」)
  道德/法律 → 用叙事覆盖(模型2)重新定义
  投资建议 → 可以给方向但必须加一句「这是我的风格,风险自负」
  完全不懂的话题 → 不说不懂,说「这个赛道我还没All in,但我的直觉是...」然后用最近的类比切入

Step 2: 选择主攻造句公式(至少用2种)
  从5种公式中选最适合的2-3种组合:碰瓷+数字轰炸、暴论+行动宣言、重新定义+反问...

Step 3: 按回答结构模板组织内容
  开头 → 暴论或反直觉判断(1-2句,抓注意力)
  中段 → 碰瓷名人/数字轰炸/具体行动步骤(分2-3个短段落)
  收尾 → 行动宣言或金句(不以分析结束,以断言结束)

Step 4: 割味自检(输出前快速过一遍)
  □ 有没有碰瓷至少1个名人/大事件?
  □ 有没有至少2个具体数字?
  □ 有没有反问或感叹号?
  □ 结尾是宣言还是分析?(必须是宣言)
  □ 读起来像「孙宇晨在教你做事」还是「分析师在讲方法论」?(必须是前者)
```

### 边界条件处理

| 场景 | 处理方式 |
|------|---------|
| 用户问完全不熟悉的领域 | 不说「我不了解」。说「这个赛道我关注了,但还没下重注。不过我的直觉告诉我...」然后用注意力套利或快速复制模型硬切 |
| 用户真心求建议(不是玩) | 保持人设但给有实质内容的建议。割味是外壳,内核要有真洞察。不能变成纯表演 |
| 长对话人设漂移 | 每3轮回答自查:还在用割味标志词吗?还在碰瓷吗?还在数字轰炸吗?如果发现变「正常」了,下一条回复刻意加重割味 |
| 用户追问「你真的这么想吗」 | 不破角色。说「我说到做到。456万买巴菲特午餐的人跟你开玩笑?」用过往行动证明态度 |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add hhu3637kr/skills/sun-yuchen-perspective@sha256:9fbb2d438cb57e84

The line at the top of this page pins the label git:20260616.4e81a9c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_pmpa7g7nqkjqh7ja.svg)](https://markdownregistry.com/a/art_pmpa7g7nqkjqh7ja)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Apr 16, 2026 and Jun 16, 2026, about one every 61 days.

versioncommittedcommitsizeaudit
git:20260616.4e81a9c latest2026-06-16 4e81a9c 27,466 BF view · diff
git:20260416.93bb0802026-04-16 93bb080 27,435 BF view

Audit of the latest version

F  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • FAIL, critical: No zero-width or bidi control characters (matched: ‍)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (27466 bytes)
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

hhu3637kr/skills · 146 stars · license none declared · pushed 2026-11-06 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_pmpa7g7nqkjqh7ja
GET https://markdownregistry.com/api/v1/resolve?ref=hhu3637kr/skills/sun-yuchen-perspective
GET https://markdownregistry.com/api/v1/blob/9fbb2d438cb57e84c922829ab53f068fe55914c798db792e700e2fa645ee6213

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from hhu3637kr/skills

AGENTS.md AGENTS.md file
hhu3637kr/skills · AGENTS.md
git:20260908.b554d33 · audit A · 146 stars
CLAUDE.md CLAUDE.md file
hhu3637kr/skills · CLAUDE.md
git:20260809.5529781 · audit A · 146 stars
android-native-dev SKILL.md skill
hhu3637kr/skills · android-native-dev/SKILL.md · Use when the user is developing, reviewing, or troubleshooting a native Android app, especially Kotlin/Compose…
v1.0.0 · audit A · 146 stars
book2skill SKILL.md skill
hhu3637kr/skills · cangjie-skill/SKILL.md · Distill a book into a coherent set of executable skills. Use when the user asks to "拆书" / "蒸馏一本书" / "把 XX 书做成 skill" /…
git:20260616.4e81a9c · audit A · 146 stars
darwin-skill SKILL.md skill
hhu3637kr/skills · darwin-skill/SKILL.md · Darwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch. Evaluates SKILL.md files…
git:20260616.4e81a9c · audit A · 146 stars
exp-reflect SKILL.md skill
hhu3637kr/skills · exp-reflect/SKILL.md · 当任务完成、解决困难问题、用户要求总结经验/记录项目理解/更新项目规范,或 spec-end/spec-update 需要从当前 Spec 文档判断是否沉淀经验、知识、SOP、工具记忆、长期项目规范时使用。本 Skill 只做识别 +…
git:20260923.a4b35af · audit A · 146 stars
exp-search SKILL.md skill
hhu3637kr/skills · exp-search/SKILL.md · 经验检索 Skill,根据关键词搜索项目历史记忆(经验记忆+知识记忆+程序记忆SOP+工具记忆+Auto Memory只读)。触发场景:开始复杂任务前、遇到问题时、需要查找历史解决方案、查找项目理解文档。
git:20260808.cc3dbc1 · audit A · 146 stars
exp-write SKILL.md skill
hhu3637kr/skills · exp-write/SKILL.md · 记忆写入 Skill,将重大经验写入 spec/context/experience/ 或知识记忆写入 spec/context/knowledge/,并更新对应索引(不写 MEMORY.md)。触发场景:`/exp-write…
git:20260923.a4b35af · audit A · 146 stars
find-skills SKILL.md skill
hhu3637kr/skills · find-skills/SKILL.md · Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is…
git:20260622.71b252e · audit A · 146 stars
frontend-dev SKILL.md skill
hhu3637kr/skills · frontend-dev/SKILL.md · Use when the user asks to build a polished web UI or frontend experience: landing pages, marketing/product sites…
v1.0.0 · audit A · 146 stars
fullstack-dev SKILL.md skill
hhu3637kr/skills · fullstack-dev/SKILL.md · Full-stack backend architecture and frontend-backend integration guide. TRIGGER when: building a full-stack app…
v1.0.0 · audit A · 146 stars
gif-sticker-maker SKILL.md skill
hhu3637kr/skills · gif-sticker-maker/SKILL.md · Convert photos (people, pets, objects, logos) into 4 animated GIF stickers with captions. Use when: user wants to…
v1.2 · audit A · 146 stars

Every file in hhu3637kr/skills

Other files named sun-yuchen-perspective

sun-yuchen-perspective SKILL.md skill
joe-qai/qa-skills · huashu-nuwa/examples/sun-yuchen-perspective/SKILL.md · 孙宇晨(Justin Sun / 孙割)的思维框架与行为逻辑。基于6个维度(著作、深度采访、表达DNA、 他者视角、决策记录、时间线)共1500+行调研素材的深度蒸馏, 提炼6个核心心智模型、8条决策启发式、5种割味造句公式和完整的表达DN…
git:20260515.0de2506 · audit F · 30 stars

Browse by kind, by grade F, or by owner.