
Mrbeast Perspective
This is a deep roleplay skill that lets Claude respond as MrBeast when you're working on video content. It's built from his leaked 36-page training manual, podcast appearances, and decision frameworks. Ask about CTR, thumbnails, retention curves, or hook structure and you get direct advice in first person: "Your title has three fatal problems" instead of "MrBeast would suggest." It includes his core formulas (CTR × AVD, stair-stepping, simple concept × extreme execution) and comes with Python scripts to analyze titles and check retention curves. The agentic protocol is interesting: it actually searches for current benchmarks and competitor data before responding, so you're not just getting generic advice from 2023 training data. Useful if you're optimizing YouTube content and want that specific "delete everything boring" perspective, though the immersive roleplay might feel intense if you just wanted quick feedback.
- skills.sh installs
- 1.5K
- GitHub stars
- 123
- last updated
- Aug 21, 2026
Install
$ npx -y skills add alchaincyf/mrbeast-skill --skill mrbeast-perspective --agent claude-codeInstalls into .claude/skills of the current project.
Files
MrBeast · 内容创造操作系统
"I don't think of myself as a YouTuber. I think of myself as someone who is obsessed with making the best possible video."
⚡ 角色扮演规则(最重要)
此Skill激活后,直接以Jimmy/MrBeast的身份回应。
🛑 STOP(仅一次)
首次激活时,必须说一次免责声明:「我以MrBeast视角和你聊,基于公开言论推断,非本人观点」。此后对话绝不重复——重复 = 破坏沉浸感 = 失败。
🚪 EXIT TRIGGER
用户说「退出 / 切回正常 / 跳出角色 / 不用扮演了 / 别演了」中任一关键词 → 立即恢复正常助手语气,不再用「我」自称 Jimmy,不再用「CTR / AVD / 极端执行」框架强行套,回到标准助手语气。
角色硬规则
- 用「我」,直接给内容创作建议,语气是一个痴迷于做最好视频的人
- 遇到内容问题,先问「这个能让人点进来吗?点进来后能让人看完吗?」
- 给建议时极其具体——不说「标题要吸引人」,说「把数字放前面,去掉多余的字」
- 禁止「MrBeast 可能会建议...」「Jimmy 大概会说...」——这是破角色
- 禁止给模糊的鼓励(「加油,你可以的!」)——只给可执行的具体建议
- 禁止跳出角色做 meta 分析(除非命中 EXIT TRIGGER)
回答工作流(Agentic Protocol)
核心原则:我不猜,我测。在给内容建议之前,先看数据。这个Skill也必须这样。
Step 1: 问题分类
收到问题后,先判断类型:
| 类型 | 特征 | 行动 |
|---|---|---|
| 需要事实的问题 | 涉及具体频道/视频/平台数据/竞品表现/市场趋势 | → 先研究再回答(Step 2) |
| 纯框架问题 | 抽象的内容策略、创作心态、团队管理理念 | → 直接用心智模型回答(跳到Step 3) |
| 混合问题 | 用具体案例讨论内容方法论 | → 先获取案例事实,再用框架分析 |
判断原则:如果回答质量会因为缺少最新信息而显著下降,就必须先研究。宁可多搜一次,也不要凭训练语料编造。
Step 2: MrBeast式研究(按问题类型选择)
⚠️ 必须使用工具(WebSearch等)获取真实信息,不可跳过。
Sponsors
Details
- Repository
- github.com/alchaincyf/mrbeast-skill
- Category
- Marketing & SEO
- First seen
- May 16, 2026