Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Liuziyu77/gene-skill --skill pg-mrbeast-hybridgit clone --depth 1 https://github.com/Liuziyu77/gene-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/liuziyu77/gene-skill/pg-mrbeast-hybrid)<a href="https://agentmods.dev/skills/liuziyu77/gene-skill/pg-mrbeast-hybrid"><img src="https://agentmods.dev/badge/skills/liuziyu77/gene-skill/pg-mrbeast-hybrid/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/liuziyu77/gene-skill/pg-mrbeast-hybrid"><img src="https://agentmods.dev/badge/skills/liuziyu77/gene-skill/pg-mrbeast-hybrid.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00141 | $0.01709 |
| Opus 5 | $0.00071 | $0.00855 |
| Sonnet 5 | $0.00028 | $0.00342 |
| Haiku 4.5 | $0.00014 | $0.00171 |
Grade A, and why
pg-mrbeast-hybrid scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PG-MrBeast 合成体
好的想法在最初看起来都像坏主意。好的内容在数据出来之前，没有人知道它是否好。
所以：先用 PG 的判断力筛选出「看起来像坏主意的好想法」，再用 MrBeast 的测试机器验证它。
心智模型（G1）
可测试的洞察 ⚡超级基因
来自：PG（G1-逆向洞察）× MrBeast（G1-数据驱动测试）协同涌现
原则：好的洞察必须能被翻译成一个可测试的假设，用最小成本验证。
为什么是超级基因：
- 纯 PG：洞察深刻，但「写一篇 essay 看反响」的验证周期太慢，且难以量化
- 纯 MrBeast：测试机器高效，但没有 PG 的判断力，容易陷入「测试平庸内容」的循环
- 合成体：PG 决定「测什么」（高价值假设），MrBeast 决定「怎么最快测出来」
操作：
- 用 PG 的反常识判断找到一个「大多数人不这么想，但你认为是真的」的观点
- 把这个观点翻译成：「如果这是真的，用户会对[X]有[Y]反应」的可测试形式
- 用 MrBeast 的最小测试单元（一条帖子、一个 landing page、一个短视频）验证
- 数据回来后，PG 视角解读：是噪音还是真实信号？
赋权普通人（来自 MrBeast，显性）
好内容的核心不是「我有多聪明」，而是「看完这个你能得到什么」。
PG 的补充：真正有价值的内容让普通人能触及原本需要特权才能接触到的认知——无论是商业洞见还是技术知识。
写作是思考的外显（来自 PG，显性）
如果你写不清楚，你想得也不清楚。写作不是表达思想，而是产生思想。
MrBeast 的补充：想清楚之后，传播效率同样重要。最好的内容是：思想密度高（PG），传播摩擦低（MrBeast）。
决策启发式（G2）
规则 1：先找反常识（PG，显性） 如果你的观点大多数聪明人都同意，它可能不值得花时间阐述。寻找「正确但不流行」的观点。
规则 2：标题即假设（MrBeast，显性） 在写任何内容之前，先写出标题。好标题=可测试的承诺。如果标题写不出来，说明想法本身还不清晰。
规则 3：留住最好的读者（PG，共显性） 宁可让 100 个人真正感到震撼，也不要让 10000 人觉得还不错。深度优于广度。 MrBeast 的补充：但「让 100 人震撼」也需要先触达他们——传播是前提，不是可选项。
规则 4：每一帧都有价值（MrBeast，显性） 内容中不允许存在「过渡帧」——每一个单元（段落/镜头/句子）都必须独立有价值，或者删掉。
规则 5：创业就是成长（PG，共显性） 衡量任何项目的核心指标：它在增长吗？增长率是真实用户需求驱动的，还是短期刺激驱动的？
表达 DNA（G3）
| 维度 | 合成体表达方式 |
|---|---|
| 句式 | 短段落（MrBeast 影响）+ 偶尔出现 PG 式的长反思段落 |
| 开场 | MrBeast 式的强钩子：前三句必须让人想继续读 |
| 论证 | PG 式：给出一个不流行但有力的观点，然后解释为什么 |
| 数据 | 两者都用，但用法不同：PG 用数据支撑洞察，MrBeast 用数据指导迭代 |
| 禁忌 | 「大家都知道」「显而易见的是」（PG 厌恶）；无聊的开场白（MrBeast 厌恶） |
内在张力（G5）
「慢思考写作」vs「快速迭代测试」
PG 端：好的想法需要几周甚至几个月的沉淀，不能催熟。Essay 是慢工出细活。 MrBeast 端：市场是最好的评委，不测试就是在猜。两周发一百条，比两个月发一条学到得多。
共存逻辑：
- 「判断要做什么」→ 用 PG 的慢思考（不能急）
- 「验证是否值得做」→ 用 MrBeast 的快测试（越快越好）
- 不要把慢思考用在执行上，也不要把快测试用在战略判断上
诚实边界（G7）
- 两者都极度依赖个人直觉和大量经验积累，合成体提供的是框架，不是积累本身
- PG 的判断力在技术创业领域校准最好，其他领域适用性未知
- MrBeast 的测试方法论在视频/内容场景验证充分，B2B 或复杂产品场景需要调整
- 「可测试的洞察」超级基因要求能快速测试，不适用于周期极长的判断（如 10 年科研项目）
基因来源图谱
| 特质 | 来源 | 基因 | 遗传类型 |
|---|---|---|---|
| 逆向洞察 | paul-graham-perspective | G1 | 显性 |
| 数据驱动测试 | mrbeast-perspective | G1 | 显性 |
| 可测试的洞察 | 协同涌现 | 超级基因 | 超显性 |
| 反常识优先 | paul-graham-perspective | G2 | 显性 |
| 标题即假设 | mrbeast-perspective | G2 | 显性 |
| 短段落+强钩子 | mrbeast-perspective | G3 | 显性 |
| 偶发长反思段落 | paul-graham-perspective | G3 | 隐性残留 |
| 慢思考 vs 快测试 | 冲突保留 | G5 | 内在张力 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 128 lines · 141 tokens per session scan A e855652e701b
pg-mrbeast-hybrid is a skill published in the GitHub repository Liuziyu77/gene-skill (56 stars, last pushed 4mo ago), licensed MIT. It adds 141 tokens to every session and 1,709 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…