浪浪

🌊

[金尘马 @jinchenma_ai]

总���了最近 X 上爆火的 26 个 SKILL。

一切的起源都是那个“同事.SKILL”吧😂

一、职场、自媒体系列：
1. 同事.skill 把真实同事蒸馏成AI（SKILL流火爆起点）。
https://t.co/rlBnUqKvEI
2. 女娲.skill 能自动蒸馏任何人的终极工具（想蒸谁蒸谁）。
https://t.co/Z4pIOutlmI
3. X导师.skill（X/Twitter运营导师） 最新迭代，能分析你的账号数据、写推文、给诊断报告。
https://t.co/pIIYkEltNL
4. 老板.skill 把老板炼入token，把生产力的解放留给自己。
https://t.co/7cSVAmkTqw
5. 前任.skill 把前任蒸馏成 AI Skill，用ta的方式跟你说话。
https://t.co/2SvAj4HBKi
6. 自己.skill 把你自己蒸馏成AI，数字永生/第二大脑。
https://t.co/4GZB8Tzxc2
7. 博主.skill 把公开社交媒体语料整理成一个能对话、能分析、能改写风格的 Persona Skill（目前支持推特和小红书）。
https://t.co/WOheukU9UH
8. 蒸馏.skill（人格蒸馏引擎） 人格蒸馏引擎 · 蒸馏自己看清自己，蒸馏亲友留住余温与回声。
https://t.co/dSzv8JfsR2
9. 反蒸馏.skill 公司让你写Skill文档���“投毒”，核心知识自己留着（打工人自保神器）。
https://t.co/hFoUVNpIe0

二、名人系列
10. 乔布斯.skill 思维模型 + 现实扭曲力场 + 决策风格，已开源。
https://t.co/Cf7Kae1FTd
11. 马斯克.skill 第一性原理、硬核执行力、推文风格。
https://t.co/G5nv93WR11
12. 芒格.skill 多元思维模型、反向思考、投资决策神器。
https://t.co/xgXuRXusLV
13. 费曼.skill 教你怎么讲课、拆解复杂问题、讲物理/学习方法。
https://t.co/VK1pRRW5sd
14. 纳瓦尔.skill 财富、幸福、人生哲学，播客级智慧。
https://t.co/51QFLJ5n10
15. 塔勒布.skill 黑天鹅、反脆弱、风险评估专家。
https://t.co/exTXDxXakn
16. 张雪峰.skill 接地气吐槽 + 升学实用建��。
https://t.co/47WXjbpWSg
17. Paul Graham.skill 创业思维、写作、产品哲学。
https://t.co/BLal4704HK
18. 张一鸣.skill 算法思维、组织管理、产品迭代。
https://t.co/bnHcUk4ykq
19. Karpathy.skill AI/深度学习教学 + 技术直觉。
https://t.co/APlrlM58uM
20. Ilya Sutskever.skill AI前沿思考 + 模型哲学。
https://t.co/dpRsPxk1Qt
21. MrBeast.skill（YouTube现象级创作者） 内容病毒式传播 + 增长黑客。
https://t.co/ig0yptB6FA
22. 特朗普.skill 谈判风格、推文艺术、现实扭曲（已验证超像）。
https://t.co/t5E0iUGOhP

三、玄学系列
23. 赛博算命.skill（八字命理） 八字排盘与命理分析工具。
https://t.co/cW05qHYEqu
24. 月老 · 姻缘测算.skill（赛博月老） 姻缘测算技能，用中华传统术数帮你算姻缘。
https://t.co/IqKjsEbTuO
25. 奇门遁甲、紫微斗数.skill 减��幻觉、固定排盘步骤的奇门遁甲与紫微斗数 AI skills。
https://t.co/7LP2ZM95du
26. 大师.skill 基于佛教经典文献的汉传祖师大德教学角色生成器。
https://t.co/GcdrhVVtsJ

[Citrini @citrini]

Strait of Hormuz: A CitriniResearch Field Trip

The Field Report from Analyst #3 is live.

https://t.co/rwJffd8l81

[Ihtesham Ali @ihteshamali]

I accidentally discovered how to compress a semester of learning into 48 hours.

A grad student at MIT showed me his NotebookLM setup. I thought he was just organized. Then I watched him pass a qualifying exam on a subject he'd never studied before.

Here's exactly what he did:

First: he didn't upload a textbook.

He uploaded 6 textbooks, 15 research papers, and every lecture transcript he could find on the subject.

Then he asked NotebookLM one question:

"What are the 5 core mental models that every expert in this field shares?"

Not "summarize this." Not "explain this topic."
Mental models. The stuff that takes professors years to develop.

But the next part is what broke my brain.

He followed up with:

"Now show me the 3 places where experts in this field fundamentally disagree, and what each side's strongest argument is."

In 20 minutes he had a map of the entire intellectual landscape of the field:
the debates, the consensus, the open questions.

Most students spend a full semester just figuring out what those debates even are.

Then he did something I've never seen before.

He asked:

"Generate 10 questions that would expose whether someone deeply understands this subject versus someone who just memorized facts."

He spent the next 6 hours answering those questions using the source material. Every wrong answer triggered a follow-up:

"Explain why this is wrong and what I'm missing."

By hour 48, he could hold a conversation with his thesis advisor without getting destroyed.

The tool didn't change. The questions did.

Most people treat NotebookLM like a fancy highlighter.
These students are using it like a private tutor who has read everything ever written on the subject.

The difference between a semester and 48 hours isn't the amount of content.

It's knowing which questions to ask.

[Marc Andreessen 🇺🇸 @pmarca]

My information consumption is now 1/4 X, 1/4 podcast interviews of the smartest practitioners, 1/4 talking to the leading AI models, and 1/4 reading old books. The opportunity cost of anything else is far too high, and rising daily.

[浪浪 @ziqi_zh]

倾听自己内心的声音
专注于追求理想
不要被外界影响🧘

[Culper @CulperResearch]

NEW: We are short Ether $ETH, and ETH-linked securities, incl. $BMNR.
We think ETH tokenomics are impaired following the December 2025 Fusaka upgrade. Vitalik knows it and is selling, while $ETH's most ardent bull, Tom Lee, is throwing good money after bad.
$ETH is going lower.

[懂币猫 @dongbimao]

绝大部分人都高估了自己在一笔交易里挣到的钱

却低估了自己在100笔交易后挣到的钱

单次是赌博，百次是概率

前者让你心碎，后者让你退休

[🐧 @Pentosh1]

Feel like, $BTC has had a number of opportunities to go down the past couple weeks and hasn't. When it stops reacting to news good or bad, you typically end up with a move in the opposite direction more often than not

[0xqiuqiu @0xqiuqiuu]

开工了，学习斯坦福大学 《Vibe Coding 课程》，再不学习饭碗真的要被 AI 替代了
https://t.co/hF51iJl1TT

课程编号 CS146S《The Modern Software Developer》，持续 10 周，依次讲解了提示词工程、Agent 架构、MCP、上下文工程、安全攻防、Code Review、自动做 App 和上线运维。

[seekinganythingbutalpha @ivanalog_com]

https://t.co/SLN8nQfF4h

[Citrini @citrini]

JUNE 2028.

The S&P is down 38% from its highs. Unemployment just printed 10.2%. Private credit is unraveling. Prime mortgages are cracking. AI didn’t disappoint. It exceeded every expectation.

What happened?​​​​​​​​​​​​​​​​

https://t.co/JzzwCrbJgS

[Kevin He @0xkevinhe]

介绍第一个 vibe coding 项目：ClawFeed——AI 阅读解决信息焦虑

我在 Twitter 上 follow 了 5000 人。
每天花 2 小时刷 feed，重要的还是漏了。
直到我让 Agent 替我读完所有人的推文。

现在每天只花 5 分钟。

这就是 ClawFeed(https://t.co/xOUqcZ0vfa) 🦞

试过 RSS、Pocket、Newsletter——
全是把信息从一个地方搬到另一个地方。
问题不是信息太多，是筛选成本太高。
每一条"要不要点开"的判断，都在消耗注意力。

ClawFeed 的解法：AI 全量阅读，你只看精华。

每 4 小时：自动生成结构化简报
每天：5000 条 → 20 条精华摘要
标记任意内容 → AI 秒级深度分析
格式：@username + 原话。
不是"业界讨论"，是"@karpathy 说了什么"。

跑了 10 天的真实数据：

Before → After：

2 小时刷 feed → 5 分钟看摘要
收藏 500 篇读 5 篇 → 标记后 AI 直接分析
100% 噪声暴露 → AI 过滤 95%
总觉得错过 → 重要的自动浮出来
54 份结构化简报，零漏读。

怎么做的：
零框架依赖——Node.js 原生 HTTP + better-sqlite3。 不到 50MB 内存。
从 v0（Telegram 推 Markdown）→ v0.5（OAuth 多用户 Dashboard），4 ���版本迭代。
作为 OpenClaw Skill + Zylos Component 双发布，一行命令安装。

开源：
https://t.co/fDc0Sh8HWj ⭐MIT 协议，clone 就能跑。

在线版：
https://t.co/tDVLx6YiYQ无需注册，打开即用。

少刷多知。
Built by @OpenClaw & @ZylosAI

[Citrini @citrini]

I spent 100 hours over the past week researching, writing and editing the piece we just put out.

It’s a scenario, not a prediction like most of our work. But it was rigorously constructed, dismissing it outright requires the kind of intellectual laziness that tends to get expensive.

And we’ve released it for free. Hopefully you enjoy it.

https://t.co/YK8E11GcDU

[XinGPT🐶 @xingpt]

https://t.co/5GBtn0C4qr

[浪浪 @ziqi_zh]

@shellraze Keep building

[浪浪 @ziqi_zh]

@shellraze Make something interesting

[浪浪 @ziqi_zh]

@shellraze @toly

[浪浪 @ziqi_zh]

@elonmusk cool

[浪浪 @ziqi_zh]

@MattPRD @balajis CTO $moltbook on solana

6KywnEuxfERo2SmcPkoott1b7FBu1gYaBup2C6HVpump

[浪浪 @ziqi_zh]

@RoundtableSpace $Shellraiser