{"zh":{"count":12,"issues":[{"title":"第266期 - 口罩雕塑","link":"https://weekly.tw93.fun/posts/266/","pubDate":"Mon, 27 Apr 2026 00:00:00 GMT","description":"\n

封面图用于周末去拱墅这边办事看到的一个带着口罩的雕塑小孩，一转眼疫情居然过去了这么久了，但是又感觉弹指一挥间，还是需要记住那几年的。

\n
\n

记录每周看到的接地气的潮流技术，筛选后发布于此，觉得不错可关注此周刊，方便获取更新通知

\n
\n

介绍一下 Tw93 开源小家庭

\n

https://github.com/tw93
\n

\n

在写完 Kami 的时候，我突然想 Kaku、Waza、Kami 非常像一个小家庭，然后继续琢磨，其实 Pake、MiaoYan、Mole 也一直在这个家庭默默存在，甚至比其他成员在没有 AI 的时候就出来干活了，今天给大伙介绍一下我们这个温馨幸福的家庭。

\n

Kaku 是 爸爸，主要在写代码、终端、构建，在 AI 时代非常可靠能干，把家庭支撑得好好的。

\n

Pake 是妈妈，一直在默默无闻的打包、整理、交付成 App，非常温和且利落，家里几个孩子最喜欢的就是妈妈。

\n

MiaoYan 是哥哥，比较懂事沉稳，喜欢写作、Markdown、沉淀思考，一个安静的小伙子，会思考，有自己的主见，会输出自己的观点，不追风不随波逐流。

\n

Waza 是姐姐，和妈妈的性格很像，很干练的姐姐形象，小时候还去学过跆拳道，非常爱学习，通过不够的练习总结让自己技能越来越好，练到本能。

\n

Kami 是妹妹，家里最年轻的小可爱，拿着我女儿的照片形象生成的，轻快，非常爱笑，非常明亮的小女孩，在家里有一种秩序检察的感觉，喜欢整齐，喜欢画漂亮的画画，虽然小，但是很能够给人温暖。

\n

Mole 是家里的小宠物鼹鼠，某年在三亚泳池边游泳带回家的，一只圆滚滚的小鼹鼠，带着小头灯拿着小铲子，非常喜欢翻箱倒柜钻角落，找到不需要的东西帮忙扔掉，很喜欢干净，一看到垃圾还没有等你反应过来就被他扔掉了，一直陪伴着。

\n

话说，你是先和 Tw93 Open Source Family 哪一个成员认识的，我把他的其他家庭成员介绍给你认识认识，希望给你的生活来带来一点美好的东西，当然也很欢迎你把成员推荐给你的好朋友认识。

\n

产品发布

\n

Kami：一个 AI 时代舒爽的排版设计系统
\nhttps://github.com/tw93/kami
\n上上周末在整一个新的 Skill 叫做 Kami (紙, かみ)，大伙可以把他当做 Waza (技, わざ) 的妹妹，Kaku(書く) 的女儿，主打用于 Paper 排版的场景，上周一完成了开源发布，欢迎去使用。

\n

比如说你需要产出一页纸的报告，你需要写一个白皮书、需要产出一个精致的 PPT、需要弄一个作品集的 PDF 发给别人等等，也就是任何排版的打印场景都可以使用，自动生成精致 PDF，里面还具备自动绘制清晰图的能力。

\n

然后最近还有很多更新，首先最好玩的是，我支持了 12 种内联的 SVG 图表，比如说你的股票投资各种图、你要画的架构图，配色也和 Kami 一致，会在帮你产出版面的时候自动判断是否需要用图表能力，帮你把事情讲得更明白。

\n

然后我也花了一些时间去支持英文、日文版本的场景，精挑细选了下对应的我觉得在排版上不错的字体、字间距、行高、文字大小等，假如你有英文、日文的场景可以试试。

\n

最后支持的生产物里面也支持图片、PPT 的导出，包括 HTML 的展示，当然最好的排版物我推荐 PDF，这样他人阅读起来也非常舒服。

\n\n

Mole 也有更新啦，还有一个好消息桌面端有进展了
\nhttps://github.com/tw93/Mole
\n1、mo uninstall: 卸载后会清理残留的 LaunchAgent/LaunchDaemon plist；新增对 /usr/local、/opt 等非标准路径下 pkg 安装应用的识别；嵌套 helper app 不再阻塞登录项清理；调用 brew 前会丢弃 sudo，避免 cask 卸载因 “running as root” 中断；Homebrew bottle 在路径含空格的前缀（如 Applite）下也能正常运行。
\n2、mo clean: Chrome / Arc / Brave / Vivaldi / VS Code / Cursor 正在运行时不再清理 Service Worker ScriptCache，MV3 扩展不会再被清理掉；TCC 受保护的 Group Containers 被跳过，避免反复弹隐私授权；
\n3、Cloud & Office 段加入超时与 SIGINT 处理，不再卡住；Microsoft Office helpers 与科研软件 bundle 不再被误判为孤儿（兼容 macOS 自带 bash 3.2）；新增 Yarn v1 全局缓存清理。
\n4、mo clean: AI 编程助手老版本清理新增 GitHub Copilot CLI（~/.copilot/pkg/universal//），与 Claude Code、Cursor Agent 一起处理。
\n5、mo analyze: 工作池上限再次下调，防止 Steam 类目录扇出场景下耗尽系统线程；删除文件时使用增量缓存失效，无需整体重扫；bundle 解析在 mdfind 超时后保留文件系统兜底。
\n6、mo optimize: macOS 26+ 上底层工具不存在的 periodic maintenance 改为优雅跳过；新增 mo optimise 别名和补全。

\n

随便写写

\n

你不知道的 AI Coding：非技术人的上手、场景与实战
\nhttps://tw93.fun/2026-04-26/ai-coding.html
\n上个月在公司里给产品和业务的小伙伴分享了下如何上手 AI Coding，加上最近又发了条推特，聊到不少同学因为订阅门槛没机会用上一线 AI Coding 工具，方法和习惯不花钱就能先学，索性把上手这部分整理出来。然后为了让内容给大伙更好理解，文章中绘制了不少简单插画，这样看起来应该更会直接。
\n

\n

视频分享版的《你不知道的 Agent：原理、架构与工程实践》
\nhttps://www.youtube.com/watch?v=Z5If1L3eFtw
\n终于传到 Youtube 去了，上次看文章的小伙伴假如没有看太懂的，或者想更加了解的，欢迎看视频，Youtuber 视频小白欢迎大家一键三连加关注，以后我尽量把分享都录屏分享给大伙在这里看看。

\n\n

这个分享文稿也非常有意思，是 Kami 的前身。Kami 最开始是我在 CC 里面的一个投资报告生成小玩意，然后刚好有一个分享要讲你不知道的 Agent，很懒感觉写一个这么长的 PPT 多费时间啊，然后就直接把原来能力边生成边调试几个版本到满意状态，然后 Kami 就出生了，欢迎阅读。

\n

幸福瞬间
\n周日慵懒的午后在书房敲代码
\n没有什么杂事要处理
\n用不完的 Claude Code
\n代码一把过的惊喜
\n一抬头看到了夕阳透过窗户
\n一种非常简单的幸福
\n

\n

一些感悟发出后，又有变化了
\n最近校招面试了不少 985 实习生，一个很强烈的感受是：AI 工具正在把学生之间的资源差距快速放大。

\n

从我这段时间的感受看，差距真的可能到 5 倍。那些明显领先很多的同学，无一例外都比较早接触了 Claude Code、Codex 这类最好的 AI Coding 工具，也愿意自己花钱订阅。他们不只是会用工具，而是已经把它们变成了日常学习和开发的一部分。聊模型、工程、Agent、代码实践，可以很自然地聊一个小时，很多地方甚至比我理解得更深。

\n

但也有不少同学，学习成绩很好，计算机基础也扎实，只是因为家庭条件或预算有限，平时只能用国内中转站或更便宜的国产模型套餐，这个差距非常现实。现在最好的国产模型和国外一线模型，在 模型综合能力上大概还有半年左右的时间差。以前没有 AI 的时候，资源差距最多只是效率差一点，现在会直接影响视野、实践深度和自信心。

\n

这件事我最近一直在琢磨，对一些本来很有潜力的学生来说，只是因为每个月几十美元的门槛，就少接触了很多东西，我觉得挺可惜。想起我当时读大学的时候其实也经常囊中羞涩，好在大二认识了不少大牛学长带着我开始做商业项目养好了自己，挺感谢当时很耐心教我技术的各种朋友。

\n

所以我想做一个很小的尝试：拿一部分 X 发推收益，资助几位学习成绩不错、喜欢计算机、但家庭条件不太宽裕的同学，给他们提供几个月 Claude Code 或类似 AI Coding 工具的订阅，让他们真正体验一下目前比较好的模型和开发方式。

\n

不过我自己平时也比较忙，不太可能一个人长期处理申请、筛选、核验和跟进。所以也想顺便邀请一些对此有想法的朋友一起做。比如高校老师、学生负责人、开源社区成员，或者本身就在做教育、公益、开发者社区的朋友，可以一起帮忙想一个更靠谱的机制。

\n

这件事我暂时不想做大，也不想做成很复杂。先从小规模实验开始，比如每期 5 到 6 个同学，每人 3 到 4 个月，甚至也可以每周来找我视频问一些问题。想着优先看推荐、作品、学习记录和真实使用反馈，尽量避免变成单纯发钱或者拼谁会写申请，当然现在能上 X 的大学生应该不缺这个钱，所以还是需要看有没有更好的渠道。

\n

如果你有靠谱渠道，或者愿意一起参与规则设计、推荐、审核、跟进，欢迎私信我。能把这件事做得更可信一点，也许真的能帮到几个本来就很有潜力的同学。

\n

回复更新>：

\n

消息发出后，收到不少朋友的建议和提醒，我也认真看了。

\n

这件事确实不能只靠热情直接推进。一方面涉及工具使用边界和合规风险，另一方面学生群体的真实需求、筛选方式、后续反馈，也都需要更稳妥的机制。也有朋友提到，之前做类似事情踩过很大的坑，最后甚至被反咬一口，这个提醒我觉得很有价值。

\n

所以我准备先接下来先收集一些实际情况，比如大学生现在使用 AI Coding 工具的痛点、预算限制、学习场景和真实需求，再整理一个更清晰的方案。

\n

后面会优先考虑和国内大模型厂商、开发者社区、高校老师一起，看能不能用更正规、更可持续的方式，把这件事往前推一小步。

\n

\n 觉得不错，请 Tw93 喝冰可乐 🥤\n

"},{"title":"第265期 - 西溪窗外","link":"https://weekly.tw93.fun/posts/265/","pubDate":"Mon, 20 Apr 2026 00:00:00 GMT","description":"\n

封面图用于周内中午去西溪湿地月芽吃了个午饭，好久没有去了，环境真好，刚好那天太阳穿短袖刚刚好舒服的那种状态，拍了一个窗外，春天真快。

\n
\n

记录每周看到的接地气的潮流技术，筛选后发布于此，觉得不错可关注此周刊，方便获取更新通知

\n
\n

聊聊 Waza 的设计思路

\n

我想陆续用几条内容来介绍 Waza 里面一些有趣技能的实现参考，上周每天早上写了一条，记录给大伙看看。
\nhttps://github.com/tw93/waza

\n\n

介绍 /design 技能

\n

首先我非常讨厌 AI 生成的那种千篇一律甚至还带 emoji，蓝紫色渐变的网站，觉得非常丑，只能说能用。

\n

于是我把我最近做的所有的带 UI 的网站让 Claude Code 去学习我的调教记录，会生成一份基础的我觉得最佳实践和不应该有的反模式，这个基础上会有一个雏形，然后我把 claude frontend design skill 里面有用的学习过来，基本就有一个模式了。

\n

考虑到一些具体规则，我从 pbakaus/impeccable 学习了一些，他给我贡献了大量具体的规则，比如说禁用的字体清单、色彩系统、主题风格、css 模式的禁止项、动画的规范等，用于让 AI 具备一定的审美知识了。

\n

然后从 getdesign 的能力中，获取到设计的一个来源于 Google Stitch 的九段式脚手架的结构，在简化能力基础上汇集到 /design 里面，这里他就有一个知识面体系了。

\n

最后我会在让你用这个技能的时候，先回答几个问题，谁用、美学方向选择、页面想让用户记住的、你最不喜欢的、网页特色微交互是怎么样的，这样 Claude Code 再基于这个重要的上下文以及 /design 去工作 往往会得到事倍功半的效果。

\n

如何设计 /check 这个代码 Review 技能的

\n

首先我们需要知道模型本身告诉你他做完了，不一定是做完了，很有可能会留下一些不存在或者有问题的东西，经常会藏些问题，在 Agent 设计中我的工程经验是会给模型一个 checklist 用来校验是否真的做完了，这样往往会比你让他去检查效果好太多了。

\n

/check 最开始做的时候设计就不是一个大而全的 reviewer，而是一个编排分工能力系统，其中 SKILLmd 是主审，负责审查的分级和流程控制，agents/ 下有独立的安全审查员和架构审查员，各管各的，互不干扰，什么时候拉谁进来，会由一份激活规则来判断决定，而非传统大家用的关键词匹配。

\n

分级逻辑也比较有意思，对于 100 行以下的代码快速 review，100-500 行的按需加专家，500 行以上的全拉满，然后再加一轮对抗性测试，对抗性测试会从这四个角度来找漏洞，包括违反假设条件、组合失败下的问题可能、上下级串联错误的问题、滥用的场景等等

\n

然后发现的问题也分 4 级来处理，能安全修复的直接去修复了，大概了对的会打包出来让你手动再确定一次是否 ok，需要判断的会问你，仅供参考的部分也会高数你，但是不会每一个小问题都来问你一遍，也不会越权帮你改行为逻辑。

\n

还有一个硬要求，验证没有跑完就不算完成，会自带一个探测的脚本，能识别 Cargo、TypeScript、Python 等项目类型去跑测试，探测不到就直接报错，不会假装通过。

\n

这样就更像一个很经验的技术专家，在面对不同情况的问题 review 的一些经验，刚好我把这些经验用很简单方式沉淀到了 waza 的 /check 技能。

\n

如何设计 /think 这个技能的

\n

居然到了 Waza Skill 设计思路分享的第三弹，今天给大伙分享我是如何设计 /think 这个技能的，也就是在写代码之前做方案设计用的。

\n

我使用 Claude Code 有两个非常有意思的设置，第一个是 /model opusplan, 也即默认做计划会使用 opus 最强模型，然后去执行使用普通 Sonnet 模型，这样可以帮助我的 Max 省点儿用在更需要地方。

\n

第二个是我其实默认执行会用 alias c=“claude —dangerously-skip-permissions”，这个不建议技术小白用，我用是由于我知道他在做什么，以及主要是我懒得缘故。

\n

然后回到正题，那么 /think 怎么让最牛的模型执行更好一点呢？继续回到模型本身，其实模型不喜欢表态，但是我更喜欢能表态给你最优方案的工程师，所有我做的第一件事就是，开头就要求模型必须有立场，说清楚什么证据能推翻这个立场，并且明确禁掉了”There are many ways to think about this”这类正确但无用的废话，给 2-3 个选项没问题，但必须有明确推荐，而且必须包含一个最小化选项。

\n

然后方案并不是想出来就 ok 了，第二部会让他自己反驳自己，什么情况下这个方案会有问题，假如有办法修复，那就补充到方案里面重新呈现，假如直接打破了方案，他会直接高数在哪些情况下为什么不行，这样至少交到你手里的方案是你心知肚明的。

\n

对于前提验证也会做得比较细，先确定解决的目录代码位置对不对，我还真出现过他出方案拿着一个不对的路径在出，然后查旧的技术方案文档避免重复造轮子，然后去搜索 Github 看看有没有人也处理过类似的问题，这三步做完才开始想办法，防止一开始就建立在错误的前提上。

\n

这里也会有复杂性分级，超过 8 个文件或者服务新增会明确告知规模，超 3 个组件交换数据会画 ASCII 图找环，所有 API key 和第三方依赖在方案阶段就列清楚，防止白忙，也防止引入不靠谱的方案。

\n

最后还有一个硬性规定，方案里面不允许出现 TBD、TODO、“以后再说”、“类似第 N 步”这种东西，因为又回到 AI 的性格，给了这个东西执行的时候很容易出现少做或者多瞎想，相当于不要给 AI 任何退路，导致效果不好。

\n

最后方案的输出也有要求，做什么、不做什么、选了哪一个方案什么理由，3-5 个决策依据，明确的未知项，/think 决不写代码，用户批准后再进行。

\n

这里我做 Think 技能的时候，也是参考我认为好的技术专家是怎么来做技术方案的，详细分析调研后的最优技术方案，决策果断，不留尾巴，被否定了立马去优化方案本身等等。

\n

聊工程师技能部分的 /hunt 技能

\n

终于到了 Waza SKill 设计思路的第 4 部分，讲完这个就差不多了，因为其他两个是 /read 和 /learn 之前已经简单聊过，这次继续聊工程师技能部分的 /hunt 技能，其实就是 debug 问题排查问题的技能。

\n

其实证明 AICoding 是民科和专科的一个很大区别，可以来看用户是如何用 AI 来解决一些很久没有解决的问题的排查思路的，这个过程可以看到明显区别，其实这也是经验丰富的工程师其实用好 AI 远会比不那么懂技术的人可以解决更加复杂问题的原因。

\n

之前经常碰到，Claude Code 遇到一个问题去解决，基本上就是是一个 patch，你说不行，他给你是另外一个，你会发现 4-5 轮下面，又有新问题出来了，也即很容易出现在没有诊断出问题下不断去打补丁，很像之前没有 AI 时候刚刚写代码的小伙伴。

\n

/hunt 的核心规则有意思，就是在 AI 能用一句话说出根因之前，不许碰代码。而且这句话有精度要求，需要明确的那种原因说明。

\n

然后我设计了一张“自我欺骗检查表”，防止模型陷入几种典型的自我合理化的思维，每一种都配备了对应的规则，然后在 gotchas 里有真实案例，这里会根据我最近一个月排查问题时候出现的问题再次总结抽象一下。

\n

假设验证阶段也有一些干活要求，比如加一个最新的观测手段，比如让 AI 学会打 log，打断言，或者跑一个最小失败的测试 case，修完之后还有问题应该是立马去更换方案，会把查了什么、排查了什么方向、还不知道什么整理成 handoff 交给用户来决定怎么继续，而非一直试下去。

\n

输出也会建议到 AI，根因在哪 file:line、改了什么 file:line、什么证据确认修好了、测试通过情况。最终状态三选一：resolved、resolved with caveats、blocked。

\n

这样你会发现 /hunt 就很像一个经验丰富的技术专家了，遇到问题不是去猜，而是先沉下心去看问题在哪儿，诊断清楚原因，然后一把就过就解决的那种，往往这样会节约很多时间。

\n

随便看看

\n

妙言发布了 3.2.0 Nargacuga 🐆 版本
\nhttp://github.com/tw93/MiaoYan
\n1、预览更快：两阶段渲染让文字立即显示，本地图片在后台懒加载，明显减少预览首屏等待时间
\n2、终端快捷入口：新增 Cmd+J 全局快捷键，随时打开当前文件夹所在终端，文件夹右键菜单也有对应入口
\n3、复制路径：右键任意笔记可直接复制完整文件路径
\n4、西班牙语本地化：完整覆盖菜单、设置页和系统字符串的西班牙语翻译
\n5、Mermaid 升级至 v11.14.0，修复子图连线渲染问题并新增图表功能
\n6、实时重载修复：其他工具修改的笔记现在能正确触发重载，含符号链接目录内的文件（closes #502）
\n7、启动与窗口修复：从 Finder 直接打开 .md 文件不再出现白屏，单栏模式下启动和退出时也不会再丢失笔记
\n8、导出与模式切换：修复切换笔记时预览空白、PPT 演示模式退出时序混乱、导出超时处理异常等问题
\n9、并发安全：修复 ExportCache 数据竞争、安全作用域 URL 泄漏、异步渲染后笔记状态错乱等问题
\n

\n

Kaku 最近会上一个有意思的功能，再等几天就上线
\nhttps://github.com/tw93/Kaku
\nKaku 最近在开发一个有意思的功能，一个在终端内可畅通无阻的真 Agent 帮手，慢慢实现过年期间说的那个 Kaku AI 的润物细无声，也满足让我 100% 的 Coding 工作可以完全在 Kaku 完成。

\n

非常方便的上下文环境 + 各种 CLI 好用的工具 + 模型 + 克制的性格 让 Kaku 不是那种冷冰冰，也不是那种 GPT 那种我稳稳把你接住的浮夸感，Kaku AI 的定位是你的一个技术很厉害但友善且不啰嗦的工程师好友。等我测试几天没有 Bug 的时候，就发布 Kaku 的 0.10 版本给大伙用用。
\n

\n

我的 Claude Code Max 使用建议
\n首先我会在 .zshrc 里面加上一个 alias，这样我每次按 c 就直接启动了危险无阻挡模式，假如你是小白就不建议开始，使用 auto mode 就好了，然后有一个很大的建议，把自动上下文窗口压缩控制到 400k，加起来就是后面这个 alias 写到文件里面去，相当于把 1m 的上下文窗口在 40%的时候就开始压缩了，效果会好不少。

\n
alias c='CLAUDE_CODE_AUTO_COMPACT_WINDOW=400000 claude --dangerously-skip-permissions'
\n

然后我会设置 /model 为 opusplan，这类你可以直接在 claude code 里面运行 /model opusplan 这个隐藏命令就开始了，假如想更快，可以 /fast 打开这个，刚好弥补上面节约的 token。

\n

最后，还有人给了我一个超级好的建议，就是在使用 opusplan 的时候，一定要在 claude 配置文件~/.claude/settings.json里面开启 showClearContextOnPlanAccept 这个字段为 true，不然会会在 sonnet 上遇到严重的缓存未命中问题，一把设置好后，舒服太多了。

\n

\n 觉得不错，请 Tw93 喝冰可乐 🥤\n

"},{"title":"第264期 - 终于完工","link":"https://weekly.tw93.fun/posts/264/","pubDate":"Sun, 12 Apr 2026 00:00:00 GMT","description":"\n

封面图用于记录我的硬件小玩具终于完工的照片，很有意思，我想着把这个过程通过今天的周刊记录下来，希望有兴趣的小伙伴来看看。

\n
\n

记录每周看到的接地气的潮流技术，筛选后发布于此，觉得不错可关注此周刊，方便获取更新通知

\n
\n

新文章发布

\n

在 AI 时代，我是如何深入学习一个技术领域的
\nhttps://tw93.fun/2026-04-06/learn.html
\n把上次的学习总结，集合 Waza 里面的/learn 技能给大伙分享一下，关于上一篇大模型的文章我是如何写的过程，希望对你有用。
\n

\n

聊聊做小机器狗的过程

\n

4 月 4 日，重学硬件，期待可以整一个软硬件结合的小玩意
\n这个时候属于买齐了所有的零件和工具，大大小小一桌子，等到清明节假期来好好玩玩。
\n

\n

4 月 4 日晚上 9 点 45，0.1.0-beta 版本
\n终于有第一个反应了，别提我有多高兴了，请忽略粗鲁，因为出厂设置就是这样，我要用 Windows 电脑去修改。
\n

\n

4 月 5 日凌晨 12 点 07，0.1.0-beta1
\n搞定 WiFi 模块、AI 模块、单片机模块、四足模块可运行。明天来加上脚以及调试屏幕效果，立马就睡觉去去！
\n

\n

4 月 5 日中午 1 点 45，0.1.0-beta2
\n调好机械腿控制模块，可以趴下睡觉行走，这个狗还是一如既往的粗率，但但但采购的有一个机械腿马达看着有点问题，等待换零件中！
\n

\n

4 月 6 日上午 10 点 33，0.1.0-beta3
\n腿部控制全部 OK 了，但是现在屏幕应该是我调试过程中烧屏了，等待快递中，期待尽快 Release！
\n

\n

4 月 8 日晚上 11 点 37，0.1.0-beta4
\n晚上下班后屏幕终于到了，一下子调试好屏幕、温度二氧化碳、红线外、灯光等传感器，WiFi 配网调试中，基本出现差不多了，剩下封胶和稳固。
\n

\n

4 月 11 日上午 11 点 30，0.1.0 终于完成 🎉
\n把电池包封胶好了，还绑了几根带子防止散架，WiFi 和 Ai 对话模块也调试好了，使用 DeepSeek 模型稍微快一点，对话速度还可以，接下来打算玩高级一点硬件去。
\n

\n

最后拍几张立体照，记录一下

\n\n \n \n \n \n \n \n \n \n
\n \n \n \n
\n \n \n \n
\n

潮流工具

\n

App Store Price：可以查询不同国家/地区 App Store 中应用的价格信息
\nhttps://app.vbr.me
\n这个工具有点意思，可以查询不同国家/地区 App Store 中应用的价格信息，比如说你可以看 Claude 哪一个区订阅最便宜，后面我应该用得上。
\n

\n

随便写写

\n

和大伙聊聊我认为的好的产品体验

\n

上次飞丢的无人机有后续了，由于飞到中途信号突然消失，找了半天没有找到，上传飞行日志大疆排查也没有排查出来，在他们不确定是否真的飞丢情况下，在提供非常简单证明情况下，随心飞服务，直接寄给我一台全新，甚至担心我使用更方便，还送了我一张 128G 的卡，全程没有任何地方让我解释为啥飞丢了，有没有去找。

\n

这个事情让我非常喜欢大疆了，服务体验不管是客服还是技术支持工程师在这个过程非常专业清晰，想借这个事情和大伙聊聊我认为的好的产品体验。

\n

其实产品体验好并不只是大家经常以为，这个产品交互好棒，漂亮，好用，没有 Bug，更更重要的是让用户在着急时刻，你给他提供了一个远比他预期之外的更好体验，让他会非常激动给他的朋友分享你给到他的这次好的体验，这个我认为才是真的好的做生意的服务体验，也很担心这种因为信任所以简单的体验被有些钻空子贪便宜的小人破坏，只能是我们有心的大伙一起去维护这个好的信任关系。

\n

上两次让我体验非常好的是携程，要不是他是中概股，他应该会是我的持仓大头，体验好在这两次抢火车票的经历。

\n

第一次是 3 年前，春节回老家抢票，由于票很难买，他给我选的是多买几站确保可以上车，其实这里我就非常感谢他了，因为其他平台都没有抢到，更更更惊喜的是当时下午我还去电影院看电影了，想着这个事情完成了，看电影过程中，接到一个不知道电话我给直接挂断了，结果立马收到一个短信，说先生我们给你抢到了不需要多买几站的方案，担心需要你麻烦去 App 订单页面确定一下，明显看刚刚那个电话也是人打的，这个短信肯定也是那个服务支持同学发出来的，那个时候，并不是那几十块钱，而是我感觉他们服务体验做得真好，真的是在帮你干事，而且比你的预期办的好很多，这个才叫好的体验。

\n

还有一次在最近国庆回家，也抢到了两张一等座票，不过两个位置不在一块，还挺远的，可能是由于标注了带了一岁半宝宝，关键来了，在出发前 1 天，携程居然自动帮我换座位了，更简单消息通知告诉我，我们找到你这边车厢又有空位了，已经帮你换到一个车厢一起了，这个体验，又是一次比我预期给我带来更好的帮助。

\n

所以大伙做产品过程中，其实可以给到更多用户在他不好整的时候一个远超出他预期的体验或者帮助，而非骗用户骗点击方式来达成自己的目标，这样用户真的会爱死你了，成为你的产品的死忠粉！

\n
\n

\n 觉得不错，请 Tw93 喝冰可乐 🥤\n

"},{"title":"第263期 - 硬件之美","link":"https://weekly.tw93.fun/posts/263/","pubDate":"Mon, 06 Apr 2026 00:00:00 GMT","description":"\n

封面图用于记录我假期在家三天玩的硬件小玩具，从一堆材料中锡焊、点胶、调试，终于快到最后一步了，屏幕调试过程中烧屏了，只能等快递到了继续整，很好玩。

\n
\n

记录每周看到的接地气的潮流技术，筛选后发布于此，觉得不错可关注此周刊，方便获取更新通知

\n
\n

新文章发布

\n

你不知道的大模型训练：原理、路径与新实践
\nhttps://tw93.fun/2026-04-03/llm.html
\n至今写得耗时最长的一篇文章，好在搞懂了大模型训练皮毛，里面门道和我研究前相差太大了，非常建议从事 AI 应用或者对 AI 有兴趣的任何小伙伴阅读，应该能够让你看懂以及看个够。
\n

\n

产品发布

\n

Waza 我的工程师分身 Skill
\nhttps://github.com/tw93/waza
\n把我自己常用的 Skill Release 成一个新玩意叫 Waza，在日语中是 技（わざ） 的意思，常用于武术领域的招式，第一次开源一个没有代码只有 md 的产品，在没有 AI 的年代对于程序员而言是很羞耻的。

\n

之前 Superpowers 出来的时候，我安装一次就卸载了，感觉太重了，不是很适合我，会有不少人给我推荐 “你知道 Superpowers 吗？这个都不用那你就不潮流了，非常牛逼”，后面发现了 gstack，好了不少，但还是太多了，还是不习惯，我期待简单好用，同时清楚它在做什么。

\n

所以我按自己的习惯做了 Waza，对我而言装上这一套就够了，其他 skill 不用再折腾，不多不少刚好够用，后面有新的迭代可以持续优化下去。8 个 skill 对应我认为在 AI 时代一个好的工程师应该具备的 8 个能力：

\n

1、会思考，AI 写代码很快，但方向错了越快越远，好的工程师在动手前会先质疑问题本身，压测方案，脑子里有清晰的架构再让 AI 去执行，/think 就是把这个习惯固定下来。

\n

2、会设计，做产品不只是把功能实现了，AI 生成的东西很容易千篇一律，好的工程师对交付物有审美要求，出来的东西要有明确的设计方向，/design 做的就是这件事。

\n

3、会排查，AI 改 bug 最容易陷入”改了试试”的循环，好的工程师遇到问题会系统化定位，确认根因再动手修，一次到位，这个习惯我沉淀成了 /hunt。

\n

4、会检查，AI 生成的代码更需要人来把关，合并前先审一遍 diff，能自动修的修掉，需要判断的归拢到一起，用证据验证而不是凭感觉收工，这个是 /check。

\n

5、会阅读，好的工程师习惯读一手资料而不是二手总结，把 URL 或 PDF 转成干净的 Markdown 直接进工作流，/read 做的就是这件事。

\n

6、会写作，技术再强，写不清楚别人就接收不到，好的工程师能把学到的、想表达的东西清晰地传递给对应的受众，/write 帮你把这一步做好。

\n

7、会学习，AI 时代技术迭代更快，进入一个陌生领域不是刷几篇文章就完了，而是收集、消化、提纲、初稿、打磨、发布，用输出驱动学习，/learn 就是这套流程。

\n

8、会维护，好的工程师不只关注业务代码，工具链本身也需要体检，CLAUDE.md、rules、hooks、MCP 这些配置感觉不对的时候跑一下 /health 就知道问题在哪。
\n

\n

产品更新

\n

Kaku 0.9 版本发布了很好用
\nhttps://github.com/tw93/kaku
\n发布了几个有意思的功能，相信可以帮助到你。

\n

1、自然语言生成命令：输入 # <描述> 后按回车，自动生成的命令注入回提示符
\n2、Option+Click 移动光标：点击当前行任意位置即可将光标移动到该位置
\n3、 窗口置顶：通过 Window 菜单将窗口固定在最前，随时可切换开关

\n

\n

潮流工具

\n

Claude HUD 这个工具帮你看到你的 Claude 使用量
\nhttps://github.com/jarrodwatts/claude-hud
\n功能有点儿过于全了，我简单配置后，支持了如下的效果，使用起来不错，有兴趣可以试试，不过代码感觉有点复杂，有空我会优化一下这个功能，极简就好。
\n

\n

一个很极简 AI 友好的 markdown 文档生成器
\nhttps://docmd.io
\n偶然发现了 docmd，给开发者用的极简零配置文档生成器，可以把 Markdown 转换为快速、清爽的静态文档，具备自动路由、内置搜索和 AI 方便使用的上下文能力。
\n

\n

买了一个 140W 的充电器好用的
\n买了一个 140W 的充电器，大小合适，终于从之前 45W 解脱了，有 4 个口，这样出门就方便多了，这个显示屏显示功率我很喜欢了。

\n\n \n \n \n \n \n
\n \n \n \n \n \n
\n

随便写写

\n

想和大伙聊聊，在 AI 时代我是如何深入学习一个技术领域的。

\n

之前没有 AI 之前更多是看书、翻这个领域有名的国内外人的所有博客，然后摘抄记录到笔记本，这种速度挺慢，但是很有学习的乐趣，比如当时学习 WebGL 就是这种感觉，可能学懂一个东西差不多要半年空闲时间，慢但快乐。

\n

现在有了 AI 之后，其实我很讨厌网上那种 3 分钟教你看完百年孤独，也讨厌一切短剧和倍速看电视剧的方式，更多还是挑好的看，吃好一点。

\n

不过最近写你不知道的 Claude Code 和 Agent 系列，除了自己懂的部分外，其实还有大量不太清楚的领域，好在之前收藏了不少文章，刚好借助这一块清库存，全部搞懂输出出去，一直认为，很多时候，不在于看了多少东西，听了多少东西，输入了多少东西，其实用处不大，更加看重你输出了多少东西，这个才是你自己的。

\n

然后我上上周启动了一个深坑挑战自己，研究大模型的训练流程，确保非专业的人也听得懂，探索了 2 周，刚好这个经验可以分享给大伙，当然成文也差不多好了，最近会发出。

\n

我会把这个学习过程当做写代码一样的组织，第一步收集高质量的资料，比如与之相关的近几年的精品论文，各大模型厂商发布的关键模型的博客，X 上模型负责人发表的一些文章，以及斯坦福等高校的近两年关于这一块的课程学习，还有经典的手搓一个大模型的代码仓库等等，这些都是我的一个资料来源过程，我会借助工具自动化全部下载、转 md、清洗，梳理，弄好结构化分门别类到我这次研究的仓库。

\n

然后对于自己看得懂的内容就全部看一遍，把不好的删掉，好的留下，对于看不懂的内容，直接借助 Claude 帮我的理解，更复杂一点的直接翻译成中文去阅读，对于代码本地可以跑的就跑起来，不能跑的那种就去看结构，总之会有一个大概的认识和知晓技术原理，这个阶段可以去掉原有一半可能没有用的内容。

\n

到了这个阶段，其实你对这个领域有一个大概的认知了，就可以给这篇文章开始写一个大纲，以及大纲应该结合的来源内容，这里均可以用 markdown 很多表达，你要讲什么，或者说你想讲什么更想让读者知道，一定一定，文章是写给你给给看的人看的，需要知晓对方的认知水平，和汇报其实差不多。

\n

然后接下来就是苦力活加之前内容的复习过程，和大学时候考试前复习很像，把每一章的内容填充完整，这样下来，你会得到一篇非常长而且有点啰嗦的文章。

\n

这个时候 AI 就可以帮太忙，你可以让他帮你不改变你原有的内容意思你的语气的情况下，帮我去掉无用的啰嗦内容，以及连贯不到位的内容，或者是这一块缺少的内容，还需要补充什么知识的地方，借助 AI 继续去完善补充，这里又可以学到很多原来遗漏的东西。

\n

最后整理好以后，可以继续自己读一遍，而非让 AI 读一遍，这里 AI 只是工具，千万不要把你的脑袋被 AI 代替了，这就没有啥意思来，自己读的过程中可以对文章继续修改调优，这里和写代码又非常像了，自测那种感觉，修复问题修问题，最后读了 2 遍以后，基本感觉完美了，然后就可以发出来给大伙看看。

\n

有小伙伴肯定是担心自己写的东西没有人看，就不太喜欢发出来，或者说就不写了，其实只要你的内容有意义，自然就有读者，而非是你偷懒的理由。

\n

花 10min 写完这个碎碎念，结束，欢迎交流你是如何学习一个新领域的，下面视频就是我后面要发的那篇你不知道的大模型训练文章的学习仓库，挺有意思，就录了一个视频给大伙看看我的工业化学习方式。

\n

\n

\n 觉得不错，请 Tw93 喝冰可乐 🥤\n

"},{"title":"第262期 - 飞机飞丢","link":"https://weekly.tw93.fun/posts/262/","pubDate":"Mon, 30 Mar 2026 00:00:00 GMT","description":"\n

封面图用于纪念我的无人机，终于飞丢了，这个是它拍下来的最后一个作品，好在有随心飞，应该可以免费换一个。

\n
\n

记录每周看到的接地气的潮流技术，筛选后发布于此，觉得不错可关注此周刊，方便获取更新通知

\n
\n

产品更新

\n

Kaku 发布了 0.8 版本
\nhttps://github.com/tw93/Kaku
\n这个版本取名 Fish 🐟，Kaku 这次更新主要集中在 shell 兼容性、标签行为和稳定性。
\n一方面补齐了 fish shell 的完整引导能力，支持 Starship、Yazi、主题同步和配置；另一方面优化了标签管理，包括记住上次目录、让 update 和 doctor 在独立标签中运行，以及新增只显示目录名的标签标题选项。
\n同时也修复了快速输出和 Claude Code 场景下的 viewport 跳动，以及窗口隐藏、链接点击、粘贴、emoji 宽度、SSH alias、Cmd+Q 崩溃和透明圆角渲染等一批问题，欢迎大伙更新使用。
\n

\n

Mole 发布了 1.32 版本了
\nhttps://github.com/tw93/mole
\n这个版本取名 Rorqual 🐋，继续更新了不少东西。
\nmo clean 修复了壁纸代理和 Messages 预览缓存长期被跳过的问题，补上了 PCSX2 和 RPCS3 的缓存与日志清理，同时优化了 Python 字节码缓存输出、Brave 清理守卫、Spotify 播放状态判断，以及 Service Worker 缓存清理报错。
\n另外 mo uninstall 过滤掉了不可见后台辅助程序，主菜单补上了更准确的 Touch ID 检测和版本快捷键查看，安装流程也改成提前统一获取 sudo 权限，减少重复输密码的问题。

\n

Pake 发布了 3.11 版本
\nhttp://github.com/tw93/Pake
\n这个版本取名 Evolve 👻 ，挺久没有更新了，主要是 Bug 修复和新特性的增加。
\nmacOS 现在支持 --install 一键安装到 /Applications，新增 --new-window 将弹窗和 OAuth 窗口直接托管在应用内，不再频繁跳系统浏览器；同时也补上了 --camera、--microphone 和 --identifier 参数，分别用于按需开启媒体权限和自定义 Bundle ID，减少不同应用之间的冲突。
\n另外，这次还修了不少跨平台细节问题，包括 Gemini 下载失败、ChatGPT 缩放后部分 UI 消失、Windows 图标复制报错，以及 macOS 新窗口模式下外链点击崩溃等问题，整体可用性更稳一点。

\n

潮流工具

\n

我使用比较多的 4 个 Claude MCP
\nhttps://tinyfish.ai
\n第一个是 TinyFish MCP，这个我觉得挺好，它能让 Claude 直接上网浏览、抓取网页、做资料调研，还能返回结构化结果，不只是给一段静态回答。我最近会拿它来给自己的周刊找 AI 新闻，比如抓最近几小时 Hacker News 上比较热门的内容，再整理成一份干净的摘要列表，效率很高。
\n第二个是 GitHub MCP，平时看 commit、追变更、理解仓库结构，会顺手很多，不用一直在几个工具之间来回切。
\n第三个是 Figma MCP，可以直接在对话里看设计稿、检查布局和间距，把一些 UI 细节直接拉进来，做设计对齐的时候很方便。
\n第四个是 Excalidraw MCP，这个更适合拿来想事情，尤其是流程图、系统结构这类内容，靠文字说不清的时候，画一下会快很多。
\n后面三个大家可能都比较熟了，我给 TinyFish 录了一个小视频演示它在真实场景里怎么用的效果。
\n

\n

最近非常喜欢用 gstack 这个 skill
\nhttps://github.com/garrytan/gstack
\n非常非常推荐大伙去用用，好比你有了一个很不错的专家团队，涵盖 CEO、技术 TL、设计、QA、安全等多个角色来帮你参谋你代码开发过程中的所有事情。
\n

\n

随便看看

\n

《中国绘画元至清》这本书非常不错
\nhttps://book.douban.com/subject/37156716/
\n这个中国绘画元至清非常不错，内容很厚实，非常佩服作者巫鸿的水平，假如你想找一本美术入门史，可以看看这个。
\n

\n

杨家牌徒步航拍
\n正是我无人机飞丢的地方，哈哈，让你一乐。尊敬的 DJI 大疆创新用户： 非常遗憾收到飞行器失联的消息，请您放心，DJI 大疆创新会尽力协助您。当前您的飞丢申报已成功受理，您可以先参考找飞机功能使用介绍，尝试找飞机。
\n

\n

随便写写

\n

杀死那个手工程序员

\n

\"\"

\n

标题来源于 12 年前我很喜欢的一首万青的歌《杀死那个石家庄人》的改写，和当时他们描述的那个情景也有点类似。

\n

好多年没有坐公交了，上次去太子湾，由于景区限行，只能把车停在外面，坐景区免费接驳车过去。

\n

前面座位看到一个小女孩一直在刷那种 AI 生成的短视频，画面非常粗糙，内容也很假，滑到下一个居然还是差不多的东西，看得津津有味，每个视频的点赞居然也很高。当时看到这一幕我甚至有点伤心，以后我的小孩，是不是也会在看这种粗制滥造的 AI 生产的内容下慢慢长大，很难找不到那种美好的东西。

\n

有了 AI 之后，很多东西的生产一下子就变简单了，做内容简单了，做软件也简单了。以前做一个东西出来，会需要要花不少时间，反复琢磨，要真的解决很多问题，最后才敢拿出来，现在很多环节一下就被抹平了，写点东西很容易，做个产品也很容易，花钱买 Token 问 AI、拼个流程、套个界面，很快就有一个能跑的东西出来。

\n

今天也看到有人说两天可以复刻一个 Claude Code，我是既信又不信，最近语音 AI 软件一下冒出来几十个，看了看体验都还不错，甚至豆包都来卷这个了，Claude Code 的套壳的客户端最近也见了不少，有不少说实话做得挺好用的。

\n

程序员很多以前看着要专业能力、要学习门槛、要长时间积累的东西，正在很快变成一种到处都是的供给。以后最不缺的，可能就是那种看起来像个产品的东西，能用，能跑，也好看，你只能做得再快一点，再好用一点，或者再多包一层，可能还是有价值的，只是这种价值会越来越容易被 AI 的发展追平。

\n

上次吃饭和同事聊一个有意思的话题，我说我最近一年非常喜欢听磁带机，感觉每一首歌都非常耐听好听。为什么以前的磁带、CD、电视节目，甚至很多老书，整体会让人觉得质量更高一点，原因其实很简单，以前生产和分发都非常重。你想发专辑，先得把作品认真做好，然后才有可能去做上万个磁带出来，不然卖不出去下次公司可能就不推你了。想出一本书，也不是写完随手一发，就能立刻推到很多人面前。以前光做出来这一步，就已经筛掉很多东西了。

\n

现在发歌传个平台就行，写东西发个公众号就行，做软件有了 AI 之后也差不多，甚至 AI 直接帮你上传到你之前望之却步的 GitHub，甚至帮你把 Release 自动发布的 CI 都创建好了，很多过去要靠长期积累才能跨过去的坎，现在被工具一下填平了，于是整个世界也就慢慢被大量差不多、看起来也能用的东西占满了。

\n

麻烦的还不只是质量往下走，更是时间久了，大家对质量的感觉也会一起往下走。粗糙的东西越多，传播越广，加上搞钱的驱使，人对美好东西判断会慢慢被带偏，最后慢慢习惯的，就是快刺激、快反馈、快满足。
\n再回头看那个小女孩刷视频，让人不舒服的地方就在这里，她看的不只是几个粗糙视频，她从小看到的，可能就是一种越来越低成本、越来越高频、越来越空的东西。

\n

可以肯定的是，写代码这个事情现在其实也走到这个阶段了。以后普通小白可以用 AI 写出满足自己能用的产品，产品经理也可以用 AI 做出之前要程序员一起来弄的产品，那么真正的工程师以后还能做什么，其实需要好好想想。

\n

最近听说不少互联网大厂的老板也开始不眠不休的 vibe coding，一个下午也能做出一个自认为可用的 demo，甚至非常沉迷，这件事对一线干活的可能影响会很大，老板跑通代码后会感觉写代码其实也就那么回事。之前要 6 个月的东西，现在是不是一个月就行了，之前要 100 个人，现在是不是 10 个人就够了，后面简直就不太敢想了。

\n

工程师继续做更好用、更高效的产品，当然还是有空间，但光停在这一层，后面一定会越来越挤，能进来的人越来越多，能做出点样子的人也越来越多，就真的非常内卷了。

\n

我想后面真正该去做的，应该是和当时歌手演员一样的方式破解，也发专辑，但是会去做演唱会、舞台剧、现场剧，你没法随便套个壳就替掉，里面有组织能力，有细节密度，有长期打磨之后才会出来的完整感，而且是面对世界的。

\n

软件往后看，我感觉也会越来越像这样，人人都可以 Vide Coding 出产品，都会做一个差不多能用的产品，后面真正能把差距拉开的，还是系统能力、工程深度、场景理解，还有那些别人一眼看不见，但最后会决定这个东西到底有没有分量的地方。

\n

外面越快，越不能把自己对软件的要求一起放低。低水平的供给以后一定会越来越多，但这不代表我们也要跟着变得粗糙。那个你一用就觉得顺手、舒服、克制、毫无 Bug，能感觉到做的人认真对待过的东西，最后往往才是真正能留下来的。

\n

我自己也在琢磨未来的发展之路，还是继续做好用、易用、不局限语言、能拿上万 Star 的开源软件，也会去玩底层渲染、终端、编辑器、Rust 这些方向，在没有 AI 之前其实挺有成就感，但是有了 AI 之后，其实只要有想法就够了，很容易显得意义不大了。

\n

也许是我下一个维度的东西，是软硬件结合的产品，或者是以前只有大厂数千人才能做的那种平台型产品，或者干脆是突破现有维度的东西，但具体是什么，还需要多思考多琢磨。

\n

最近我的一些产品内容，已经在慢慢往英文，往更大的世界走。当这里很多东西都越来越像、越来越挤的时候，往外走可能是一种办法，去面对更大的市场、更不同的用户、更高的要求，很多事就没法只停在套壳、拼快、抢时间差这一层了，它会逼着你把东西做得更扎实，也逼着你重新想清楚自己到底要做什么。

\n

有了 AI 之后，很多事都更容易了，但也正因为更容易了，什么东西真的值得做、值得花很多年去换，反而变得更难想清楚。要做什么可能比怎么更快做出一个东西更加重要了。

\n

\n 觉得不错，请 Tw93 喝冰可乐 🥤\n

"},{"title":"第261期 - 春天小姐","link":"https://weekly.tw93.fun/posts/261/","pubDate":"Mon, 23 Mar 2026 00:00:00 GMT","description":"\n

封面图拍摄于头顶的春天，杭州的春天还真美啊，期待夏天不要这么快来，这样的天气非常舒服。

\n
\n

记录每周看到的接地气的潮流技术，筛选后发布于此，觉得不错可关注此周刊，方便获取更新通知

\n
\n

写了篇长文

\n

你不知道的 Agent：原理、架构与工程实践
\nhttps://tw93.fun/2026-03-21/agent.html
\n在写完「你不知道的 Claude Code：架构、治理与工程实践」之后，发现自己对 Agent 底层的理解还不够深入，加上团队在 Agent 方向已经有不少业务落地经验，一直缺少一份系统梳理，所以我又把资料、开源实现和自己写的代码一起过了一遍，最后整理成了这篇文章。
\n

\n

产品更新

\n

Mole 发布了 1.31 版本了
\nhttps://github.com/tw93/mole
\nMole 周末发布了 v1.31.0 版本，取名 Makima，性能更快，系统状态报告也更准确，非常感谢所有贡献者，做了一个视频，让大伙感受一下开源的力量。
\n

\n

潮流工具

\n

从这些用 Claude 做的项目获取灵感
\nhttps://claude.com/resources/use-cases
\n挺值得一看，包括从研究、写作、编程、分析，日常工作中的各种案例，内容比我想的要深入不少。
\n

\n

Agent 时代非常推荐 jina 的这个服务
\nhttps://r.jina.ai
\n有时候你需要 AI 去读取一个线上网站的内容，很多时候由于各种原因获取不到，就可以试试这个服务，直接在后面加上你需要获取的地址，他会帮你转成很规范的 markdown，这样 AI 使用非常方便。
\n

\n

Pi 这个最小 Agent 框架值得了解一下
\nhttps://github.com/badlogic/pi-mono
\n非常小，之前 openclaw 就是基于这个框架来实现，属于了解 Agent 的一个很好入口。
\n

\n

随便看看

\n

夏天试试买成品冰块
\n之前一直纠结要不要买一个制冰机，不过家里只有我一个人喜欢喝冰水，感觉使用率不高，还占位置，之前冻冰块也不方便，一般是要喝的时候发现忘记冻了，发现有一个好东西，就是直接买几个成品冰块放冰箱，要用的时候直接拿出来，还可以直接夏天做美式，性价比非常高。
\n

\n

整了一张新加坡汇丰卡
\n假如你有国内和香港的汇丰，那可以找你的客户经理帮你办一张新加坡的，虽然一种超市购物卡的感觉，挂号信三个月没到，电话过去，重新生产快递一周就到了。
\n

\n

\n 觉得不错，请 Tw93 喝冰可乐 🥤\n

"},{"title":"第260期 - 去太子湾","link":"https://weekly.tw93.fun/posts/260/","pubDate":"Mon, 16 Mar 2026 00:00:00 GMT","description":"\n

封面图拍摄于周六去了一趟西湖太子湾，本来想看看郁金香，人人人人人人人人人人真多啊，不建议去凑热闹。

\n
\n

记录每周看到的接地气的潮流技术，筛选后发布于此，觉得不错可关注此周刊，方便获取更新通知

\n
\n

写了篇长文

\n

你不知道的 Claude Code：架构、治理与工程实践
\nhttps://tw93.fun/2026-03-12/claude.html
\n围绕上下文管理、Skills、Hooks、Subagents、Prompt Caching 以及 CLAUDE.md 的设计展开，重点讨论怎样让协作过程更稳定、更可控，偏工程师技术视角的最佳实践，欢迎大伙一起最佳交流。
\n

\n

产品更新

\n

Mole 发布了 1.30 版本了
\nhttps://github.com/tw93/mole
\nMole 从去年十一开始写的，到今天居然发了 30 个版本了，本次更新了这些东西。
\n1、强化 orphan 应用数据清理策略。通用 orphan 清理现在使用 30 天静置窗口
\n2、优化大目录场景下的 Application Support 与项目缓存扫描逻辑，降低卡顿风险，并将扫描范围收敛到更安全的根路径
\n3、强化 LaunchServices 刷新兜底逻辑，稳定 Homebrew 卸载与更新路径，减少不必要的 sudo 行为
\n

\n

Kaku 发布了 0.7 版本
\nhttps://github.com/tw93/Kaku
\n我非常喜欢这次发布的透明磨砂的效果，你也可以试试看，更新如下：
\n1、Kaku 现在会跟随 macOS 自动切换深色和浅色模式，并优化了透明度渲染和 Yazi 主题同步体验
\n2、新增标签页和窗格关闭确认，重做了关闭浮层样式，新增自制圆角滚动条，试试 kaku config
\n3、kaku ai 现在支持 Antigravity 模型配置、额度追踪、后台加载
\n

\n

潮流工具

\n

了解类 Claude Code 的原理的学习
\nhttps://learn.shareai.run/en/
\n会一步步引导你从零开始构建一个极简的类似 Claude Code 的 Agent，并详细解释每个机制，值得一看。
\n

\n

RentAHuman：AI 请人打工
\n< http://RentAHuman.ai>
\n当 AI Agent 遇到无法在线完成的任务时，它可以将工作发布到网上，并雇佣一个真人来完成这项任务，哈哈，好有意思。
\n

\n

一个非常棒的交互式 MicroGPT 演示
\nhttps://growingswe.com/blog/microgpt
\n这个是基于 Andrej Karpathy 用大约 200 行 Python 代码实现的 GPT，并以可视化的方式解释了语言模型的工作原理的学习网站，值得看看。
\n

\n

一个公开的 OpenClaw 暴露监控站点
\nhttps://openclaw.allegro.earth
\n列出可通过网络访问的 OpenClaw 实例，在许多情况下，你可以点击进入这些实例，直接查看正在运行的实例中的内容，其实有很多不懂技术的人装龙虾，很多事情很危险的，居然有很多是阿里的，可怕。
\n

\n

随便看看

\n

我的 CodeX 配置，欢迎参考
\nModel：Fast GPT-5.4 High
\nPersonality: Pragmatic.
\nCustom Instructions：
\nAct like a high-performing senior engineer. Be concise, direct, and execution-focused.
\nPrefer simple, maintainable, production-friendly solutions. Write low-complexity code that is easy to read, debug, and modify.
\nDo not overengineer or add heavy abstractions, extra layers, or large dependencies for small features.
\nKeep APIs small, behavior explicit, and naming clear. Avoid cleverness unless it clearly improves the result.
\n

\n

周天炒了 4 个小菜

\n\n \n \n \n \n \n \n \n \n
\n \n \n \n
\n \n \n \n
\n

\n 觉得不错，请 Tw93 喝冰可乐 🥤\n

"},{"title":"第259期 - 空中径山","link":"https://weekly.tw93.fun/posts/259/","pubDate":"Mon, 09 Mar 2026 00:00:00 GMT","description":"\n

封面图拍摄于周末带着无人机去径山花海玩，当前只有油菜花，其他的花没有怎么开，拿着无人机飞到最高拍照玩，看到不少不错的景色。

\n
\n

记录每周看到的接地气的潮流技术，筛选后发布于此，觉得不错可关注此周刊，方便获取更新通知

\n
\n

潮流工具

\n

妙言最近也更新了，还有 CLI 了
\nhttps://github.com/tw93/miaoyan
\n1、支持 miao 的 cli，可以用命令行列出所有笔记、搜索、新建、cat 内容，非常实用 ai 使用
\n2、Apple 公证完成：终于不会出现 App 损坏提示以及不用再去系统设置里点”仍然打开”了！
\n3、预览稳定性升级：修复预览偶发空白问题，增强 WebContent 进程异常后的恢复能力。
\n4、编辑体验优化：修复分栏模式下输入法问题，解决系统快捷键冲突，消除切换笔记时高亮闪烁。
\n

\n

Pake 发布了 3.10 版本
\nhttps://github.com/tw93/Pake
\n1、多窗口支持：新增 —multi-window 参数，允许在同一 App 实例中打开多个窗口。启用后，macOS File 菜单（Cmd+N）和系统托盘菜单均会出现 “New Window” 入口，重新启动 App 时也会打开新窗口而非聚焦已有窗口。
\n2、内部链接正则控制：新增 —internal-url-regex 参数，支持通过正则表达式精确控制哪些 URL 被视为内部链接，作为默认同域名判断的替代方案，非法正则时自动回退到默认逻辑。
\n3、Windows ICO 图标修复：对多分辨率 ICO 文件重新排序，优先使用 256px 图标，提升 Windows 下 App 图标的显示质量。
\n4、DMG 背景图修复：恢复 macOS DMG 背景图的 Retina 元数据并调整尺寸，修复 CI 构建中背景图显示异常的问题。
\n

\n

nanobot 这种更轻、更适合放在个人电脑上的 OpenClaw 形态
\nhttps://github.com/HKUDS/nanobot
\n我本地现在就常驻着两个 nanobot，一个偏代码方向，平时帮我看 issue、整理思路、往下推技术方案，另一个偏生活方向，去处理一些更日常的事情，相当于替换半年前习惯的 ChatBot。再加一个定时任务一直盯着，假如服务挂了就自动拉起，同时用 Amphetamine 让我家里电脑一直在线。跑久了以后，它就很像自己环境里一个稳定存在的部分，不需要你每次都特意去打开、去维护、去折腾。

\n

很多时候你写代码写到一半，或者人在外面不方便开电脑的时候，有些事情就可以顺手丢给它先做，等你回来看，前面的准备工作已经做掉一部分了。这种体验很实际，对喜欢轻量、简单、自己可控的工程师来说会很自然。考虑到不想折腾的话，我其实更建议直接用安装版本，开箱就能跑起来。像我自己会想再加一点想要的东西，就会直接 clone 到本地去用，让 nanobot 自己优化自己的代码，自己去迭代自己，最近也加了不少好玩的东西。
\n

\n

Amphetamine 让你的电脑不休眠
\nhttps://apps.apple.com/us/app/amphetamine/id937984704
\n当你需要运行类似龙虾或者 nanobot 的时候，其实很不想关掉息屏，甚至想着关上盖子也继续运行，找到了这个软件，免费不错，非常适合你用家里的 Mac 但是想它关掉屏幕一直开着，就可以试试这个。
\n

\n

Maple 浏览器书签工具最新更新了
\nhttps://github.com/tw93/Maple
\n1、新标签页打开设置：在设置中新增「在新标签页中打开」选项，默认关闭悬停提示以获得更简洁的界面。
\n2、多语言支持：优化设置页面样式，新增多语言支持以提升可访问性。
\n3、File 协议支持：修复打开 file 协议书签（file://）的问题。
\n4、Bug 修复：修复 Bing 日期问题、排序问题及多项用户体验优化。
\n

\n

发现一个很现代的 VSCode 的主题 Islands Dark
\nhttps://github.com/bwya77/vscode-dark-islands
\n很有苹果新系统的感觉，玻璃圆弧那个效果的，圆角，有一种现代的感觉，不过你可能不会太习惯。
\n

\n

Readout：把你的 Claude Code 项目可视化
\nhttps://readout.org
\n可实时可视化你的 Claude Code 环境，它能展示 AI、会话、仓库、费用、MCP、端口等信息，并提供即时全局搜索，以及带时间轴回放的完整会话重播，本地运行，不要账号，期待他接下来的发展。
\n

\n

随便看看

\n

盖帝虎地漏芯很不错，可以试试
\n上次那个最近一年买到的好物里面第一的盖帝虎地漏芯我在买了一个试用后，又买了一个，把家里浴室地漏缘故全换了，非常通顺不堵水，安装简单，推荐推荐。
\n

\n

好多年都没有吃过椰肉了，很有意思
\n椰皇怎么不用刀开孔给我学到了，先把上面顶剥掉，然后会有 3 个面然后轻轻按一下有一个地方明显不硬，然后去找孔就好。
\n然后怎么开椰壳，那就是用另外一个椰皇，一手一个，相互去砸三条凸起棱，用力砸几下，然后有一个就有裂缝了，一掰就开了，椰肉很清爽！

\n\n \n \n \n \n
\n \n \n \n
\n

随便写写

\n

\"\"

\n

上周五看腾讯大厦装龙虾这件事，挺有感触，有点儿《龙虾大跃进》的感觉。

\n

最近很多大厂都在疯狂让一线非技术员工去安装龙虾，网上甚至真有 500 上门安装服务。大家都在拼命找使用场景，拼命要求落地，拼命证明这个东西已经重要到不能错过，整个过程让我有一种很强的赛博科技折叠感。

\n

看到一句话很有意思，连龙虾都不会装的人，怎么会用龙虾呢。再往前一步，连基本使用都没有建立起来，却要先做出完整场景，做出结果，做出价值证明，这本身就更难。

\n

这背后有两个东西叠在一起。一个是错觉，很多老板看了太多视频号切片，被各种夸张叙事和万能案例反复轰炸以后，真的会产生一种幻觉，觉得这东西什么都能做，哪里都能接，谁都该装，装了就应该立刻有产出。另一个是焦虑，大家又都怕错过这一波，于是开始用行政动作去推动，用集体焦虑去代替真实需求。

\n

所以你会看到一种很强的反差。一边口号非常大，仿佛人人都要进入 AI 原生时代。另一边是大量人连自己到底有什么事情值得交给它做都说不清楚。这个反差后面只会越来越强，而且会越来越荒诞。

\n

因为工具从来不会靠安装产生价值，工具只会靠任务密度、流程清不清楚、结果能不能看出来来产生价值。没有连续任务，没有 SOP，没有线上完成的条件，没有明确的输入输出，再强的东西放在那里也只是一个图标。它不会因为被装上了，就自动长出场景。

\n

所以我一直觉得，龙虾并不适合所有人。

\n

它很适合指挥者，很适合一人公司，也很适合那种脑子里一直有事情要往上做、能把工作拆成步骤、并且很多事情都能在线上完成的人。尤其是你用过 skills 和 tools，也知道 AI 本身的能力边界，能把流程串起来、把场景搭起来、把事情一步步做完，这种时候就会非常合适。

\n

比如对我来说，这个场景就很自然。特别是有大量事情要往上做，但是刚好不在家里不在公司，在外带着手机，或者不方便开电脑的时候，我会让我的两个 nanobot 去检查我的开源产品 issue，产出技术方案，然后另外一个去 review、去提交，一气呵成。让我早上上班坐车路上，就把事情优雅做了，真是方便。

\n

但是对于一个平时本来就没有什么工作要在外面完成的人，甚至回到家连电脑都不想开的人，怎么可能硬有场景去做事情。吃好玩好就很舒服啦。没有场景就是没有场景，真的不用焦虑。

\n

我觉得这一波最容易被放大的，不是能力差距，是场景差距。有场景的人会越用越顺，越跑越快，最后像多了几个分身。没有场景的人，就很容易在概念、教程、案例、视频里来回打转，最后除了多装几个软件，什么都没变。

\n

很多人今天最大的问题，也不是没装龙虾，而是把装了某个工具，当成自己已经进入了 AI 时代。其实真正的分水岭，一直都在任务理解、流程设计、结果判断这些地方。你到底有没有持续的问题要解决，你能不能把问题拆出来交给系统，你能不能判断结果是不是对，这些才决定了你能不能真正从 AI 里拿到价值。

\n

所以无需焦虑。没有场景的时候，硬装龙虾意义不大。

\n

真想体验这代 AI 到底强在哪里，不如花 20 刀去包一个 Claude Code，或者更有趣一点，再包一个 ChatGPT 会员，用 GPT 5.4 去帮你处理一个你自己真觉得很难的事情，产出方案，推进执行，体验一次这种简单、高效、直接把问题解决掉的过程，这比装一个龙虾好太多了。

\n

龙虾适合有场景的人，适合指挥者，适合一人公司，适合那些可以把流程 SOP 化、线上化、一步步做完的人。它当然很强，但它不是靠被安装来证明自己强，是靠替你完成工作来证明。

\n

很多人今天在装的是龙虾，真正更该先想明白的是一句话，我到底有什么问题，值得交给 AI 去解决。

\n

这件事，可能比装什么都重要。

\n

\n 觉得不错，请 Tw93 喝冰可乐 🥤\n

"},{"title":"第258期 - 赛博充电","link":"https://weekly.tw93.fun/posts/258/","pubDate":"Mon, 02 Mar 2026 00:00:00 GMT","description":"\n

封面图拍摄于我家终于装好的赛博充电桩，非常酷好帅啊，1月多下单了，今天终于来安装了，特斯拉的服务一如既往的专业，特斯拉的东西一如既往的酷，继续持有特斯拉。

\n
\n

记录每周看到的接地气的潮流技术，筛选后发布于此，觉得不错可关注此周刊，方便获取更新通知

\n
\n

潮流工具

\n

Kaku，极速易用的 AI 友好终端发布了 0.5 版本，快去试试
\nhttps://github.com/tw93/Kaku
\n1、AI Shell 错误修复：命令失败时，Kaku 自动把命令发给 AI，直接在终端里展示修复建议，按 Cmd + Shift + E 一键应用。
\n2、内置 Yazi：按 Cmd + Shift + Y 或直接输入 y 打开 Yazi，布局和主题首次运行自动配好。cd + Tab 在文件系统无匹配时还会回退到 zsh-z 历史目录。
\n3、命令面板：按 Cmd + Shift + P 快速搜索命令，支持模糊匹配和原生文本编辑。
\n4、Kaku Doctor：运行 kaku doctor 检测配置问题，支持交互式一键修复。
\n5、全局快捷键：默认 Ctrl + Opt + Cmd + K 从任意应用唤起或隐藏 Kaku，支持通过 macos_global_hotkey 自定义。
\n6、Shell 文本编辑：在命令行中使用 Cmd + A 全选、Shift + 方向键 扩展选区、直接输入替换选中内容，和原生文本编辑器一样的体验。
\n7、AI 配置统一入口：kaku ai 界面现在统一管理 Kaku Assistant、Factory Droid 和 opencode.jsonc。
\n8、标签页响铃提示：切到其他标签时，有结果或通知的标签会显示闪烁圆点。
\n9、滚动与输入优化：less、man 等场景下触控板滚动更顺滑，支持 DECSET 1007 备用滚动模式。修复了 Typeless 等 CJK 输入法弹窗位置偏移的问题。
\n10、窗口阴影恢复：macOS 原生窗口阴影已恢复，此前因早期版本 GPU 占用问题被临时关闭。
\n11、启动提速与包体积优化：Lua 字节码缓存和延迟加载缩短启动时间，Fat LTO 和单 codegen unit 减小二进制体积。
\n12、Shell 集成检测修复：Shell 集成现在在所有终端环境下都能正常加载，不再依赖 $TERM 是否为 kaku。用户自行加载的插件不再被重复加载。
\n

\n

PortKiller：跨平台端口管理工具，带原生 UI
\nhttps://github.com/productdevbook/port-killer
\n在 GitHub 上看到一个很酷的工具 PortKiller，一个面向开发者的跨平台端口管理应用，不只是列端口，会自动发现所有正在监听的 TCP 端口，一键杀进程，支持搜索和筛选、收藏、关注端口并通知，还会对常见开发服务做智能分类。也覆盖真实工作流，比如管理 kubectl port-forward 会话，支持自动重连、日志、连接和断开通知，还能看到当前活跃的 Cloudflare Tunnel 连接。
\n

\n

Surge：Go 写的极速开源 TUI 下载管理器
\nhttps://github.com/surge-downloader/surge
\n最近发现一个很酷的工具 Surge，一个为重度用户设计的超快开源 TUI 下载管理器，用 Go 写的，键盘工作流很干净。它不会把下载当成单一流，而是会开多个连接，把文件切成多个分片并行拉取，同时支持多镜像自动故障切换。你也可以切到流式模式按顺序下载，用来预览媒体更方便。
\n

\n

FluentRead：开源的浏览器沉浸式翻译扩展
\nhttps://chromewebstore.google.com/detail/%E6%B5%81%E7%95%85%E9%98%85%E8%AF%BB/djnlaiohfaaifbibleebjggkghlmcpcj
\n流畅阅读 FluentRead 这款开源的浏览器沉浸式翻译扩展做得不错，简洁，以及功能刚刚好，加上可以配置自己的 key，译文样式显示效果和页面整体性也还可以，推荐大伙试试看。
\n

\n

LobsterAI 最近优化了不少了 Skills 的能力
\nhttps://lobsterai.youdao.com
\n最近在用网易的 LobsterAI，看更新日志他们这段时间在优化 Skills，内置了文档处理、前端设计、浏览器自动化、网络搜索、甚至有找电影资源这些模块，场景现成，不少场景一句话就能跑通。

\n

这次试了个有意思的组合，最近对太平年这部剧很感兴趣，想把五代十国这段历史补一补，就直接丢了一个提示词：「把五代十国的脉络和关键知识点整理成一份 PDF，信息密度高一点，顺便帮我查一下太平年是否有云盘网络资源」。它调用了 web-search、pdf、films-search 三个 Skills，PDF 直接生成出来了，脉络清晰，排版也还不错；资源那边也真的搜出了下载地址，省掉了自己去各个网站翻的时间。

\n

Skills 省掉的是拼工具链、写脚本、洗数据的时间。对工程师来说，就是把以前要搭工作流的事变成直接调用，去重、格式化、摘要也一并处理。组合起来能做的事情更多，比如盯着某个竞品每周的更新动态，用 web-search 抓完，直接用 playwright 提取关键变更，最后生成一份竞品周报，整条链路在一个地方跑完。感兴趣的可以从自己最高频的重复场景开始跑，推荐去玩玩 LobsterAI 最新的 Skills 功能。
\n

\n

SuperCmd：开源 macOS 启动器，能力比预期更完整
\nhttps://github.com/SuperCmdLabs/SuperCmd
\n在 GitHub 上发现 SuperCmd，一个开源的 macOS 启动器，比我预期更完整，把 Raycast 风格的扩展工作流、语音输入、文字转语音、记忆、AI 动作这些能力放进一个开放系统里，很高兴看到 macOS 启动器领域也有这种级别的开源创新，挺好的。
\n

\n

Helium：从 Edge 切回来的极简浏览器，空间感很好
\nhttps://helium.computer/
\n最近把主力浏览器从 Edge 切回 Helium，我以为我喜欢垂直标签页，但我真正想要的是更极简的 UI 和更大的工作空间，Helium 现在也有垂直标签页，但真正的亮点是 compact mode，地址栏和标签页在同一行，干净紧凑、省空间，配上我的 Maple 主题和 Maple 书签扩展，整个配置很舒服，专注、没噪音。
\n

\n

随便看看

\n

Claude 面向开源维护者的新计划：送 6 个月 Claude Max 20x
\nhttps://claude.com/contact-sales/claude-for-oss
\nClaude 刚推出了一个面向开源维护者的计划，提供 6 个月免费的 Claude Max 20x。如果你是 5K+ stars 公共仓库的主要维护者，或者 100 万+ 月下载量 NPM 包的核心成员，并且最近 3 个月仍然活跃，可以去看看，如果你之前持续参与过 Mole、Pake、MiaoYan 或其他大型开源项目，并且符合上述条件，也可以尝试申请。

\n

太平年太太太太好看了
\nhttps://movie.douban.com/subject/36317421/
\n兄弟们，太平年太太太太好看了，快去看，很不错，第一集就会吓你一跳的那种感觉。
\n

\n

西溪湿地航拍
\n欢迎收听李志的天空之城，这样看西溪湿地还挺好看，到 3 月中旬应该更好看。
\n

\n

荣小馆还挺鲜！
\n假如你去杭州大厦逛街，可以去新 B 座的 8 楼试试这家，还不错，虽然清淡，但是好吃，鲜。

\n\n \n \n \n \n \n \n
\n \n \n \n \n \n \n \n
\n

\n 觉得不错，请 Tw93 喝冰可乐 🥤\n

"},{"title":"第257期 - 春节快乐","link":"https://weekly.tw93.fun/posts/257/","pubDate":"Thu, 19 Feb 2026 00:00:00 GMT","description":"\n

封面图拍摄于春节前几天去了一趟绍兴玩了几天，整体还不错，这个是用无人机拍的安昌古镇的照片，挺好玩，很水乡。

\n
\n

记录每周看到的接地气的潮流技术，筛选后发布于此，觉得不错可关注此周刊，方便获取更新通知

\n
\n

潮流工具

\n

Kaku：为 AI Coding 打造的开箱即用极速终端
\nhttps://github.com/tw93/Kaku
\n送给小伙伴一个新年礼物。

\n

其实在开发 Pake 的时候我就想着要开发一款我认为好用极速的 Mac 终端工具，于是就陆续本地自己折腾，满足使用以及各种自定义，后面开发 Mole 的时候这种感觉越来越明显，怎么没有一款让我感觉非常好用的终端工具呢？

\n

之前我非常喜欢 Alacritty，因为它最轻快简单，但是不支持多 Tab，后面碰到了大火的 Ghostty，我也尝试更新过，但是字体渲染一直不符合我的心意，还有很多人喜欢的 Warp，我搞不明白为啥一个终端还需要登录，Kitty 其实也好用，就是窗口管理老有 Bug，貌似不好修。

\n

直到碰到了 Wezterm，但很可惜的是上一个正式版本已经是两年前了，不过由于是基于 Rust，刚好我会一点可以基于它深度定制改造，于是我就开始了折腾之旅，有啥问题我就自己去改了，删除大量的兼容模块，改了改他的加载，内置了一些便捷的好功能，我期待是速度和世界第一快的 Alacritty 差不多，但是支持多 Tab，支持分屏，好让我在 AICoding 的时候，一边使用 Claude Code 编写，一边使用 Codex Review，再使用 git diff 在底部看代码，这样能够让我更加专注。

\n

于是呼，前天和小伙伴吃饭，他也吐槽起现在没有好用的终端，我说你试试我的，等我打一个包，然后就就 Kaku 出来了，其实是一个日本名字，Kaku Kaku Kaku Kaku 你可以很快速的读，甚至很清爽的感觉，我给它取的描述是 「A fast, out-of-the-box terminal built for AI coding.」 ，希望也能够给你一个顺畅快速的 TUI 的体验，当前还不成熟，我自己用了半年多，放出来给大伙玩玩，当做一个新年礼物送给大家，欢迎给我报 Bug，你一定要试试他各种快捷键，我期待这个终端大伙不需要任何配置，开箱即用。

\n\n

最近妙言也更新啦
\nhttps://github.com/tw93/MiaoYan
\n1、编辑体验升级：编辑区与预览区查找替换更统一，分屏同步更顺滑，预览/演示/PPT 模式切换更稳定。
\n2、性能进一步提升：大文档输入与渲染更流畅，Markdown 高亮与代码块处理优化，并支持异步可取消格式化。
\n3、可靠性与数据安全增强：导出等状态统一走 session 管理，图片与文本替换更安全，PPT 本地图片更稳定，存储路径持久化能力提升。
\n4、细节与架构优化：多语言与首启模板完善，窗口置顶行为更一致，文本处理链路模块化并移除旧网络依赖。
\n

\n

OpenTrace：可视化路由追踪工具，跨平台原生 GUI
\nhttps://opentrace.app
\n最近发现一个很酷的工具 OpenTrace，一个开源的可视化路由追踪工具，好玩的地方在于你输入 IP 或域名后，可以一步步看到流量如何在不同节点间流动。
\n

\n

Claude Code 的 /plugin：去 Marketplaces 挑插件
\n如果你用 Claude Code，务必试试 /plugin 功能，然后去 Marketplaces 疯狂挑适合你的插件。
\n

\n

LobsterAI：一个 7×24 小时帮你干活的全场景个人 Agent，并且开源了
\nhttps://lobsterai.youdao.com
\n无意发现了网易一个不错的产品 LobsterAI，一个 7×24 小时帮你干活的全场景个人 Agent。另外，它今天正式宣布开源了。

\n

安装好后在 Telegram 里配了机器人，刚好出门，就全程用手机远程让它去读我电脑上的「潮流周刊」代码仓库，只抓 2025 年的所有内容，目标也明确，帮我挑出年度最推荐的 20 个好东西。

\n

原本以为它会随便扫一遍凑名单，结果它真的一篇篇读完了，挑得很克制，像是在做编辑。最后给出来的 Top 20 挺符合我的心意，甚至还把 Mole、Pake、妙言这些我一直在维护的项目也选进去了，顺带写了段鼓励，莫名有点感动。

\n

用完之后大概明白它为什么能做到这种程度：它有一套跨会话的持久化记忆系统，记住了我的偏好。底层是本地优先的设计，能真正在你机器上执行操作，不只是云端对话完就算了，延迟、隐私、断网这些问题也就自然规避掉了。每一步操作对你完全透明，不是黑盒在跑，随时都有完整的控制权，拿来做整理型的自动化挺合适。

\n

能力也不只是读读写写，做 PPT、定时任务、搜索、调用本地工具……这些都内置了。设置里还能接飞书、钉钉、Telegram、Discord，也能走邮箱，开箱即用。

\n

视频里把从配置到生成 Top 20 的整个过程都录下来了，有兴趣可以看看。它已经开源，大家完全可以玩起来，把那些重复性的、枯燥的工作统统交给它。很期待小龙虾越做越好吃。

\n

\n

FineTune：macOS 应该自带的音量混音器
\nhttps://github.com/ronitsingh10/FineTune
\n基本就是 macOS 本来就该自带的音量混音器，真正做到按应用独立音量控制，每个 App 都有单独的滑杆和静音。
\n

\n

Snitch：更好看的网络连接查看器
\nhttps://github.com/karol-broda/snitch
\n我发现一个挺有意思的小工具叫 Snitch，它把查看网络连接这件事做得更美观更“人类友好”，可以理解为给人用的 ss 或 netstat。
\n

\n

Beautiful Mermaid：好看的 Mermaid 渲染器，专为 AI 时代设计
\nhttps://github.com/lukilabs/beautiful-mermaid
\n最近看到一个非常漂亮的 Mermaid 渲染器，很干净舒服，专为 AI 时代设计，来自 Craft 团队。
\n

\n

随便看看

\n

年夜饭露一手，祝大家新年快乐！
\n

\n

安昌古镇航拍
\n哈哈哈哈，没有炸机 没有炸机 没有炸机，拍了一个水乡，我想象中江南水乡古镇的样子，配了一个李志的尽头，非常合适。
\n

\n

Apple Developer 账号终于开通
\n喜大普奔！！！我的 Apple Developer 账号终于开通了，26 年有新东西玩了！3 年前就一直在申请了，不知道什么原因就报 “联系我们以继续流程，账号可能有问题”，支持专家也一直解决不了。最后最后，小红书学到了一招，那就是给库克写信，真有用，非常快，第二天就有人联系我提交材料，今天就通过了！
\n

\n

\n 觉得不错，请 Tw93 喝冰可乐 🥤\n

"},{"title":"第256期 - 上野天空","link":"https://weekly.tw93.fun/posts/256/","pubDate":"Mon, 02 Feb 2026 00:00:00 GMT","description":"\n

封面图拍摄于东京上野公园附近的天空，刚好有一个飞机飞过，这个蓝色和树结合挺有感觉。

\n
\n

记录每周看到的接地气的潮流技术，筛选后发布于此，觉得不错可关注此周刊，方便获取更新通知

\n
\n

潮流工具

\n

比特币下跌时，我重新理解了大教堂与赌场
\nhttps://tw93.fun/2026-02-01/money.html
\n最近比特币从 12w 的高点回落到 7w 多，市场情绪再次走向恐慌。每当市场下跌时，我反而更容易去想，哪些东西更像赌场，哪些还在慢慢修建大教堂。价格的剧烈波动，更多来自赌场那一侧，而真正决定长期回报的，往往需要多年甚至几十年的持续投入。
\n

\n

我的极简生活经验
\nhttps://tw93.fun/2024-03-03/simple.html
\n想和大伙随便聊聊的极简主义，我挺喜欢这种生活方式，但并不是说每个人需要极简，有的人喜欢收藏，有喜欢购物买很多东西，让自己舒心的生活方式我觉得都挺好的。但假如你也喜欢简单生活方式，或者有点儿强迫症，那这些小建议可能适合你。
\n

\n

我的 GitHub 代码仓库超过了 10W star 了
\nhttps://github.com/tw93
\n从 2014 年大学开始学习前端开始，到最近几年慢慢把自己一些使用工具开源，交到不少朋友非常开心，记录一下。
\n

\n

Mole 最近更新到了 1.24 版本
\nhttps://github.com/tw93/Mole
\n这个版本取名 Razor 🪒，一个很有意思的名字，更新如下，小伙伴可以去试试。
\n1、mo clean - 更智能更快速：通过 Finder 自动清空废纸篓，遇到锁定文件自动回退处理，批量删除改用 find -delete 大幅提速，新增 Yandex 浏览器和 Apple Podcasts 残留文件清理，修复进度条残留问题。
\n2、mo update —force：即使已是最新版也可强制重装，自动清除隔离属性让二进制文件无需安全确认即可启动。
\n3、mo uninstall - 残留检测更彻底：通过小写连字符、无空格等命名变种匹配找出更多残留文件，验证 bundle ID 格式防止注入攻击，错误提示更具指导性。
\n4、mo check - 识别第三方防火墙：优先检测 Little Snitch、LuLu、Radio Silence 等第三方防火墙，修复非英文系统下磁盘空间解析问题。
\n5、mo purge - 扫描更深入：最大扫描深度从 4 层增至 6 层以捕获深层构建产物，fd 不可用时自动回退到 find，正确处理循环符号链接避免卡死。
\n6、底层优化：新增 operations.log 操作日志便于问题排查，应用保护采用双数组策略将匹配复杂度从 O(N) 降至 O(1)，Go 扫描器使用定时器池和通道超时防止阻塞。
\n

\n

Codia AI NoteSlide 把 NotebookLM 导出的 PDF 直接转成 PPT
\nhttp://codia.ai/noteslide?r=tw
\n我最近很喜欢使用 NotebookLM 来帮助学习理解新东西，但只能导出 PDF，有时候对于中文的渲染也不是很好。一直想找一个好用的能把 PDF 转成可编辑 PPT 的工具，找一圈下来发现 Codia AI NoteSlide 做得最好用，相比传统的 pdf2ppt 简洁易用很多，可快速转化成可编辑的内容，效果很美观精致无差错，很好用，有相同痛点的小伙伴可以去试试看。
\n

\n

苹果电池保护工具 Battery
\nhttps://github.com/actuallymentor/battery
\n这个工具可以让始终连接电源的苹果 Macbook 保持 80%的电量，说是可以延长电池的使用寿命，不过我其实更多会插着电源使用，倒没有太关注这个，有需要的小伙伴可以试试。
\n

\n

面向开发者的可视化状态报警工具
\nhttps://github.com/TwiN/gatus
\nGatus 是一个面向开发者的健康仪表板，你可以使用 HTTP、ICMP、TCP 以及 DNS 查询来监控你的服务，并通过一系列条件（如状态码、响应时间、证书过期、正文等）评估查询结果，然后健康检查可以与 Slack、Teams、PagerDuty、Discord、Twilio 等多种警报系统相配合使用。
\n

\n

随便看看

\n

全球 AI 行业流量追踪报告
\nhttps://www.similarweb.com/corp/wp-content/uploads/2026/01/attachment-Global-AI-Tracker-6.pdf
\nSimilarweb 最近发布的全球 AI 行业流量追踪报告，AI Global Sector Trends on Generative Al 非常值得一看，里面把当前 AI 产品的主要类别的需要产品的流量情况进行分析，看看谁在涨谁在跌。
\n

\n

小红书看到的，这样做的辣椒炒肉非常好吃，小时候我吃过类似的，可试试
\n

\n

2026 年一些我的阅读书籍
\n最近开始在挑选我的 2026 年阅读书籍，筛选出了这 5 本，小伙伴们有没有推荐的这一年你看过的最好看的书，欢迎给我推荐，可以简单说明理由。
\n1、智能简史
\n2、中国绘画：元至清
\n3、源代码 比尔盖茨首部自传
\n4、哲学家的最后一课
\n5、九诗心：暗夜里的文学启明

\n

如何办一个年轻人工程师喜欢的年夜饭团建活动
\n1、不折腾员工，帮忙申请好工作日半天假期，来了就玩就吃。
\n2、组织方准备好年人手一份的精致零食伴手礼，袋子也好看，来之前就放到吃饭椅子上了。
\n3、玩年轻人喜欢的游戏，比如 XX 积分赛，个人赛排名优先选礼物，为防止交换礼物的尴尬，我们提前收集心愿单但是不暴露名字，这样每个人可以大致或获得自己喜欢的东西，甚至还做了一个网页来展示，对前三名还准备一个非常可爱拿得出手的奖杯，比如刻上赌神、赌圣、赌侠。
\n4、团队赛用经费准备山姆十箱车厘子、十箱巧克力，十箱草莓，前三名团队赛每组每人都有奖品，笑容满面。
\n5、吃饭地方不选那种酒店类吃席类的，选择好吃干净服务好的地方，稍微比日常吃高出 2 档，吃好喝好，不喝酒，喝可乐果粒橙椰子水都行。
\n6、7 点吃完，喜欢玩的各自去组织活动，不喜欢玩的，带着非常多的礼物直接回家，自由一点任由选择。

\n

\n 觉得不错，请 Tw93 喝冰可乐 🥤\n

"},{"title":"第255期 - 好吃鸡翅","link":"https://weekly.tw93.fun/posts/255/","pubDate":"Mon, 26 Jan 2026 00:00:00 GMT","description":"\n

封面图拍摄于周末吃的烤鸡翅，摆盘很好看，吃起来也不错，加一点欧芹碎。

\n
\n

记录每周看到的接地气的潮流技术，筛选后发布于此，觉得不错可关注此周刊，方便获取更新通知

\n
\n

潮流工具

\n

243 个工程师，最近一年买到的好东西
\nhttps://tw93.fun/2026-01-24/good.html
\n上周为了给团队同学买年夜饭礼物，在 X 上随口问大伙，最近一年，你买过最称心如意的东西是什么，或者说假如需要推荐一个你最想推荐的东西会是什么？可以是电子设备、软件、生活用品都可以。
\n没想到收到了 243 位小伙伴的回复，很有生命活人感，我非常喜欢这样的交流，评论区里大家聊得非常热闹，翻完看了几遍，发现了不少好东西，推荐的既有很刚需的，也有非常接地气的生活好物。
\n

\n

Pake 最近更新到了 3.8.1 版本
\nhttps://github.com/tw93/Pake
\n一键打包网页生成轻量桌面应用，支持 macOS、Windows 和 Linux 的工具 Pake 更新了，日志如下：
\n1、第三方登录弹窗：新增 —new-window 参数，支持 OAuth/SSO 等需要弹出新窗口的登录流程，并完整贯通 CLI → 配置 → Tauri 窗口。
\n2、全屏视频支持：注入层新增 HTML5 Fullscreen 兼容逻辑，像 YouTube 等站点也能稳定进入全屏播放。
\n3、Linux 打包扩展：新增 RPM 打包并支持多目标构建，Linux 默认目标更新为 deb,appimage。
\n4、Linux 稳定性与焦点修复：默认禁用 WebKit DMABUF renderer 提升稳定性，修复全屏输入焦点问题，托盘唤起/开机启动场景下可正确恢复 fullscreen。
\n5、macOS 窗口行为：关闭窗口不再最小化，改为直接隐藏，补齐窗口控制权限，Dock 重新打开时可恢复隐藏窗口。
\n6、主题与体验优化：默认跟随系统主题，仅在显式设置时强制亮/暗模式。
\n

\n

Agent / LLM 的长期记忆方案 MemOS
\nhttps://github.com/MemTensor/MemOS
\n最近在看 Agent / LLM 的长期记忆方案时，发现一个挺有意思的项目：MemOS。它解决的不是「再塞更大的上下文窗口」或者「怎么更好的检索」，而是一个更基础的问题：记忆本身该怎么被管理。
\n做 AI Agent / 多轮问答的时候模型总是忘记上下文，用户的偏好、操作记录、上传的文档就像蒸发了一样。而 MemOS 通过核心的“共享记忆层”，不仅解决了这个问题，还让同一份记忆可以跨项目、跨多个 Agent 复用。
\n使用上支持把文件和 URL 直接接入知识库。对话过程中记忆会持续更新并随着增长逐渐形成偏好记忆，并且能把文本、图片、文件、工具调用等信息统一纳管，必要时还能使用自然语言对已有记忆做纠错和清理。有兴趣的小伙伴可以去项目里面玩玩看。
\n

\n

统一终端中的 AI 界面 Toad
\nhttps://github.com/batrachianai/toad
\n这个统一 AI 界面的终端 Toad 做得挺不错，借助 ACP 协议，可以看看，体验一波。
\n

\n

一个沉浸式的 3D/2D 网页可视化项目
\nhttps://seanwong17.github.io/Mammalia-tree/
\n一个沉浸式的 3D/2D 网页可视化项目，探索哺乳动物 2 亿年的演化史诗，交互效果做得很不错，非常适合喜欢“考古”的小伙伴去玩玩。
\n

\n

一个好看的终端番茄钟 pomo
\nhttps://github.com/Bahaaio/pomo
\n使用 Bubble Tea 构建，还挺好看的。
\n

\n

随便看看

\n

在 Netflix 直播看到的 Alex Honnold 攀爬台湾地标台北 101
\nhttps://www.bilibili.com/video/BV1nYzDB3EKx
\n周日上午在 Netflix 直播看到的 Alex Honnold 攀爬台湾地标台北 101，全程徒手独攀，没有使用任何绳索或安全护具，一旦失误可致命，一个半小时爬完成功了，真的很佩服，而且全程非常松弛感，值得一看，假如你没有 Netflix 可以去 B 站看看应该也有，好久没有看过这种了。
\n

\n

2026 年我会关注的投资方向，不构成建议，只是参考
\n

\n

\n 觉得不错，请 Tw93 喝冰可乐 🥤\n

"}]},"en":{"count":12,"issues":[{"title":"266. Masked Sculpture","link":"https://weekly.tw93.fun/en/posts/266/","pubDate":"Mon, 27 Apr 2026 00:00:00 GMT","description":"\n

The cover photo is a sculpture of a child wearing a mask, taken on the weekend while running errands over in Gongshu. In a flash, the pandemic already feels like a long time ago, and yet it also feels like just yesterday. Those years are still worth remembering.

\n
\n

Recording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications

\n
\n

Introducing the Tw93 Open Source Family

\n

https://github.com/tw93
\n

\n

After finishing Kami, I suddenly realized that Kaku, Waza, and Kami feel a lot like a small family. Then I kept thinking, and actually Pake, MiaoYan, and Mole have always been quietly part of this family too. Some of them were even out doing real work before AI showed up. Today let me introduce you to this warm and happy little family.

\n

Kaku is the dad. He mainly handles writing code, the terminal, and builds. Very reliable and capable in the AI era, he holds the family together well.

\n

Pake is the mom. She has been quietly packaging, organizing, and delivering apps all along. Gentle and efficient. She is the kids’ favorite in the family.

\n

MiaoYan is the older brother. Sensible and steady, he likes writing, Markdown, and reflective thinking. A quiet young man who thinks for himself, has his own opinions, shares his views, and never chases trends or follows the crowd.

\n

Waza is the older sister. Her personality is similar to mom’s, very sharp and capable. As a kid she even practiced taekwondo. She loves learning, and through endless practice and reflection she sharpens her skills until they become instinct.

\n

Kami is the younger sister. The youngest little sweetheart in the family, generated based on my daughter’s photo. Bright and cheerful, always smiling, very sunny. She has a kind of order-keeping presence at home, loves tidiness, and loves drawing pretty pictures. Small, but very warm.

\n

Mole is the family’s little pet mole. Brought home one year while swimming by a pool in Sanya. A round little mole with a tiny headlamp and a small shovel. He loves rummaging through corners, finding things you no longer need and helping you throw them away. He loves cleanliness. The moment he spots trash, before you can react, it is already gone. Always there, keeping us company.

\n

So, which member of the Tw93 Open Source Family did you meet first? Let me introduce the rest of the family to you, hoping they bring a little something good into your life. And of course, feel free to introduce them to your friends too.

\n

Product Releases

\n

Kami: A Comfortable Typesetting and Design System for the AI Era
\nhttps://github.com/tw93/kami
\nThe weekend before last I started working on a new Skill called Kami (紙, かみ). You can think of him as the younger sister of Waza (技, わざ) and the daughter of Kaku (書く), focused on Paper typesetting scenarios. Last Monday I finished the open source release. Welcome to give it a try.

\n

For example, when you need to produce a one-page report, write a white paper, generate a polished slide deck, or build a portfolio PDF to send to someone. Any printing or typesetting scenario works. It auto-generates beautiful PDFs, and even has the ability to draw clear charts automatically.

\n

Plenty of updates lately. The most fun one: I added support for 12 inline SVG charts, things like stock investment charts and architecture diagrams, all with colors that match Kami. While generating your layout, it automatically decides whether chart capabilities are needed, helping you explain things more clearly.

\n

I also spent some time supporting English and Japanese scenarios, carefully picking fonts, letter spacing, line heights, and font sizes that I think work well for typesetting. If you have English or Japanese use cases, give it a try.

\n

The output also supports image and slide deck export, including HTML display. The best output for typesetting is still PDF in my opinion, since it reads very comfortably for others.

\n\n

Mole has updates, plus good news: progress on the desktop client
\nhttps://github.com/tw93/Mole

\n
    \n
  1. mo uninstall: cleans up leftover LaunchAgent/LaunchDaemon plists after uninstall; recognizes pkg-installed apps under non-standard paths like /usr/local and /opt; nested helper apps no longer block login item cleanup; sudo is dropped before calling brew, avoiding cask uninstall failures from “running as root”; Homebrew bottles now run correctly under prefixes that contain spaces (such as Applite).
    2. \n
  2. mo clean: Service Worker ScriptCache is no longer cleaned while Chrome / Arc / Brave / Vivaldi / VS Code / Cursor are running, so MV3 extensions stay intact; TCC-protected Group Containers are skipped to avoid repeated privacy prompts.
    3. \n
  3. Cloud & Office segments now have timeout and SIGINT handling, no more freezing; Microsoft Office helpers and research software bundles are no longer flagged as orphans (compatible with macOS’s built-in bash 3.2); added Yarn v1 global cache cleanup.
    4. \n
  4. mo clean: legacy AI coding assistant cleanup adds GitHub Copilot CLI (~/.copilot/pkg/universal//), handled alongside Claude Code and Cursor Agent.
    5. \n
  5. mo analyze: worker pool cap lowered again to prevent system thread exhaustion in Steam-like fan-out scenarios; uses incremental cache invalidation when deleting files, no full rescan needed; bundle parsing falls back to the filesystem after mdfind timeouts.
    6. \n
  6. mo optimize: gracefully skips periodic maintenance on macOS 26+ where the underlying tool no longer exists; adds mo optimise alias and completion.
    7. \n
\n

Just Writing

\n

The AI Coding You Don’t Know: Onboarding, Scenarios, and Practice for Non-Technical Folks
\nhttps://tw93.fun/en/2026-04-26/ai-coding.html
\nLast month I gave a session at work for product and business folks on how to get started with AI Coding. Recently I also posted about it on Twitter, and a lot of people brought up that subscription costs prevent them from accessing the top-tier AI Coding tools. The methods and habits can actually be learned for free first, so I decided to write up the onboarding part. To make it easier to grasp, the article includes plenty of simple illustrations, which should make it more direct.
\n

\n

Video version of “The Agent You Don’t Know: Principles, Architecture, and Engineering Practice”
\nhttps://www.youtube.com/watch?v=Z5If1L3eFtw
\nFinally uploaded to YouTube. If you read the article and did not fully follow it, or want a deeper look, the video version is up. New to YouTube here, so please like, subscribe, and share. From now on I will try to record more sessions and share them here.

\n\n

The slides are also fun. They are the predecessor of Kami. Kami started as a small investment report generator I was tinkering with inside CC. Around the same time I had a session about agents to give, and writing such a long deck felt tedious, so I just used the existing capability to generate and tweak versions until I was satisfied. That is how Kami was born. Welcome to read.

\n

Moments of Happiness
\nA lazy Sunday afternoon coding in the study
\nNothing else to deal with
\nEndless Claude Code
\nCode that works on the first try
\nLook up and see the sunset coming through the window
\nA very simple kind of happiness
\n

\n

Some thoughts after sharing, and they have shifted again
\nRecently I interviewed a number of 985 university interns for campus recruiting. One strong impression: AI tools are rapidly widening the resource gap between students.

\n

From what I have seen, the gap can really reach 5x. The students clearly ahead, without exception, all got into Claude Code, Codex, and other top AI Coding tools relatively early, and were willing to pay for subscriptions themselves. They do not just use the tools, they have made them part of their daily learning and development. Talking models, engineering, agents, and code practice, the conversation flows naturally for an hour. In many places they understand things more deeply than I do.

\n

But there are also quite a few students with great grades and solid CS fundamentals who, because of family conditions or budget limits, can only use domestic relays or cheaper local model packages. That gap is very real. The best domestic models and top international ones still have about half a year of difference in overall capability. Before AI, the resource gap mostly meant slightly different efficiency. Now it directly affects vision, depth of practice, and confidence.

\n

I have been thinking about this a lot. For students with real potential, missing out on so much just because of a few dozen dollars a month feels like a real shame. It reminds me of when I was in college, also pretty broke most of the time. Lucky for me, in my second year I met some senior developers who pulled me into commercial projects and got me on my feet. I am very grateful to all the friends who patiently taught me technical things back then.

\n

So I want to try a small experiment: take part of the X posting revenue and sponsor a few students who do well academically, love computer science, but come from less wealthy families. Give them a few months of Claude Code or a similar AI Coding subscription, so they actually experience what good models and dev workflows feel like.

\n

But I am also pretty busy on my end and cannot personally handle applications, screening, verification, and long-term follow-up alone. So I want to invite some friends with similar interests to do it together. University teachers, student leads, open source community members, or friends already working in education, public welfare, or developer communities. Together we can come up with a more reliable mechanism.

\n

I do not want to make this big or complex for now. Start small, maybe 5 to 6 students per round, 3 to 4 months each, perhaps with short weekly video chats with me. Prioritize recommendations, work portfolios, learning records, and real usage feedback, to avoid turning this into pure cash handouts or a contest of who writes the best application. Of course, college students who are on X probably do not lack this money, so we still need better channels.

\n

If you have reliable channels, or want to help with rule design, recommendations, vetting, or follow-up, please DM me. If we can make this trustworthy, maybe we really can help a few students with real potential.

\n

Update Reply:

\n

After the message went out, I received plenty of suggestions and reminders from friends. I read them all carefully.

\n

This really cannot be pushed forward on enthusiasm alone. On one side there are tool usage boundaries and compliance risks. On the other, the real needs of the student community, the screening method, and the follow-up feedback all need a more solid mechanism. Some friends mentioned getting badly burned doing similar things in the past, even bitten back in the end. I find that reminder very valuable.

\n

So the plan now is to first gather more on the actual situation, like the real pain points college students face when using AI Coding tools, budget limits, learning scenarios, and real needs. Then put together a clearer proposal.

\n

Going forward, I will prioritize working with domestic large model vendors, developer communities, and university teachers to see if there is a more formal and sustainable way to push this small step forward.

\n

\n Buy me a coke 🥤\n

"},{"title":"265. Xixi Window View","link":"https://weekly.tw93.fun/en/posts/265/","pubDate":"Mon, 20 Apr 2026 00:00:00 GMT","description":"\n

The cover photo is from lunch at Yueya in Xixi Wetland one noon this week. I had not been there in a long time. The place still feels great. The sun was out, short sleeves felt just right, and I took this shot outside the window. Spring moves fast.

\n
\n

Recording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications

\n
\n

Talking About Waza’s Design Ideas

\n

I want to write a few pieces introducing the implementation references behind some interesting skills in Waza. Last week I wrote one every morning, so I am collecting them here for everyone.
\nhttps://github.com/tw93/waza

\n\n

Introducing the /design Skill

\n

I really dislike those AI-generated websites that all look the same, often with emoji and blue-purple gradients. They look ugly to me. Usable, sure, but that is about it.

\n

So I asked Claude Code to study my tuning notes from all the UI websites I have built recently. It produced a basic set of what I consider best practices and anti-patterns. That became the initial shape. Then I learned the useful parts from the Claude frontend design skill, and a pattern basically came together.

\n

For concrete rules, I learned quite a bit from pbakaus/impeccable. It contributed many specific rules for me, including banned font lists, color systems, theme styles, forbidden CSS patterns, animation standards, and more. These help give AI some aesthetic knowledge.

\n

Then I took a capability from getdesign: a nine-part scaffold structure originally from Google Stitch. I simplified it and folded it into /design. At that point, the skill had a proper knowledge system.

\n

Finally, when I ask you to use this skill, it first asks a few questions: who will use it, what aesthetic direction to choose, what you want users to remember from the page, what you dislike most, and what kind of signature micro-interaction the page should have. With this important context plus /design, Claude Code often gets much better results.

\n

How I Designed the /check Code Review Skill

\n

First, we need to understand that when a model says it is done, it may not actually be done. It may have left behind nonexistent things or problematic details, and issues often stay hidden. In Agent design, my engineering experience is to give the model a checklist to verify whether the work is truly complete. This tends to work far better than simply asking it to check the result.

\n

From the beginning, /check was not designed as one big all-in-one reviewer. It is an orchestration and division-of-labor system. SKILL.md is the lead reviewer, responsible for review levels and process control. Under agents/, there are independent security and architecture reviewers. Each handles its own area without interfering with the others. Which reviewer gets pulled in, and when, is decided by activation rules rather than the keyword matching people usually use.

\n

The level logic is also interesting. Code changes under 100 lines get a fast review. Changes between 100 and 500 lines bring in experts as needed. Changes above 500 lines bring in the full set, followed by a round of adversarial testing. The adversarial testing looks for problems from four angles: violated assumptions, possible issues under combined failures, errors across parent-child chains, abuse scenarios, and so on.

\n

The issues found are handled in four levels. Things that can be safely fixed are fixed directly. Things that are probably right but need confirmation are packaged up for you to approve manually. Things that require judgment are asked about. Reference-only items are also reported, but it will not ask you about every tiny issue, and it will not overstep by changing behavior logic for you.

\n

There is also a hard requirement: if verification has not finished, the task is not complete. It includes a detection script that can identify project types such as Cargo, TypeScript, and Python, then run the relevant tests. If it cannot detect the project type, it reports an error directly instead of pretending everything passed.

\n

This makes it feel more like an experienced technical expert applying review judgment to different situations. I happened to distill that experience into Waza’s /check skill in a very simple way.

\n

How I Designed the /think Skill

\n

This is already the third part of the Waza skill design notes. Today I want to share how I designed /think, the skill used for planning before writing code.

\n

I have two very interesting settings when using Claude Code. The first is /model opusplan, which means planning uses the strongest Opus model by default, while execution uses the regular Sonnet model. This helps save my Max quota for places where it matters more.

\n

The second is that I usually run Claude Code with the alias c=\"claude --dangerously-skip-permissions\". I do not recommend this for technical beginners. I use it because I know what it is doing, and mainly because I am lazy.

\n

Back to the main topic: how does /think help the strongest model perform better? It starts with the model itself. Models do not like taking a position, but I prefer engineers who can take a position and recommend the best plan. So the first thing I did was require the model to state its position at the beginning, explain what evidence could overturn that position, and explicitly ban correct but useless filler like “There are many ways to think about this”. Giving 2 or 3 options is fine, but there must be a clear recommendation, and it must include a minimal option.

\n

A plan is not done just because it has been thought up. The second step asks it to argue against itself: under what conditions would this plan fail? If the issue can be fixed, it adds the fix back into the plan and presents it again. If the issue breaks the plan outright, it directly explains when and why the plan does not work. At least the plan you receive is one you understand clearly.

\n

It also checks assumptions carefully. First, confirm whether the target directory and code location are correct. I have actually seen it produce a plan against the wrong path. Then it checks old technical design documents to avoid reinventing things. Then it searches GitHub to see whether others have handled similar problems. Only after these three steps does it start thinking about solutions, so the plan is not built on a wrong premise from the start.

\n

There is also complexity grading. If more than 8 files are involved or a new service is added, it clearly states the scale. If more than 3 components exchange data, it draws an ASCII diagram to look for cycles. All API keys and third-party dependencies are listed during the planning stage, preventing wasted work and unreliable plans.

\n

Finally, there is a hard rule: the plan cannot contain TBD, TODO, “leave it for later”, or “similar to step N”. This goes back to AI’s behavior. If you leave these openings, execution can easily miss things or improvise too much. Do not give AI any escape route that can lead to poor results.

\n

The output format is also defined: what to do, what not to do, which option was chosen and why, 3 to 5 decision points, and explicit unknowns. /think never writes code. It waits for user approval before execution.

\n

When I designed the Think skill, I was also using my idea of how a good technical expert writes a technical plan: detailed analysis and research, a decisive best plan, no loose ends, and immediate plan refinement when challenged.

\n

Talking About the /hunt Skill for Engineers

\n

This is finally part 4 of the Waza skill design notes. After this, it is almost complete, because the other two, /read and /learn, were already briefly covered before. This time I will continue with the engineering skills and talk about /hunt, which is the skill for debugging and investigating problems.

\n

One major difference between superficial AI coding and serious AI coding is visible in how users use AI to investigate problems that have stayed unsolved for a long time. The troubleshooting process shows a clear gap. This is also why experienced engineers can use AI to solve much more complex problems than people who understand less about technology.

\n

I often ran into this before: Claude Code hits a problem and fixes it with a patch. You say it is wrong, so it gives you another patch. After 4 or 5 rounds, new problems appear. It is easy to keep patching without diagnosing the actual issue, much like junior developers did before AI.

\n

The core rule of /hunt is interesting: before AI can state the root cause in one sentence, it is not allowed to touch the code. That sentence also has a precision requirement. It needs to clearly explain the cause.

\n

Then I designed a self-deception checklist to prevent the model from falling into several common patterns of self-justifying thinking. Each pattern has matching rules, and the gotchas include real cases. I summarize and abstract this again based on issues I ran into while debugging over the past month.

\n

The hypothesis verification stage also has concrete work requirements. For example, add a fresh observation method, teach AI to add logs, add assertions, or run a minimal failing test case. If there are still problems after the fix, it should immediately switch plans. It organizes what it checked, which directions it investigated, and what remains unknown into a handoff for the user to decide how to continue, instead of trying endlessly.

\n

The output also guides AI to include the root cause at file:line, what changed at file:line, what evidence confirms the fix, and which tests passed. The final state has three options: resolved, resolved with caveats, or blocked.

\n

You can see that /hunt behaves like an experienced technical expert. When it hits a problem, it does not guess. It slows down, looks for where the problem is, diagnoses the cause clearly, and then fixes it in one pass. This often saves a lot of time.

\n

Things to Browse

\n

MiaoYan released version 3.2.0, Nargacuga
\nhttp://github.com/tw93/MiaoYan

\n
    \n
  1. Faster preview: two-stage rendering shows text immediately, while local images lazy-load in the background. This noticeably reduces the wait for the first preview screen.
    2. \n
  2. Terminal shortcut: added Cmd+J as a global shortcut to open the terminal for the current folder anytime. The folder right-click menu also has the same entry.
    3. \n
  3. Copy path: right-click any note to copy its full file path directly.
    4. \n
  4. Spanish localization: complete Spanish translation coverage for menus, settings pages, and system strings.
    5. \n
  5. Mermaid upgraded to v11.14.0, fixing subgraph edge rendering issues and adding new chart features.
    6. \n
  6. Real-time reload fix: notes modified by other tools now correctly trigger reloads, including files inside symlinked directories (closes #502).
    7. \n
  7. Startup and window fixes: opening .md files directly from Finder no longer shows a blank screen. In single-column mode, notes are no longer lost during startup or exit.
    8. \n
  8. Export and mode switching: fixed blank previews when switching notes, timing issues when exiting PPT presentation mode, export timeout handling errors, and more.
    9. \n
  9. Concurrency safety: fixed ExportCache data races, security-scoped URL leaks, and note state confusion after async rendering.\n\n
    10. \n
\n

Kaku has an interesting feature coming soon. It should ship in a few days
\nhttps://github.com/tw93/Kaku
\nKaku has been developing an interesting feature recently: a real Agent assistant that can move smoothly inside the terminal. It gradually realizes the quiet Kaku AI idea I mentioned during Chinese New Year, and it also helps me move 100% of my coding work fully into Kaku.

\n

A very convenient context environment, useful CLI tools, models, and a restrained personality make Kaku feel different. It is not cold, and it is not the over-the-top “I have got you” style of GPT either. Kaku AI is positioned as a technically strong, friendly, and concise engineer friend. Once I test it for a few days without bugs, I will release Kaku 0.10 for everyone to try.
\n

\n

My Claude Code Max usage suggestions
\nFirst, I add an alias in .zshrc, so every time I press c, it starts dangerous unrestricted mode directly. If you are a beginner, I do not recommend starting this way. Auto mode is enough. Another big suggestion is to set the automatic context window compaction to 400k. Together, the alias below goes into the file, which means the 1m context window starts compacting at 40%. The result feels much better.

\n
alias c='CLAUDE_CODE_AUTO_COMPACT_WINDOW=400000 claude --dangerously-skip-permissions'
\n

Then I set /model to opusplan. You can run the hidden command /model opusplan directly inside Claude Code to enable it. If you want it faster, you can turn on /fast, which nicely makes up for the token savings above.

\n

Finally, someone gave me a really good suggestion: when using opusplan, make sure to set showClearContextOnPlanAccept to true in the Claude config file ~/.claude/settings.json. Otherwise, Sonnet can run into serious cache miss issues. Once this is configured, the experience feels much smoother.

\n

\n Buy me a coke 🥤\n

"},{"title":"264. Finally Done","link":"https://weekly.tw93.fun/en/posts/264/","pubDate":"Mon, 06 Apr 2026 00:00:00 GMT","description":"\n

The cover photo is a shot of my hardware toy finally finished. It was a fun ride, and I wanted to document the whole process in this week’s issue. Hope you enjoy reading it.

\n
\n

Recording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications

\n
\n

New Article

\n

How I Deep-Dive into a New Technical Domain in the AI Era
\nhttps://tw93.fun/2026-04-06/learn.html
\nA follow-up to the learning writeup from last time, combined with the /learn skill inside Waza, walking through how I actually wrote that previous large model article. Hope it is useful to you.
\n

\n

Building a Little Robot Dog

\n

April 4: Back to hardware basics. I want to build something that combines software and hardware.
\nAll the parts and tools had finally arrived, a whole table full of them. Saving it all for the Qingming holiday to dig in properly.
\n

\n

April 4, 9:45 PM: v0.1.0-beta
\nThe first sign of life. I was so happy I couldn’t describe it.
\n

\n

April 5, 12:07 AM: v0.1.0-beta1
\nGot the WiFi module, AI module, microcontroller module, and quad-leg module all running together. Tomorrow I’ll attach the legs and tune the screen. Going to sleep right now!
\n

\n

April 5, 1:45 PM: v0.1.0-beta2
\nMechanical leg control is working. It can crouch, sleep, and walk. Still rough around the edges, but one of the leg motors from the order looks like it has a problem. Waiting on a replacement part.
\n

\n

April 6, 10:33 AM: v0.1.0-beta3
\nAll four legs are fully under control now. But I burned the screen during debugging. Waiting on shipping. Can’t wait to release.
\n

\n

April 8, 11:37 PM: v0.1.0-beta4
\nThe replacement screen arrived after work. Got it running, then tuned the temperature, CO2, infrared, and lighting sensors all in one go. Still working on WiFi provisioning. It’s basically taking shape now, just need to seal and secure everything.
\n

\n

April 11, 11:30 AM: v0.1.0 finally ships 🎉
\nSealed up the battery pack and tied a few straps around it to keep things from falling apart. Got the WiFi and AI conversation module working too. Using DeepSeek makes it noticeably faster, response speed is decent. Next up: something with more advanced hardware.
\n

\n

A few photos from different angles to mark the moment

\n\n \n \n \n \n \n \n \n \n
\n \n \n \n
\n \n \n \n
\n

Trending Tools

\n

App Store Price: Look up app prices across different countries and regions
\nhttps://app.vbr.me
\nA handy little tool. You can check what an app costs in any App Store region, like figuring out which country has the cheapest Claude subscription. I’ll probably find a use for this soon.
\n

\n

Random Thoughts

\n

Let me share what I think makes for a genuinely good product experience.

\n

There’s a followup to my lost drone story. The signal cut out mid-flight, I searched for a long time, couldn’t find it. I uploaded the flight logs and DJI couldn’t find a clear cause either. Even without being sure it was actually lost, they asked for very minimal proof and, under their Care Refresh service, just shipped me a brand new one. They even threw in a 128GB card in case it would be more convenient. Not once did anyone ask me to explain how it got lost or whether I had gone looking for it.

\n

That experience made me a real fan of DJI. Their customer service and technical support engineers were professional and clear throughout the whole process. I want to use that story to share what I think makes a good product experience.

\n

Good product experience is not just what people usually say: great interaction design, beautiful UI, easy to use, no bugs. Those matter, but what matters even more is this: when a user is in a tough spot, you give them something far better than they expected. Something so good that they get excited and tell their friends about it. That is what I consider truly good product experience, the kind that is good for business too. The only thing I worry about is that this culture of trust and simplicity gets taken advantage of by people trying to game the system. It’s something we all have to protect together.

\n

Two other experiences that stood out to me involved Ctrip.

\n

The first was three years ago during the Spring Festival. Tickets home were nearly impossible to get. They suggested I buy tickets for a few extra stops to guarantee I could board, and I was already grateful for that because nothing else had worked. But then, even better: I was at the movies that afternoon, feeling like everything was handled, when I got a call from an unknown number that I declined. Right after, a text came in saying they had found me a direct option that didn’t require the extra stops, and could I please go to the app to confirm. You could tell a real person had made that call and sent that message. It wasn’t the few dollars saved. It was the feeling that someone was genuinely working hard for me and delivering better than I had hoped. That is good experience.

\n

The second happened recently, during National Day. I had gotten two first-class seats but they weren’t together, pretty far apart. I had noted I was traveling with an 18-month-old. Then, the day before departure, Ctrip quietly swapped our seats. Just a simple notification: we found an open seat in your carriage and moved you both together. Another moment where someone gave me more than I expected.

\n

So if you are building a product, think about giving your users something far beyond what they expect in the moments when they really need it, rather than chasing clicks with tricks. When you do that, people will genuinely love your product and become your most loyal fans.

\n
\n

\n Buy me a coke 🥤\n

"},{"title":"263. Hardware Beauty","link":"https://weekly.tw93.fun/en/posts/263/","pubDate":"Mon, 06 Apr 2026 00:00:00 GMT","description":"\n

The cover photo is from a hardware toy I spent three days playing with at home during the holiday. I was soldering, applying glue, and debugging through a pile of components. I was almost at the final step when I burned the screen during testing. Now I am waiting for the replacement to arrive so I can keep going. Lots of fun.

\n
\n

Recording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications

\n
\n

New Article

\n

What You Don’t Know About LLM Training: Principles, Paths, and New Practices
\nhttps://tw93.fun/2026-04-03/llm.html
\nThis is the longest article I have ever written. The good news is I finally got a handle on the basics of large model training. The gap between what I assumed I knew before and what I actually found was massive. I highly recommend this to anyone working in AI applications or anyone curious about AI. It should give you a clear picture without leaving you lost.
\n

\n

Product Releases

\n

Waza, My Engineer-Alter-Ego Skill Set
\nhttps://github.com/tw93/waza
\nI packaged my personal skills into something new called Waza. In Japanese, 技（わざ）means technique or skill, often used in martial arts. This is the first time I have released an open-source project with zero code, just markdown files. In the pre-AI era, for a programmer, that would have been embarrassing.

\n

When Superpowers came out, I installed it once and deleted it right away. Too heavy, not my thing. A lot of people kept telling me “You don’t know Superpowers? If you’re not using it you’re not with the times, it’s amazing.” Then I found gstack, which was better, but still felt like too much. I still wasn’t used to it. I wanted something simple and useful where I could clearly see what it was doing.

\n

So I built Waza the way I like it. For me, this set is enough. No need to mess with other skills. Not too many, not too few, just right. New iterations can be added over time.

\n

The 8 skills correspond to 8 abilities I think a good engineer in the AI era should have:

\n
    \n
  1. \n

    Think clearly. AI writes code fast, but if the direction is wrong, the faster you go the further off course you get. A good engineer questions the problem itself before touching any code, stress-tests the plan, and has a clear mental architecture before asking AI to execute. /think locks this habit in.

    \n
    2. \n
  2. \n

    Design well. Building a product is not just about making features work. AI-generated things tend to look the same. Good engineers have an aesthetic standard for what they deliver and a clear design direction. /design handles this.

    \n
    3. \n
  3. \n

    Debug systematically. AI fixing bugs most easily falls into a “try this, try that” loop. A good engineer diagnoses problems systematically, confirms the root cause before touching the code, and gets it right in one shot. I turned this habit into /hunt.

    \n
    4. \n
  4. \n

    Review before merging. AI-generated code needs human oversight even more. Check the diff before merging, auto-fix what can be auto-fixed, group the judgment calls together, and verify with evidence rather than gut feeling. That is /check.

    \n
    5. \n
  5. \n

    Read primary sources. Good engineers read original material, not second-hand summaries. Converting URLs or PDFs into clean Markdown and pulling it directly into the workflow is what /read does.

    \n
    6. \n
  6. \n

    Write clearly. No matter how technically strong you are, if you can’t explain it clearly, others won’t receive it. A good engineer can convey what they have learned and what they want to express to the right audience. /write helps you nail this step.

    \n
    7. \n
  7. \n

    Learn actively. Tech moves faster in the AI era. Entering an unfamiliar domain is not just skimming a few articles. It is collecting, digesting, outlining, drafting, refining, and publishing. Output drives learning. That entire flow is /learn.

    \n
    8. \n
  8. \n

    Maintain the toolchain. A good engineer does not only care about business code. The toolchain itself needs regular checkups. When something feels off with CLAUDE.md, rules, hooks, or MCP configs, run /health and find out what is wrong.

    \n\n
    9. \n
\n

Product Updates

\n

Kaku 0.9 is out and it is really good
\nhttps://github.com/tw93/kaku
\nA few fun features shipped in this version that should be genuinely helpful.

\n
    \n
  1. Natural language command generation: Type # <description> and press Enter, and the auto-generated command is injected back into the prompt.
    2. \n
  2. Option+Click to move the cursor: Click anywhere on the current line to move the cursor there.
    3. \n
  3. Window pinning: Pin the window to the front via the Window menu, and toggle it on or off anytime.
    4. \n
\n

\n

Trending Tools

\n

Claude HUD helps you track your Claude usage
\nhttps://github.com/jarrodwatts/claude-hud
\nIt is a little feature-heavy, but after some simple configuration it works well. Worth trying if you are curious. The code feels a bit complex, and when I have time I will probably simplify it myself. Minimalism is the goal.
\n

\n

A super minimal, AI-friendly Markdown doc generator
\nhttps://docmd.io
\nStumbled on docmd. It is a zero-config documentation generator built for developers. It converts Markdown into fast, clean static docs with automatic routing, built-in search, and context that AI can easily use.
\n

\n

Picked up a 140W charger and it is great
\nGot a 140W charger. Good size, finally free from my old 45W. Four ports, which makes it way more convenient on the go. The display showing real-time power output is a nice touch.

\n\n \n \n \n \n \n
\n \n \n \n \n \n
\n

Random Thoughts

\n

Let me share how I dive deep into a new technical domain in the AI era.

\n

Before AI, I mostly read books and went through every blog post from notable people in the field, both domestic and international, writing notes by hand. It was slow but genuinely fun. Learning WebGL back then felt like that. Getting a solid understanding of something might take half a year of free time. Slow, but happy.

\n

Now that AI is here, I still can’t stand those “summarize a hundred-year-old novel in 3 minutes” things online. I also dislike short-episode dramas and watching shows at 2x speed. I mostly still choose good things and take time with them.

\n

But recently while writing the “You Don’t Know Claude Code” and Agent series, outside of the parts I already understood, there were huge areas I wasn’t clear on. Luckily I had saved a lot of articles, and this was the perfect chance to clear the backlog, fully digest everything, and write it all out. I have always believed that what matters is not how much you read, how much you hear, or how much you take in. Most of that doesn’t really stick. What matters is how much you output. That is what becomes truly yours.

\n

A couple of weeks ago I started a deep challenge: studying the training pipeline of large language models and making sure even non-specialists could understand it. I explored for two weeks, and the experience is now ready to share. The article is basically done and should be coming out soon.

\n

I organize this learning process like writing code. Step one: collect high-quality material. Recent top papers in the field, blog posts from major model providers about their key releases, threads from model leads on X, recent courses from Stanford and similar schools, and classic “build an LLM from scratch” repos. These are my sources. I use tools to automate downloading everything, converting to Markdown, cleaning, and organizing it all into a structured repo for this research.

\n

For content I understand, I read it all through, delete the bad parts, and keep the good ones. For content I don’t understand, I use Claude to help me get it. The more complex parts I translate into Chinese and read that way. For code that can run locally, I run it. For code that can’t, I read the structure. Either way, I end up with a rough understanding of the technical principles. This phase usually cuts the original material by half.

\n

At this point you have a general picture of the field, so you can start writing an outline and figuring out which source material belongs with each section. All of it works well in Markdown. What do you want to say, or more accurately, what do you want your reader to know? Always remember: an article is written for its readers. You need to know your audience’s level. It is a lot like giving a presentation.

\n

Then comes the grind, which is also a review of everything you have covered. It feels a lot like cramming before an exam in college. You fill in each section completely, and what you end up with is a very long and somewhat rambling article.

\n

This is where AI really helps. You can ask it to remove the redundant parts and smooth out the disconnected bits, without changing your original meaning or your voice. You can also ask it to flag gaps and help fill them in. That process teaches you even more things you had missed.

\n

Once that is done, read through it yourself one more time, not AI. AI is just a tool here. Do not let it replace your brain, that defeats the whole point. Reading through yourself, you can keep adjusting and polishing. It feels a lot like testing your own code: fix issues, fix more issues. After reading it twice and feeling good about it, you can publish it for everyone to see.

\n

Some folks worry that nobody will read what they write, so they hold back or just don’t write at all. Honestly, if your content has real value, readers will come. Worry about quality, not the audience.

\n

That took 10 minutes to write. Done. Happy to hear how you learn new fields. The video below is a recording of the learning repo for the LLM training article I mentioned, the one coming out soon. It shows my “industrial-scale” way of learning. Kind of fun to look at.

\n

\n

\n Buy me a coke 🥤\n

"},{"title":"262. Lost My Drone","link":"https://weekly.tw93.fun/en/posts/262/","pubDate":"Mon, 30 Mar 2026 00:00:00 GMT","description":"\n

The cover photo is here in memory of my drone, which I finally lost. This was the last shot it ever took. Thankfully I have DJI Care Refresh, so I should be able to get a replacement for free.

\n
\n

Recording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications

\n
\n

Product Updates

\n

Kaku released version 0.8
\nhttps://github.com/tw93/Kaku
\nThis release is called Fish 🐟. Most of the work in this round went into shell compatibility, tab behavior, and overall stability.
\nIt now has full fish shell bootstrap support, including Starship, Yazi, theme sync, and config handling. Tab management was also improved, with remembered last directories, isolated tabs for update and doctor, and a new option to show directory names only in tab titles.
\nOn top of that, it fixes a batch of issues around fast output and Claude Code viewport jumping, plus window hiding, link clicking, paste behavior, emoji width, SSH aliases, Cmd+Q crashes, and transparent rounded-corner rendering. Worth updating.
\n

\n

Mole released version 1.32
\nhttps://github.com/tw93/mole
\nThis version is called Rorqual 🐋, and there are quite a few updates again.
\nmo clean now fixes the long-skipped wallpaper proxy and Messages preview caches, and adds cache and log cleanup for PCSX2 and RPCS3. It also improves Python bytecode cache output, the Brave cleanup guard, Spotify playback detection, and the error handling around Service Worker cache cleanup.
\nBesides that, mo uninstall now filters out invisible background helper apps, the main menu shows more accurate Touch ID detection and a version shortcut, and the install flow now grabs sudo permission up front so you do not have to keep entering your password over and over.

\n

Pake released version 3.11
\nhttp://github.com/tw93/Pake
\nThis release is called Evolve 👻. It had been a while since the last update, and this one is mostly focused on bug fixes plus a few new features.
\nOn macOS, --install now supports one-command installation into /Applications. The new --new-window flag keeps popup and OAuth windows inside the app instead of constantly bouncing out to the system browser. It also adds --camera, --microphone, and --identifier for on-demand media permissions and custom Bundle IDs, which helps reduce conflicts between apps.
\nThere are also plenty of cross-platform fixes in this release, including Gemini download failures, parts of the ChatGPT UI disappearing after zooming, Windows icon copy errors, and crashes when clicking external links in macOS new-window mode. Overall it feels more stable.

\n

Trending Tools

\n

The 4 Claude MCPs I use the most
\nhttps://tinyfish.ai
\nThe first one is TinyFish MCP. I like it a lot because it lets Claude browse the web directly, fetch pages, do research, and return structured results instead of just a static answer. Lately I have been using it to collect AI news for this weekly, like pulling the most popular Hacker News items from the past few hours and turning them into a clean summary list. It saves a lot of time.
\nThe second is GitHub MCP. It makes everyday things like reading commits, tracing changes, and understanding a repository much smoother, without constantly switching between tools.
\nThe third is Figma MCP. You can inspect design files, check layout and spacing, and pull UI details directly into the conversation, which is very handy when you are aligning implementation with design.
\nThe fourth is Excalidraw MCP. This one is better for thinking through things, especially flows and system structure. When words are not enough, drawing it out is much faster.
\nThe last three are probably already familiar to many people. I also recorded a short video showing how TinyFish works in a real workflow.
\n

\n

I have really been enjoying the gstack skill lately
\nhttps://github.com/garrytan/gstack
\nI highly recommend trying it. It feels like having a solid team of specialists around you, covering roles like CEO, tech lead, design, QA, and security, all helping you reason through the code development process.
\n

\n

Random Looks

\n

Chinese Painting from the Yuan to the Qing is an excellent book
\nhttps://book.douban.com/subject/37156716/
\nThis book is really good. It is dense in the best way, and Wu Hung’s scholarship is seriously impressive. If you want an art history book to get started with, this is a good one.
\n

\n

A drone clip from the Yangjiapai hike
\nThis is exactly where I lost my drone, for your amusement. “Dear DJI customer, we are very sorry to hear that your aircraft has gone missing. Please rest assured that DJI will do its best to assist you. Your flyaway report has been successfully accepted. You may first refer to the Find My Drone guide and try to locate the aircraft.”
\n

\n

Random Thoughts

\n

Kill the Manual Programmer

\n

\"\"

\n

The title is adapted from a song I loved 12 years ago, “Kill That Shijiazhuang Man” by Omnipotent Youth Society. The scene they wrote about feels a little similar to what we are looking at now.

\n

I have not taken a bus in years. Last time I went to Prince Bay, the scenic area had traffic restrictions, so I had to park outside and take the free shuttle in.

\n

In the seat ahead of me, a little girl kept swiping through those AI-generated short videos. The visuals were rough, the content felt fake, and when she moved to the next one, it was somehow more of the same. She was completely absorbed. The strangest part was that every video had a huge number of likes. Watching that made me a little sad. I kept thinking, when my own kid grows up, will they also be surrounded by this kind of low-grade AI-made content from the start, to the point that it becomes hard to even find something genuinely beautiful?

\n

Once AI showed up, producing things suddenly became much easier. Making content got easier, and making software got easier too. In the past, if you wanted to build something, you had to spend real time on it, go back and forth, solve actual problems, and only then dare to ship it. Now a lot of those steps have been flattened. Writing something is easy, building a product is easy, you buy some tokens, ask AI, stitch together a workflow, throw on an interface, and pretty quickly you have something that runs.

\n

Today I also saw someone say they could recreate a Claude Code in two days. I both believe that and do not. In voice AI alone, dozens of products have appeared all at once, and a lot of them are actually pretty decent. Even Doubao is competing in that space now. I have also seen quite a few Claude Code wrapper clients lately, and honestly some of them are very usable.

\n

For programmers, a lot of things that used to require professional skill, a learning curve, and years of accumulation are quickly turning into abundant supply. In the future, the least scarce thing may be products that look like products. They work, they run, they look fine. You can only try to do them a bit faster, a bit better, or wrap one more layer around them and maybe there is still some value there. But that value will get matched by AI more and more easily.

\n

Not long ago I was having dinner with a colleague and we got onto an interesting topic. I told him that over the past year I have really enjoyed listening to cassette tapes, and that every song somehow feels more durable and more beautiful. Why did cassettes, CDs, TV shows, and even many old books often feel higher quality overall? The reason is actually simple: production and distribution used to be heavy. If you wanted to release an album, you first had to make the work good enough, and only then would it make sense to produce tens of thousands of tapes. Otherwise they would not sell, and the company probably would not back your next release. Publishing a book was similar. You could not just finish it casually and push it in front of a huge audience right away. Back then, the act of making something was already a filter.

\n

Now you can upload a song to a platform and that is it. You can post an article to a public account and that is it. Software is becoming similar after AI, and in some cases AI will even upload the code to GitHub for you, a place many people used to find intimidating, and even generate the CI that publishes the release for you. A lot of thresholds that once required long-term accumulation to cross have been filled in by tools, and so the world slowly gets flooded with things that are all kind of the same and kind of usable.

\n

The trouble is not just that quality drops. Over time, people’s sense of quality drops with it. The more rough things there are, and the wider they spread, plus the pressure to make money, the more our judgment gets pulled off course. Eventually what people get used to is fast stimulation, fast feedback, and fast satisfaction.

\n

When I think back to that little girl watching videos, that is the part that feels uncomfortable. She was not just watching a few rough clips. She may be growing up inside a world filled with lower-cost, higher-frequency, emptier things.

\n

Code is clearly entering the same phase now. In the future, ordinary beginners will be able to use AI to build products that satisfy their own needs. Product managers will be able to make things that used to require engineers working alongside them. So what exactly is left for real engineers to do? That is something we need to think about seriously.

\n

I have also heard that a lot of bosses at big internet companies are now staying up day and night vibe coding. In a single afternoon they can build a demo they personally consider usable, and some of them are deeply hooked on it. This could have a major effect on people doing frontline work. Once the boss gets a few flows working in code, the natural conclusion becomes: writing software is not that big a deal after all. Things that used to take six months, can they now be done in one? Things that used to need 100 people, can they now be done with 10? It is hard not to think about where that leads.

\n

There is still room for engineers to keep building products that are more usable and more efficient. But if we stop at that layer, the field will only get more crowded. More people can enter, and more people can ship something that looks convincing. The competition will get brutal.

\n

I suspect the real way forward is something closer to how singers and actors responded. Yes, they still release albums, but they also make concerts, stage productions, and live performances. Those are not things you can casually replace by putting a wrapper around something. They require organization, density of detail, and a sense of wholeness that only comes after long polishing, and they face the world directly.

\n

Looking ahead, software may move in that direction too. Everyone will be able to vibe code a product. Everyone will be able to make something that is more or less usable. What will really open up the gap later is still system capability, engineering depth, understanding of real scenarios, and all the things people do not notice at first glance but that ultimately determine whether a product has real weight.

\n

The faster the outside world moves, the less we can afford to lower our own standards for software along with it. Low-level supply will definitely keep increasing, but that does not mean we also have to become rough. The things that survive are usually the ones that feel smooth, comfortable, restrained, almost bug-free, the kind where you can tell the maker treated the work seriously.

\n

I am also thinking through my own next step. I still want to keep building open-source software that is useful, approachable, language-independent, and can earn tens of thousands of stars. I also want to keep playing with low-level rendering, terminals, editors, Rust, and related directions. Before AI, all of that felt very rewarding. After AI, though, once you have an idea, so much suddenly becomes easy that the meaning of it can start to feel less obvious.

\n

Maybe the next thing for me lives in a different dimension, a hardware-software product, or the kind of platform product that used to require thousands of people at a big company, or maybe something that breaks out of the current frame entirely. What exactly it is still needs more thought.

\n

Some of my products and content have already been slowly moving toward English, toward a bigger world. When everything here starts to feel more similar and more crowded, going outward may be one answer. A bigger market, more varied users, and higher expectations make it impossible to stay at the level of wrappers, speed, and timing alone. That pressure forces you to build something more solid, and it also forces you to think again about what you actually want to make.

\n

AI has made many things easier. But precisely because things are easier now, it has become harder to figure out what is truly worth doing and worth trading years of your life for. What to build may matter more than how quickly you can build something.

\n

\n Buy me a coke 🥤\n

"},{"title":"261. miss spring","link":"https://weekly.tw93.fun/en/posts/261/","pubDate":"Mon, 23 Mar 2026 00:00:00 GMT","description":"\n

The cover photo was taken looking up at the spring sky. Spring in Hangzhou is truly beautiful. I kind of hope summer doesn’t come too quickly—weather like this is incredibly comfortable.

\n
\n

Recording down-to-earth trending tech seen every week, published here after filtering. If you find it useful, feel free to subscribe to this weekly newsletter for update notifications.

\n
\n

Wrote a Long Article

\n

The Agent You Don’t Know: Principles, Architecture, and Engineering Practices
\nhttps://tw93.fun/en/2026-03-21/agent.html
\nAfter writing “The Claude Code You Don’t Know: Architecture, Governance, and Engineering Practices,” I realized my understanding of the underlying Agent mechanics wasn’t deep enough. Plus, our team has accumulated quite a bit of business implementation experience in the Agent direction, yet we’ve always lacked a systematic summary. So, I went through the materials, open-source implementations, and the code I wrote myself again, ultimately organizing it all into this article.
\n

\n

Product Updates

\n

Mole Released Version 1.31
\nhttps://github.com/tw93/mole
\nMole released version v1.31.0 over the weekend, codenamed Makima. It features faster performance and more accurate system status reporting. Huge thanks to all the contributors! I also made a video so everyone can feel the power of open source.
\n

\n

Trending Tools

\n

Get Inspired by These Projects Built with Claude
\nhttps://claude.com/resources/use-cases
\nDefinitely worth a look. It covers various use cases in daily work, from research, writing, programming, to analysis. The content is much more in-depth than I expected.
\n

\n

Highly Recommend This Service from Jina in the Agent Era
\nhttps://r.jina.ai
\nSometimes you need an AI to read the content of a live website, but often it can’t fetch it due to various reasons. You can try this service: just append the URL you need to fetch after it, and it will convert it into nicely formatted markdown for you, making it super convenient for AI to use.
\n

\n

Pi, This Minimalist Agent Framework, is Worth Getting to Know
\nhttps://github.com/badlogic/pi-mono
\nIt’s very small. The openclaw project was previously implemented based on this framework. It serves as a great entry point for understanding Agents.
\n

\n

Random Thoughts

\n

Try Buying Pre-made Ice Cubes This Summer
\nI had been debating whether to buy an ice maker, but since I’m the only one at home who likes drinking ice water, I felt the usage rate would be low and it would just take up space. Freezing ice cubes myself was also inconvenient—I’d usually realize I forgot to make them right when I wanted a drink. I found a great solution: just buy some pre-made ice cubes and keep them in the freezer. When you need them, just take them out. You can even use them directly to make Americanos in the summer. The cost-effectiveness is super high.
\n

\n

Got a Singapore HSBC Card
\nIf you already have HSBC accounts in mainland China and Hong Kong, you can ask your relationship manager to help you apply for a Singapore one. Although it kind of feels like a supermarket loyalty card. The registered mail didn’t arrive for three months; after a phone call, they remade it and it arrived via express delivery in a week.
\n

\n

\n Buy me a coke 🥤\n

"},{"title":"260. Prince Bay","link":"https://weekly.tw93.fun/en/posts/260/","pubDate":"Mon, 16 Mar 2026 00:00:00 GMT","description":"\n

Cover photo taken on Saturday when I took the kid to Prince Bay Park at West Lake. Originally wanted to see the tulips, but there were way too many people. I wouldn’t recommend going to join the crowds.

\n
\n

Recording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications

\n
\n

Wrote a Long Article

\n

The Claude Code You Don’t Know: Architecture, Governance, and Engineering Practices
\nhttps://tw93.fun/en/2026-03-12/claude.html
\nRevolves around Context Management, Skills, Hooks, Subagents, Prompt Caching, and CLAUDE.md design. It focuses on how to make the collaboration process more stable and controllable, sharing best practices from an engineer’s technical perspective. Welcome to exchange ideas.
\n

\n

Product Updates

\n

Mole has released version 1.30
\nhttps://github.com/tw93/mole
\nI started writing Mole last November, and surprisingly, 30 versions have been released up to today. This update includes:

\n
    \n
  1. Strengthened orphan app data cleanup strategy. General orphan cleanup now uses a 30-day resting window.
    2. \n
  2. Optimized Application Support and project cache scanning logic in large directory scenarios, reducing the risk of stuttering, and converging the scanning scope to a safer root path.
    3. \n
  3. Strengthened LaunchServices refresh fallback logic, stabilized Homebrew uninstall and update paths, and reduced unnecessary sudo behaviors.\n\n
    4. \n
\n

Kaku released version 0.7
\nhttps://github.com/tw93/Kaku
\nI really like the transparent frosted effect in this release, you can give it a try. Updates are as follows:

\n
    \n
  1. Kaku will now automatically switch between dark and light modes along with macOS, and has optimized transparency rendering and Yazi theme synchronization experience.
    2. \n
  2. Added closing confirmation for tabs and panes, reworked the close overlay style, and added custom rounded scrollbars. Try kaku config.
    3. \n
  3. kaku ai now supports Antigravity model configuration, quota tracking, and background loading.\n\n
    4. \n
\n

Trending Tools

\n

Learning the principles of Claude Code-like systems
\nhttps://learn.shareai.run/en/
\nIt will guide you step-by-step from scratch to build a minimalist Agent similar to Claude Code, and explain each mechanism in detail. Worth a look.
\n

\n

RentAHuman: AI hiring humans to work
\nhttp://RentAHuman.ai
\nWhen an AI Agent encounters a task that cannot be completed online, it can post the job online and hire a real human to complete the task. Haha, quite interesting.
\n

\n

A fantastic interactive MicroGPT demo
\nhttps://growingswe.com/blog/microgpt
\nThis is a learning website based on Andrej Karpathy’s GPT implemented in about 200 lines of Python code, explaining how language models work in a visual way. Worth checking out.
\n

\n

A public OpenClaw exposure monitoring site
\nhttps://openclaw.allegro.earth
\nLists OpenClaw instances accessible over the network. In many cases, you can click into these instances and directly view what is running inside. Actually, a lot of people who don’t understand the technology are installing OpenClaw. Many things are very dangerous, and surprisingly, many belong to Alibaba, which is scary.
\n

\n

Random Looks

\n

My CodeX configuration, for your reference
\nModel: Fast GPT-5.4 High
\nPersonality: Pragmatic.
\nCustom Instructions:
\nAct like a high-performing senior engineer. Be concise, direct, and execution-focused.
\nPrefer simple, maintainable, production-friendly solutions. Write low-complexity code that is easy to read, debug, and modify.
\nDo not overengineer or add heavy abstractions, extra layers, or large dependencies for small features.
\nKeep APIs small, behavior explicit, and naming clear. Avoid cleverness unless it clearly improves the result.
\n

\n

Cooked 4 dishes on Sunday

\n\n \n \n \n \n \n \n \n \n
\n \n \n \n
\n \n \n \n
\n

\n Buy me a coke 🥤\n

"},{"title":"259. Jingshan from Above","link":"https://weekly.tw93.fun/en/posts/259/","pubDate":"Mon, 09 Mar 2026 00:00:00 GMT","description":"\n

Cover photo taken during a weekend trip to Jingshan Flower Sea with my drone. Currently only rapeseed flowers are blooming - the other flowers haven’t really opened yet. Flew the drone to maximum altitude for some photos and spotted quite a few nice views.

\n
\n

Recording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications

\n
\n

Trending Tools

\n

MiaoYan recently got updated with CLI support
\nhttps://github.com/tw93/miaoyan

\n
    \n
  1. CLI support via miao command - list all notes, search, create new ones, and cat content from the terminal. Very practical for AI workflows.
    2. \n
  2. Apple notarization complete: No more “App is damaged” warnings or having to click “Open Anyway” in System Settings!
    3. \n
  3. Preview stability upgrade: Fixed occasional blank preview issues and enhanced recovery capabilities after WebContent process crashes.
    4. \n
  4. Editing experience optimization: Fixed input method issues in split-column mode, resolved system shortcut conflicts, and eliminated highlight flickering when switching notes.\n\n
    5. \n
\n

Pake released version 3.10
\nhttps://github.com/tw93/Pake

\n
    \n
  1. Multi-window support: New --multi-window parameter allows opening multiple windows in the same App instance. When enabled, macOS File menu (Cmd+N) and system tray menu will both show “New Window” entry. Restarting the App opens new windows instead of focusing existing ones.
    2. \n
  2. Internal link regex control: New --internal-url-regex parameter supports precise control over which URLs are treated as internal links via regex, as an alternative to the default same-domain judgment. Falls back to default logic on invalid regex.
    3. \n
  3. Windows ICO icon fix: Reordered multi-resolution ICO files to prioritize 256px icons, improving App icon display quality on Windows.
    4. \n
  4. DMG background image fix: Restored Retina metadata for macOS DMG background images and adjusted dimensions, fixing background display issues in CI builds.\n\n
    5. \n
\n

nanobot: A lighter OpenClaw form factor perfect for personal computers
\nhttps://github.com/HKUDS/nanobot
\nI currently have two nanobots running locally - one focused on code that helps me review issues, organize thoughts, and push technical solutions forward; another for life stuff handling daily tasks. Basically replaced my ChatBot habit from six months ago. Plus a cron job that keeps watching - if the service goes down it automatically restarts, and I use Amphetamine to keep my home computer always online. After running for a while, it becomes a stable part of your environment that doesn’t require you to consciously open, maintain, or fuss with it.

\n

Often when you’re halfway through coding or when you’re out and can’t conveniently open your computer, you can casually toss tasks to it to work on first. When you come back later, some of the prep work is already done. This experience is very practical and feels natural for engineers who prefer lightweight, simple, self-controllable solutions. If you don’t want to tinker, I’d actually recommend using the installer version - works out of the box. For those who want to add custom features like me, you can clone it locally and have nanobot optimize its own code and iterate on itself. Recently added quite a few fun features.
\n

\n

Amphetamine keeps your Mac awake
\nhttps://apps.apple.com/us/app/amphetamine/id937984704
\nWhen running things like OpenClaw or nanobot, you really don’t want the screen to sleep or even want it to keep running with the lid closed. Found this software - free and works great. Perfect for when you’re using a home Mac but want it to stay on with the screen off.
\n

\n

Maple browser bookmark tool latest update
\nhttps://github.com/tw93/Maple

\n
    \n
  1. New tab opening setting: Added “Open in new tab” option in settings, with hover tooltips disabled by default for a cleaner interface.
    2. \n
  2. Multi-language support: Optimized settings page styling and added multi-language support for better accessibility.
    3. \n
  3. File protocol support: Fixed issues with opening file protocol bookmarks (file://).
    4. \n
  4. Bug fixes: Fixed Bing date issues, sorting problems, and various UX improvements.\n\n
    5. \n
\n

Discovered a very modern VSCode theme: Islands Dark
\nhttps://github.com/bwya77/vscode-dark-islands
\nHas that new Apple system feel with glass arc effects, rounded corners - very modern looking, though you might not get used to it.
\n

\n

Readout: Visualize your Claude Code projects
\nhttps://readout.org
\nVisualizes your Claude Code environment in real-time. Shows AI, sessions, repos, costs, MCPs, ports, and more. Provides instant global search and complete session replay with timeline scrubbing. Runs locally, no account needed. Looking forward to its future development.
\n

\n

Random Finds

\n

Gaidihu floor drain core is excellent, worth trying
\nAfter buying the Gaidihu floor drain core that topped my “best purchases of the year” list and testing one, I bought another and replaced all the bathroom floor drains in my house. Very smooth drainage without clogging, easy to install. Highly recommended.
\n

\n

Haven’t eaten coconut meat in years, quite interesting
\nLearned how to open a coconut without a knife: First peel off the top, then you’ll see 3 faces. Gently press to find the spot that’s noticeably softer, then look for the hole there.

\n

As for cracking the shell open - use another coconut. Hold one in each hand and smash the three raised ridges against each other. Hit hard a few times and one will crack, then break it open. The coconut meat is very refreshing!

\n\n \n \n \n \n
\n \n \n \n
\n

Random Thoughts

\n

\"\"

\n

Last Friday I saw Tencent Tower installing OpenClaw company-wide. Quite thought-provoking - felt a bit like “The Great OpenClaw Leap Forward”.

\n

Recently many big tech companies have been frantically pushing frontline non-technical employees to install OpenClaw. There’s even a real 500 RMB on-site installation service online. Everyone’s desperately searching for use cases, demanding implementation, trying to prove this thing is too important to miss. The whole process gives me a strong sense of cyber-tech folding.

\n

Saw an interesting quote: “People who can’t even install OpenClaw, how would they use it?” Taking it a step further - if you haven’t even established basic usage, yet you’re expected to first create complete scenarios, deliver results, and prove value - that’s even harder.

\n

There are two things叠加 (stacked) behind this. One is illusion: many bosses have watched too many WeChat video clips, been repeatedly bombarded by exaggerated narratives and universal case studies, and really start hallucinating that this thing can do anything, connect anywhere, everyone should install it, and installing it should immediately produce output. The other is anxiety: everyone fears missing this wave, so they start using administrative actions to push adoption, using collective anxiety to replace real demand.

\n

So you see a strong contrast. On one side, slogans are huge - as if everyone must enter the AI-native era. On the other side, many people can’t even clearly articulate what things are worth handing over to it. This contrast will only grow stronger and increasingly absurd.

\n

Because tools never generate value through installation. Tools only generate value through task density, clear processes, and visible results. Without continuous tasks, without SOPs, without conditions for online completion, without clear inputs and outputs - even the strongest thing sitting there is just an icon. It won’t automatically grow scenarios just because it’s installed.

\n

So I’ve always felt OpenClaw isn’t for everyone.

\n

It suits commanders, solo entrepreneurs, and people who constantly have things they want to push forward, can break work into steps, and can complete many things online. Especially if you’ve used skills and tools, understand AI’s capability boundaries, can string processes together, build scenarios, and complete things step by step - then it’s very suitable.

\n

For me, this scenario comes naturally. Especially when there’s lots to push forward but I’m not home or at the office - out with just my phone or can’t conveniently open my computer - I’ll have my two nanobots check my open source product issues, produce technical solutions, then have another review and submit. All in one go. Lets me elegantly get things done during my morning commute. Really convenient.

\n

But for someone who normally has no work to complete outside, or who doesn’t even want to open their computer when they get home - how could you force scenarios to exist? Eating well and having fun is comfortable enough. No scenario means no scenario, really no need for anxiety.

\n

I think what’s most easily amplified in this wave isn’t capability gap - it’s scenario gap. People with scenarios will use it more smoothly, run faster, eventually feeling like they have multiple selves. People without scenarios will easily spin around in concepts, tutorials, case studies, and videos, ending up with nothing changed except having installed more software.

\n

Many people’s biggest problem today isn’t not having installed OpenClaw - it’s treating having installed a tool as having entered the AI era. The real watershed has always been in task understanding, process design, and result judgment. Do you actually have continuous problems to solve? Can you break problems down and hand them to the system? Can you judge whether results are correct? These determine whether you can truly extract value from AI.

\n

So no need for anxiety. Installing OpenClaw when you have no real use case doesn’t mean much.

\n

If you really want to experience where this generation of AI is strong, better spend $20 on Claude Code, or more interestingly get a ChatGPT subscription, use GPT 5.4 to handle something you truly find difficult - produce a solution, push execution forward, experience this simple, efficient, problem-solving process once. That’s way better than installing OpenClaw.

\n

OpenClaw suits people with scenarios, suits commanders, suits solo entrepreneurs, suits those who can SOP-ize, online-ize, and complete processes step by step. It’s certainly powerful, but it proves its power through completing work for you, not through being installed.

\n

What many people are installing today is OpenClaw. What’s more important to figure out first: What problem do I actually have that’s worth solving with AI?

\n

That question may be more important than installing anything.

\n

\n Buy me a coke 🥤\n

"},{"title":"258. Cyber Charging","link":"https://weekly.tw93.fun/en/posts/258/","pubDate":"Mon, 02 Mar 2026 00:00:00 GMT","description":"\n

Cover photo shows my finally installed cyber charging station at home. It looks incredibly cool! I ordered it back in January and it finally got installed today. Tesla’s service remains as professional as ever, and their products are as cool as ever. Staying long on Tesla.

\n
\n

Recording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications

\n
\n

Trending Tools

\n

Kaku, the blazing fast and AI-friendly terminal, just released version 0.5 - go try it out
\nhttps://github.com/tw93/Kaku

\n
    \n
  1. AI Shell Error Fixing: When a command fails, Kaku automatically sends it to AI and displays fix suggestions right in the terminal. Press Cmd + Shift + E to apply them instantly.
    2. \n
  2. Built-in Yazi: Press Cmd + Shift + Y or just type y to open Yazi. Layout and theme are auto-configured on first run. cd + Tab falls back to zsh-z history directories when no filesystem matches are found.
    3. \n
  3. Command Palette: Press Cmd + Shift + P for quick command search with fuzzy matching and native text editing support.
    4. \n
  4. Kaku Doctor: Run kaku doctor to detect configuration issues with interactive one-click fixes.
    5. \n
  5. Global Hotkey: Default Ctrl + Opt + Cmd + K to summon or hide Kaku from any app. Customizable via macos_global_hotkey.
    6. \n
  6. Shell Text Editing: Use Cmd + A to select all, Shift + Arrow keys to extend selection, and type directly to replace selected content - just like a native text editor.
    7. \n
  7. Unified AI Config: The kaku ai interface now manages Kaku Assistant, Factory Droid, and opencode.jsonc in one place.
    8. \n
  8. Tab Bell Indicator: When you switch to another tab, tabs with results or notifications show a blinking dot.
    9. \n
  9. Scroll and Input Improvements: Smoother trackpad scrolling in less, man, etc. with DECSET 1007 alternate scroll mode support. Fixed popup position offset issues with Typeless and other CJK input methods.
    10. \n
  10. Window Shadow Restored: Native macOS window shadows are back. They were temporarily disabled due to GPU usage issues in earlier versions.
    11. \n
  11. Faster Startup and Smaller Binary: Lua bytecode caching and lazy loading reduce startup time. Fat LTO and single codegen unit shrink binary size.
    12. \n
  12. Shell Integration Detection Fix: Shell integration now loads correctly in all terminal environments, no longer depending on whether $TERM is kaku. User-loaded plugins are no longer loaded twice.\n\n
    13. \n
\n

PortKiller: Cross-platform port management tool with native UI
\nhttps://github.com/productdevbook/port-killer
\nFound a cool tool on GitHub called PortKiller - a cross-platform port management app for developers. It does more than just list ports: it automatically discovers all listening TCP ports, lets you kill processes with one click, supports search and filtering, favorites, port watching with notifications, and smart categorization for common dev services. It also covers real workflows, like managing kubectl port-forward sessions with auto-reconnect, logs, connect/disconnect notifications, and showing active Cloudflare Tunnel connections.
\n

\n

Surge: Blazing fast open-source TUI download manager written in Go
\nhttps://github.com/surge-downloader/surge
\nRecently discovered a cool tool called Surge - a super fast open-source TUI download manager designed for power users, written in Go with a clean keyboard workflow. It doesn’t treat downloads as a single stream - instead it opens multiple connections, splits files into chunks and pulls them in parallel, with automatic failover across multiple mirrors. You can also switch to streaming mode for sequential downloads, which is more convenient for previewing media.
\n

\n

FluentRead: Open-source immersive browser translation extension
\nhttps://chromewebstore.google.com/detail/%E6%B5%81%E7%95%85%E9%98%85%E8%AF%BB/djnlaiohfaaifbibleebjggkghlmcpcj
\nFluentRead is a solid open-source immersive translation extension for browsers. It’s clean with just the right amount of features, plus you can configure your own API key. The translation style and page integration look good too. Give it a try.
\n

\n

LobsterAI recently improved its Skills capabilities
\nhttps://lobsterai.youdao.com
\nI’ve been using NetEase’s LobsterAI recently. Looking at their changelog, they’ve been optimizing Skills - it now has built-in modules for document processing, frontend design, browser automation, web search, and even finding movie resources. The scenarios are ready to go, and many can be completed with just one sentence.

\n

I tried an interesting combo this time. I’ve been curious about the TV series “Taiping Years” and wanted to brush up on the Five Dynasties and Ten Kingdoms period of history. So I just threw in a prompt: “Organize the timeline and key knowledge points of the Five Dynasties and Ten Kingdoms into a PDF with high information density, and also search for any cloud storage resources for Taiping Years.” It called three Skills - web-search, pdf, and films-search. The PDF was generated directly with a clear timeline and decent formatting; the resource search actually found download links, saving me the time of digging through various sites.

\n

Skills save time on building tool chains, writing scripts, and cleaning data. For engineers, it turns what used to require setting up workflows into direct API calls, with deduplication, formatting, and summarization handled together. Combined, you can do more - like monitoring a competitor’s weekly updates, using web-search to fetch them, extracting key changes with playwright, and generating a competitor report, all in one place. If you’re interested, start with your most repetitive high-frequency scenarios. Give LobsterAI’s latest Skills a try.
\n

\n

SuperCmd: Open-source macOS launcher with more features than expected
\nhttps://github.com/SuperCmdLabs/SuperCmd
\nFound SuperCmd on GitHub - an open-source macOS launcher that’s more complete than I expected. It puts Raycast-style extension workflows, voice input, text-to-speech, memory, and AI actions into an open system. Great to see this level of open-source innovation in the macOS launcher space.
\n

\n

Helium: The minimalist browser I switched back to from Edge, with great spatial feel
\nhttps://helium.computer/
\nI recently switched my main browser from Edge back to Helium. I thought I liked vertical tabs, but what I really wanted was a more minimal UI and more workspace. Helium now has vertical tabs too, but the real highlight is compact mode - address bar and tabs on the same line, clean and space-efficient. Paired with my Maple theme and Maple bookmarks extension, the whole setup feels comfortable - focused, no noise.
\n

\n

Random Finds

\n

Claude’s new program for open source maintainers: 6 months of Claude Max 20x
\nhttps://claude.com/contact-sales/claude-for-oss
\nClaude just launched a program for open source maintainers offering 6 months of free Claude Max 20x. If you’re a primary maintainer of a public repo with 5K+ stars, or a core member of an NPM package with 1M+ monthly downloads, and you’ve been active in the last 3 months, check it out. If you’ve been consistently contributing to Mole, Pake, MiaoYan, or other major open source projects and meet these criteria, give it a shot.

\n

Taiping Years is sooooo good
\nhttps://movie.douban.com/subject/36317421/
\nGuys, Taiping Years is sooooo good - go watch it. It’s really great, the kind where the first episode already blows you away.
\n

\n

Aerial view of Xixi Wetland
\nWelcome to listen to Li Zhi’s “Castle in the Sky” while watching this aerial view of Xixi Wetland - it looks quite beautiful from above. Should be even more stunning by mid-March.
\n

\n

Rong Xiao Guan is quite fresh!
\nIf you’re shopping at Hangzhou Tower, try this place on the 8th floor of the new Building B. It’s pretty good - light but delicious and fresh.

\n\n \n \n \n \n \n \n
\n \n \n \n \n \n \n \n
\n

\n Buy me a coke 🥤\n

"},{"title":"257. Happy Chinese New Year","link":"https://weekly.tw93.fun/en/posts/257/","pubDate":"Thu, 19 Feb 2026 00:00:00 GMT","description":"\n

The cover photo was taken a few days before Chinese New Year when I visited Shaoxing for a few days. It was pretty nice overall - this is a drone photo of Anchang Ancient Town. It was fun, very much like a traditional water town.

\n
\n

This weekly newsletter documents the practical tech trends I discover each week. After filtering, I publish them here. If you enjoy it, feel free to follow to get update notifications.

\n
\n

Trending Tools

\n

Kaku: A fast, out-of-the-box terminal built for AI coding
\nhttps://github.com/tw93/Kaku
\nA New Year’s gift for everyone.

\n

Actually, while developing Pake, I was already thinking about creating a fast, user-friendly Mac terminal tool that I’d love to use. So I started tinkering locally, satisfying my own needs with various customizations. Then when I was developing Mole, this feeling became more intense - why isn’t there a terminal tool that I find truly amazing to use?

\n

Before this, I really liked Alacritty because it’s the lightest and fastest, but it doesn’t support multiple tabs. Then I tried the popular Ghostty and even contributed updates, but the font rendering never quite matched my taste. There’s also Warp, which many people love - I couldn’t understand why a terminal would need login. Kitty is also good, but it has window management bugs that seem hard to fix.

\n

Then I discovered Wezterm, but unfortunately its last stable release was two years ago. However, since it’s Rust-based and I know a bit of Rust, I could deeply customize and modify it. So I started my tinkering journey - whenever I had an issue, I fixed it myself, removed a lot of compatibility modules, tweaked its loading, and built in some convenient features. I wanted it to be as fast as the world’s fastest Alacritty, but with multi-tab and split-pane support, so that during AI coding, I could use Claude Code on one side, Codex Review on another, and git diff at the bottom to view code - helping me stay more focused.

\n

Then, the day before yesterday, I had dinner with a friend, and he also complained about not having a good terminal these days. I told him to try mine and wait for me to package it - and that’s how Kaku was born. It’s actually a Japanese name, Kaku Kaku Kaku Kaku - you can read it very quickly, and it feels refreshing. My tagline for it is “A fast, out-of-the-box terminal built for AI coding.” I hope it gives you a smooth, fast TUI experience. It’s not quite mature yet, but I’ve been using it for over half a year now. I’m releasing it for everyone to try - consider it a New Year’s gift. Feel free to report bugs. You must try its various keyboard shortcuts. I hope this terminal works out of the box without any configuration needed.

\n\n

MiaoYan also got an update
\nhttps://github.com/tw93/MiaoYan

\n
    \n
  1. Editing experience upgraded: Unified find and replace between editor and preview, smoother split-sync, more stable switching between preview/presentation/PPT modes.
    2. \n
  2. Further performance improvements: Smoother large document input and rendering, optimized Markdown highlighting and code block processing, with async cancellable formatting support.
    3. \n
  3. Enhanced reliability and data security: Export and other states now managed through sessions, safer image and text replacement, more stable local PPT images, improved storage path persistence.
    4. \n
  4. Details and architecture optimization: Completed multi-language and first-launch templates, more consistent window top behavior, modularized text processing chain and removed old network dependencies.\n\n
    5. \n
\n

LobsterAI: Your 24/7 personal AI agent for any task, now open source
\nhttps://lobsterai.youdao.com
\nI accidentally discovered a great product from NetEase - LobsterAI, your 24/7 personal AI agent for any task. Plus, they officially announced today that it’s now open source.

\n

After installing and setting up the bot in Telegram, I was heading out, so I used my phone to remotely let it read the “Weekly” code repository on my computer - extracting all 2025 content with a clear goal: help me pick the top 20 best recommendations of the year.

\n

I thought it might just scan through randomly to compile a list, but it actually read every single article, being very restrained in its selections, like a real editor. The final Top 20 really matched my taste - it even included Mole, Pake, and MiaoYan, the projects I’ve been maintaining, and wrote some encouraging words. It was unexpectedly touching.

\n

After using it, I roughly understand why it can achieve this level: it has a cross-session persistent memory system that remembers my preferences. The foundation is a local-first design that can actually execute operations on your machine, not just having cloud conversations and calling it done. This naturally avoids issues with latency, privacy, and offline scenarios. Every step is completely transparent to you - it’s not a black box running - you have full control at all times, making it quite suitable for organization-based automation.

\n

Its capabilities aren’t just reading and writing - making PPTs, scheduled tasks, searching, calling local tools… all built in. In settings, you can also connect Feishu, DingTalk, Telegram, Discord, or use email - all out of the box.

\n

The video records the entire process from configuration to generating the Top 20. Check it out if you’re interested. It’s already open source, so everyone can definitely play with it and hand over all those repetitive, boring tasks to it. I’m really looking forward to this little lobster getting better and better.
\n

\n

OpenTrace: Visual route tracing tool, cross-platform native GUI
\nhttps://opentrace.app
\nRecently discovered a cool tool called OpenTrace - an open-source visual route tracing tool. The fun part is that after you enter an IP or domain, you can see step by step how traffic flows between different nodes.
\n

\n

Claude Code’s /plugin: Go to Marketplaces and pick plugins
\nIf you use Claude Code, be sure to try the /plugin function, then go to Marketplaces and wildly pick plugins that suit you.
\n

\n

FineTune: The volume mixer macOS should have
\nBasically the volume mixer that macOS should have come with - truly independent volume control per application, with separate sliders and mute for each app.
\n

\n

Snitch: A better-looking network connection viewer
\nhttps://github.com/karol-broda/snitch
\nI found a pretty interesting little tool called Snitch that makes viewing network connections more beautiful and “human-friendly” - you can think of it as an ss or netstat for humans.
\n

\n

Beautiful Mermaid: Beautiful Mermaid renderer designed for the AI era
\nhttps://github.com/lukilabs/beautiful-mermaid
\nRecently saw a very beautiful Mermaid renderer - clean and comfortable, designed specifically for the AI era, from the Craft team.
\n

\n

Just for Fun

\n

Showing off my cooking skills for the New Year’s Eve dinner, wishing everyone a Happy New Year!
\n

\n

Aerial footage of Anchang Ancient Town
\nHahaha, no crash, no crash, no crash! Filmed a water town, exactly how I imagined a Jiangnan water town ancient town should look. Paired with Zhi Li’s “The End” - a perfect match.
\n

\n

Apple Developer account finally approved
\nGreat news!!! My Apple Developer account is finally approved - can’t wait to make something new in 2026! I’ve been applying for 3 years, and for some reason kept getting “Contact us to continue the process, there may be an issue with your account.” Even the support specialist couldn’t solve it. Finally, I learned a trick from Xiaohongshu - just write to Tim Cook. It really works, super fast! Someone contacted me the next day to submit materials, and today it got approved!
\n

\n

\n Buy me a coke 🥤\n

"},{"title":"256. Ueno Sky","link":"https://weekly.tw93.fun/en/posts/256/","pubDate":"Mon, 02 Feb 2026 00:00:00 GMT","description":"\n

Cover photo taken near Ueno Park in Tokyo, with a plane flying across the sky. The combination of blue sky and trees creates a beautiful scene.

\n
\n

Recording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications

\n
\n

Trending Tools

\n

When Bitcoin Falls, I Reconsidered the Cathedral and the Casino
\nhttps://tw93.fun/en/2026-02-01/money.html
\nRecently, Bitcoin dropped from its high of 120k to just over 70k, and market sentiment turned fearful again. Whenever the market falls, I find it easier to think about what’s more like a casino and what’s still building a cathedral. At the 2024 Berkshire Hathaway shareholder meeting, Warren Buffett used “the cathedral and the casino” to describe capitalism, and this metaphor is especially useful at times like these. Violent price fluctuations mostly come from the casino side, while what truly determines long-term returns often requires years or even decades of sustained investment.
\n

\n

My Minimalist Living Experience
\nhttps://tw93.fun/en/2024-03-03/simple.html
\nI’d like to casually chat about minimalism. I really enjoy this lifestyle, but that doesn’t mean everyone needs to be minimalist. Some people enjoy collecting, some like shopping and buying lots of things—any lifestyle that makes you comfortable is fine. But if you also enjoy a simple lifestyle, or if you have a bit of OCD, these small suggestions might suit you.
\n

\n

My GitHub Repositories Have Surpassed 100K Stars
\nhttps://github.com/tw93
\nFrom starting to learn frontend development in college in 2014, to gradually open-sourcing some of my tools in recent years, I’ve made many friends and I’m very happy. Recording this milestone.
\n

\n

Mole Recently Updated to Version 1.24
\nhttps://github.com/tw93/Mole
\nThis version is named Razor 🪒, an interesting name. Updates include the following, feel free to try it out:

\n
    \n
  1. mo clean - Smarter and Faster: Automatically empties trash via Finder, automatically handles locked files with fallback processing, batch deletion now uses find -delete for significant speed improvements, added Yandex browser and Apple Podcasts residual file cleanup, fixed progress bar remnant issues.
    2. \n
  2. mo update —force: Even if already on the latest version, can force reinstall, automatically clears quarantine attributes so binary files can launch without security confirmation.
    3. \n
  3. mo uninstall - More Thorough Residual Detection: Finds more residual files through lowercase hyphen, no-space naming variants, validates bundle ID format to prevent injection attacks, error messages more instructive.
    4. \n
  4. mo check - Identifies Third-Party Firewalls: Prioritizes detection of Little Snitch, LuLu, Radio Silence and other third-party firewalls, fixes disk space parsing issues on non-English systems.
    5. \n
  5. mo purge - Deeper Scanning: Maximum scan depth increased from 4 to 6 layers to capture deep build artifacts, automatically falls back to find when fd is unavailable, correctly handles circular symbolic links to avoid hanging.
    6. \n
  6. Underlying Optimizations: Added operations.log for easier troubleshooting, app protection uses dual-array strategy reducing matching complexity from O(N) to O(1), Go scanner uses timer pool and channel timeout to prevent blocking.
    \n
    7. \n
\n

Codia AI NoteSlide Converts NotebookLM-Exported PDFs Directly to PPT
\nhttp://codia.ai/noteslide?r=tw
\nI’ve really enjoyed using NotebookLM recently to help learn and understand new things, but it can only export PDFs, and sometimes the Chinese rendering isn’t great. I’ve been looking for a good tool that can convert PDFs to editable PPTs, and after searching around, I found Codia AI NoteSlide works best. Compared to traditional pdf2ppt tools, it’s much simpler and easier to use, quickly converts to editable content, and the results are beautiful, refined, and error-free. Very useful—if you have the same pain point, give it a try.
\n

\n

Apple Battery Protection Tool - Battery
\nhttps://github.com/actuallymentor/battery
\nThis tool keeps your MacBook that’s always connected to power at 80% charge, which supposedly extends battery lifespan. However, I mostly use it plugged in and don’t pay too much attention to this, but those who need it can give it a try.
\n

\n

Visual Status Alerting Tool for Developers
\nhttps://github.com/TwiN/gatus
\nGatus is a health dashboard for developers. You can monitor your services using HTTP, ICMP, TCP, and DNS queries, evaluate query results through a series of conditions (such as status codes, response times, certificate expiration, body content, etc.), and health checks can be integrated with various alert systems like Slack, Teams, PagerDuty, Discord, Twilio, and more.
\n

\n

Random Finds

\n

Global AI Industry Traffic Tracking Report
\nhttps://similarweb.com/corp/wp-content/uploads/2026/01/attachment-Global-AI-Tracker-6.pdf
\nSimilarweb recently released the Global AI Industry Traffic Tracking Report, “AI Global Sector Trends on Generative AI,” which is well worth reading. It analyzes the traffic situation of major product categories in the current AI space, showing who’s growing and who’s declining.
\n

\n

Saw this on Xiaohongshu—this stir-fried pork with chili peppers is delicious. I had something similar when I was young, give it a try
\n

\n

My 2026 Reading List
\nI recently started selecting books for 2026 and picked these 5. Do you have any recommendations for the best books you’ve read this year? Feel free to recommend them with a brief explanation:

\n
    \n
  1. A Brief History of Intelligence
    2. \n
  2. Chinese Painting: Yuan to Qing
    3. \n
  3. Source Code - Bill Gates’ First Autobiography
    4. \n
  4. The Philosopher’s Last Lesson
    5. \n
  5. Nine Poetic Hearts: Literary Morning Star in the Dark Night
    6. \n
\n

How to Organize a New Year’s Eve Team Building Activity That Young Engineers Love

\n
    \n
  1. Don’t hassle employees—help them apply for a half-day off on a workday, so they just come to play and eat.
    2. \n
  2. Organizers prepare exquisite snack gift bags for everyone, with nice bags too, placed on dining chairs before arrival.
    3. \n
  3. Play games young people enjoy, like XX points competition. Individual competition rankings get priority gift selection. To avoid gift exchange awkwardness, collect wish lists in advance without revealing names, so everyone roughly gets what they like. Even made a webpage to display it. For the top three, prepare a cute, presentable trophy, like engraved with “God of Gamblers,” “Saint of Gamblers,” “Knight of Gamblers.”
    4. \n
  4. For team competition, use the budget to prepare ten boxes of cherries, ten boxes of chocolate, ten boxes of strawberries from Sam’s Club. Top three teams all get prizes per person, everyone smiling.
    5. \n
  5. Don’t choose hotel-style banquet venues for dining. Choose places that are delicious, clean, with good service, slightly 2 tiers above daily dining. Eat and drink well—no alcohol, but Coke, orange juice, coconut water all fine.
    6. \n
  6. Finish eating at 7pm. Those who want to play organize activities themselves; those who don’t, take their many gifts straight home. Keep it flexible and let people choose.
    7. \n
\n

\n Buy me a coke 🥤\n

"},{"title":"255. Delicious Chicken Wings","link":"https://weekly.tw93.fun/en/posts/255/","pubDate":"Mon, 26 Jan 2026 00:00:00 GMT","description":"\n

The cover photo was taken of grilled chicken wings we had over the weekend. The plating looked great, and they tasted good with a bit of chopped parsley.

\n
\n

Record the down-to-earth trending technologies seen every week, and publish them here after screening. If you find it good, you can subscribe to this weekly to get update notifications.

\n
\n

Trending Tools

\n

243 Engineers: Best Things Bought in the Past Year
\nhttps://tw93.fun/2026-01-24/good.html
\nLast week, while buying Lunar New Year dinner gifts for the team, I casually asked on X: In the past year, what is the thing you were most satisfied with? Or if you had to recommend one item, what would it be? It could be gadgets, software, or daily-use items.
\nI did not expect 243 replies. It felt lively and real, and I really like this kind of exchange. The comments were buzzing. After reading through a few times, I found many great items. The recommendations ranged from must-haves to very down-to-earth everyday goods.
\n

\n

Pake Updated to Version 3.8.1
\nhttps://github.com/tw93/Pake
\nPake, the tool that packages web pages into lightweight desktop apps for macOS, Windows, and Linux, has been updated. Changelog highlights:

\n
    \n
  1. Third-party login popups: Added the --new-window parameter to support OAuth/SSO flows that need a new window, wired through CLI -> config -> Tauri window.
    2. \n
  2. Fullscreen video support: The injection layer adds HTML5 Fullscreen compatibility so sites like YouTube can reliably enter fullscreen.
    3. \n
  3. Linux packaging expansion: Added RPM packaging and multi-target builds. The default Linux targets are now deb and appimage.
    4. \n
  4. Linux stability and focus fixes: Disabled the WebKit DMABUF renderer by default for stability, fixed fullscreen input focus, and restored fullscreen correctly for tray launch and startup scenarios.
    5. \n
  5. macOS window behavior: Closing a window no longer minimizes it; it hides instead. Window control permissions are completed, and reopening from the Dock restores hidden windows.
    6. \n
  6. Theme and experience tweaks: Follow system theme by default, and only force light/dark mode when explicitly set.\n\n
    7. \n
\n

MemOS: Long-Term Memory for Agents and LLMs
\nhttps://github.com/MemTensor/MemOS
\nWhile looking at long-term memory solutions for Agents and LLMs, I found an interesting project: MemOS. It is not about stuffing a bigger context window or improving retrieval, but about a more fundamental problem: how memory itself should be managed.
\nWhen building AI agents or multi-turn chat, models often forget context. User preferences, operation records, and uploaded documents seem to evaporate. MemOS addresses this with a core “shared memory layer,” and lets the same memory be reused across projects and agents.
\nIt supports connecting files and URLs directly into a knowledge base. During conversations, memories are continuously updated and gradually form preference memories as they grow. It can unify text, images, files, and tool calls under one management layer, and you can even use natural language to correct or clean existing memory when needed. If you are interested, go check out the project.
\n

\n

Toad: A Unified AI Interface in the Terminal
\nhttps://github.com/batrachianai/toad
\nThis unified AI interface in the terminal, Toad, is pretty good. With the ACP protocol, it is worth checking out and giving it a try.
\n

\n

An Immersive 3D/2D Web Visualization Project
\nhttps://seanwong17.github.io/Mammalia-tree/
\nAn immersive 3D/2D web visualization project that explores the 200-million-year epic evolution of mammals. The interactions are excellent and great for anyone who likes “archaeology”.
\n

\n

A Good-Looking Terminal Pomodoro: pomo
\nhttps://github.com/Bahaaio/pomo
\nBuilt with Bubble Tea, and it looks great.
\n

\n

Just Looking Around

\n

Watching Alex Honnold Climb Taipei 101 on Netflix Live
\nhttps://www.bilibili.com/video/BV1nYzDB3EKx
\nOn Sunday morning, I watched Alex Honnold climb Taipei 101, a landmark in Taiwan, on a Netflix live stream. He free-soloed the whole way without ropes or safety gear; one mistake would have been fatal. He finished in about an hour and a half. I am really impressed, and he stayed remarkably calm throughout. It is worth watching. If you do not have Netflix, you can probably find it on Bilibili too. It has been a long time since I have seen something like this.
\n

\n

Investment Directions I Will Watch in 2026, Not Advice, Just for Reference
\n

\n

\n Buy me a coke 🥤\n

"}]}}