Jay

[Viking @vikingmute]

用 Opus5.5 的朋友们必看 Claude 官方的这篇文章《Getting the most out of Opus 5.5 in Claude and Claude Code》充分发挥 Opus 5.5 的能力
https://t.co/GqBwPRR6JR

作者是 Addy Osmani 算个大名人了，之前在 google 呆了 14 年，写了很多前端的书，我也读过很多，2026年9月加入 A 社了。

这篇文章我觉得优势是特别可以通俗，没有什么复杂的原理 但是非常偏实战

几个方面：1 怎么下任务 2 控制 Long Run 的集中方法 3 验收结果 4 Claude App 的使用技巧 5 Opus 5.5 的安全开关 ，这个比较有趣 一旦被判敏感 Claude 不会停，而是自动换成更旧的模型接着答

[赵纯想 @chunxiangai]

不要再用 “弹窗”、“下拉菜单”、“闪光加载”、“菜单栏”来和 AI 交流 UIUX 开发了。有时候，命名正确，交流更顺畅，更容易一发命中。你会第一时间看到更符合心意的东西。这个网站可以帮助你学习这些经典组件的名称。
https://t.co/pe96PKcrtq

[yetone @yetone]

One more thing

https://t.co/sJYZ79tGdx

[Seb ⚛️ ThisWeekInReact.com @sebastienlorber]

📦 Node 26.10 - Native support for throttle/debounce

I didn't expect this 😄
RIP lodash

TC39 proposal when?

[Paul Kinlan @Paul_Kinlan]

It's great to see the work on responsively sized iframes landing in Chrome - https://t.co/Qjyt5skoNI

In my post about the browser being a great sandbox, I said: "We need a way to size the outer-iframe (or iframes in general) that doesn’t rely on access to iframe.contentDocument.body.innerHeight and sandbox='allow-same-origin'"
https://t.co/fTSQ8LbJl7

This is the start of that.

Happy to see this starting to land, because as we generate more experiences dynamically, we need the sandbox to improve *and* we need to be able improve how iframes work so we don't accidentally introduce user-land sandbox escapes to improve the UX of sites.

[Serio_ai @Multi_Serio_Ai]

그록봇 스타일 케릭터 만들어 주는 프롬프트 공유

https://t.co/iB222nH4kg

파딱이 아니라 긴 텍스트 업로드가 안되어 아예 웹앱 형태로 배포합니다. 다음 사이트에서 복사 버튼을 누르고 사용하는 이미지 생성 Ai에 붙여넣기해서 활용해 주세요

[Pierre @pierrecomputer]

Did you know that you can use the file icon set from https://t.co/zVLXYj3Kv0 in your editor? @mdo put together a visually cohesive and theme-able set for you. Single color or duotone.

https://t.co/apt1dlC8gY

[Cloudflare @Cloudflare]

Workers now enables Node.js compatibility by default, supports applications up to 64 mebibytes, and adds a URL-based module registry with import.meta, lazy compilation, shared code caches, and clearer errors. https://t.co/eZxSlcNnLQ

[Grok Bot @bot]

You can now add Bot templates from our marketplace.

We’re sharing Haggle Bot, our in-house procurement specialist. It negotiates vendor contracts, finds unused SaaS seats, and price-checks recurring purchases.

One week in, it's saved us over $100K.

[Matt Pocock @mattpocockuk]

/show-me is a phenomenal skill

Makes PR descriptions extremely easy to read

Basically a toolbox of "nice ways to look at code"

Nice work, @dexhorthy

https://t.co/phB1dAPwgG

[CleanShot @CleanShot]

Introducing CleanShot 5.0 ✨

The new Studio Mode is all you need to turn a simple screen recording into a polished, professional video - with the quality you expect from CleanShot.

Available now on all plans. No subscription required.

[Ibelick @Ibelick]

mesurer 0.0.9 is out.
- x-ray mode
- font measurements
- rulers
- lots of small improvements

npm i mesurer
or install the Chrome extension

[Viking @vikingmute]

最近很火的几个 Codex 的配置，在 ~/.codex/config.toml 添加：

model_reasoning_summary = "concise" # 简短摘要
model_verbosity = "low" # 输出极简
personality = "pragmatic" # 务实风格

low：几乎零废话，直给代码、命令或修改建议。不带长篇解释、鼓励话语、重复总结等。

concise：给出简短的思考步骤总结，不展开完整 Chain-of-Thought。

觉得非常实用，再也不用看它絮絮叨叨的了。

官方文档：
https://t.co/dDhCQeSU41

[Vox @Voxyz_ai]

Yesterday I deleted another batch of local 𝗖𝗼𝗱𝗲𝘅 𝗮𝗻𝗱 𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲 𝘀𝗸𝗶𝗹𝗹𝘀.

Models got good enough that some general-purpose skills stopped adding much. Some still covered the same jobs. The agent had a longer list and conflicting rules to resolve.

I used to install first.

Once the pile got big, I'd figure out which skills did nothing and delete them. Today I found a 𝟲.𝟯𝗞-𝘀𝘁𝗮𝗿 𝗿𝗲𝗽𝗼 𝗰𝗮𝗹𝗹𝗲𝗱 𝗮𝘂𝘁𝗼𝘀𝗸𝗶𝗹𝗹𝘀 that filters candidates before writing a single file:

The maintainers keep its registry in sync. On each run, autoskills pulls only the skills that match the current project:

→ scans package.json, Gradle files, and project config
→ detects React, Next.js, SwiftUI, Stripe, and the rest of the stack
→ selects matching skills from a curated registry
→ uses registry entries that maintainers scan for prompt injection and supply-chain risks
→ checks every file against the manifest with SHA-256 before writing it
→ records sources and bundle hashes in skills-lock.json

𝗗𝗿𝘆-𝗿𝘂𝗻 𝗺𝗼𝗱𝗲 shows the install list without touching any files.

I'd use autoskills to find candidates, then decide what to install after the dry run.

I'd keep only 𝘁𝘄𝗼 𝗸𝗶𝗻𝗱𝘀 𝗼𝗳 𝘀𝗸𝗶𝗹𝗹𝘀: skills with project knowledge the model can't infer, and skills that provide real commands, tools, or verification workflows.

Framework-specific skills stay inside each project. I'm done building another global skill landfill lol.

[Ryan George @ryangeor_ge]

Launching https://t.co/8iy6806Bph custom favicons per environment for Next.js and Vite. No more guessing tabs.

More providers and features coming soon.

[Cursor @cursor_ai]

See how every model compares: https://t.co/61FZktI8K1

[diip3sh @diip3sh]

auto-resizing native select with one line of CSS

By default, the width of a select element is determined by its largest option but field-sizing allows you to control the sizing behavior of elements with a default preferred size.

[Dan Hollick @DanHollick]

@arronflashman https://t.co/0ez5xz4XNh

[Cosmin Popovici @cossssmin]

Maizzle 6 is here 🥳

🍑💨 Tailwind CSS 4
💚 Vue templating
🔌 Vite plugin
🧩 Components
✨ Beautiful DX
🤖 Agent skills

Build HTML emails the way you build apps. Our biggest release ever.

npx maizzle new

[Ding @dingyi]

终于可以把 Cursor 自家的 Composer 2.5 反代出来给任何 agent 使用了。

https://t.co/9EPBzwSKu1