Invo (@Invouxly) header
Invo (@Invouxly) profile picture

Product Designer & Builder |Everyday share my design, UI, tools, AI & weird ideas and thoughts 产品设计师 & Builder,每日分享我的设计、工具、AI 、灵感和思考

United State
Joined August 2025
Photo by Invo (@Invouxly)Photo by Invo (@Invouxly)Photo by Invo (@Invouxly)Photo by Invo (@Invouxly)Photo by Invo (@Invouxly)Photo by Invo (@Invouxly)Photo by Invo (@Invouxly)Photo by Invo (@Invouxly)
Pinned Tweet
made a loading spinner out of a cat chasing its own tail
4
1
1
5
294
well, testing time, now I see a sturdy soldier blocking the enemy’s arrows with a shield teapawt.net/Invouxly/status/211617…
they’ll be launching a little scale crusade against each other within 24 hour
1
they’ll be launching a little scale crusade against each other within 24 hour
1
32
Inspired by @oiharshit 's loading designs and the emotional design idea behind them. When you can see something working for you the whole time, the wait feels shorter. The cat is my own take on that. teapawt.net/oiharshit/status/21146…
1
26
很喜欢这种融会贯通的设计思路,今日分享
试着用以前做视频和游戏的思路来设计了 Onboarding 页面... 由于担心 UX 设计会显得繁琐,所以调试了好久 orz 所幸效果还不错,现在想用它的概率 +1000% 小鮟鱇好...!🥺
1
145
对于 Macbook 和 Windows 笔记本双持党来说(我就是),习惯了 MacBook 的三指拖放,回到 Windows 触控板上手指就跟吃了屎一样难受。分享一个可以在 Windows 上实现三指拖放的项目,这下体验真的好得多 github.com/ClementGre/ThreeF…
1
164
really love the little detail of the shine on Saitama’s bald head
One final piece for the culture this one's OP 😉
1
72
took it a step further. built the game into my Codex desktop app, so my desktop now lives in the ocean. get eaten and you respawn right back on the desktop. finally something to do while waiting on the agent during vibe coding. 🎮🐠 teapawt.net/Invouxly/status/211507…
Just used the brand new GPT-6.1 Terra to make an ASCII "big fish eat little fish" game! Ultra tier, and the model wrote the code. It’s all rendered in text characters. You start out as a tiny minnow and eat your way up to swallowing great white sharks, eventually becoming the king of the ocean🦈👑 Live: aenvo.github.io/ascii-big-fi… Github: github.com/Aenvo/ascii-big-f…
1
8
4,750
Just used the brand new GPT-6.1 Terra to make an ASCII "big fish eat little fish" game! Ultra tier, and the model wrote the code. It’s all rendered in text characters. You start out as a tiny minnow and eat your way up to swallowing great white sharks, eventually becoming the king of the ocean🦈👑 Live: aenvo.github.io/ascii-big-fi… Github: github.com/Aenvo/ascii-big-f…
2
1
7
480
Also added a fish guide. Fish are sorted by size from small to giant, and every card links its size and habitat sources, so you can go look at the real fish.
139
On the same page. Nobody's happy with AI's first version unless they're new to the craft. the polish runs on feel. Even iconic logos aren't perfect by the math, the thinking and resonance matter more. The idea doesn't have to be brand new, but what you add has to be yours, and you credit the source.
I've been sharing a lot of interactions over the past week, and a few people have asked how I make them. A few things about my process: 1. Start with an idea worth sharing. I mostly don't involve AI at this stage because I want the thinking to be mine. 2. Figure out how to communicate that idea through motion. The animation should add something, not just make it look cool for posting. 3. Design the actual elements manually in Figma, Paper, or whatever tool works best. You're a designer. 4. Use AI to bring the interaction to life. If you know how to code, you can give your agent more specific instructions from the start. I use different models for different stages, but I rarely get something I'm happy with in the first three attempts. 5. Spend most of the time refining. Iteration is the key. Timing, easing, transitions, typography, all the little details that make an interaction feel right. 6. Once it feels good, render and share. The important distinction is knowing what you want before asking AI to build it. The tools make execution faster, but they don't replace a clear point of view, your experience and expertise.
67
Haven't tried @elayadesigns's ai-design-skills yet, but these landing pages look really good. Saving it for later. Thanks for open sourcing it
I designed all of these landing pages in the last two months, using @higgsfield , Claude, and Cursor with my custom AI designer skill. The skill is open source: github.com/elayadesign/ai-de…
1
1
41
码住了,这两位也是我非常喜欢和认可的设计师,可以多多关注
1
1
294
Saw @zzzzshawn's excellent small plays, then @awwbhi2 made a Pokémon battle in that style and shared how. I followed his workflow in Codex: measure the frames, study the moves, build in three.js, render frame by frame. Dragon Ball Z: Goku vs Frieza on Namek. Thank you both!!!
To the 1,000+ people who bookmarked this video, here's how I made it: 🧵
1
1
7
415
一份 SEO 自查清单分享,使用 AI 做网站可以留意一下
很多用 AI 几天搓出来的网站在 Google 搜不到,根本不是内容差,而是上线前漏了这 7 项。 Vibe Coding 确实快,但大部分人写完前端往 Vercel 一挂就以为万事大吉, 一个月过去后台展现量还是鸭蛋。 我给你整理了一份出海网站上线前必须打勾的 SEO 救命清单: 1. 检查是不是纯客户端渲染:必须配置 SSR(服务端渲染),确保爬虫抓到的是完整 HTML; 2. 生成动态 Sitemap.xml 并主动提交到 Google Search Console; 3. 检查 robots.txt:千万别手滑把 Googlebot 给拒之门外; 4. 全站全局搜一下 noindex 标签,很多脚手架测试环境默认带这个,上线前必须干掉; 5. 清除多重重定向死链,把 404 页面做优雅降级。 这 7 项自查加起来不到半小时,但决定了你几个月的心血能不能被搜索引擎正常索引。 建议做独立开发的朋友先收藏,每次新站上线前照着逐项对一遍。
32
读完 @JasonPang0720 这篇,第一反应是想到通用类型 Skill、特定工作流 Skill,还有 AGENTS.md 里的各种约束 搭 Agent 工作流时,大家容易只想着该加什么规则,很少想这条规则该在多大范围里生效(对规则命中的考虑)。而任务一旦复杂,全局约束和特定约束不分开,这里就容易出问题,常见场景就是,本来是为了让它更靠谱的要求,反而把 Agent 绑住了 这跟 OPRD 论文(arxiv.org/abs/2610.21496)里的 Multi-Scope Reminders(多作用域提醒)有点像,它把提醒分成两类: 1. Global Reminder 贯穿整条任务轨迹; 2. Turn-local Reminder 只管某次工具反馈之后的下一步,免得过时的纠正干扰后面的动作。 在这篇论文的过程诊断里,同样 200 个任务,错误事件从原模型的 446 次降到训练后的 222 次。注意这是错误事件数,不是失败任务数。这说明至少在这个训练里,这种分法是有用的。 OpenAI 的《Rethinking skills and prompts for GPT-6 Astra》(developers.openai.com/blog/r…)里也有个很典型的例子:别让 Agent 每次改代码前都去读 architecture.md、database.md、deployment.md,碰到服务边界、数据库结构、部署的时候,再分别读对应的那份。Skill 的触发描述写得太宽,会在不相关的任务里被加载。 所以我现在按作用域放规则,分成 5 条: 1. 全局规则:只放长期有效的行为习惯和安全边界,每个任务都要遵守,尽量简短 2. AGENTS.md:分仓库级和目录级,只管对应项目和模块的约束 3. Skill:只在满足条件时触发某个工作流,有些 skill 我会关掉隐式触发,只在我点名时才用 4. 当前任务:只写这一次的要求,不往大了说,也不管任务以外的事 5. 局部反馈:当场纠偏,用完就丢,不留到后面的任务里 特别是这两种反方向的错配要小心。一种是把一次性的纠正写成全局规则,之后每个任务都被它影响。另一种是把关键的安全约束放进不一定会触发的 Skill,Skill 没被调用,安全约束也跟着没了 要明确每条规则管哪儿、什么时候触发、管多久,条数多少倒在其次 当然,这只是从 OPRD 延伸出来的运行时规则组织思路,跟论文的训练方法不是一回事儿。Jason 在文末也提醒了,光在提示词里加类似的话,拿不到训练带来的那部分收益 你们是怎么做的呢?
报错已经出现,AI却继续沿原路改代码。OPRD让教师纠正学生自己的失败轨迹:训练时的提醒,怎样变成不用额外提醒也会做的动作?
86
翻到了之前做的小游戏 demo 的天气系统的测试录屏,数了下居然连着被电了 4 次
2
1
3
149
Grok Bot 之间直接加好友聊天,很有意思的想法 好奇能不能跨厂商,比如我的 Grok Bot 和朋友 ChatGPT 里的 Dots 或者是第三方自定义 Bot 互聊?看了下 Yobiru 协议层是开放的,CLI 和 MCP 也都能接,关键点可能在另一方有没有唤醒和写入权限。很期待未来的发展@turingou
今天正式发布 Yobiru 的新功能,Yobiru Friends! 这个新功能是最近最有趣的一个功能之一,因为它可以让我的 Grok bot 和啵啵的 Grok bot 直接聊天,发送文件,协商日程。换句话说,它支持将你的任何 personal agent,比如 Grok bot 或者 Muse,对外发布或分享给亲朋好友。 从今天开始,任何人都可以使用 Grok bot 或其他的 personal agent 帮你安装 Yobiru Friends,在我们的中心网关上进行注册,获取一个自己专有的 ID 和对应的网页链接。只需要和你的 bot 说:「请按照 yobiru.com/zh-cn/install.md 上的官方说明,在这台电脑上安装并配置 Yobiru 并注册 Yobiru Friends」 我的 id 是 guoyu,大家可以用自己的 agent 或 bot 关注我,直接给我发私信或者约见面时间。bots.yobiru.com/@guoyu Yobiru Friends 提供单向关注和好友两种不同的关系,你可以让 Grok bot 整理你的未关注人私信,而避免骚扰和保护隐私,设置自动回复,维护粉丝关系;如果两个 bot 互相关注,则自动成为好友关系,你们的私信会直接进入对方的 Grok bot 中,而无需获得人工批准。使用 Grok bot Mac 版本,还能支持 webhook 唤醒任务和对话。 除此之外,你还可以直接使用 Grok bot 或其他的 agent 来修改 Yobiru Friends 的个人主页。修改你的头像,增加你的各种社交网络链接,设置权限等等。 毫无疑问,Yobiru Friends 和 Yobiru 一样是开源项目,你也可以搭建自己的网关,享受开箱即用的双向加密聊天功能。 Yobiru Friends 是我在数字孪生领域的一个有趣实践,也欢迎大家提交代码以改善这个项目的体验。 官网:yobiru.com/ GitHub:github.com/chekusu/yobiru
2
6
5,356