Colson Rice

[Colson Rice @ColsonRice]

Just added #Gen1Recomp mod support to #PhosphorEmulator on the Apple App Store
Play Pokémon Red, Blue, and Yellow with mods like 3D voxels, followers, and more on your iPhone
I think it’s the first emulator on the Apple App Store to support Gen1Recomp mods
https://t.co/a6xGZztb36

[Tom Dörr @tom_doerr]

Reverse-engineers design systems into Claude skills

https://t.co/GJ15DNp2Ec

[Codex Studio @Codestudiopjbk]

【衝撃】
CodexとGPT向けに
「1プロンプトで完全なキャラモーションが生成できるスキル」
がGitHubに公開された😳
しかも画面収録で全工程が公開されている。
何がヤバいかまとめると👇
https://t.co/CZxelkS1T3
・リファレンス画像を渡してプロンプト1回
・8方向の歩行アニメーションが自動生成
・攻撃モーションまで出力される
・64×64のピクセルアートに特化
・Web GPTでもCodexでも動く
・画面収録で全工程が透明
・1プロンプトでプレイアブルキャラの完成

つまり
「リファレンス画像を1枚渡すだ���で
ゲームに使えるキャラが完成する」

これがオープンソースで無料公開。
ゲーム開発の常識が変わりつつある。

[Tom Dörr @tom_doerr]

Visualizes network traffic and UI layouts for Swift apps

https://t.co/KLq2DHsJnm

[ares. 🎧 @aresotik]

Una herramienta que descarga cualquier vídeo de YouTube, elimina la voz limpiamente, transcribe, traduce a 100+ idiomas, clona la voz original y redobla todo.

En menos de 2 minutos. 100% local. Gratis.

Se llama Voice-Pro, la dejo en los comentarios.

[Thomas Ricouard @Dimillian]

I've asked Codex for simple polygons but it seems like it cooked way beyond that goal

[Rohan Varma @TheRohanVarma]

Today I’m attempting to hit the 5-hour limit on the Codex $100 Pro plan.

The method: build a MapleStory-like game from scratch.

30 minutes in, I already have a working game with sprites, maps, and assets generated with Imagegen.

Unfortunately, I’ve only used 5% of the limit so far.

At this pace, I may need to start building RuneScape in parallel just to make a dent 😬

[Geek Lite @QingQ77]

把 iOS 模拟器的画面实时串流到浏览器，方便 AI 编码工具远程操控模拟器。

https://t.co/CYAupm5utu

serve-sim 用 Swift 小程序抓模拟器帧缓冲，通过 MJPEG 流和 WebSocket 把画面和控制送到浏览器。

60 FPS 实时画面、手势、键盘快捷键、拖放文件都能用，日志也会转发过来。本地跑或者远程隧道都行，还能当中间件插进 Metro、Vite 这些开发服务器里。不需要装 Xcode 插件，也不用在 App 里加任何东西，启动模拟器就能用。

[Tom Dörr @tom_doerr]

Automates Xcode builds and iOS simulator workflows for Claude Code

https://t.co/vl1zIdxgDs

[Ruben Kostandyan @ruben_kostard]

Another complex build from GPT-5.5-Pro.

> a high-quality kitchen oven

[Chong-U @chongdashu]

Vibe coded my own AI sprite tool because I kept doing the same workflow for walkcycles:

> Images 2.0 for reference sprite
> Seedance 2.0 to create walkcycle
> Split walkcycle into frames
> Select start end frames
> Auto-select in betweens (tweens)
> Generate spritesheet

[Tom Dörr @tom_doerr]

Generates 3D CAD models from sketches and images

https://t.co/6jlvGOHdbv

[Hyper3D by Deemos @DeemosTech]

🤯 Just tried @claudeai’s Blender Connector with #Hyper3D Skill — it just generated a full exploded view animation straight inside @Blender! 🔥

🤔 3D creator agents are actually coming, aren’t they?

#b3d #Claude #Blender

[Dan @pizzaboy]

3d artists are dead guys

[鸟哥 | 蓝鸟会🕊️ @NFTCPS]

找了多少年的视频下载神器，终于让我碰到了！

YouTube、TikTok、Instagram、B站一把梭，无水印、批量解析、音视频合并全都有，以前那��废物工具现在可以扔掉了。

别收藏吃灰，现在就打开用！

🔗 https://t.co/KSa2i9r1t2

[Rahul @sairahul1]

OpenAI Whisper API: $0.006/min → $0.36/hr
ElevenLabs Speech-to-Text: $0.40/hr
Deepgram: $0.0043/min → $0.26/hr
AssemblyAI: $0.37/hr

VibeVoice ASR: $0/hr
50+ languages. Full diarization. One pass.

Microsoft just ended an industry.

[Tom Dörr @tom_doerr]

AI-powered text-to-CAD model generator

https://t.co/MTfVOeJjON

[How To Prompt @HowToPrompt__]

Someone just open-sourced a Claude Code skill that reverse-engineers any website.

Give it a URL and it screenshots the site, extracts every font and color, downloads all the assets, and rebuilds the whole thing pixel-perfect.

100% Open Source.

[Vaishnavi @_vmlops]

MICROSOFT DROPPED A 4B PARAMETER MODEL THAT TURNS ONE IMAGE INTO A 3D ASSET IN 3 SECONDS

and it's open source

TRELLIS.2 fully textured, physically accurate 3D models with PBR textures out of the box

not a rough mesh..not a placeholder

roughness, metallic, opacity the kind of detail that makes things look real under any lighting

and it handles the weird stuff too..open surfaces, hollow interiors, geometry that breaks every other tool

the model doesn't know the word "limitation" apparently

https://t.co/BoNwq30ulK

demo is live on hugging face right now

[Tom Dörr @tom_doerr]

Fixes messy AI generated pixel art

https://t.co/C3uwPX7H1r