正在加载视频...

视频加载失败

返回首页

Updated my scroll-world skill: it now builds the mobile version too. Most scroll-fly through sites look incredible on desktop and fall apart on a phone. The skill now generates the phone-native assets and framing, so works on both. One shot result for 3d printer farm

the_cyw's profile picture

Peter Wang

1,073 subscribers

57,055 次观看 • 17 天前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I built a skill to let my Claude Code build premium landing pages like this in one shot. The 3 sites in the video are one-shot results, ~$10-15 each. Register Higgsfield AI 🧩 , install the CLI and scroll-world skill, hand the rest to Claude Code.
0:59

I built a skill to let my Claude Code build premium landing pages like this in one shot. The 3 sites in the video are one-shot results, ~$10-15 each. Register Higgsfield AI 🧩 , install the CLI and scroll-world skill, hand the rest to Claude Code.

Peter Wang

512,606 次观看 • 24 天前

Apple's product pages have that scroll effect. The camera flies through a 3D world. Products float. Scenes transition. No cuts. One continuous flight driven by your scroll wheel. Here is what one costs to build in 2026. Big storytelling agencies (Noomo, WithLore, Utsubo): $15,000 to $100,000. Three to six months. A team of designers, 3D artists, and WebGL developers. Awwwards-tier flagship from a senior freelancer: $8,000 minimum. Three.js multi-scene site with GSAP scroll: $3,500 to $8,000. That is if you can find a Three.js specialist. They charge $75 to $150 an hour. There are fewer of them than there are brands that want the site. Now meet scroll-world. A free, open-source agent skill for Claude Code and Codex that generates the entire thing from a prompt. Describe your brand. Describe the scenes. "A coffee brand. Start outside the farm. Fly into the roasting facility. Pass through the packaging. Land in the cafe." It generates the isometric stills. It generates the camera flights. It generates the connector clips between scenes from the actual boundary frames of both neighbors, so every seam is pixel-identical. No flicker. No cut. One continuous flight. Then it wires the chain into a portable vanilla JS scroll engine that drops into plain HTML, Next.js, or Vue. One prompt. Hours. Not months. 6,096 stars on GitHub in 25 days. 724 forks. MIT license. Built by cyw, founder and CTO of Hermai AI, out of San Francisco. Here is what scroll-world does: - Interviews you on brand, scenes, art direction, and budget before spending a cent - Generates the isometric stills through GPT Image 2 - Generates the camera flights through Seedance on Monid - Renders a native 9:16 portrait chain for mobile, not a crop - Ships a vanilla JS scrub engine with blob-seek, lazy load, and seam crossfade - Installs into Claude Code as a plugin or Codex through the Vercel skills CLI - Framework-agnostic Here is what scroll-world costs to install: Zero. Forever. Generation burns credits. A 6-scene 1080p chain on Monid pay-per-clip lands around $27, printed before the run starts. Big storytelling agency: $15,000 to $100,000. scroll-world: $27. Awwwards WebGL flagship: $8,000. scroll-world: $27. Three.js contractor for a month: $12,000. scroll-world: this afternoon. Your brand. Your world. Your scroll. 100% Open Source. (Link in the comments)
0:59

Apple's product pages have that scroll effect. The camera flies through a 3D world. Products float. Scenes transition. No cuts. One continuous flight driven by your scroll wheel. Here is what one costs to build in 2026. Big storytelling agencies (Noomo, WithLore, Utsubo): $15,000 to $100,000. Three to six months. A team of designers, 3D artists, and WebGL developers. Awwwards-tier flagship from a senior freelancer: $8,000 minimum. Three.js multi-scene site with GSAP scroll: $3,500 to $8,000. That is if you can find a Three.js specialist. They charge $75 to $150 an hour. There are fewer of them than there are brands that want the site. Now meet scroll-world. A free, open-source agent skill for Claude Code and Codex that generates the entire thing from a prompt. Describe your brand. Describe the scenes. "A coffee brand. Start outside the farm. Fly into the roasting facility. Pass through the packaging. Land in the cafe." It generates the isometric stills. It generates the camera flights. It generates the connector clips between scenes from the actual boundary frames of both neighbors, so every seam is pixel-identical. No flicker. No cut. One continuous flight. Then it wires the chain into a portable vanilla JS scroll engine that drops into plain HTML, Next.js, or Vue. One prompt. Hours. Not months. 6,096 stars on GitHub in 25 days. 724 forks. MIT license. Built by cyw, founder and CTO of Hermai AI, out of San Francisco. Here is what scroll-world does: - Interviews you on brand, scenes, art direction, and budget before spending a cent - Generates the isometric stills through GPT Image 2 - Generates the camera flights through Seedance on Monid - Renders a native 9:16 portrait chain for mobile, not a crop - Ships a vanilla JS scrub engine with blob-seek, lazy load, and seam crossfade - Installs into Claude Code as a plugin or Codex through the Vercel skills CLI - Framework-agnostic Here is what scroll-world costs to install: Zero. Forever. Generation burns credits. A 6-scene 1080p chain on Monid pay-per-clip lands around $27, printed before the run starts. Big storytelling agency: $15,000 to $100,000. scroll-world: $27. Awwwards WebGL flagship: $8,000. scroll-world: $27. Three.js contractor for a month: $12,000. scroll-world: this afternoon. Your brand. Your world. Your scroll. 100% Open Source. (Link in the comments)

Nav Toor

338,032 次观看 • 2 天前

🔥 Tesla has redesigned its website! The new look is available on both desktop and mobile, but only in the U.S. for now.
0:22

🔥 Tesla has redesigned its website! The new look is available on both desktop and mobile, but only in the U.S. for now.

Tesla Newswire

37,155 次观看 • 1 年前

Fable 5 and GPT-5.6 built the same scroll-animated website from 1 skill in 32 minutes and only 1 of them made it feel like a film. Same prompt: boutique Japan travel brand, origami style. A subway pulls in, a paper house unfolds into a hotel, a bird takes flight as you scroll. Doing this by hand is brutal multiple videos, matched starting frames, frames ripped out 1 by 1 and synced to scroll position. The skill does all of it: Generate 1 anchor image and approve it every scene inherits the style Turn it into video through the Higgs Field MCP (Seedance), straight from the terminal FFmpeg pulls every frame Each frame maps to scroll position, so your scrollbar becomes the playhead Setup is just connecting the MCP and loading the skill works in Claude Code and Codex. It interviews you first about scenes, budget and mobile, then shows the anchor image before burning a single credit on video. Budget reality: 6 scenes runs ~800 credits and is overkill, 4 scenes is the sweet spot, crop-safe mobile is the cheap path. The verdict came down to transitions. GPT-5.6 Soul built strong scenes with incredible detail inside each one then hard cuts between scene 1 and 2, and again between 2 and 3. Fable 5 stitched them together: wires push out of the top of frame while the next scene blurs in behind, gains depth and locks into place. Same skill, same prompts, 10 generations each. Credit to Peter Wang for the original Scroll World skill open source, now forked with budget tiers and mobile fixes. Soul built 4 scenes. Fable built 1 film.
9:48

Fable 5 and GPT-5.6 built the same scroll-animated website from 1 skill in 32 minutes and only 1 of them made it feel like a film. Same prompt: boutique Japan travel brand, origami style. A subway pulls in, a paper house unfolds into a hotel, a bird takes flight as you scroll. Doing this by hand is brutal multiple videos, matched starting frames, frames ripped out 1 by 1 and synced to scroll position. The skill does all of it: Generate 1 anchor image and approve it every scene inherits the style Turn it into video through the Higgs Field MCP (Seedance), straight from the terminal FFmpeg pulls every frame Each frame maps to scroll position, so your scrollbar becomes the playhead Setup is just connecting the MCP and loading the skill works in Claude Code and Codex. It interviews you first about scenes, budget and mobile, then shows the anchor image before burning a single credit on video. Budget reality: 6 scenes runs ~800 credits and is overkill, 4 scenes is the sweet spot, crop-safe mobile is the cheap path. The verdict came down to transitions. GPT-5.6 Soul built strong scenes with incredible detail inside each one then hard cuts between scene 1 and 2, and again between 2 and 3. Fable 5 stitched them together: wires push out of the top of frame while the next scene blurs in behind, gains depth and locks into place. Same skill, same prompts, 10 generations each. Credit to Peter Wang for the original Scroll World skill open source, now forked with budget tiers and mobile fixes. Soul built 4 scenes. Fable built 1 film.

Spike 1%

44,834 次观看 • 21 天前

ml-intern is fully on mobile now you can launch 8 A100s from your phone. while on the couch. while commuting. wherever I just did this while biking. same sessions as your desktop too — start a run on your laptop, check on it from your phone, it's all there the research lab is now just wherever you are
1:08

ml-intern is fully on mobile now you can launch 8 A100s from your phone. while on the couch. while commuting. wherever I just did this while biking. same sessions as your desktop too — start a run on your laptop, check on it from your phone, it's all there the research lab is now just wherever you are

Aksel

20,803 次观看 • 3 个月前

NEW: Google just launched a new laptop category for the AI era. Googlebook is coming this fall with Gemini built into the cursor, desktop, and Android phone connection. • Magic Pointer lets you select anything on screen and ask Gemini about it • Create My Widget builds custom desktop widgets from a prompt • Cast My Apps opens your Android phone apps on the laptop • Quick Access lets phone files show up like they live on your laptop • built with partners including Acer, Asus, Dell, HP, and Lenovo
0:57

NEW: Google just launched a new laptop category for the AI era. Googlebook is coming this fall with Gemini built into the cursor, desktop, and Android phone connection. • Magic Pointer lets you select anything on screen and ask Gemini about it • Create My Widget builds custom desktop widgets from a prompt • Cast My Apps opens your Android phone apps on the laptop • Quick Access lets phone files show up like they live on your laptop • built with partners including Acer, Asus, Dell, HP, and Lenovo

Ritwik Pavan

81,227 次观看 • 2 个月前

Is 8 months the lag time for the Richers to tell the truth? Scroll back on the highlight tab on my page. It all builds on itself and from the facts
2:00

Is 8 months the lag time for the Richers to tell the truth? Scroll back on the highlight tab on my page. It all builds on itself and from the facts

VincentScott

17,509 次观看 • 11 个月前

Mansour Bahrami is one of the most entertaining and beloved figures in the world of tennis, known not just for his skill but for his incredible showmanship and humor on the court.
0:26

Mansour Bahrami is one of the most entertaining and beloved figures in the world of tennis, known not just for his skill but for his incredible showmanship and humor on the court.

S.M.K

157,117 次观看 • 6 个月前

And you thought it was hard to scroll through all the photos on your phone... NASA’s Mars Reconnaissance Orbiter has snapped its 100,000th image of the surface with its HiRISE camera. More on this milestone image:
0:23

And you thought it was hard to scroll through all the photos on your phone... NASA’s Mars Reconnaissance Orbiter has snapped its 100,000th image of the surface with its HiRISE camera. More on this milestone image:

NASA Mars

641,392 次观看 • 7 个月前

A GITHUB REPO WILL BUILD YOU A SCROLLABLE 3D WORLD FOR ANY BRAND Imagine describing your brand, then getting a cinematic 3D webpage where every scroll pushes the camera deeper into the next environment with perfectly smooth transitions, similar to the immersive storytelling used on Apple's product pages. This repository works as an AI agent skill for Claude Code and Codex. Give it your brand details along with the scenes you want, and it automatically creates the images, animated zoom sequences, and transition clips that blend every section together into one continuous experience.
0:59

A GITHUB REPO WILL BUILD YOU A SCROLLABLE 3D WORLD FOR ANY BRAND Imagine describing your brand, then getting a cinematic 3D webpage where every scroll pushes the camera deeper into the next environment with perfectly smooth transitions, similar to the immersive storytelling used on Apple's product pages. This repository works as an AI agent skill for Claude Code and Codex. Give it your brand details along with the scenes you want, and it automatically creates the images, animated zoom sequences, and transition clips that blend every section together into one continuous experience.

Kshitij Mishra | AI & Tech

23,597 次观看 • 18 天前

How to convert ANY web app into a Mobile App... That can be shipped to the App Store from your phone. (Zero Coding Required) This works with web apps made on Replit, Bolt, v0, Replit or Cursor. Tech Stack: 1. Claude Desktop (works with ChatGPT) 2. - Builds the Mobile app, Ships to App Store directly from the phone (Uses Claude Code) (Prompt for conversion below) TIMESTAMPS Intro The Web App We Will Convert The Mobile App that Builds Mobile Apps Mobile App Version 1 You can Publish this to the App Store Adding Additional Features (AI APIs) to your app Editing the Mobile App with the Select Feature
12:40

How to convert ANY web app into a Mobile App... That can be shipped to the App Store from your phone. (Zero Coding Required) This works with web apps made on Replit, Bolt, v0, Replit or Cursor. Tech Stack: 1. Claude Desktop (works with ChatGPT) 2. - Builds the Mobile app, Ships to App Store directly from the phone (Uses Claude Code) (Prompt for conversion below) TIMESTAMPS Intro The Web App We Will Convert The Mobile App that Builds Mobile Apps Mobile App Version 1 You can Publish this to the App Store Adding Additional Features (AI APIs) to your app Editing the Mobile App with the Select Feature

Riley Brown

59,326 次观看 • 9 个月前

Good news: Mobile ticketing validators are now installed system wide! You now have the option to pay fare on all rail cars, buses, and both inclines with tickets purchased on your mobile phone.🎫📱🚍🚉
2:41

Good news: Mobile ticketing validators are now installed system wide! You now have the option to pay fare on all rail cars, buses, and both inclines with tickets purchased on your mobile phone.🎫📱🚍🚉

Pittsburgh Regional Transit

17,430 次观看 • 2 年前

Prediction markets are now native on Jupiter Mobile! Stop using your browser. Stop switching tabs or apps. Politics, sports, crypto, culture in your pocket. So when news breaks, you act quickly on it. The prediction wave is here and the easiest place to ride it? Is right here, on your phone. Just Use Jupiter (Mobile). 📲
0:35

Prediction markets are now native on Jupiter Mobile! Stop using your browser. Stop switching tabs or apps. Politics, sports, crypto, culture in your pocket. So when news breaks, you act quickly on it. The prediction wave is here and the easiest place to ride it? Is right here, on your phone. Just Use Jupiter (Mobile). 📲

Jupiter

77,551 次观看 • 1 个月前

ChatGPT Sites is now available to Plus, Pro, Business and Enterprise. On web, mobile, and desktop. I turned an idea into a personal to-do app with the Sites plugin in the new ChatGPT. Here’s how I built it.
0:24

ChatGPT Sites is now available to Plus, Pro, Business and Enterprise. On web, mobile, and desktop. I turned an idea into a personal to-do app with the Sites plugin in the new ChatGPT. Here’s how I built it.

pranav

81,984 次观看 • 24 天前

spent a few hours last night revamping my website, focused mainly on improving the comic reading experience there! and i FINALLY optimized things for mobile, so reading my stuff on your phone should be easier too check it out :) CSS stole my rations, and i swear the recording makes the site look choppier than it actually is, it's actually really smooth 😭
1:46

spent a few hours last night revamping my website, focused mainly on improving the comic reading experience there! and i FINALLY optimized things for mobile, so reading my stuff on your phone should be easier too check it out :) CSS stole my rations, and i swear the recording makes the site look choppier than it actually is, it's actually really smooth 😭

dakkii ☁️

27,885 次观看 • 6 个月前

Introducing iMessage video ads in Claude We taught Claude to make iMessage video ads in one shot with a single skill. These iMessage ads are absolutely killing it on Meta right now. The skill teaches Claude to make a full video ad in one shot with iPhone frame, SFX, music, and end card. And it's just HTML. It doesn't use any video generation models, so it's cheap! Comment Goose below and I'll send you the skill.
0:26

Introducing iMessage video ads in Claude We taught Claude to make iMessage video ads in one shot with a single skill. These iMessage ads are absolutely killing it on Meta right now. The skill teaches Claude to make a full video ad in one shot with iPhone frame, SFX, music, and end card. And it's just HTML. It doesn't use any video generation models, so it's cheap! Comment Goose below and I'll send you the skill.

Shiv

240,889 次观看 • 26 天前

The softest and most elastic female mask 😊 it does require some skill to put this on for a most realistic look #femalemask #伪娘 #CD #Femboy
1:23

Sensitive content

The softest and most elastic female mask 😊 it does require some skill to put this on for a most realistic look #femalemask #伪娘 #CD #Femboy

Weimi 伪秘花园

57,245 次观看 • 3 年前

ZELENSKYY: NOW OUR PARTNERS FULLY UNDERSTAND THE HIGH LEVEL OF SKILL OUR MILITARY HAS "It's also crucial now that everyone sees that even with all the air defense in the Middle East the Shaheds are getting through. They're getting through because there are so many of them. There are missiles, and Iranian drones and so on. These are basically the same Shaheds that fly toward us. We shoot down a large percentage. I think now our partners fully understand the high level of skill our specialists have, our military", - Zelenskyy on Mon, Mar 2nd
0:35

ZELENSKYY: NOW OUR PARTNERS FULLY UNDERSTAND THE HIGH LEVEL OF SKILL OUR MILITARY HAS "It's also crucial now that everyone sees that even with all the air defense in the Middle East the Shaheds are getting through. They're getting through because there are so many of them. There are missiles, and Iranian drones and so on. These are basically the same Shaheds that fly toward us. We shoot down a large percentage. I think now our partners fully understand the high level of skill our specialists have, our military", - Zelenskyy on Mon, Mar 2nd

Kateryna Lisunova

24,278 次观看 • 5 个月前

Fable 5 and GPT-5.6 built the same scroll-animated website from one skill in 32 minutes. Only one of them made it feel like a film. Same prompt. Boutique Japan travel brand, origami style. A subway pulls in, a paper house unfolds into a hotel, a bird takes flight as you scroll. Doing this by hand is brutal, so the skill handles everything automatically. Here is how it works: → One anchor image sets the visual style and every scene that follows inherits it automatically → Higgsfield generates the video straight from the terminal through the MCP connection, no manual exporting → FFmpeg rips every frame out of the generated video automatically → Each frame then gets mapped to a scroll position so your scrollbar literally becomes the playhead The verdict came down to transitions. GPT-5.6 built strong individual scenes with incredible detail inside each one, but then hard-cut between them with no connection. Fable 5 stitched everything together. Wires push out of the top of the frame while the next scene blurs in behind it, gains depth and locks into place seamlessly. Same skill, same prompts, 10 generations each from both models. GPT-5.6 built 4 scenes. Fable 5 built one continuous film. Credit: Chase AI
9:48

Fable 5 and GPT-5.6 built the same scroll-animated website from one skill in 32 minutes. Only one of them made it feel like a film. Same prompt. Boutique Japan travel brand, origami style. A subway pulls in, a paper house unfolds into a hotel, a bird takes flight as you scroll. Doing this by hand is brutal, so the skill handles everything automatically. Here is how it works: → One anchor image sets the visual style and every scene that follows inherits it automatically → Higgsfield generates the video straight from the terminal through the MCP connection, no manual exporting → FFmpeg rips every frame out of the generated video automatically → Each frame then gets mapped to a scroll position so your scrollbar literally becomes the playhead The verdict came down to transitions. GPT-5.6 built strong individual scenes with incredible detail inside each one, but then hard-cut between them with no connection. Fable 5 stitched everything together. Wires push out of the top of the frame while the next scene blurs in behind it, gains depth and locks into place seamlessly. Same skill, same prompts, 10 generations each from both models. GPT-5.6 built 4 scenes. Fable 5 built one continuous film. Credit: Chase AI

0xMarioNawfal

48,091 次观看 • 20 天前