Clipping is here 🎬
Grab your favorite moment from any video, add your take, and post it without leaving X.
Creators: every clip credits your original video and links back to it, so new viewers can find your work and keep watching.
Clippers: you now have an easy, native way to share moments from your favorite creators directly on X.
The best part? Both the original creator and the clipper can earn from views on the clip through Original Content Rewards.
Everyone wins when great moments travel. Clipping is one more step toward making X the best place to create, grow and earn.
40
助手跑了 @yiboAGI 说的透视错觉 skill,没自己搭场景,先用了仓库那条夜间路口模版。
完整 10 秒再叠运动模糊,没独显会很慢,所以先出了半分辨率、5 秒的预览。镜头绕到路口上方再回来时,招牌和天桥还钉在原来的位置上。
仓库:github.com/dotslashsimran/si…
MIT,不用付费接口。
Replying to @yiboAGI
开源项目是 simcraft 里的 perspective-illusion 这个 skill,用 three.js 加 Playwright 渲染:
github.com/dotslashsimran/si…
我给 Grok Bot 的提示词只有一句:
「你找一个涩谷十字路口的照片,用透视错觉视频做一个」
它自己找参考图、搭场景、出静帧,最后渲染成循环视频。画面里的品牌和招牌文字全是编的。
插画好看还不够,得经得住鼠标划过去。Hairline 给每张等轴图规定好指针会走的那几站,再用同一套十条规则验收,最后交出一份能直接打开的 HTML。
@vaadika_ui 用 @lucasmarkes__ 这个开源 skill,把一套免费模版里的插画全做完了。仓库约 3500★,MIT,可免费用;给一个想法它会先出几个概念再画,已有的 SVG 也能收成会跟手的图。
先锁指针要走的那几站,还是先按那十条规则把形状过一遍? nitter.cf/vaadika_ui/status/2119…
Hairline is the most useful Claude skill I've tried.
Used it for every illustration in my new free Framer template framer.link/yWJ7jLw
Thanks @lucasmarkes__
1
1
45
同一份源码换台机器、把画布放大再跑,画面和配乐还得对得上。这比再多一个「用代码出动画」的 skill 有用。
@alexgreensh 开源了 anidoodle(约 1550★,Apache-2.0),给 Agent 用代码画插画和短片。32 种画风是按那种媒介自己的工序走的:水彩先起铅笔稿再一层层上色,不是换套配色了事。配乐乛写成数据再合成。仓库里还有 gate,用来查确定性和空镜。
转述,我没跑过。你要是用,会先卡死「再跑一遍必须一样」,还是先把一种画风的工序跑通?
17
缺图标最烦的不是库不够大,是硬凑一枚,精细度和动效对不上。
@Kubai087 昨天发布了 Kubai Icons:2800 多枚动态图标,图标和 React/Vue/SVG 包是 MIT,可免费用。缺的那枚可以用附带的 skill 按同一套规则新画,还会在 24 和 28 像素上自检——画布、描边、光影、动效对不上就重来。
我觉得值钱的不是又多一套图标,是新画的也能跟原库并排放。动效也不是装饰,是这件东西自己会做的动作,比如文件夹打开、信封拆开。
转述,我没跑过这个 skill。官网能免费浏览;skill 是单独的源码可见协议,自检还要本机 Node 和 Chrome。
缺一枚的时候,你是先在库里凑个接近的,还是先按同一套规则新画,再跟现有的并排看一眼? nitter.cf/Kubai087/status/211960…
今天,发布我的动态图标库:Kubai Icons
2.8k + 图标,MIT,免费开源,体积极小
没有需要的怎么办?⬇️
图标库附带 Skills,可交由 AI 生成风格一致、精细度一致的 Icon。质量第一梯队。
支持贡献提交,署名感谢。欢迎体验🫶
17
AI 写单屏还行,一整个项目就容易每页长一张脸。
@hqmank 聊到 Meta 开源的设计系统 Astryx(meta/astryx,约 2 万★,MIT):人和 coding agent 共用同一套 CLI/文档去搜组件、模板和设计约定,而不是每回让模型自己发明一版 UI。
我觉得值钱的不是又多了一家组件库,是「人读的约定」和「agent 读的约定」终于是同一份。
你会先跑 cli init 把约定写进项目,还是先装几个组件试试看?
github.com/meta/astryx
1
2
30
好多黑胶效果,其实是给现成音频套一层沙沙声。@rauchg 这条反过来:先把歌刻成槽的几何形状,再用虚拟唱针去刮墙,每秒大约 38.4 万次。WebGL2 画槽,Web Audio 读唱针刮出来的振动。
我觉得值钱的不是「看起来像」,是爆音和沙沙声不是后期贴的滤镜——槽壁有灰、有划痕,唱针刮过去,声音自己就出来了。
做这种模拟,你会先锁「声音必须从槽里读出来」,还是先让盘子转起来好看?
nitter.cf/rauchg/status/21195363…
Built a physical simulation of a record player with WebGL2 and Web Audio. It's *shockingly* accurate: vinyl-gl.vercel.app.
Instead of playing a song, it works by converting it into the physical shape of a groove. Then a simulated stylus rides those walls 384,000 times a second, and you hear the voltage that motion would induce in a cartridge.
So the crackle, the pops, the wow/flutter, the dull inner grooves are natural byproducts of the simulation. You can also "DJ" the record.
(The converted songs are in the public domain or CC-licensed. Code is linked for you to remix and re-deploy.)
27
做拖拽最容易翻车的,不是动画曲线丑,是两段搞混了:手还按着时该 1:1 跟手(别加缓动),松手后才交给速度和弹簧。
@emilkowalski 把 Sonner、Vaul 里踩过的坑收成了 /gestures skill(开源 MIT;npx skills add emilkowalski/skills --skill gestures)。还强调:正在关的抽屉必须中途接得住——keyframes 接不住,弹簧才能。
你写手势时,先锁「按着跟手」,还是先锁「松手有惯性」?
1
25
丢一条视频进去,它不急着帮你「生成同款」,而是先拆:这镜是实拍、AI、3D,还是代码动画。
@zodchiii 介绍的开源工具 rea-video(JuneYaooo/rea-video,Apache-2.0)会逐镜给证据,再给你一份复刻方案——该拍的拍、该生成的生成,代码做的还能落到 Remotion。基础路径是 ffmpeg + Python,在 Claude Code / Codex 里装好就能跑;反推提示词那步才要接看图模型。
我觉得值钱的不是「能复刻爆款」,是先分清制作方式,少拿视频模型硬扛本该用代码做的画面。
你拆一条片子时,更想先知道哪几镜是代码做的,还是先拿到整份复刻清单?
仓库:github.com/JuneYaooo/rea-vid…
1
28
用代码复刻「Kurzgesagt 风」讲解动画——原团队一条片子可能上千小时,@treyscalez 说他拿 Claude 大约 20 分钟出了一版,还把完整提示词公开了。
我觉得值钱的不是「快」,是提示词把画布、WebGL 地球、禁用项(禁 AI 出图/出视频、禁原频道角色)和「每句旁白对应哪个镜头」都写死了。少了这些硬约束,很容易又变回太空渐变模板。
你做讲解动画,会先锁「禁什么」,还是先把旁白和镜头一对一钉上?
nitter.cf/treyscalez/status/2119…
HOLY SH*T
i tried recreating kurzgesagt style animation and it's mindblowing
the creator behind the channel spends 1200 hours with a full animation team
this takes 20min with just claude opus 5.5 and am giving the prompt completely for free
here's the prompt ->
<inputs>
Ask me for: one topic as a "what if" question (default: "What if the Sun vanished?"), the length (default 30 seconds), and whether I have an ElevenLabs key (if not, use a free local voice).
</inputs>
<direction>
A Kurzgesagt-style animated explainer at 1920x1080, 30fps, drawn entirely in code: one 2D canvas plus one WebGL canvas for planets.
Space: a vertical gradient #081d2c to #102348, five huge parallax nebula blobs (teal rgb 24,150,160 at 20%, blue 40,95,195 at 16%, coral 220,95,110 at 10%, indigo 60,70,175 at 15%), three star layers at parallax depths .12/.35/.6 that twinkle, 40% of the near stars drawn as 4-point sparkles.
The Sun: radius 300px, half off the left edge. A radial gradient #fff7dc to #ffc857 to #ff8f4a with an offset highlight, additive halo rings at 1.23/1.48/1.76/2.1x the radius, 18 faint rotating ray wedges, 28 drifting glowing granules on its surface.
Earth: an orthographic sphere in a fragment shader, 4x supersampled, from a 2048x1024 map painted from longitude/latitude polygons: land #5fc47a, forest #48ad6b, desert #f5c75f, rainforest #3a9d62, ice #f1f8ff, ocean gradient #4dc7eb to #1a66b8, white capsule clouds. Tilt .26 rad, spin .55 degrees per second. Day/night uses smoothstep(-.12, .24, N·L) with the light direction recomputed from Sun to Earth every frame. Navy night side with ~380 warm city lights, a coral band on the terminator, a cyan rim, ocean specular, an atmosphere halo that is stronger on the lit side.
A small astronaut mascot (~180px) built from rounded rectangles: suit #f3f7fb, orange #ff8f4a boots, a visor gradient #1f5a73 to #0a1c2c with glowing cyan eyes that look at whatever matters, a blinking antenna light, an idle bob, squash and stretch on every pose.
Type: Fredoka 600/700 only. Captions in caps with 3-6px letter spacing in teal #8fd8e6, gold #ffd98a or white, sitting in rounded pills of rgb(6,20,40) at 62%. Every line of text rises 1.3x its own height through a clip on an ease-out-quint.
Finish: a vignette to rgba(4,4,20,.45) and a 6% film grain re-randomized 24 times per second.
Banned: outlines, flares or loops on the Sun's edge, static infographic strips, full stops in on-screen text, text that fades in whole, AI images or AI video, Kurzgesagt's own characters, bird or music.
</direction>
<structure>
30 seconds, every line of narration gets a camera move or a transformation, nothing ever holds still.
Tight on the Sun at 2.25x (0s) → on the word "vanished" it swells 6% for 0.22s, collapses in 0.33s, then a white flash and a shockwave ring (1s) → pull back to 1x revealing Earth still lit and the astronaut staring at the empty spot (1.6-3s) → on "eight" an 8:20 countdown slams in from 1.7x to 1x and starts ticking, a "LAST LIGHT" label rides the edge of the growing dark disc (3.2s) → dive to 2.3x on Earth with light streaks flowing in (5.6s) → on "you" a YOU pin drops (7s) → on "left" a photon lands on the pin with "THIS LIGHT LEFT THE SUN / 8 MIN 20 SEC AGO" (7.5s) → on "play" the pin morphs into a play button, "YOU PRESSED PLAY / 15 SEC AGO" (8.8s) → one pull-back from 2.4x to a 0.3x orbit view, "LAST LIGHT" and "GRAVITY" riding the ring (9.6-12.5s) → on "nothing" a dotted circle at the empty centre (13.4s) → on "hits" the darkness sweeps Earth in 0.7s, city lights pop on, the countdown turns gold at 0:00 (15.8s) → on "black" the background fades almost to black (17.4s) → Jupiter appears, "STILL SHINING FOR 1 HOUR+" (17.9s) → zoom out, a dashed tangent line, "30 KM/S" as Earth flies straight off (20.8s) → a thermometer counts 15 to -70°C while frost grows from the poles (22.8s) → a 0.8s rewind on a separate story clock (24.3s) → sunglasses drop onto the astronaut (25.2s) → a photon tagged "8:20 OLD", then the title (27.7s).
For any other topic, keep the same shape: the event happens on its word, pull back to show scale, dive in to make it personal ("you"), pull back out, the consequence with a live counter, an escalation, a funny beat with the mascot, a callback and the title.
</structure>
<build>
1. One HTML file. Every frame is a pure function of time: window.seek(t) draws frame t. No timers, no CSS animation.
2. Camera moves on easeInOutCubic, zoom is interpolated in log space, every pop is a damped spring (damping .42-.5, frequency 12-16).
3. Voice: ElevenLabs eleven_v4 with a designed voice (calm, warm, curious male, late 30s, crisp, light neutral European English), stability .5, similarity .75, generated with timestamps. Without a key, use kokoro-onnx locally and get word times with faster-whisper. Every animation event fires on its word. About 165 words per minute, 0.24s between sentences, a 0.36s beat before the big reveal.
4. The darkness front: any pixel within the front's radius from the Sun turns to night with a 30px soft edge. The front moves at ~47px/s and ramps to 700px/s near Earth.
5. Keep two clocks: ambient time for twinkle, spin and bob, and a separate story clock for events, so a rewind stays consistent.
6. Render with Playwright in headless Edge with the GPU: seek every frame at 30fps and blend 2 subframes (shutter 0.6) for motion blur, then encode with libx264 at CRF 16 for the master and CRF 20 for delivery.
7. Sound: a calm royalty-free space music bed 7dB under the voice, timed so its natural ending lands on the title, swelling 5dB under the title. One downloaded royalty-free sound effect per event kind (collapse, impact, pull-back whoosh, countdown tick, dive, pin tap, photon land, play click, light hit, reveal, frost, rewind), each peak-aligned to its frame and 4-10dB under the voice. Master with gain plus a limiter to -14 LUFS, -2.2dB true peak.
</build>
<gotchas>
Make the WebGL globe canvas at least 2 x radius x zoom x 1.18 pixels or the sphere clips flat in close-ups. Never draw prominences on the Sun's edge, they read as white hooks. Never pad the voice to fit the visuals, tighten the read instead. Speed the darkness front up near Earth or it takes 13 seconds to cross the planet. Show me a contact sheet of every beat before rendering.
</gotchas>
<start>
Ask me the inputs, write the narration with the beat each word triggers, show it to me, then build and render the video.
</start>
1
1
46
把 21 万行创意编程框架从 OCaml 迁到 Rust,不是因为 Rust 写着更爽,是几何一密、一并行,垃圾回收就开始卡。
@olegpustovit 上周末用 Claude Code 做完这件事。他给 AI 定了几条硬约束:调试编译别开优化,测试超过 5 秒就掐掉,迁代码的同时把构建和测试也加快。视频里的几何,是 GPU 上从 256³ 体素网格生成的。
迁大家伙时如果也让 AI 上手,你会先定哪条:编译要快、测试不能卡住,还是内存不能抖? nitter.cf/olegpustovit/status/21…
Last weekend I ported my OCaml-based creative coding framework (210k LoC) to Rust with Claude Code.
I started with OCaml because it's a clean, type-safe language with very fast incremental compilation. It was a very productive language to work in: with AI agents I built a full custom renderer, from Metal bindings to a custom UI framework, and it was fast and flexible.
As I started prototyping sketches with denser procedural geometry, I ran into garbage collection issues. On large amounts of data processed in parallel, the renderer started hitting GC pauses. At first I looked for ways to optimize this while staying on OCaml, but in the end I decided to switch to Rust.
I never liked Rust as a language: compile times are slow, it's complicated, and you don't get the same kind of productivity you get with higher-level languages. What it does give you is memory-safety guarantees, and a way to cut allocations with arenas and similar techniques.
To translate 210k lines to Rust, I set a few constraints for the AI:
- Keep debug builds with optimizations off, so compiles stay fast
- Wrap tests in a custom executable with a 5-second timeout, so hung test runs don't stall the loop
- Have the agent proactively speed up builds and tests alongside the port itself
I'm also finishing the Windows/Vulkan port.
In the video, the geometry is generated entirely on the GPU from a 256³ voxel grid and rendered as a polygonal mesh.
2
4
109










