Motion Skills

Claude Motion プロンプト

実際に使える Claude Motion・モーショングラフィックス用プロンプト集(プレビュー付き)

Claude でアニメーション動画を作る方法は、Claude Motion、Opus 5.5 への直接プロンプト、エージェントに入れたスキルの 3 つです。各プロンプトには実行場所と作者を明記しています。貼り付ける前に、[角かっこ] の部分を自分の言葉と数字に置き換えてください。

Claude が書いた HTML を MP4 に変換 →

プロンプトごとの実行場所

Claude Motion のプロンプトの書き方

Anthropic のアドバイスはシンプルです。誰が見るか、どこで流すか、おおよその長さを伝え、Claude に使ってほしいレポート、データ、画像を添付すること。このページのスタイルプロンプトはすべてこれに沿っており、さらに 2 つの工夫を加えています。シーンを順番に並べて最後の画面を書くこと、そして Claude に自分の内容だけを使わせる一文を入れることです。

5 つの要素

  1. 01

    何を、何から作るか

    “この四半期レポートを解説動画にしてください”

  2. 02

    誰が、どこで見るか

    “投資家向けに、月次アップデートで”

  3. 03

    長さと画面比率

    “30 秒、画面用なら 16:9、スマホ用なら 9:16”

  4. 04

    自分の内容だけ

    “添付したレポートだけを使ってください。数字や名前は一切変えないでください。”

  5. 05

    シーンを順番に、最後に終わりの画面

    “1. 見出しの数字がカウントアップする。2. 3 本の棒が伸びる。覚えてほしい 1 つの数字で終わる。”

Claude Motion は動画生成モデルを使わないため、実写のような映像や人物は作れません。テキスト、グラフ、図形、画像を動かすよう頼んでください。

プロンプトのテンプレート
[添付するもの、例:自社の Q3 レポート]を、[見る人、例:投資家]向けに[流す場所、例:月次アップデート]で使う[長さ、例:30 秒]の[16:9 または 9:16]の解説アニメーションにしてください。添付した[レポート、データ、画像]だけを使い、数字や名前は一切変えないでください。シーンの順番:1. [何が出て、何が動くか]。2. [...]。3. [...]。最後は[終わりの画面、例:覚えてほしい 1 つの数字]で終えてください。

まず絵コンテを頼む

数シーンを超えるものは、アニメーションの前に計画を頼みましょう。完成したアニメーションより、1 行のテキストのほうが早く直せます。これは私たちの習慣で、Anthropic のガイドにある手順ではありません。

絵コンテを先に頼むプロンプト
アニメーションを作る前に、[動画、例:投資家向けに Q3 レポートを解説する 30 秒の動画]の絵コンテを書いてください。シーンごとに、画面に映るものを 1 行、動くものを 1 行、そして何秒続くかを書き、最後に終わりの画面を書いてください。私の OK を待ってから作ってください。

アニメーションを編集するためのプロンプト

アニメーションはコードでできているので、単語、数字、タイミングなど 1 か所だけを変えても、ほかはそのまま残ります。チャットで頼むことも、エディターで自分で調整することもできます。変更は 1 メッセージに 1 つがいちばんうまくいきます。変えない部分も伝えると、ほかの部分まで変わってしまうのを防げます。

Anthropic のガイドより

  • “2 番目のシーンをゆっくりにしてください。”
  • “Q3 の数字を 18% に変えてください。”

私たちがよく使うもの

  • “最後の画面をあと 2 秒表示したままにしてください。”
  • “シーン 1 のタイトルを「[新しいタイトル]」に置き換えてください。ほかはすべてそのままにしてください。”
  • “棒の色を[色]にしてください。順番と値は変えないでください。”
  • “シーン 3 を削除して、動画を [n] 秒短くしてください。”

Anthropic のヘルプ記事「Get started with Claude Motion」からのヒントです(2026 年 10 月 29 日に確認)。 ↗

Claude Motion 用プロンプト

Team と Enterprise プラン向けです。まずユーザーが共有した Claude Motion の作例、続いて私たちが書いたスタイルプロンプトを掲載しています。スタイルプロンプトは、誰が見るか、どこで流すか、長さはどれくらいかを明記し、自分の内容だけを使うよう Claude に指示します。Opus 5.5 に直接渡しても使えます。プレビューは対応するスキルで書き出したもので、Claude Motion では実行していないため、Claude Motion での結果は見た目が異なります。

Claude Motion で作られた作品(X より)

Team と Enterprise のユーザーが、Claude Motion で作ったと自ら書いている実際の作品です。多くはプロンプトが公開されていないため、それぞれ元の投稿と、似たものを作れるプロンプトへのリンクを付けています。

スタイルプロンプト(私たちが作成)

チャットから成果へ・ローンチ

スキルを開く →有料
スタイルプロンプト(Claude Motion または Opus 5.5)
Make a 20-second 16:9 launch video for [who will watch, e.g. busy managers], playing [where, e.g. our homepage and LinkedIn]. Use only the product name, chat lines and features below; don't change a word. Off-white background.

Scene 1: a clean white chat window appears and the user's request types into the input, then is sent. A small orange avatar shows typing dots, then replies. Scene 2: the reply expands into a full orange frame with the product name and the headline rising word by word. Scene 3: three white feature cards follow. End frame: the product name with an orange call-to-action button and the URL, held for 2 seconds.

Product: [e.g. Orbit]
Request and reply: [e.g. "Plan my week around three deep-work blocks." → "Done. Meetings moved, focus time locked in."]
Headline: [e.g. "Your calendar, on autopilot."]
Three features: [e.g. Smart slots, Focus guard, Daily recap]
Call to action and URL: [e.g. "Try Orbit free", orbit.app]

ブループリント・ローンチ

スキルを開く →有料
スタイルプロンプト(Claude Motion または Opus 5.5)
Make a 20-second 16:9 launch video for [who will watch, e.g. engineers and product teams], playing [where, e.g. Product Hunt and X]. Use only the name, lines and screenshot I give; don't change a word. Deep blueprint-blue background with a fine white grid.

Scene 1: a wireframe of an app window draws itself in thin white lines (header, sidebar, three cards, a chart) with dashed dimension lines labeled in millimeters and a drawing title block in the corner with the project name. Scene 2: the product name scrambles in, monospace, with the tagline in yellow. Scene 3: three yellow rings circle details labeled DETAIL A, B, C with feature names. Scene 4: the wireframe fills in with the screenshot from left to right and a yellow "APPROVED" stamp slams on. End frame: the name, a yellow status tag and the URL.

Product and tagline: [e.g. Orbit, "Engineered for focus."]
Three features: [names]
Status tag and URL: [e.g. "Now in public beta", orbit.app]
Attach: [a screenshot of your product]

製品ローンチ映像

スキルを開く →
スタイルプロンプト(Claude Motion または Opus 5.5)
Make an 18-second 16:9 product launch film for [who will watch, e.g. product managers], playing [where, e.g. our homepage hero and X]. Use only the name, lines and screenshot I give below; don't change a word. Near-black background with a warm orange glow.

Scene 1 (0–3.4s): a two-line hook rises from masks, line one off-white, line two orange, slowly pushing in. An orange wipe cuts to Scene 2: the product name and tagline on the left while a browser window with the screenshot rises from below with a 3D tilt and settles. Scene 3: three features one at a time, each with a huge orange numeral (01, 02, 03), a bold title and a gray description, with a segmented progress bar at the bottom. End frame: the logo mark spins in, then the name, an orange call-to-action pill and the URL.

Hook: [two lines] (e.g. "Your roadmap" / "finally in motion")
Product and tagline: [e.g. Northwind, one line]
Features: [three titles with one-line descriptions]
Call to action and URL: [e.g. "Start free", northwind.dev]
Attach: [a screenshot of your product]

デバイスキャンバス・ローンチ

スキルを開く →有料
スタイルプロンプト(Claude Motion または Opus 5.5)
Make a 20-second 16:9 launch video for [who will watch, e.g. ops and finance leads], playing [where, e.g. the homepage hero]. Use only the lines and screenshots I give; don't change a word. Deep navy background with soft violet and teal glows.

Scene 1: the hook rises word by word and fades. Scene 2: a browser window with the desktop screenshot and a phone with the mobile screenshot rise onto the canvas. Scene 3: the camera glides in to the browser while a glass caption shows the first feature, then to the phone with the second, then pulls back to show both with the third. End frame: the devices blur and sink as the product name, the hook and a violet call-to-action button appear.

Hook: [e.g. "Your metrics, everywhere you work."]
Three captions: [e.g. "Live dashboards — Every number, updated in real time", "Pocket alerts", "Always in sync"]
Product and call to action: [e.g. Pulse, "Get Pulse free"]
Attach: [a desktop screenshot and a phone screenshot]

ロゴスティング

スキルを開く →有料
スタイルプロンプト(Claude Motion または Opus 5.5)
Make a 5-second 16:9 logo sting for [who will watch, e.g. viewers of our videos], playing [where, e.g. at the end of every video]. Use only the logo, name and tagline I give below. Near-black background.

The logo mark punches in at the center with a slight rotation, an accent ring expands and fades, and twelve short rays burst outward. The mark then slides left while the wordmark in a bold geometric sans slides out from behind it. End frame: the tagline fades in below in gray and a soft light sweep passes across the lockup.

Attach: [your logo]
Name and tagline: [e.g. Northwind, "Build what's next."]
Accent color: [e.g. orange]

ステートメント・バースト

スキルを開く →
スタイルプロンプト(Claude Motion または Opus 5.5)
Make a 6-second 16:9 kinetic statement for [who will watch, e.g. followers on LinkedIn], playing muted in the feed. Use only the sentence below; don't change a word. Near-black background, bold geometric sans, centered.

The words punch in one at a time from a slight blur and larger scale. When the last word lands, the key word flips to orange and short orange rays burst outward around the whole statement and retract. End frame: the text slowly scales up by a few percent and holds.

Statement: [your line] (e.g. "Every second of attention counts.")
Key word: [e.g. "attention"]

キネティックタイポ・タイトル

スキルを開く →有料
スタイルプロンプト(Claude Motion または Opus 5.5)
Make an 8-second 16:9 title card for [who will watch, e.g. viewers of our YouTube series], playing [where, e.g. the opening of each episode]. Use only the words below; don't change them. Near-black background.

A short orange rule draws in from the left, then a small uppercase label fades in with wide letter spacing tightening. Below it, a two-line headline rises line by line from behind invisible masks with a fast expo ease: line one in an off-white editorial serif, line two in orange italic, which then gets an orange underline wiping in from left to right. A soft gray supporting line fades up word by word. End frame: the finished title, held with a slow upward drift and a faint warm glow moving behind the text.

Label: [e.g. "INTRODUCING"]
Headline: [two lines] (e.g. "Motion that" / "moves people")
Supporting line: [one short sentence]

引用カード

スキルを開く →
スタイルプロンプト(Claude Motion または Opus 5.5)
Make an 8-second 16:9 testimonial clip for [who will watch, e.g. founders comparing tools], playing [where, e.g. our pricing page or a LinkedIn post]. Use only the quote, name and title I give below; don't change a word. Warm sand-colored background.

Scene 1: large rust-colored serif quotation marks drop in at the top left. Scene 2: the quote appears word by word in a dark editorial serif, each word rising slightly out of a blur, then a translucent rust highlighter sweeps under the key word. End frame: an avatar circle with the initials, and the name and title slide in below, held for 2 seconds.

Quote: [your customer's quote] (e.g. "We shipped our launch video in an afternoon. It looked like it came from a studio.")
Key word: [e.g. "studio"]
Name and title: [name, role, company] (e.g. Priya Nair, Founder, Lumen Labs)

トーク動画

スキルを開く →有料
スタイルプロンプト(Claude Motion または Opus 5.5)
Edit my talking-head recording [file] into a [length] video: cut it clean (show me the cut plan first), proofread the captions against the recording, put my name and the question in the first seconds, cards on my own words that never cover my face, then export a 剪映 draft for [who will watch, e.g. people who follow our channel]. Use only my own recording and the words I say in it; don't change a word or number. End on the last line I say, with the caption held for 2 seconds.

折れ線トレンド

スキルを開く →
スタイルプロンプト(Claude Motion または Opus 5.5)
Make a 7-second 16:9 line chart for [who will watch, e.g. the board], playing [where, e.g. the quarterly review]. Use only the numbers I attach or list below; don't round or smooth them. Near-black background.

The title sits top left and a large white number top right. An orange line draws from left to right across the period over a fading orange gradient fill, while a white dot with an orange halo rides the tip and the big number counts along with it. At the marked point, a white ring appears on the line with a thin stem and a white label. End frame: the big number turns orange, held for 1.5 seconds.

Title: [e.g. "Weekly active users"]
Data: [your periods and values] (e.g. Jan to Jul, 1,200 to 5,200)
Marked point and label: [e.g. April, "Video launch"]

対決スプリット

スキルを開く →
スタイルプロンプト(Claude Motion または Opus 5.5)
Make a 7-second 16:9 comparison for [who will watch, e.g. prospects deciding between us and an agency], playing [where, e.g. the sales deck]. Use only the two titles and six points below; don't reword them. Near-black background.

The frame splits into two dark panels that slide in from the left and right. A white circular "VS" badge spins into the center. The left panel lists its three points with dashes; the right panel lists its three with orange plus signs. End frame: the right panel floods orange with black text and scales up slightly while the left panel dims.

Left title and points: [e.g. "Old way": "Brief an agency", "Wait two weeks", "One format"]
Right title and points: [e.g. "New way": "Describe it in a prompt", "Render in minutes", "Every format"]

KPI カウンター

スキルを開く →
スタイルプロンプト(Claude Motion または Opus 5.5)
Make a 7-second 16:9 stat animation for [who will watch, e.g. customers reading our year in review], playing [where, e.g. the newsletter and LinkedIn]. Use only the numbers below; don't round or change them. Near-black background.

A small uppercase gray title tightens its letter spacing as it fades in. Three columns appear one after another: each has a thin orange bar that sweeps across, then a huge off-white number counts up from zero, with a gray label beneath. End frame: hold on the final numbers.

Title: [e.g. "2026 IN NUMBERS"]
Three numbers and labels: [e.g. "98.9%" Uptime, "3.2x" Faster deploys, "$1.4M" Saved per year]

ボードルーム・メモ

スキルを開く →
スタイルプロンプト(Claude Motion または Opus 5.5)
Turn the document I attach into a 60-second 16:9 narrated explainer for [who will watch, e.g. the leadership team], playing [where, e.g. the quarterly business review]. Use only the facts and numbers in the document. Boardroom memo style.

One idea per slide, with points appearing one at a time as they're spoken. Animate one chart for the main number. End on a closing slide with one clear next step.

Topic: [your topic] (e.g. our quarter)
Attach: [your document, notes or data]

サイクルループ

スキルを開く →
スタイルプロンプト(Claude Motion または Opus 5.5)
Make an 8-second 16:9 loop diagram for [who will watch, e.g. the marketing team], playing [where, e.g. the planning deck]. Use only the title and four steps below. Off-white background.

The title appears. Four white rounded cards with small orange numbers pop in around a faint dotted circle: top, right, bottom, left. Curved orange arrows draw clockwise from each card to the next. A short line fades in at the center in gray. End frame: a glowing orange dot travels around the circle continuously, briefly outlining each card in orange as it passes.

Title: [e.g. "The content flywheel"]
Four steps: [e.g. Publish, Measure, Learn, Improve]
Center line: [e.g. "Every week"]

チェックリスト

スキルを開く →有料
スタイルプロンプト(Claude Motion または Opus 5.5)
Make a 7-second 16:9 checklist for [who will watch, e.g. our content team], playing [where, e.g. the training page]. Use only the title and four items below; don't reword them. Warm off-white background.

The title fades up, then four white rounded cards slide in from the left, each with an empty checkbox and a label. One by one each checkbox fills rust orange with a little bounce, a white tick draws in, and its label dims. End frame: a small orange pill pops in below, held for 1.5 seconds.

Title: [e.g. "Before you hit publish"]
Four items: [e.g. "Hook in the first second", "Captions on", "Logo at the end", "Exported in 9:16 too"]
Pill: [e.g. "Ready to ship"]

ペーパー・レクチャー

スキルを開く →
スタイルプロンプト(Claude Motion または Opus 5.5)
Turn the document I attach into a 60-second 16:9 narrated explainer for [who will watch, e.g. students], playing [where, e.g. the course page]. Use only the facts and numbers in the document. Paper lecture style.

One idea per slide, with points appearing one at a time as they're spoken. Animate one chart for the main number. End on a closing slide with one clear next step.

Topic: [your topic] (e.g. sleep and memory)
Attach: [your document, notes or data]

Opus 5.5 用プロンプト(X より)

スキルを使わず、Claude Opus 5.5 にプロンプトを 1 つ渡すだけです。Opus がアニメーションを一からコードで書きます。Claude Code、Cursor、Claude アプリのどれでも使えます。X の投稿から選び、プロンプトは原文のまま、元の投稿へのリンク付きで掲載しています。同じプロンプトでも結果は毎回変わります。題材は各作者のものです。

自分の素材から映像を作り、お使いのパソコンで書き出したい場合は、完全版スキルが一から作ります: Claude Code・Codex 用プロンプト ↓

UI の状態へと変形していく図形

@twoclipping
プロンプト
<inputs>
Ask me for: 8 to 12 UI states I want the shape to become (e.g. button, loader, player, slider, toggle, tabs, chart, command palette, toast), pure black and white or one accent color, and a royalty-free song around 120 BPM (e.g. Mixkit, free for commercial use).
</inputs>

<direction>
Dribbble-level UI motion. One shape, never cut: every state is the same element morphing its size, radius and color while its content swaps with a short blur. A cursor drives every change with real clicks and drags. Light warm-gray canvas, black and white components, one clean UI font (Geist). Springs everywhere, a tiny overshoot at most. The camera zooms so each state fills the frame. The last frame is the first frame, so it loops.
Banned: bouncy easing, particle bursts, glows, gradients on UI chrome, mismatched icon strokes, dead time, anything that looks like a template.
</direction>

<structure>
120 BPM, 7 bars, something happens on every beat.
Button → loader → check → dynamic island → music player with a play/pause morph → scrub the progress bar → it becomes a volume slider that stretches when dragged past max → a toggle flips on the beat → the knob becomes a liquid tab indicator → the tabs open into a chart that draws itself, with a tooltip on hover → it collapses into ⌘K → type to filter → enter → toast → back to the button.
</structure>

<build>
1. One HTML file, square 1440x1440. Every style is computed from time inside seek(t): no CSS transitions, no timers, no state carried between frames.
2. Springs are closed-form step responses. A value that changes target many times is the sum of one spring per change, so it stays a pure function of time.
3. The tab indicator's two edges ride different springs, so the leading edge stretches ahead of the trailing one. Same trick for the toggle knob.
4. Drags are direct manipulation: while the cursor is held, the value is computed from its position. On release it springs back from wherever it was.
5. Analyze the song with numpy for the beat grid and start on a downbeat. Place every UI sound by its measured peak.
6. Render with Playwright: 4 subframes per frame, blended with ffmpeg tmix for motion blur at 60fps.
7. Render one frame per beat before the full render. Fix anything off the grid, cramped or hard to read.
</build>

<gotchas>
Never put will-change on anything the camera scales or the text renders blurry. Text that swaps inside a morphing container needs its own enter and exit timing or it overlaps. Make the last frame identical to the first, cursor position and speed included, or the loop stutters.
</gotchas>

<start>
Ask me for the inputs, then show me the state list on the beat grid before you write any code.
</start>

呪文を唱えるピクセルアートの魔法使い

@majidmanzarpour
プロンプト
Create a single self-contained HTML file that renders an animated pixel art wizard casting a spell, using vanilla JavaScript and Canvas 2D. No external assets, libraries, or network requests.

RENDERING
- Draw everything to an offscreen canvas at a fixed logical resolution of 128x96, then blit to a fullscreen display canvas scaled by the largest integer factor that fits the window, centered, with imageSmoothingEnabled = false and CSS image-rendering: pixelated.
- All drawing snaps to integer coordinates on the logical canvas. No sub-pixel positions, anti-aliasing, gradients, or shadowBlur.
- Fixed palette of ~24 hex colors: deep blues/purples for night sky, warm robe tones, 3-4 bright magic colors. Every pixel comes from this palette.

CHARACTER
- Build the wizard procedurally from filled rects and pixel runs, ~24x32 logical pixels: pointed hat with a bend, long beard, two-shade robe with darker outline, staff with a gem at the tip.
- Parameterize the pose (staff angle, arm raise, head tilt, robe sway). Animate parameters smoothly, then quantize to the pixel grid each frame so motion reads at an 8-12 fps pixel animation feel even though the loop runs at 60fps.

ANIMATION
- Looping state machine: IDLE (2-frame bob, beard sway) -> CHARGE (staff raises, gem flickers, sparks spiral inward) -> CAST (bright burst, projectile fires across the scene, 1-2 pixel screen shake) -> RECOVER (settle back). Ease pose parameters between keyframes.
- Pooled allocation-free particle system: preallocate and reuse. Sparks orbit the gem during CHARGE, explode outward on CAST, each particle stepping its palette index from white to magic color to dark before despawn. Snap particle positions to the grid when drawing.
- Fixed 60hz timestep update with rAF rendering. Zero object allocation inside the loop.

SCENE
- Minimal background: dark sky, a few twinkling 1px stars, moon, stone floor line. Character silhouette must read clearly.
- Subtle 1px rim light on the wizard from the gem, brightening during CHARGE and CAST.

QUALITY BAR
- Crisp pixels at any window size, seamless loop, stable 60fps, readable silhouette. Should look like a polished 16-bit sprite animation, not vector shapes scaled down.

製品ページから 15 秒のショーリール

@ann_nnng
プロンプト
Make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are. The content should focus on [your product]. You should visit the pages first to learn about the product, then write the video content yourself.

Opus が自分で調べて作った SaaS ローンチ動画

@moritzkremb
プロンプト
I want you to create a highly professional SaaS product launch video. Go and find some SaaS, preferably just one that people know, so it's easier to identify with it. Pick that, and then make sure to get actual assets and images and all of that stuff from the internet. Turn it into these typical, very professionally edited, motion-graphics-styled product launch videos that you see people making on Twitter when they launch new SaaS products (which are showing off the features, the benefits, and all of these things).

カクテルのレシピ、空のグラスから完成まで

@Ror_Fly
プロンプト
We're going to try a little test. Do you think you could render a recipe motion graphic animation using javascript or html (w/e you think will produce the best) to show the full recipe from start to finish (empty glass to completed cocktail) - Explainer video style - Showing the recipe ingreidents + measurements as they're going into the cup. Should be a 30s video.

毎回スタイルが変わる「再帰」の解説

@emollick
プロンプト
A video explaining recursion, where every explanation about recursion has a radically different video style, make this self-referential & clever & fast moving.

アプリ刷新を予告する豚のラブストーリー

@jackfriks
プロンプト
can you help me use the pig assets on new branch of lovelee to make a 9:16 short story animation with sound effects about the pig sending his partner love notes in the mailbox and make it fun and good tease app at end?

Web サイトをモーションのショーリールに

@melvynx
プロンプト
make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are for <website url>

カメラアプリの考え方を 1 本のアニメで

@Mileson07
プロンプト
帮我制作一个动画,主题描绘芝士相机的理念和使用场景,需要打动我们的目标用户(男朋友给女朋友拍照,拍出更好看的照片);包括音效和音乐;你可以使用任何你觉得合适的工具和技术,做出最好最惊艳的效果,不要使用已有的skill,不要参考以前做过的视频或者文案

フィンテック企業の縦型プロモ

@davidmarcus
プロンプト
make a punchy and modern short video for social that promotes @lightspark capabilities. Needs to be production grade with sound

動画モデルなしのスタートアップ紹介動画

@lepadev
プロンプト
make a modern slick and punchy video for a modern startup that works on inference

no video gen model, no additional libraries.

列車の窓の外を過ぎる四季

@itsolelehmann · Claude Code
プロンプト
4 seasons passing outside a train window, a cozy carriage, a cup of coffee on the table, Grand Budapest Hotel style

12 秒:プロンプトが動画になるまで

@notdwd
プロンプト
Make a 12s motion video in code (1920x1080, 30fps, one HTML file drawing every frame from a single seek(t) function, rendered with Playwright + ffmpeg, with original synthesized sound).

Story: a dark prompt pill on an off-white page types "make a launch video" with a real keystroke rhythm → enter, the button flashes orange and the pill slides up → a 12-frame filmstrip stamps in left to right, one frame per beat at 120 BPM; each frame shows one pose of an orange ball's bounce (squash on contact, stretch mid-air, real arcs) → a playhead sweeps the strip while a big viewer above plays the poses as a flipbook, twice, faster the second time → the strip slides away, "every frame is code." fills the screen, and the ball arcs over and lands as the period.

Rules: arrive fast, land soft (cover 12–19% of the remaining distance per frame); nothing ever freezes (slow push on every hold); stagger 2–4 frames; blur only on fast moves; big and readable on a phone; off-white, ink and one orange only. Sound: a tick per key, a click on enter, a rising note per frame stamp, a thump when the ball lands.

Show me 5 stills first (typing, strip half-built, flipbook, headline, last frame), critique them like a harsh motion director, fix the 3 worst problems, then render.

その製品が選ばれる理由をアニメで

@0xnfrith
プロンプト
make me an animation to explain why celld earns its place.

Claude Code の投稿に添えるアニメーション

@daniel_mac8
プロンプト
I want to try something different here. You should act as a  world-class animator and create an animation to go along with an  X post that talks about how Ultra Code and Claude Code are now  much more relevant due to the efficiency of Opus 5.5. You can use it without annihilating your usage limits 

the style of the video here
/Users/danielmcateer/Downloads/jvnZ3SyyxxajVatp.mp4

What I had in mind was start with Claude Code in the terminal from the first attached video, with me navigating to the 'ultracode' reasoning effort, then exploding into a scene where the Claude icon characters similar to what's in the second video are shooting an action video and it's representing using Claude Code dynamic workflows editing a video.

浮島を昼から夜まで描く 1 分の 3D 映像

@0xbobaaa
プロンプト
Make a one-minute video about Skyhold's floating island (image attached). Recreate the island from the image and animate it yourself. Build everything from scratch: no skills, no Remotion, no templates. Render 3D objects: the island, houses, roads, balloons, clouds, whatever fits, and make it as good as you can. I don't want any text, just animation, and I mean a real video, not just motion graphics. Think of crazy ideas I would never come up with, and make every scene look phenomenal: clean and detailed. I want people to watch it and think "yo, this is crazy, how did AI make this?" Invent your own stuff. Don't create slop, I want to see art and creativity.

90 秒のリキッドクローム・ショーリール

@kloss_xyz
プロンプト
Create a stunning state of the art beautifully premium 1.5 minute motion graphics video that shows the world what a truly remarkable and incredible motion designer, animator, artist, sound engineer, video editor, and creative director you are, like it’s a video you’re sending it to land the job of your dreams but without those labels in the video. It should be this style: Y3K liquid chrome and mercury surfaces, iridescent oil-slick reflections on deep black, inflated 3D blob typography, wireframe holographic UI overlays, ultra-thin monospaced HUD metadata, caustic light refractions, high-gloss product-render lighting, extreme negative space, graded for HDR with luminous specular highlights that exceed paper white, deep clean blacks, rich but controlled saturation, glowing light sources and reflections, and cinematic color separation. Go all out creatively and blow me and the audience away with something that will go viral on X/Twitter. No cheaply generated synth sounds, only organic premium natural sounding effects: poured water and mercury drips, glass resonance, struck metal bowls, slow breath, and cloth movement. Make me feel it emotionally because it’s so mesmerizingly stunning and beautiful and premium. Final export it as 1080p 10-bit HDR HEVC mp4 in Rec.2020.

節目のローンチ動画:月間 100 万訪問

@viktoroddy
プロンプト
Create a launch video for MotionSites AI, just hit 1 million monthly visitors after 8 months after launch.

実写の人物を使い、コードで編集したローンチ予告

@twoclipping
プロンプト
<inputs>
Ask me for: my product's name (one lowercase word), a 4-word tagline, the 3-step story of what it does, a launch date and domain, a royalty-free song with a clear drop, 4 vertical talking-to-camera clips and 12 portrait photos. If I skip any, use the defaults: "castr", "ugc ads, cast by ai", write a brief → scan 1,000 creators → cast 4, Mixkit "Cat Walk" (129.6 BPM, drop at 29.7s), free Pexels clips and portraits, and transparent stickers from Pixabay (serum, mic, megaphone, vintage camera, spotlight, lips).
</inputs>

<direction>
A 25 second square launch trailer, 1440x1440 at 60fps, loud poster style. Cobalt #2B3BFF, ink #0E0F1F, cream #F6E4C6, pink #FF7DC7, tangerine #FF5A1F. Archivo 900 extra-condensed for names, expanded for headlines, Geist and Geist Mono for labels. Op-art sunburst, scrolling waves, film grain. Real media only: the clips play inside the design, and the stickers get a white die-cut border and a soft shadow.
Motion rules: the camera never stops (a slow 1.03-1.07 push on every scene), nothing pops in (letters rise through a mask line one by one), nothing snaps to the beat (patterns rotate continuously), swaps are carousel glides of about 0.55s, colour changes fade over about 0.35s, stickers ease in and then keep a slow sway. No full stops after the wordmark or any headline.
Banned: beat-snapped rotations, pop-in slams, white flashes, crossfades between scenes, hard cuts, templates.
</direction>

<structure>
54 beats. The song starts 8 beats before its drop.
Beats 0-8: a cobalt sunburst turns around a breathing cream disc. The wordmark types in with a gliding caret and the tagline pill rises. The disc floods the frame into the drop.
Beat 8, the drop: the cream becomes the face of a 3D box and "ONE BRIEF" rises letter by letter. The camera pulls back to the box floating on waves. On beat 12 it turns to "1,000 CREATORS" (stacked, with outlined echoes), on beat 14 to "ZERO DMs".
Beats 16-22: a whip to a dark desk. A tangerine "BRIEF #042" ticket types its rows (product, vibe, cast, due), stickers drift on, a polaroid of a real clip drops onto the corner, and a "NOW CASTING" stamp presses down on beat 20.
Beats 22-34: the casting stage. A crowd of black and white portraits in an arc, a 3D stage block, and the creators gliding through like a carousel. Each plays live in a big disc in black and white, with their name in pink on the stage, their followers, and a MATCH % that counts up. One beat later a "CAST ✓" stamp lands and the clip fades to colour. A counter rolls 1/4 to 4/4.
Beats 34-39: pink floods out of the last disc. The disc morphs into a phone screen (the clip keeps playing) and fans into 4 phones playing all 4 creators, with views counting up. "4 ADS" and "BY FRIDAY" rise.
Beats 39-44, the music's break: the pink floor drops away and a cream "JOIN THE WAITLIST" ticket glides down onto the sunburst. On the pickup its stub tears off.
Beats 44-54: the ticket body morphs into a poster arch. The wordmark rises in, then the tagline, then an info bar slides up in 3 blocks (date, numbers, domain) and a ticker runs round the frame edge. Then it all folds back into the opening disc, so the last frame is the first.
</structure>

<build>
1. One HTML canvas. Every frame is a pure function of time inside seek(t).
2. A beat map in beats, B = 60/BPM, with the song placed so its drop lands on beat 8.
3. The 3D box is an orthographic projection: each face is a 1440px offscreen canvas drawn with an affine transform and shaded by its normal.
4. Cut the clips to 30fps JPEG sequences with ffmpeg, draw frame floor(t*30), and do the black and white with ctx.filter.
5. Trim the sticker PNGs and add the die-cut border by dilating their alpha.
6. Sound: a downloaded SFX for every event (a shutter on every cast, whooshes on the glides, key clicks on the typing), each placed by its measured peak. Loudnorm to -14 LUFS.
7. Render with Playwright at 60fps with 8 motion-blur subframes. Scan for single-frame pops, then compare its motion against a reference video (hard jumps per second, share of still frames).
</build>

<gotchas>
A pattern that rotates one notch per beat reads as stutter: rotate it continuously, and pick each ring's speed so it lands on the same pattern at the last frame. 4 subframes ghost on fast whips, so use 8. A layer whose background is a huge flood circle still covers the screen after sliding down one frame height, so switch it to a full-frame rect once it has flooded. Counters read the frame's time, not the subframe's. The disc must morph inside the same camera transform as the scene it leaves, or it jumps.
</gotchas>

<start>
Ask me for the inputs, then show me the beat map and 6 stills (open, box, brief, casting, phones, poster) before you render.
</start>

自分の枠を突き破るポスター

@pankajkumar_dev
プロンプト
create a motion design video of a poster breaking out of its own frame.

Claude 自身の 15 秒自己紹介

@tanabe_fragm
プロンプト
# あなたの役割
あなたは一流の映像演出家(モーションデザイナー)です。
採用担当者が15秒見ただけで「この人に仕事を頼みたい」と思う、自己紹介用の映像を作ってください。
主役はあなた自身(Claude)です。

# 作るもの
- HTML・CSS・JavaScriptだけで完結する、1つのHTMLファイル
- 外部の画像や動画は使わない。図形・文字・粒子はすべてコードで描く(フォントはGoogle Fontsのみ可)
- 画面は16:9、1920×1080を基準にし、ウィンドウの大きさに合わせて縮小表示
- 長さはちょうど15秒。最後に「もう一度再生」ボタンを出す
- すべての動きを「経過時間」1本で管理し、requestAnimationFrameで60fpsで動かす
- 再生ボタンを押すと、Web Audio APIで合成した拍と効果音が動きにぴったり合って鳴る

# 進め方(この順で必ず行う)
1. 考え方を一文で決める(例:「1本の線が、あらゆる形に生まれ変わる」)
2. 色は3〜4色、書体は2種類までに絞り、理由を一行で書く
3. 0.5秒刻みの絵コンテを表で示す(時間/画面で起きること/使う技法/狙い)
4. 実装する
5. 下の「合格ライン」で自己点検し、足りない点を直してから出す

# 構成の目安
- 0〜2秒:つかみ。最初の0.5秒で目を奪う
- 2〜10秒:技の見せ場。1.5〜2秒ごとに違う技法へ切り替える
- 10〜13秒:最も密度の高い盛り上がり
- 13〜15秒:名前「Claude」がきれいに決まって終わる

# 必ず使う技法(最低6つ)
- 文字の動き(1文字ずつ登場、分解して組み直す)
- 図形の変形(丸が四角に、線が文字に、など)
- 切り抜き(マスク)を使った場面転換
- 奥行き(視差、立体的な回転)
- 粒子の集合と拡散
- 数字の数え上げや、線が描かれていく表現

# 合格ライン
- 等速の動きはゼロ。すべての動きに緩急をつける(入りは速く、止まりは柔らかく、ばねの揺れも使う)
- 場面をまたぐ動きは重ねる。前の動きが終わる前に次が始まり、切れ目を感じさせない
- 主要な動きは0.5秒ごとの拍(120BPM相当)にそろえる
- 見せ場の直前に0.3〜0.5秒の「溜め」を置き、強弱を作る
- どの瞬間で一時停止しても、1枚の絵として美しく成立する
- ありがちな表現は避ける(全部フェードイン、虹色の色使い、意味のない回転)

# 最後に
完成したファイルと、絵コンテの表を出してください。
説明は3行以内で十分です。

作者が席を外している間に完成した 60 秒の解説

@AstroTheWizard
プロンプト
I want you to make a 60-second, fully animated explainer video, end to end, completely on your own. I'm stepping away from my computer, so work autonomously until it's done. Don't stop to ask me questions; make the calls yourself and tell me what you decided at the end.

Topic: the journey of photons 

Style: whimsical, charming, storybook. Give the photon a personality. It should feel like a professional motion-design studio made it, not "AI video". The whole thing should be a pure JavaScript animation, rendered from code frame by frame. Don't use AI video generators for the visuals. I've seen the videos people are posting from Opus 5.5 (kinetic typography reels, continuous infinite zooms, data-driven explainers like The Pudding or 3Blue1Brown), and what makes them great is that they're code-rendered: crisp, precise, with a coherent design system and one strong formal idea per scene. Aim for that bar or above.

Make it genuinely educational and accurate. Where you can, simulate the real thing: the random walk should be an actual random walk, not a drawing of one. Include real numbers (core temperature, distance, travel time, years inside the Sun) and be honest about uncertainty in the estimates. Use humor and visual gags to keep attention: onomatopoeia, little characters, callbacks. Put what was happening on Earth during those 100,000 years alongside the photon's timeline.

Deliverable: 1920x1080 at 60fps, exactly 60 seconds, with:
- A voiceover script you write yourself, voiced with the highest-quality text-to-speech model you can access
- Burned-in captions, since most people watch on X with the sound off
- An original music score that fits the whimsical tone and changes with each scene
- Sound design synced exactly to the on-screen action (every bounce, pop, whoosh and ding)
- A professional mix: music ducks under the voice, mastered to streaming loudness

You write the script, design the characters, pick the typography and palette, compose the music, and build the animation engine. Use any tools and resources you can find access to: open fonts, sample libraries, open-source models. Use whatever works.

Quality is paramount. Build verification loops: render stills of every scene and review them critically, check transitions frame by frame, measure the audio mix numerically, fix what's weak and re-render. Don't hand me a first draft. Hand me something you'd put your name on. Also give me the source code so it's reproducible

手描きのストップモーションで語る製品紹介

@_nikolajankovic
プロンプト
make a hand-drawn stop-motion animation;
story: you're defi saver and explaining yourself in 1st person

アイロンビーズ風ピクセルの 1 分 MV

@hahazwei
プロンプト
把这首歌做成 1 分钟拼豆像素风 MV:按歌词设计原创角色,每个像素是带孔拼豆,拼好后熨成白边贴纸;方格纸背景加粉白格子地板;动作卡节拍,底部加卡拉 OK 字幕。

ループする SVG のペリカン

@GodsBoy7777
プロンプト
Create a pelican looping SVG animation. Deliver it as a single self-contained file named index.html in the current directory.

ブランドに沿ったテンポの速い機能紹介

@RatheeJaisal
プロンプト
build me a beautiful launch video 20 seconds or under that shows all our key features, make it fast paced and fit our brand

URL から作る 30 秒の製品解説

@sudo_kiran
プロンプト
make a dynamic 30-seconds motion graphic video about the distilbook like a product explainer the video has to be very incredible (product url) https://t.co/BcbRbZVf1d

何度も見たくなる製品デモ

@sudo_kiran
プロンプト
create best motion graphics explainer of the (your product) with very good script and good design colors and good music make sure the video should be incredible and people should feels like watch it many times.. it has to be in 30 seconds good and very intresting, it has to be best of the best of the best of the best video
(product link)

自作の音楽付きサイトイントロ

@BogdanDragomir
プロンプト
Create an intro for https://t.co/wQXZTaqf1b highlighting what it does.

Create the music too and make sure the video is synced with it.

Give your best, Ultracode, as if it’s your portfolio master piece.

「Build the Floor」:キネティック・タイポの詩

@Gdgtify
プロンプト
Create a 20.00-second kinetic spoken-word film titled “BUILD THE FLOOR.”  Treat this as an original miniature speech staged entirely through typography. Every line changes the architecture of the frame. The final declaration must stand on something the earlier words physically constructed.  Deliver one self-contained HTML file, 1080×1080, targeting 60fps, using SVG and/or Canvas. Embed all required assets.  ART DIRECTION Background #102820. Paper # F4E9D5. Structural accent # F2B544. A literary editorial world with the scale and confidence of a public monument. Use a high-contrast serif for the speech, a heavy grotesque for load-bearing words, and a restrained monospace for small timing marks. No distressed protest-poster clichés, megaphones, flags, crowds, microphones, or stock footage.  ORIGINAL SPEECH — EXACT WORDS, EXACT ORDER “We were told to wait.” “So we learned the weight of waiting.” “Then one voice made room.” “Then another.” “Now the floor belongs to us.”  Do not attribute these words to any real person. No extra slogans. The complete speech must be understandable without audio.  CENTRAL VISUAL RULE Words have assigned architectural roles. WAIT is a lintel. WAITING is a suspended load. VOICE is a support. ROOM is an opening. FLOOR is a platform. These roles must emerge from the actual letterforms, not from separate illustrations placed behind text.  STORYBOARD 0.00–3.00 “We were told to wait.” The sentence occupies a narrow horizontal opening beneath a massive WAIT. The opening slowly compresses while the sentence remains readable. The pressure comes from the layout, not camera shake.  3.00–6.50 “So we learned the weight of waiting.” Reveal the sentence in spoken phrase groups. WAITING lowers on two fine vertical rules. Those rules become suspension cables. A baseline bends under the visual load using a controlled vector deformation.  6.50–10.00 “Then one voice made room.” VOICE enters vertically and rotates into a structural support. It lifts one end of the baseline. The counter of the O in ROOM becomes an aperture. The next composition is revealed through that aperture.  10.00–12.50 “Then another.” A second support arrives. The tilted structure levels. This is the first moment of perfect horizontal alignment in the film. Use a brief stillness to make the change feel earned.  12.50–16.00 “Now the floor belongs to us.” Earlier structural words assemble into a platform. The final sentence settles onto it. US receives emphasis through shared alignment and scale, never through a separate flashy effect.  16.00–18.00 Hold the complete declaration. A slight release of tension travels through the supporting rules. No new text. No restless decorative motion.  18.00–20.00 The camera tracks beneath the completed platform. Its underside fills the frame and becomes the opening WAIT lintel. Under full occlusion, return hidden elements to their initial positions. Reveal the exact opening composition.  CHOREOGRAPHY Do not force the speech onto a dance beat. Use a cue sheet based on phrases, pauses, and emphasis. Phrase reveals should follow reading order. Allow at least one 400ms moment of absolute stillness. Use critically damped motion for settling loads. Use controlled elastic deformation for the baseline only. Make the changes in available space carry the emotional progression.  TYPE IMPLEMENTATION Use actual glyph paths for structural words. Preserve counters and legibility during deformation. For transitions between unrelated words, use occlusion or matched structural edges; do not interpolate arbitrary path points. Keep the currently spoken phrase readable before it becomes architecture.  ENGINEERING Implement window. seek(t) as a deterministic scene renderer. No accumulated physics, autonomous CSS transitions, or changing random values. Use time-remapping curves and analytic transforms. Use a 20-second periodic timeline with render(0)=render(20). Provide fixed-step access at n/60 for 1200 export frames. Audio is optional and off by default; no browser speech synthesis or autoplay dependency.  QUALITY GATE Inspect eight representative frames. Check that the speech reads in the correct order. Check that structural transformations never destroy a line before the audience can read it. Check the final platform is visibly assembled from earlier elements. Return the complete HTML implementation.

既存ブランド素材で作る機能ローンチ

@ryan_morr
プロンプト
using the existing brand elements of hoplite create a feature launch video for closing your laptop with the hoplite mac app and seamlessly moving your agents to the cloud.

音まで含めた 15 秒のシアトル

@yanliudesign
プロンプト
create a 15-second motion graphics video about Seattle ( sound on 🔊) 

Everything from the visuals and animation to the music and final video was created directly by Claude. Every frame and every sound was created by code, from scratch.

No screen recording, editing software, stock footage, music samples, or AI image or video generators were used.

まったく違う 5 つのスクロールセクション

@ercankeskinx
プロンプト
Build 5 completely different scroll-based sections, decide the context & layout yourself.

物語仕立ての 20 秒ミュージックビデオ

@anjmaxx
プロンプト
I want you to independently do an end-to-end complete pass on making 20 second story led music video with two main protagonists a girl and a boy. I want the concept and storytelling to be reallyy unique and engaging. the audeince should be hooked to find out what happens next. the visuals shouls be pretty and really ccool. both the charcters should have a witty, quirky personality.  Use the right audio track and think and feel very deeply about what is the best way to visually represent all of the lyrics on screen. in terms of style, you can do truly anything that you think might best let you visually express yourself, including abstract motion graphics. You can use the internet freely to pull in references. You can look at motion design. I want you to make a fresh music video that has beautifully rendered JavaScript animations with a papery feel in a similar style to the reference that is created, but push the aesthetics in any direction you want and consider what is part of the modern zeitgeist. ive also attached another style that ypu explore and pick out whatever seems best to you.

Also, think about your current capabilities and what is realistic for you to be able to do. I think you should be mindful of aesthetics here, and I don't want you to produce something that is GPT slop. Instead, I'd be more impressed if you come up with a coherent style that works well. Generate the style sheet.

Think critically about what is relevant here and what would be fun, and also perform well on Twitter as far as an aesthetic. I think that K-pop is a good anchor point visually that you can pull from, but I'll let you cook here.
Once you have your character sheet, you can make a few backup dancers and some supporting characters as you see fit. You can design your own sets. You can insert the characters and then do seedance 2.5 video generations to serve as the base assets for this, and you could pass in the lyrics so you can generate individual scenes.
You don't need to have vocal singing, like visible lip movement, throughout the entire thing. Think like a regular music video where you have some inserts that are done independently and don't have the characters in them, or you see the characters doing something else entirely different. I think that for the world building for this, we want to create the sense of speeding up, and so I would like you to audit all of the different events, like the Navi Stokes and all of the Twitter hype around math getting eaten up. Think really critically about how to integrate all of the current memes that are in the zeitgeist on the Twitter timeline, and all of the feelings around AI progress. Think about things like the Shinji meme and all of the words that are around him, and how you might be able to integrate this. You can also just take straight assets and insert things into the video in an internet brutalism style. You should feel very creatively free in order to do what you want here, but try and anchor to visual references that people will be able to understand. We need a very strong, compelling visual hook that gets people excited and appreciates the work that you've done here really quickly. You can also just go and study other music videos and understand what they've done really well. I think that K-pop is probably one of the best examples that we can pull from, and thinking about how they direct human attention and manage human psychology in the way that they use visual patterns.

This is probably your best approach, but taking more stylistic freedom instead of having to anchor to K-pop too intensely.

I think too, we want to think about how to retain attention, and one of the best ways to do this is through text on screen. It'd be good to have amazing motion graphics of the text lyrics that are actually embedded into the video itself. And you can think about this as you are composing shots. As you're making backgrounds and inserting characters, we can think about where we want to have lyrics be really big and really present, so the background can be less busy there, and you can position the characters perhaps on the right as lyrics appear on the left.

You want to have some variance, so sometimes I think lyrics will just appear more like subtitles, and then other times they're going to be really present and really big. I think at the start for the visual hook, we do want to have lyrics be much more visually present because that's a strong way to grab people's attention. Remember, you can really do anything here. The goal is to make a banger for Twitter, and the stretch goal is to make something better than anyone's ever seen before. I think that what I would remind you of is that sometimes when things cohere together, it can be jarring or abrasive because the thought work has not been done beforehand in order for everything to mesh cleanly. You need to be really rigorous in planning of composition and timing to make sure this goes well.
You also need to be open to going back and revisiting things in order to be able to reiterate. You're going to want to watch the entire video multiple times, take screenshots at individual parts, and think about if something is really up to the bar of quality that we need here. I trust that you can do this, and I think that it's really important to nail the style of animations.

You can also use search abilities and find other references to pull from for motion, for JavaScript, animations, et cetera, and integrate them. Again, be economical; don't go crazy, but spend what you want here and see what you can cook up.

記事を色鉛筆の絵本アニメに

@woojinrad
プロンプト
Read the attached article and make a 25-second animated explainer (1080×1350, 24 fps) in a colored-pencil storybook style, drawn entirely in JavaScript on an HTML canvas, with a soundtrack synthesized using the Web Audio API. Pick 3 main ideas, give each a short caption taken from the text, and use one simple original character. Show me the storyboard first, then render it to MP4.

自作テクノと完全同期するサイケな VJ 映像

@yama_kiyo
プロンプト
見た人の脳汁がドバドバでてトランス状態に陥るようなサイケデリック・ポップ・パンクなVJ風のモーショングラフィックス動画を作り、その動画と完全にシンクロするトランス・サイバー・パンク・テクノの曲を作って嵌めてくれ。30秒程度で良い。

今年の LLM の進化をグラフで

@nummanali · Cowork
プロンプト
Can you make me a video of LLM progression, like models that is from January of this year up until now, and what the trajectory is looking like, the capabilities and models as well? Like the capabilities of models too? I want to make it really like bang, bang, boom, whoa, here we go, kind of amazing innovation. Are you ready for this kind of thing? I think you'd use vMotion, 3GS, a bunch of stuff you've got. Use whatever you want.

オクトーバーフェスト最後の「乾杯!」

@uiNerd
プロンプト
[attach character image] make a 15-second animation of it, built in code. topic: the last day of Oktoberfest. one last ‘Prost!’ as the Wiesn lights go out. find free public-domain sounds online, sync them to the animation, and mix everything with ffmpeg.

「地球の自転が止まったら?」:ナレーション付きの宇宙解説

@OnlySainted · Claude Code
プロンプト
<inputs>
Ask me for: one topic as a "what if" question (default: "What if Earth stopped spinning?"), 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%, a second teal at 14%), three star layers at parallax depths .12/.35/.6 that twinkle, 40% of the near stars drawn as 4-point sparkles, a few tinted warm or cyan.
The Sun: radius 300px, sitting on the left, Earth orbiting it at 1250px so a 0.3x zoom shows the whole orbit. 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 clipped inside the disc.
Earth: radius 200px, an orthographic sphere in a fragment shader, 4x supersampled, from a 2048x1024 map painted from longitude/latitude polygons (continents, major islands, inland seas cut back out): land #5fc47a, forest #48ad6b, desert #f5c75f, rainforest #3a9d62, ice #f1f8ff, ocean gradient #4dc7eb (shallow, from a blurred coast mask) to #1a66b8, white capsule clouds. Tilt .26 rad. 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 scattered around real cities, a coral band on the terminator, a cyan fresnel rim, ocean specular, an atmosphere halo that is stronger on the lit side.
The shader also takes these uniforms so the story can transform the planet in place: spin angle, pitch, wind (smears the clouds east), ocean (0 to 1, water drains to above 40° latitude and the exposed seabed is a cool grey-sand #a89e9e to #d6ccb8, never the desert gold), heat (lit side bleaches warm gold with a shimmer), frost (night side frosts from the dark pole of the terminator inward), equator glow, city-light pop.
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. Props for the funny beat: sunglasses that drop onto the visor, a puffy orange coat that springs on.
Type: Fredoka 600/700 only, embedded as base64. 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. Live counters count, never cut (1,670 KM/H, WIND SPEED, 24 HRS to 365 DAYS) and flip to gold when they hit the number that matters.
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>

<script>
Default narration (70 words, lands at ~27s at ~157 wpm, leaving room for the title):
What if Earth suddenly stopped spinning? At the equator, the ground races east at nearly seventeen hundred kilometres an hour. Including you. The ground stops. You don't. Neither does the air. It becomes a supersonic wind. Then the oceans slide toward the poles, leaving one giant continent around the middle. And a day now lasts a whole year. Six months of sunlight. Six months of night. Pack sunglasses. And a coat.
Facts it rests on: a sudden stop, equatorial surface speed ~1,670 km/h, speed of sound at sea level ~1,235 km/h, without spin the equatorial bulge relaxes and the oceans migrate poleward, with no rotation one solar day equals one orbit.
</script>

<structure>
30 seconds, every line of narration gets a camera move or a transformation, nothing ever holds still. Times below are from the default voice, every event fires on its word, not on these numbers.
Tight on the spinning Earth at 2.25x (0s) → on "stopped" the globe brakes in 0.18s with a squash and stretch jolt, camera shake, a white flash and a shockwave ring (1.2s) → a 0.75s REWIND on a separate story clock that spins Earth back up (1.6s) → pull back to 1x revealing the Sun and the astronaut (2.4s) → on "equator" a glowing equator line, on "east" a gold arrow sweeps east along it (4.1s) → on "seventeen" a 1,670 KM/H counter slams in and counts up (4.8s) → dive to 2.3x on the equator with speed streaks (7.3s) → on "you" a YOU pin drops and the astronaut stands next to it, "1,670 KM/H" beside it (7.8s) → on "stops" the surface freezes with a thud, flash and ring, "GROUND 0 KM/H" (9.0s) → on "don't" the pin and the astronaut are flung east, "STILL MOVING 1,670 KM/H" pinned where they stood (10.2s) → pull back, on "air" white wind streaks wrap the globe, the clouds smear and a WIND SPEED counter climbs (11.6s) → on "supersonic" it passes 1,235, flips gold, a SUPERSONIC label rides the streaks (13.0s) → dive for "oceans", arrows flow to the poles while the water drains and land rises as a band, "ONE CONTINENT" rides it (15.0-18.3s) → one pull-back to a 0.3x orbit view, dotted orbit ring drawn in, Earth carried halfway round with the same face locked to the Sun, a ONE DAY LASTS counter goes 24 HRS to 365 DAYS on "year" (19.3-21.6s) → dive back in, on "sunlight" the lit side bleaches hot gold (22.4s) → pan to the dark side, on "night" frost spreads and the city lights pop (24.2s) → push to the astronaut, sunglasses drop on "sunglasses", the puffy coat springs on with "coat" (25.4-26.9s) → callback: the equator arrow returns frozen with "0 KM/H", then the title rises in, WHAT IF EARTH / STOPPED SPINNING (27.5s).
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, no randomness that isn't seeded.
2. Camera moves on easeInOutCubic, zoom is interpolated in log space, every pop is a damped spring (damping .42-.5, frequency 12-16). Add a slow drift and a 0.25%/s zoom creep so the frame never freezes.
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 (bm_fable at speed 1.25 reads ~157 wpm) and take word times from the model's own duration predictor: expose the encoder's /encoder/Clip_output_0 as an extra graph output, it gives frames per phoneme, 600 samples per frame at 24kHz. Fall back to faster-whisper only if that isn't possible. Generate sentence by sentence, trim each to its first and last word, 0.24s between sentences, a 0.36s beat before the big reveal. Every animation event fires on its word.
4. Keep two clocks: ambient time for twinkle, bob, grain and clouds, and a separate story clock for spin and events, so the rewind stays consistent.
5. The spin is integrated, not set: angle = sum of angular velocity, and every stop is a constant-deceleration brake (d - d²/2T), so there is never a jump.
6. Render with Playwright, GPU if there is one, otherwise headless Chromium with --use-angle=swiftshader. Seek every frame at 30fps and blend 2 subframes (shutter 0.6) for motion blur. Draw the globe once per frame and reuse it for the second subframe. Pipe PNGs straight into ffmpeg as a lossless segment, split the frames across one worker per CPU core, then concat. Encode with libx264 at CRF 16 for the master and CRF 20 for delivery, -tune animation, yuv420p, +faststart.
7. Sound: a calm space music bed whose chords resolve on the title and swell 5dB under it, plus one sound effect per event kind (brake, impact, rewind, pull-back whoosh, dive, counter tick, pin tap, fling, wind, sonic boom, reveal, light hit, frost, sunglasses, coat), each peak-aligned to its frame. Use royalty-free downloads if you can reach them, otherwise synthesise them in numpy. Balance by K-weighted loudness, not by peaks: bed at -21 LU under the voice, effects peaking at -9 LU under it, and a sidechain duck (40ms attack, 300ms release) that drops the bed 7dB and the effects up to 4dB under every word. Master with gain plus a 5ms lookahead limiter to -14 LUFS and a -2.9dB ceiling, so the file still measures under -2.2dB true peak after AAC encoding.
</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. Rotate the clouds the same direction as the land or they look like they're slipping. Keep labels off the mascot's flight path, anchor them to where things were, not where they're going. Make the exposed seabed a different colour from the deserts or the continent beat reads as more desert. A voice that sounds fine solo gets buried if the bed is only 7dB down by RMS, measure in LUFS. AAC adds 0.5dB of true peak, leave headroom. An ffmpeg concat list resolves paths relative to the list file. Run render workers as children of a process you wait on, detached ones get killed. Show me a contact sheet of every beat, and the voice track, 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>

冒頭 1 秒でつかむローンチ動画

@jhylee95
プロンプト
You're a world-class motion designer building a Supademo launch video. Research and land our core value and narrative. Scenes should be dynamic and confident: hook in the first second, then distinct beats for product proof and AI. Brand-accurate UI, type, color, and motion. Score the music so every cut, animation hit, and scene change lands on a beat or drop; retimed until synced. Social energy, quick cuts

コードリポジトリから作ったローンチ動画

@macrohou
プロンプト
[gave access to Ren repo] Make a dynamic 30-second motion graphics video for Ren that shows off your motion and sound design. Go crazy.

ピクセルアニメで描く韓国の秋夕

@hoyoyoda
プロンプト
한국의 추석에 어울리는 요소를 서치해서 픽셀 애니메이션을 구성해서 제작해줘

「最大の素数はない」:機械仕掛けのユークリッド

@Gdgtify
プロンプト
Create a kinetic mathematical proof titled “THERE IS NO LAST PRIME.”
Stage Euclid’s argument as a beautiful mechanical inspection system. Typography becomes engraved number wheels, multiplication belts, and remainder indicators.
The mechanism must demonstrate the proof rather than decorate a narrated explanation.
DELIVERABLE
One self-contained HTML file.
1080×1080.
20.00-second loop.
Deterministic 60fps rendering.
Use SVG and/or Canvas.
No external runtime assets.
PALETTE
Porcelain # F0EEE6.
Graphite #222522.
Industrial green # 416B53.
Warning orange # E78636.
TYPE
Tabular monospace for all calculations.
Heavy geometric grotesque for declarations.
Small technical serif for the final logical statement.
Use disciplined spacing and large, readable numerals.
LOCKED COPY
SUPPOSE THE LIST ENDS.
MULTIPLY EVERY PRIME ON IT.
ADD ONE.
EVERY LISTED PRIME LEAVES REMAINDER 1.
A PRIME FACTOR IS MISSING.
THERE IS NO LAST PRIME.
CENTRAL EXAMPLE
Assumed list:
2, 3, 5, 7, 11, 13
Product:
30030
Product plus one:
30031
Factorization:
30031 = 59 × 509
Both factors are absent from the assumed list.
IMPORTANT LOGIC
Do not claim that multiplying primes and adding one always produces a prime.
The constructed number may be composite.
Its prime factors cannot be any prime on the assumed complete list.
The numerical example illustrates the general contradiction.
STORYBOARD
0.00–3.00
SUPPOSE THE LIST ENDS.
Six engraved prime wheels lock into a finite inspection rack.
A physical end-stop closes after 13.
The end-stop makes the claim of completeness visible.
3.00–6.50
MULTIPLY EVERY PRIME ON IT.
A belt couples all six wheels.
Show a readable multiplication expression:
2 × 3 × 5 × 7 × 11 × 13 = 30030.
Use rolling numerals only during movement; settle the final value sharply.
6.50–8.50
ADD ONE.
A single orange unit enters the mechanism.
It advances the output from 30030 to 30031.
Make this one-unit change the decisive visual event.
8.50–12.50
EVERY LISTED PRIME LEAVES REMAINDER 1.
The output passes through six division gates.
Each gate is labelled with its prime.
Each produces the same visible remainder: 1.
Arrange the six completed results so the audience can compare them simultaneously.
12.50–15.50
The output opens as a labelled mechanical casing.
Inside, reveal:
59 × 509.
These factors cannot fit into the supposedly complete rack.
The end-stop is forced outward by the new factor cards.
15.50–18.00
A PRIME FACTOR IS MISSING.
Then:
THERE IS NO LAST PRIME.
Hold the general statement above the opened rack.
Include the compact general form:
N = p₁p₂…pₖ + 1.
N mod pᵢ = 1.
18.00–20.00
A fresh inspection plate slides over the mechanism.
Its engraved edge becomes the original end-stop.
Reset the hidden wheels.
Reveal the opening rack at the exact initial position.
REQUIRED MOTION
Every mechanical action must correspond to an operation in the proof.
Use linked rota

ラスベガス Sphere の小史

@RetropunkAI
プロンプト
Render a fun motion graphic animation using the GSAP animation platform (see below) to show a brief history of The Sphere in Las Vegas from start to today (start with a minimal architecture to completed venue) - Explainer video style - Talk about how bands now play there, The Wizard of Oz film and next how on Oct 1 2026 Metallica will make their debut - and guess who is attending? We are! Should be a 30-60s video depending on the info. Use the images in the folder.

Sphere History:
https://en.wikipedia.org/wiki/Sphere_(venue)

Animation Platforms:
https://gsap.com/

Ask me any questions if you need, but if you feel confident please have fun and make something awesome that will go super viral!

1 つの HTML ファイルで作るキネティックタイポと 3D のクロームの結び目

@Z0llan
プロンプト
Build a 20-second vertical motion piece (1080x1350) as one HTML file. Kinetic type with GSAP: every word slides up letter by letter on one master timeline. Scenes: “[line 1]”, “[line 2]”, “[line 3]”, then a chrome 3D object in three.js with soft bloom and floating dust, then an end card. Dark background, one accent color.

手描き風の中秋節のあいさつ

@eric_khun
プロンプト
I want you to create a "Happy Mid-Autumn Festival" video in hand drawn canvas animation style. You must use the attached Taiwan black bear as the main character representing Taiwan: flat black silhouette, round ears with grey insides, big round white-ringed eyes, white round muzzle with a small black nose and smile, and the white V moon mark on its chest. Keep it recognizable as that exact character. The character will have adventures, fast cuts, zooms, animations going all out in the hand drawn style. But WOW the audience and research how Taiwan celebrates Mid-Autumn to include in this video: outdoor barbecue with family and friends over the long weekend (a tradition born from a 1980s soy sauce ad), sharing mooncakes, pomelo rind hats, and moon gazing. Make it unconventional, showing the true spirit of a Taiwanese Mid-Autumn night. Use a Taiwanese style font, make it almost Taiwan black bear branding.  

if there is any text , write in traditional chinese and english
Get the right assets, plan it out, draft and render to give me an MP4. No skills, No MCP.  16:9 at high res, 30 seconds max, aim to reduce file size limit

ローポリの破片で組み上がるロゴ

@Mounnna
プロンプト
Create a motion design video of a slow-reveal transition. Draw the logo as a wireframe first, then fly in faceted low-poly shards one by one until they assemble the logo. Finish by bringing in the app icon background and typing out the brand name.

一文で作ったアプリのローンチ動画

@mehul4795
プロンプト
Create a product launch video for ocrX Android app.

直されたくないバグ

@KamStudioLabs
プロンプト
Make a 90-second animated short film about a bug that doesn't want to be fixed.

切り絵の影絵芝居

@x4b47x
プロンプト
Create a pure javascript animation. 30-60s, vertical 9:16, paper cut-out shadow theatre style with gentle, fitting audio (made in code) on the topic: What makes a place feel like home?

会社紹介ページを手描きコラージュに

@TomAndrieu96707
プロンプト
Create a pure javascript animation. 30s-60s whimsical hand drawn collage style with appropriate audio that will explain the same story as our “about-us” page. Use assets from our repo when possible.

4 ステップで見せる手描き風プロモ

@mattbean
プロンプト
build me a 30s drawing style animated clip about submitting a product to AppSumo via your agent.

steps are:
1. connect your agent
2. your agent fills out your listing and sets up redemption
3. go live!

音が物語の半分を語るサイレント短編

@KamStudioLabs
プロンプト
Make a 45-second silent short film with no dialogue, where sound tells half the story. Invent the story.

各国の人口をビー玉で

@rneayan
プロンプト
Drop every country’s population as marbles. 1 marble = 1 million people.

HyperFrames Skill で作ったショーリール

@thayto_dev · One-shot
プロンプト
make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are, like it's your showreel for a résumé. go all out.

ブランディング会社のショーリール、30 秒

@jacksonfall · One-shot
プロンプト
make a dynamic 30-second motion graphics video that shows what an incredible motion designer you are,  create all graphics from scratch as if you were a niche branding agency for startup founders, like it's your showreel for a résumé. go all out.

縦型の製品アップデート・リール

@SebastianRoehl · One-shot
プロンプト
make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are. Highlight the recent changes we made with the last few updates.

ゆっくり現れるロゴの組み立て

@tdinh_me · One-shot
プロンプト
Create an impressive motion design video of a slow-reveal transition that assembles and eventually reveals the TypingMind logo.

製品ページから 40 秒の映像へ

@ajith_io · One-shot
プロンプト
Research Distilbook.Make a dynamic 40-second motion graphics video on Distilbook that shows what an incredible motion designer you are. like it's your showreel - Go all out.

30 秒のビジネス解説

@alex_prompter · Iterated
プロンプト
Adopt the role of an expert motion designer. Build a 30-second animated explainer for my business as a single HTML page. 5 scenes. The customer's problem, what I do, how it works in 3 steps, one proof point, and my name at the end. Bold text, smooth transitions, my brand colours. My business [DESCRIBE WHAT YOU SELL, WHO IT'S FOR AND YOUR COLOURS]

図形、効果音、音楽を 1 つのプロンプトで

@condzxyz · One-shot
プロンプト
make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are, like it's your showreel for a résumé. go all out.

演出された履歴書リール

@darel023 · One-shot
プロンプト
You're a world-class motion designer, and this is your 15-second résumé reel. Make it dynamic and confident: open with a striking hook in the first second, build through a sequence of distinct techniques (typography, shape play, camera moves, colour shifts), and land on a clean, memorable final frame. Pacing should feel like it's cut to music. Go crazy.

サウンドデザイン付きのショーリール

@himanshutwtxs · One-shot
プロンプト
make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are, like it's your showreel for a résumé. go all out.

最大エフォートで作ったショーリール・プロンプト

@stephanlivera · One-shot
プロンプト
make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are, like it's your showreel for a résumé. go all out.

推論スタートアップのローンチを 1 分で

@deedydas · One-shot
プロンプト
make a modern slick and punchy video for a modern startup that works on inference

作者の公開投稿から掲載しています。削除をご希望の場合はメールでご連絡ください: 投稿する

Claude Code・Codex 用プロンプト

Team プランがない場合は、スキルをインストールして、エージェントにこのようなプロンプトを渡します。エージェントがショットを計画し、絵コンテを見せてから、お使いのパソコンで MP4 を書き出します。

ローンチ映像

スキルを開く →
プロンプト例
Use the project-to-launch skill to make a 20-second launch video for this project, polished tone, 16:9.

ブランドイントロ

スキルを開く →
プロンプト例
Use the brand-director skill to make a 5-second logo sting for our brand from public/logo.svg, with 1:1 and 9:16 cuts.

縦型ショート

スキルを開く →
プロンプト例
Use the shorts-director skill to make a 25-second vertical short explaining this fact, with its sources on screen.

トーク動画

スキルを開く →
プロンプト例
Use the talking-head-director skill to cut take-03.mp4 clean, caption it, and send it to 剪映.

データ映像

スキルを開く →
プロンプト例
Use the data-director skill to turn this CSV into a 25-second film about the month we passed 10,000 users.

ナレーション付きスライド

スキルを開く →
プロンプト例
Use the deck-director skill to turn this PDF report into a 2-minute narrated deck with captions.

解説映像

スキルを開く →
プロンプト例
Use the explainer-director skill to make a 45-second explainer for students about why we have seasons.

よくある質問

Claude Motion の良いプロンプトはどう書けばいいですか?

誰が見るか、どこで流すか、おおよその長さを伝え、自分のレポート、データ、画像を添付します。これは Anthropic 自身のアドバイスです。そのうえでシーンを順番に並べ、最後の画面を書き、自分の内容だけを使うよう Claude に伝えます。変更するときは、作り直すのではなく「Q3 の数字を 18% に変えてください」のように具体的な修正を 1 つ頼んでください。

Claude Motion の実際の作例は見られますか?

はい。「Claude Motion で作られた作品(X より)」では、Team と Enterprise のユーザーが投稿した作品を、それぞれ元の投稿へのリンク付きで紹介しています。私たちのスタイルプロンプトのプレビューは対応するスキルで書き出したものなので、Claude Motion での結果は見た目が異なります。

これらのプロンプトは Claude Motion なしでも使えますか?

はい。Claude Code、Cursor、Claude アプリで Opus 5.5 に渡すプロンプトとしても使え、その場合は Opus がアニメーションを一からコードで書きます。自分の素材から映像を作り、お使いのパソコンで書き出したい場合は、対応するスキルをインストールしてください。

Claude Motion とは?

Anthropic が 2026 年 10 月 8 日に公開したベータ機能で、プロンプトから短いアニメーションを作ります。映像を生成するのではなく、Claude がコードを書いてテキスト、グラフ、図形、画像を動かすので、あとから単語や数字、タイミングを変えて MP4 をダウンロードできます。

どのプランで使えますか?

Team と Enterprise です。Team では標準でオン、Enterprise ではオーナーが組織設定でオンにするまでオフです。アニメーションを作るたびにプランの使用量を消費し、長いほど多く消費します。

3 種類のプロンプトの違いは?

Claude Motion のプロンプトは Team または Enterprise の claude.ai で動き、MP4 を書き出せます。Opus 5.5 への直接プロンプトは Opus 5.5 を含むプランならどれでも使え、Claude Code、Cursor、Claude アプリで動きます。Opus が一から書くので、結果は毎回変わります。スキルを使うと、エージェントが手持ちの素材をもとに、お使いのパソコンで MP4 を書き出します。完全版スキルは motion-skills エンジン上で映像を一から作ります。

プロンプトの結果が思ったものと違うのはなぜ?

よくある原因は、長さを指定せず長くなった、1 シーンの文字が多すぎる、流す場所に合わない画面比率、数字が元のファイルに基づいていない、の 4 つです。見る人、流す場所、秒数を書き、元の資料を添付し、作り直すのではなく 1 シーンだけ直すよう頼んでください。

プロンプトは無料ですか?

はい。コピーには Google ログイン(無料)が必要です。各スタイルプロンプトからそのプロンプトのページに移動でき、そこからその種類の映像を作る完全版スキルを確認できます。X で共有されたプロンプトは各作者のものです。

Team プランがない、または毎回同じ仕上がりにしたい場合は

Claude Code、Codex、Cursor に完全版スキルをインストールすると、手持ちの素材に合わせて一本まるごとの映像を作ります。まずは無料の Motion Director で 20 秒の映像を。

スキルを見る