Explainer / Tutorial

1. Can you use Opus 5.5 to make a video explaining "What is an Agent"? The video needs to be around 2 minutes long, in the form of a Chinese RAP. First output a script and overall plan. 2. Optimize the RAP lyrics, ensuring single and double rhymes. 3. Create a sample video for me to see first. 4. Use Suno to create the music. 5. It output two versions from Suno; I like the second one, so let's match the video length to the music duration.

Create an educational video explaining the physics behind Tesla's new Roadster staying upside down on a 20-meter high curved track during its launch event, then launching off a ramp and flipping in mid-air to land. Use 3D animation to explain how under-car fans suck the car onto the track and how gas tanks and jets push it into the air. Answer these questions: Is it like a roller coaster due to speed? How long can it fly? How does it flip in the air? Can tires handle 0-60mph in 0.81 seconds? What are the uses beyond stunts? Use Opus 5.5 for 3D modeling and animation.

Build a cinematic 3D animation explaining how a Tesla-style electric motor works.

Build an interactive 3D Li River diorama from scratch in three.js. Include karst peaks rising out of the river, drifting mist, a pavilion, a lantern raft, fog that clears under your cursor, and a day/night cycle with rain. Every model must be generated in code.

"Man is a rope, tied between beast and Overman—a rope over an abyss." — Nietzsche, Thus Spoke Zarathustra Based on this insight, create an explanatory video with incredible 2D animation, lasting 2-3 minutes. It must have coherent narration, dialogue, and sound. Shock me (truly demonstrate capabilities people didn't think were possible). Use up to 5 Agents. Use Edge TTS voice Yunjian (deep male voice).

Make a video explaining how to play the game with ElevenLabs CLI, 3D animations, lots of diagrams, no text.

"The Rings of a City", dedicated to my hometown. 3,573 frames, 7.4 billion pixels, 319 square kilometers, 71,380 buildings, scaled down at 1:10,000 ratio, all visuals rendered by Claude writing code. From 1250 BC to 2022 AD, compressing 3,271 years of history into 149 seconds. This is my hometown: Chengdu. If you like it, please support! Thanks! Data source: CMAB (Tsinghua University) ©OpenStreetMap contributors

Vertical 9:16 video, photorealistic satisfying renovation process, smooth motion, bright natural daylight. Empty room with white walls, window on the left, bare concrete floor. Shot 1: A man in blue work overalls uses a long-handled shovel to spread a huge pile of small orange and green heart-shaped candies, levelling them into an even layer across the entire floor. Shot 2: A woman in red overalls pours thick glossy white self-leveling epoxy resin from a white bucket; the liquid flows and spreads over the candy layer, gradually covering the hearts. Shot 3: A worker in a yellow reflective vest grinds and polishes the hardened floor with a professional floor polishing machine, revealing orange and green hearts embedded under glossy white resin, like colorful terrazzo. Shot 4: Two workers assemble a wooden bed frame on the new floor, place a white mattress, pillows and bedding. Final shot: Slow camera tilt down over the finished bedroom, showing the unique glossy heart-pattern epoxy floor next to the neatly made bed. Realistic physics of pouring liquid and loose candy, consistent lighting, seamless cuts between shots, high detail, no text.

Create a cinematic, ultra-realistic food video showing chicken biryani preparation in a rustic kitchen. Show onions being sliced, chicken coated in golden yogurt marinade, and spices sizzling in a traditional copper pot over a blue gas flame. Add marinated chicken, fluffy basmati rice, saffron-colored liquid, fried onions, and fresh herbs. Capture bubbling gravy, rising steam, realistic stirring, and natural ingredient movements. End with the lid lifting to reveal beautifully layered golden and white rice with tender chicken, followed by a macro close-up of the finished biryani garnished with fresh mint and lemon. Warm cinematic lighting, detailed food textures, realistic cooking physics, smooth camera movements, appetizing presentation, vertical 9:16, 30 seconds, no text, no logos, no watermark.

Reverse engineer [product] from these reference images: 1. Write down the proportions and list every visible part with the frame it appears in. 2. Build it in three.js with each part as a separate mesh. 3. Label every part with what it does and a confidence level. No frame, no claim: anything not visible is marked unknown. 4. Timeline: assemble, move, explode the parts with labels, reassemble. 20 seconds. 5. Use a deterministic render(t), render 30 fps frames and stitch them with ffmpeg. Show me the parts list with frames before writing any code.

Create an explainer video for Tesla FSD using the YouMind skill + Opus 5.5. Generate script, voiceover, BGM, and motion graphics all within YouMind, without external design tools.

GROK + JEV + OPUS 5.5 checked how thick a sheet of paper gets if you fold it 42 times, and it ends up past the Moon... a normal sheet is 0.1 mm. fold it in half, then again. 42 times most people guess a few metres question → explain → check → calculate → animate Grok took the explanation: every fold doubles the stack. so each fold adds more than all the folds before it put together Jev checked the math: 0.1 mm × 2⁴² = 439,805 km. the Moon is 384,400 km away Opus 5.5 ran every fold 10 folds: 10 cm, a phone 17 folds: 13 m, a 4-storey house 23 folds: 839 m, taller than Burj Khalifa 27 folds: 13 km, above Everest 30 folds: 107 km, edge of space 42 folds: 439,805 km, past the Moon 51 folds: 225 million km, past the Sun the strange part: after 39 folds you're only 14% of the way. the last 3 folds do 88% of the trip where this actually shows up: you can't really do it. the record is 12 folds, set by a student in 2002 with a strip of paper over a kilometre long the chessboard story: 1 grain of rice on the first square, double on each next one. the board ends with about 18 quintillion grains anything that doubles looks like nothing for a long time, then like everything at once 0.1 mm, 42 folds, 439,805 km ↓ save this

Do a deep dive into the history of optogenetics and create an explainer video for the 2026 Nobel Prize in Physiology or Medicine. Cover the contributions of Boyden, Pan, Deisseroth, Nagel, Hegemann, Bamberg, Miesenböck, Zhang, and 15 others.

Create explainer videos of how various steam frame steamOS utility apps are built. For example, @DeeJzNuts's frametop.

Grok Imagine Video Montage Prompt Create a clean, high-quality 30–40 second futuristic tech montage showing piezoelectric road tiles that generate electricity from passing electric vehicles and store it for later cars. Style notes (apply to all shots...

Build a simulation of a 9-cylinder radial engine in Three.js. Include cutaway view of cylinders, master rod and articulated rods, variable-pitch propeller, and real-time updates for RPM, torque, and pressure. Add controls for start, throttle, and magneto. Allow orbiting, exploding the view, and observing mechanics.

Make a video of neurons in the brain, overreacting, funny. This is your brain and goofballs

Build "Gummy Bears" - a single self-contained HTML file (three.js from a CDN is the only dependency): a handful of translucent gummy bears on a white table that you can grab, stretch, squash, throw and pour. The bears - Classic gummy bear silhouette: round head with two ears, short snout, plump body, stubby arms and legs, tiny molded eyes and nose - Every part melts smoothly into the next - build the body as an implicit surface (metaballs / marching cubes), not separate spheres - Material: real gummy candy. Translucent with transmission and refraction, colored light absorption that gets deeper in thick parts, glossy clearcoat with sharp highlights - Colors: cherry red, orange, lemon yellow, apple green, clear pineapple - Soft colored shadow under each bear, tinted by the bear's own color Physics (this is the whole point - it must feel like jelly, not plastic) - Each bear is a soft body: mass points for head, ears, snout, body, belly, hands and feet, held together by volume-preserving shape matching - Limbs and neck are rendered as stretchy strands between points, getting thinner as they stretch - Grab any part and pull: it stretches like rubber, the rest of the bear leans after it, on release it snaps back with a damped wobble - Pull the head up: the neck stretches, the body follows, on release the bear squashes and hops - Press down on the head: the bear pancakes, bulges sideways, then launches itself back up - Throw a bear: it flies, squashes on landing, bounces and pushes other bears out of the way - Bears collide with each other and never pass through one another - Idle bears do small random hops with squash and stretch - "Pour more bears" drops a handful from above into a wobbling, jiggling pile UI - Editorial product-page style on a white background. Large italic serif title "Gummy / Bears.", a short subtitle, a minimal card on the right with flavor swatches, a wobble slider, live "Stretch" and "Bounces" readouts and a "Pour more bears" button - A subtle circular cursor that grows while grabbing - ACES tone mapping, environment reflections, soft key and back light. Smooth 60fps