YouMind
Sign in

Explainer / Tutorial

Explore free Explainer / Tutorial video prompts from YouMind's AI prompt library, grouped under use cases. Every prompt is curated from real creative workflows and ready to copy, adapt, and reuse.

306 promptsDaily highlights
Claude Opus 5.5
View full prompt & copy

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

Generate video
Claude Opus 5.5
View full prompt & copy

I had Claude Code (Opus 5.5) create a 3D diagram of a piston and crank moving in Three.js overnight from a one-line request. The work took 8 minutes. ■ What was created - Piston, connecting rod, crank (main shaft, arm, pin, flywheel), transparent cylinder, head, spark plug, flame in the combustion chamber - A vertical 1080x1920 @ 30fps video, 32 seconds long, using Remotion - No image assets were used at all. Parts and flames are all drawn with code. ■ How it works - The height of the piston and the angle of the connecting rod are calculated every frame using formulas based on the crank's angle. - Since it's a 4-stroke engine, the combustion chamber lights up only once every 720°, right after top dead center. - The lines for part labels are drawn by projecting 3D points onto the screen using the same camera. So even if you rotate or zoom around, the lines correctly point to the parts. ■ How to make it (3 steps) 1. The request was just one line: "Make a rotatable and zoomable 3D diagram of piston and crank movement in Three.js" 2. Assemble it using only the pre-installed @remotion/three and @react-three/fiber. No additional installations. 3. Check intermediate still images 3 times, fix the orientation of the piston rings, camera distance and height, and overlapping of labels and graphs before exporting. Even with headless rendering (--gl=angle), the 3D model comes out as is, and the export finished in one go. ■ Notes - I didn't install or try the 'Anatomy' skill from the original post. I just assembled it with my local Three.js setup. - The flame is made of semi-transparent glowing cylinders and point lights. I didn't do WebGL shader-based fire, water, or plasma like the original post. - The counterweights on the crank have simplified shapes, so depending on the angle, some frames may look like dark boards. - Viewers cannot rotate or zoom themselves. The camera moves within the video to show different angles.

Generate video
Claude Opus 5.5
View full prompt & copy

Create an illustrative security workflow video with the following scenes: i. map: Show the repo, dependencies, access rules, and logs being built into a map before following the attack. ii. trace: Follow user input into raw SQL, highlighting where untrusted data reaches the query. iii. hold: Fuzzing hits orders.py, an exploit is flagged, and the workflow puts the merge on HOLD. iv. patch: Apply the fix and check whether the original exploit still works. v. attack again: A red-team subagent goes after the patched code. Display the instruction on screen: “fix it · then try to break it again.” The agent’s own work becomes the next target. vi. hand it over: Open the PR, keep the security advisory private, and wait for human approval. Highlight that the interesting part happens after the patch: another attempt to break it. Final line on screen: “opus never merges alone” Theme: Attack your own fix. Earn the human’s yes.

Generate video
Claude Opus 5.5
View full prompt & copy

Create a 30-second explainer video from the attached hrv_recovery_log.csv file. Visual style: White background, very little text. Rules: 1. Calculate every number from the CSV. 2. Show relationships without claiming causation. Key insights to display: > SLEEP - "a positive impact on recovery" > ALCOHOL - hurt recovery "by quite a bit" > LATE MEALS - 70.2 ms without, 58.1 with, -12.1 ms > WORKOUTS - "some impact on recovery, but not a ton" Takeaway message: "get plenty of sleep and don't drink too much."

Generate video
Claude Opus 5.5
View full prompt & copy

Build a live trait scanner interface for a Pudgy Penguin NFT. Subject: One specific Pudgy Penguin image. Pipeline: Hair -> Eyes -> Medal -> Full Scan -> Grade. Steps: 1. Lock one subject and one pipeline: hair, eyes, medal, full scan, then the grade. 2. Write the trait dictionary first so the model never invents parts that are not on the body. 3. Build the center stage: the penguin, the aim reticle, the FULL SCAN badge. 4. Add the left read as traits only: afro, pick, eyes, beak, fur, medal, ribbon, aura. 5. Add the right read as scan stats only: conf, depth, rate, lock, sway. 6. Wire the lower deck last: star path, crystal ball, rune track, mana curve. 7. Play the scan end to end and fix one panel at a time until the lock feels real. Rules: - One step owns one read. - The verdict never runs before the full silhouette is locked. Start with one penguin, then the next scan is just a new subject in the same machine.

Generate video
Claude Opus 5.5
View full prompt & copy

Produce an 82-second tech news video covering four topics. 1. Script: Rewrite briefing into colloquial narration, sentence by sentence. Visuals only show facts present in the briefing. 2. Voiceover: Synthesize Chinese male voice locally using VoxCPM2, verify with Whisper transcription. 3. Music: Generate pure music locally using YuE2 (jazz-hop style), auto-ducking for voice. 4. Visuals: Render HTML + GSAP animations into video using HyperFrames. Swiss-style typography, whitespace for screenshots. 5. Alignment: Measure actual duration of each voiceover line; sync camera, subtitles, and numbers to audio.

Generate video
Loading more prompts

FAQ

Where do YouMind prompts come from?
YouMind curates high-signal AI prompt examples from creator communities and public creative workflows. The library focuses on prompts that are useful to inspect, reuse, and adapt.
How are video prompt categories organized?
Video prompts are grouped into use cases, styles, and subjects. Use cases cover the production goal, styles cover motion or rendering language, and subjects describe the main scene or entity.
How are prompts assigned to categories?
YouMind uses AI to analyze each video prompt, its title, metadata, and generated result when available, then assigns the closest categories. Editors can refine categories as the taxonomy evolves.
What is YouMind?
YouMind is an AI workspace for turning research, ideas, and creative references into usable outputs. The prompt library is one public part of that workflow, built to help creators learn from strong examples faster.