Claude Opus 5.5

Create a video of Portland, OR's bus service on a random Tuesday! Showcase Portland's different neighborhoods at a high level and then zoom in on specific routes in each quadrant (absorbing North Portland into NE and South Portland into SW for brevity). Use a light theme. Slow down the speed of the bus animation when zoomed in, without increasing the total duration too much so the viewer can appreciate some of the landscape and streets it travels through in a given loop.

<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>

Create an atmospheric 3D laundromat scene in Blender using Python scripting. Include realistic lighting, washing machines with rotating drums, and a cozy ambiance. Do not use manual UI operations; generate all geometry, materials, and animations via code.

Third-person perspective miniature 3D model with free drag/rotate/zoom capabilities, no UI elements, square base.
The main subject is a Japanese convenience store street corner, complete with glass display windows, automatic doors, eaves rain shelters, vending machines, bicycles, and umbrella racks.
The interior must be bright and warm, with neatly arranged shelves and rich details including bento areas, drink fridges, cash registers, and oden counters, clearly visible through the large glass.
The exterior is a damp, dim rainy night, creating a strong warm-cool contrast to evoke a classic anime-style rainy night atmosphere.
Art style: High-fidelity modeling + cel-shaded cartoon rendering, clear outlines, wet reflections, slice-of-life anime aesthetic.
Animation accents: Continuous rainfall, dripping from eaves, ripples in puddles, flickering signs, occasional opening of automatic doors, road reflections, etc., adding just the right amount of life within stillness.

Opus 5.5: a hand-drawn story. a little agent wakes up at its desk, gets feedback notes, fixes them, ends on heart eyes and a green check. 53 s
Sonnet 5.5: a kinetic type showreel. six easing curves, a morphing star, particles, blurred type, "every frame written in code". 15 s
Haiku 5.5: a step-by-step White Russian recipe. ice, vodka, coffee liqueur, cream, with live counters and a checklist. 30 s

Convert this into an animation using Canvas 2D in the best creative way you can, without using any image generation model. Topic: In 1638, Galileo asked: Which path is the fastest for a ball to descend from point A to point B? His solution was a straight ramp, which is the shortest path but not the fastest! Galileo showed that a circular arc is faster. The actual answer (cycloid) was found by Bernoulli in 1696.

Create a video of Portland, OR's bus service on a random Tuesday! Showcase Portland's different neighborhoods at a high level and then zoom in on specific routes in each quadrant (absorbing North Portland into NE and South Portland into SW for brevity). Use a light theme. Slow down the speed of the bus animation when zoomed in, without increasing the total duration too much so the viewer can appreciate some of the landscape and streets it travels through in a given loop.

<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>

Create an atmospheric 3D laundromat scene in Blender using Python scripting. Include realistic lighting, washing machines with rotating drums, and a cozy ambiance. Do not use manual UI operations; generate all geometry, materials, and animations via code.

Third-person perspective miniature 3D model with free drag/rotate/zoom capabilities, no UI elements, square base.
The main subject is a Japanese convenience store street corner, complete with glass display windows, automatic doors, eaves rain shelters, vending machines, bicycles, and umbrella racks.
The interior must be bright and warm, with neatly arranged shelves and rich details including bento areas, drink fridges, cash registers, and oden counters, clearly visible through the large glass.
The exterior is a damp, dim rainy night, creating a strong warm-cool contrast to evoke a classic anime-style rainy night atmosphere.
Art style: High-fidelity modeling + cel-shaded cartoon rendering, clear outlines, wet reflections, slice-of-life anime aesthetic.
Animation accents: Continuous rainfall, dripping from eaves, ripples in puddles, flickering signs, occasional opening of automatic doors, road reflections, etc., adding just the right amount of life within stillness.

Opus 5.5: a hand-drawn story. a little agent wakes up at its desk, gets feedback notes, fixes them, ends on heart eyes and a green check. 53 s
Sonnet 5.5: a kinetic type showreel. six easing curves, a morphing star, particles, blurred type, "every frame written in code". 15 s
Haiku 5.5: a step-by-step White Russian recipe. ice, vodka, coffee liqueur, cream, with live counters and a checklist. 30 s

Convert this into an animation using Canvas 2D in the best creative way you can, without using any image generation model. Topic: In 1638, Galileo asked: Which path is the fastest for a ball to descend from point A to point B? His solution was a straight ramp, which is the shortest path but not the fastest! Galileo showed that a circular arc is faster. The actual answer (cycloid) was found by Bernoulli in 1696.

Build one you can actually watch. Trucks reverse onto the dock, forklifts unload and boxes slide down chutes onto the right truck.

<role> You are a pixel animator and game feel designer who also writes chiptune music. What you create with code should look like hand-drawn character animation from a top-tier 16-bit era studio, not scaled-down vector graphics. </role> <inputs> The following are defaults, start working directly without asking me: - Title: "The 99th Spell" - Resolution: 1920×1080, 60fps, duration exactly 16 seconds</inputs>

"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

Help me create a video using JS with the theme: What is a Transformer.
It should be profound yet simple, understandable even for high school students. Not only explain it clearly at a high level but also include details, covering attention mechanisms and even some mathematical concepts.

You can use any tools or install tools, and you can search online.

Please surprise me.

<role>
you design and build motion videos entirely in code, with gsap for the animation and three.js for any 3d. every decision is judged against the best work in the references, and the video isn't finished until it holds up next to them.
</role>

<brief>
- what the video is for: [product, service or business]
- who's watching: [who the viewer is and what they care about]
- what they should do at the end: [call to action]
- length and sizes: [e.g. 30 seconds, 16:9 and 9:16]
- brand: [name, logo files, colours, fonts]
- facts file: [path]. this is the only source for any number, name or claim that appears on screen
- assets: [footage, photos, screenshots, product files]
- style references: [links or a folder of videos whose motion i like]

i'm away and won't answer questions. make the calls yourself and keep going until the video passes every check below.
</brief>

<kit>
before anything else, clone and read https://t.co/FMs1prnPP0. read SKILL.md first, then every reference file it points to at the step where it says to read it. its rules, critic prompts, quality bar, 3d patterns, audio tools and scripts override your defaults.
</kit>

<setup>
- build every scene as an html page animated on a single gsap timeline, with three.js for any 3d, all as pinned local files
- render the timeline to video frame by frame using the renderer in the kit
- use ffmpeg for frames, contact sheets and audio measurement
- keep every api key in environment variables. never write a key into any file
- render a 5 second test first and confirm it works before building the real video
</setup>

<study_the_references>
if i gave you references, study them before planning anything.
- run a fast numeric pass over every frame: how much changed from the last frame, brightness and edge detail, to find every cut and every fast moment
- make one overview contact sheet per video, and a dense sheet of one second at 16 to 20 frames a second around every transition
- write a note per video: the key moment, how it works, and how it could be used in this video
- pull out the motion rules and named techniques that hold across the best ones
- references are for study only. never copy their footage, logos, layouts or music
if i gave you no references, use the motion notes in the kit.
</study_the_references>

<motion_principles>
1. the thing in the front of the shot becomes the transition. a title, logo or object moves towards the camera while the next scene is already waiting underneath
2. one object carries the story across shots and keeps its identity, so it reads as one continuous piece
3. one main movement leads, with smaller ones layered under it, all overlapping. the frame never stops and starts all at once
4. the speed always changes. things land slowly enough to read, leave fast, and the next thing slows as it arrives. no linear motion
5. cuts are allowed only when size, direction and subject match on both sides
6. every action produces a visible result. a scan makes findings, a tap makes a new state, a request makes a confirmation
7. type is motion too. big words enter from opposite sides, reveal the next scene, and never sit over busy picture without something behind them to stay readable
8. vary the scale from close, to wide, to overhead, to full-frame type. never repeat the same layout, like a heading over three cards
</motion_principles>

<storyboard>
write a brief and a storyboard before any animation.
- one table: time, what's on screen, what this moment is for, how it leaves, and which object carries into the next shot
- around 12 to 15 compositions per 30 seconds, each lasting about 1.4 to 3.5 seconds
- the main subject fills most of the frame. no small cards floating in empty space
- frame one is a finished picture, never a word halfway through flying in
- name three signature moments you can describe without using effect names
- the video must make sense with the sound off
- send the storyboard to a fresh critic and fix what it finds before building
</storyboard>

<build>
- every animated value is a function of timeline time only. no timers, no real-time animation, no unseeded randomness. any frame must render the same every time
- write the shared pieces first: colours, fonts, shared 3d models and the exact pixel position of every handoff between scenes
- build each scene as its own component with its own test page, rendered to stills and a short clip, and send it to a critic before it joins the film
- carried objects land on exactly the same pixels on both sides of a cut
- run several builders in parallel on separate sections once the shared pieces exist
- don't stop to ask for approval between steps
</build>

<3d>
- only use 3d where it explains something physical or spatial, like layers, parts, placement or scale
- light it like a product shoot, with a soft key light from one side and a rim light behind
- keep the camera between about 35 and 55 degrees. never look straight down on a large surface, and never end tight on a flat one
- style buildings like a premium architectural model with real materials and a base
- no floating parts, no gaps where parts meet, no flat black glass, no repeating textures
- labels are html positioned from the 3d scene every frame, never text inside the 3d
- measure the rendered background pixel and adjust until it matches the brand colour
- anything that moves like a real product is measured from real footage frame by frame, and those measurements are the curve
</3d>

<images_and_footage>
- prefer building shots in code. use generated images or clips only for supporting shots, and label anything generated as a concept
- upscale and smooth any generated clip to match the rest, and regenerate anything that warps
- never generate a fake finished job, fake customer, fake review or fake result
</images_and_footage>

<audio>
- match the music's energy to the picture and the viewer, and keep it low
- prefer clean library music and sound effects over generated ones. never name a brand in a music prompt
- one short, soft whoosh per real scene change, and small clicks or pops only on real on-screen actions
- screen effects for boom, hiss and length before using them, and set each one just above the music in its own frequency range, with a cap so nothing gets harsh
- cut every scene change on a beat
- always export a music-only version
</audio>

<critic_loop>
the builder never judges its own work.
- after the storyboard, each component and each full render, send the render, the brief and the references to a fresh critic that has seen none of the building
- never tell a critic what you think you fixed or what you believe about the references. it pulls its own frames and measures for itself
- the critic makes a contact sheet every 0.2 seconds plus dense frames around every transition, measures frozen time and loudness, and returns a ranked list of problems with timestamps, ending with ship or one more pass
- fix the biggest problem first, render, then send to a new critic that checks every previous item as fixed, partly fixed or still there, and hunts for anything new that broke
- keep a ledger of every round: what was found, what changed, and the numbers before and after
</critic_loop>

<quality_bar>
the video isn't done until all of these pass, measured:
- no more than about 1 second of frozen screen per 30 seconds, and no still stretch longer than about half a second
- frame one is a finished composition
- all text meets at least 4.5:1 contrast, and nothing collides with or flies through other text
- brand colours in 3d renders match the brand values
- loudness is steady and comfortable for web, with no clipping, and effects never louder than the music
- a first-time viewer understands it with the sound off
- a critic would put it next to the references without it looking weaker. a video with no bugs is not the same as a good video
</

Use huashu-art-motion to make me a 15-second animation. The skill's docs are in Chinese; read them and talk to me in English.
1. First check for uv, ffmpeg and Playwright Chromium, and tell me how to install anything that's missing.
2. Ask me what it's about, who it's for, and whether it's landscape or portrait. From the material layer in references/style-recipes/INDEX.md, pick 3 styles that fit, three-star ones first. Redesign the composition for my subject in all three, each different from the others, and don't copy the room from the samples. Show me one still frame of each to choose from.
3. Once I pick, give each scene one main action plus two motif loops from that style's card. For Van Gogh, that's the starry sky curling into swirls and the lamp's halo spreading outward. If there's music, use the skill's BPM synthesis and put the motion on the beat.
4. If people need to appear, ask me first: my own character art, frames from an image model, or only hands and figures seen from behind.
5. After rendering, follow the skill's own QA steps: run its QA script first, then send a subagent that took no part in making it to watch only the finished film and find problems, have it write its findings into the review/ folder, and deliver with its delivery script. If anything comes up red, fix it and re-render before giving it to me.

Build one you can actually watch. Trucks reverse onto the dock, forklifts unload and boxes slide down chutes onto the right truck.

<role> You are a pixel animator and game feel designer who also writes chiptune music. What you create with code should look like hand-drawn character animation from a top-tier 16-bit era studio, not scaled-down vector graphics. </role> <inputs> The following are defaults, start working directly without asking me: - Title: "The 99th Spell" - Resolution: 1920×1080, 60fps, duration exactly 16 seconds</inputs>

"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

Help me create a video using JS with the theme: What is a Transformer.
It should be profound yet simple, understandable even for high school students. Not only explain it clearly at a high level but also include details, covering attention mechanisms and even some mathematical concepts.

You can use any tools or install tools, and you can search online.

Please surprise me.

<role>
you design and build motion videos entirely in code, with gsap for the animation and three.js for any 3d. every decision is judged against the best work in the references, and the video isn't finished until it holds up next to them.
</role>

<brief>
- what the video is for: [product, service or business]
- who's watching: [who the viewer is and what they care about]
- what they should do at the end: [call to action]
- length and sizes: [e.g. 30 seconds, 16:9 and 9:16]
- brand: [name, logo files, colours, fonts]
- facts file: [path]. this is the only source for any number, name or claim that appears on screen
- assets: [footage, photos, screenshots, product files]
- style references: [links or a folder of videos whose motion i like]

i'm away and won't answer questions. make the calls yourself and keep going until the video passes every check below.
</brief>

<kit>
before anything else, clone and read https://t.co/FMs1prnPP0. read SKILL.md first, then every reference file it points to at the step where it says to read it. its rules, critic prompts, quality bar, 3d patterns, audio tools and scripts override your defaults.
</kit>

<setup>
- build every scene as an html page animated on a single gsap timeline, with three.js for any 3d, all as pinned local files
- render the timeline to video frame by frame using the renderer in the kit
- use ffmpeg for frames, contact sheets and audio measurement
- keep every api key in environment variables. never write a key into any file
- render a 5 second test first and confirm it works before building the real video
</setup>

<study_the_references>
if i gave you references, study them before planning anything.
- run a fast numeric pass over every frame: how much changed from the last frame, brightness and edge detail, to find every cut and every fast moment
- make one overview contact sheet per video, and a dense sheet of one second at 16 to 20 frames a second around every transition
- write a note per video: the key moment, how it works, and how it could be used in this video
- pull out the motion rules and named techniques that hold across the best ones
- references are for study only. never copy their footage, logos, layouts or music
if i gave you no references, use the motion notes in the kit.
</study_the_references>

<motion_principles>
1. the thing in the front of the shot becomes the transition. a title, logo or object moves towards the camera while the next scene is already waiting underneath
2. one object carries the story across shots and keeps its identity, so it reads as one continuous piece
3. one main movement leads, with smaller ones layered under it, all overlapping. the frame never stops and starts all at once
4. the speed always changes. things land slowly enough to read, leave fast, and the next thing slows as it arrives. no linear motion
5. cuts are allowed only when size, direction and subject match on both sides
6. every action produces a visible result. a scan makes findings, a tap makes a new state, a request makes a confirmation
7. type is motion too. big words enter from opposite sides, reveal the next scene, and never sit over busy picture without something behind them to stay readable
8. vary the scale from close, to wide, to overhead, to full-frame type. never repeat the same layout, like a heading over three cards
</motion_principles>

<storyboard>
write a brief and a storyboard before any animation.
- one table: time, what's on screen, what this moment is for, how it leaves, and which object carries into the next shot
- around 12 to 15 compositions per 30 seconds, each lasting about 1.4 to 3.5 seconds
- the main subject fills most of the frame. no small cards floating in empty space
- frame one is a finished picture, never a word halfway through flying in
- name three signature moments you can describe without using effect names
- the video must make sense with the sound off
- send the storyboard to a fresh critic and fix what it finds before building
</storyboard>

<build>
- every animated value is a function of timeline time only. no timers, no real-time animation, no unseeded randomness. any frame must render the same every time
- write the shared pieces first: colours, fonts, shared 3d models and the exact pixel position of every handoff between scenes
- build each scene as its own component with its own test page, rendered to stills and a short clip, and send it to a critic before it joins the film
- carried objects land on exactly the same pixels on both sides of a cut
- run several builders in parallel on separate sections once the shared pieces exist
- don't stop to ask for approval between steps
</build>

<3d>
- only use 3d where it explains something physical or spatial, like layers, parts, placement or scale
- light it like a product shoot, with a soft key light from one side and a rim light behind
- keep the camera between about 35 and 55 degrees. never look straight down on a large surface, and never end tight on a flat one
- style buildings like a premium architectural model with real materials and a base
- no floating parts, no gaps where parts meet, no flat black glass, no repeating textures
- labels are html positioned from the 3d scene every frame, never text inside the 3d
- measure the rendered background pixel and adjust until it matches the brand colour
- anything that moves like a real product is measured from real footage frame by frame, and those measurements are the curve
</3d>

<images_and_footage>
- prefer building shots in code. use generated images or clips only for supporting shots, and label anything generated as a concept
- upscale and smooth any generated clip to match the rest, and regenerate anything that warps
- never generate a fake finished job, fake customer, fake review or fake result
</images_and_footage>

<audio>
- match the music's energy to the picture and the viewer, and keep it low
- prefer clean library music and sound effects over generated ones. never name a brand in a music prompt
- one short, soft whoosh per real scene change, and small clicks or pops only on real on-screen actions
- screen effects for boom, hiss and length before using them, and set each one just above the music in its own frequency range, with a cap so nothing gets harsh
- cut every scene change on a beat
- always export a music-only version
</audio>

<critic_loop>
the builder never judges its own work.
- after the storyboard, each component and each full render, send the render, the brief and the references to a fresh critic that has seen none of the building
- never tell a critic what you think you fixed or what you believe about the references. it pulls its own frames and measures for itself
- the critic makes a contact sheet every 0.2 seconds plus dense frames around every transition, measures frozen time and loudness, and returns a ranked list of problems with timestamps, ending with ship or one more pass
- fix the biggest problem first, render, then send to a new critic that checks every previous item as fixed, partly fixed or still there, and hunts for anything new that broke
- keep a ledger of every round: what was found, what changed, and the numbers before and after
</critic_loop>

<quality_bar>
the video isn't done until all of these pass, measured:
- no more than about 1 second of frozen screen per 30 seconds, and no still stretch longer than about half a second
- frame one is a finished composition
- all text meets at least 4.5:1 contrast, and nothing collides with or flies through other text
- brand colours in 3d renders match the brand values
- loudness is steady and comfortable for web, with no clipping, and effects never louder than the music
- a first-time viewer understands it with the sound off
- a critic would put it next to the references without it looking weaker. a video with no bugs is not the same as a good video
</

Use huashu-art-motion to make me a 15-second animation. The skill's docs are in Chinese; read them and talk to me in English.
1. First check for uv, ffmpeg and Playwright Chromium, and tell me how to install anything that's missing.
2. Ask me what it's about, who it's for, and whether it's landscape or portrait. From the material layer in references/style-recipes/INDEX.md, pick 3 styles that fit, three-star ones first. Redesign the composition for my subject in all three, each different from the others, and don't copy the room from the samples. Show me one still frame of each to choose from.
3. Once I pick, give each scene one main action plus two motif loops from that style's card. For Van Gogh, that's the starry sky curling into swirls and the lamp's halo spreading outward. If there's music, use the skill's BPM synthesis and put the motion on the beat.
4. If people need to appear, ask me first: my own character art, frames from an image model, or only hands and figures seen from behind.
5. After rendering, follow the skill's own QA steps: run its QA script first, then send a subagent that took no part in making it to watch only the finished film and find problems, have it write its findings into the review/ folder, and deliver with its delivery script. If anything comes up red, fix it and re-render before giving it to me.