Skip to main content
skill CX Codex

alpha-cutout — Claude Code skill: what it does, how to install

The alpha-cutout Claude Code skill removes a clip’s background and prepares transparent animation for the web. It runs on requests for alpha video or a subject layered over page content.

MIT ★ 448 updated 2026-11-09

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add Moh4696/open-3d-skills
/plugin install open-3d-skills@open-3d-skills
Open on GitHub

What alpha-cutout does

The skill turns a character or product clip into an animation with a transparent background. It measures the chroma plate in each frame and restores edge colours to reduce colour fringing. Outputs include stacked-alpha MP4, VP9 alpha WebM, and WebP frame sequences for scroll-driven playback.

The package includes scripts/plate.py, scripts/key.py, and assets/alpha-video.js, a canvas player for stacked-alpha MP4. It requires Python 3.9+, numpy, opencv-python-headless, pillow, and ffmpeg on PATH. Video seeking needs a server that handles HTTP Range requests; python3 -m http.server does not support that requirement.

Remove the background from the still image with any background remover, then generate the clip against a flat chroma plate. If the subject touches the top edge, plate measurement fails. Stacked-alpha MP4 works in Safari; VP9 alpha WebM does not.

What it helps with

  • remove a clip background while keeping the subject’s edges
  • prepare transparent video to layer over page content
  • create WebP frames for scroll-controlled animation
  • reduce chroma-coloured fringes around a subject

Example prompts for the agent

  • Remove the background from clip.mp4 and prepare transparent video for a web page.
  • Turn this clip into WebP frames for scroll-driven playback.
  • Check the subject edges and prepare a transparent MP4 for Safari.

How to install alpha-cutout

1Plugin marketplace

/plugin marketplace add Moh4696/open-3d-skills
/plugin install open-3d-skills@open-3d-skills

This installs the whole open-3d-skills plugin with all its skills

2Skills CLI (Vercel)

npx skills add Moh4696/open-3d-skills --skill alpha-cutout -a claude-code

3Manually: put the files in place

~/.claude/skills/alpha-cutout/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/alpha-cutout/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about alpha-cutout

How do I install alpha-cutout in Claude Code?

Add the marketplace with /plugin marketplace add Moh4696/open-3d-skills, then install the skill with /plugin install open-3d-skills@open-3d-skills.

What does alpha-cutout do?

It removes a clip’s background and produces transparent animation as stacked-alpha MP4, VP9 alpha WebM, or WebP frame sequences. The chroma colour is measured separately in each frame.

What does alpha-cutout need to run?

It requires Python 3.9+, numpy, opencv-python-headless, pillow, and ffmpeg on PATH. Video seeking also requires a server that supports HTTP Range requests.

Source text

SKILL.md · MIT
---
name: alpha-cutout
description: Turns an AI-generated (or filmed) clip of a character or product into a transparent, web-ready animation by shooting it on a flat chroma plate and keying it with per-frame plate measurement and edge unmixing. Delivers stacked-alpha MP4 that plays with transparency in every browser including Safari, VP9 alpha WebM, or keyed WebP frame sequences for scroll scrubbing. Use when an animated subject has to sit over page content, between layers of type, or over a 3D scene, when someone asks for "transparent video", "video with alpha", "remove the background from this clip", or when a generated video has a background that should not be there.
---

# Alpha cutout

Image-to-video models never return alpha. A character that should stand between a giant headline and a sun disc, or a bottle that should float over a page, needs its background removed from every frame, cleanly enough that no fringe shows on any page colour. This skill does it the way a film studio does: shoot the subject on a flat key colour, then pull a matte per frame.

## Tools

| File | What it does |
| --- | --- |
| `scripts/plate.py` | Places a cut-out subject on a key plate with headroom; picks the key colour the subject clashes with least |
| `scripts/key.py` | Keys a clip or still into stacked MP4, VP9 alpha WebM, RGBA WebP frames or PNGs |
| `assets/alpha-video.js` | Plays a stacked-alpha MP4 with transparency on a canvas (WebGL), with `seek()` for scrubbing |

Needs Python 3.9+, `pip install numpy opencv-python-headless pillow`, and ffmpeg on PATH.

## Pipeline

1. **Cut the subject out of the still.** Any background remover works. Check what it dropped: thin objects (a ball in the air, racket strings, hair) often go missing. Put them back by hand.

2. **Make the plate.**

   ```bash
   python3 scripts/plate.py subject.png plate.png --size 1350x1800 --fit 0.8
   ```

   The script reports, for magenta, green and blue, how much of the subject sits close to that key, and picks the cleanest. Magenta is usually right: almost nothing in skin, clothing, product or foliage is pure magenta. Green fails on plants and green products; blue fails on denim and sky. The subject is pasted with a hard edge on purpose: a soft edge pre-mixed with the plate colour teaches the model to draw a fringe.

   Leave room for the motion. A serve needs space above the head; a turn needs space to the side. Match the plate's aspect to the video model's output aspect so nothing gets cropped.

3. **Generate on the plate.** Use the plate as the start frame (and as the end frame for a seamless loop; see `motion-assets`). The prompt must name the plate, or the model invents a background:

   > The background must remain a completely flat, uniform, pure chroma-key magenta (exact RGB 255, 0, 255) filling the entire frame, with no shadows, no floor, no gradient, no vignette and no scenery. Locked-off camera.

   **The prompt wins over the image.** A leftover "on a white background" in the prompt gets you a white background whatever the plate was. Re-read the prompt after every edit.

4. **Key it.**

   ```bash
   python3 scripts/key.py clip.mp4 --png check/ --frame-list 0,40,80,120   # inspect first
   python3 scripts/key.py clip.mp4 --stacked hero-1080.mp4 --width 1080
   python3 scripts/key.py clip.mp4 --stacked hero-720.mp4 --width 720      # phones
   python3 scripts/key.py clip.mp4 --frames serve/lg --width 960 --start 0 --end 78
   ```

   `--png` prints the plate colour it measured in each frame. Models drift the plate: a pure magenta can come back pale pink (250, 178, 243) halfway through while the subject keeps its colours. That is why the key colour is measured per frame from the frame's own border instead of being set once. If the subject touches the top edge, the measurement breaks and the script says so.

   Then, per pixel: alpha comes from how far the pixel's key excess is from the plate's, edge pixels are unmixed against the plate (`F = (C - (1 - a) K) / a`), and surviving spill is clamped. Unmixing matters. A plain colour-key or a clamp toward neutral turns magenta edge blends tan, which reads as a salmon outline on a white shirt; unmixing returns the real edge colour.

5. **Check on three backgrounds**: near-black, the page's light colour, and its loudest brand colour. Composite the `--png` output and look at the edges at 100% and 400%. Look hardest at hair, fingers, thin props, motion blur and the frame where the plate drifted most.

## Fixes

| You see | Do |
| --- | --- |
| A thin outline that follows the subject | `--erode 1` (rarely 2). The model copied a fringe into the artwork |
| Holes in light or shiny parts | That colour is too close to the key. Regenerate on a different key (`plate.py --key`) |
| Pink or green wash over the whole background | The plate gradient is stronger than usual; check the measured plate colours and raise `--solid` slightly |
| A detail changed colour mid-clip (a cap turned green) | Model drift, not a keying fault. Recolour that hue in those frames, or regenerate |
| Coloured line round the subject after compression | Already handled: colour under transparent pixels is the subject's own edge colour pushed outward, so chroma subsampling has nothing foreign to bleed in. `--fill` only sets the colour far from the subject |

## Which output

| Output | Plays in | Use for |
| --- | --- | --- |
| `--stacked` MP4 + `assets/alpha-video.js` | Every browser, Safari and iOS included | Looping heroes, characters, anything that plays |
| `--webm` VP9 alpha | Chrome, Edge, Firefox. Not Safari | A plain `<video>` tag where Safari support is not needed |
| `--frames` WebP sequence | Everywhere | Scroll-scrubbed motion (see `scroll-film`): exact frame per scroll position, no seeking lag |

Stacked alpha doubles the frame height (colour on top, matte below) and a shader recombines them, so it is plain H.264: it decodes in hardware everywhere and costs about 1.3 times the bytes of the colour alone. Ship two widths (1080 and 720) and choose by viewport.

```js
import { AlphaVideo } from "./alpha-video.js";
const hero = new AlphaVideo(document.querySelector("canvas.hero"), innerWidth > 900 ? "hero-1080.mp4" : "hero-720.mp4");
hero.onready = () => document.body.classList.add("hero-ready");
function frame() { hero.draw(); requestAnimationFrame(frame); }
requestAnimationFrame(frame);
```

The player pauses itself off screen and uploads a texture only when the video has moved on. For scrubbing, create it with `{ loop: false, autoplay: false }` and call `hero.seek(seconds)` from your scroll handler.

Serve videos from a server that answers HTTP Range requests (the `frame-capture` skill's serve.py does; `python3 -m http.server` does not), or seeking will not work.

## Reduced motion

With `prefers-reduced-motion: reduce`, show one keyed still (`--png` a good frame, convert to WebP) instead of the loop.

© exploraX · MIT · Moh4696/open-3d-skills

Similar skills

SKILL.md skills catalog →

From the same set9

site-check The site-check Claude Code skill checks 3D and animated web pages in Chromium and WebKit. Run it after page changes to catch browser errors, mobile layout issues, and slow frames before publishing. CX Codex +1 ★ 448repo stars exploded-view The exploded-view Claude Code skill builds interactive three.js explainers for machines and products. It animates parts in stages, reveals the casing’s interior, and attaches labels to the model. CX Codex +1 ★ 448repo stars motion-assets The motion-assets skill for Claude Code plans and generates images and video clips for animated websites. It activates for requests to create site visuals, loop a background, or animate an image. CX Codex +1 ★ 448repo stars cursor-rig The cursor-rig Claude Code skill turns an illustration into a portrait that follows the cursor with its head. It’s for adding a reactive character to a page without a 3D model or face tracking. CX Codex +1 ★ 448repo stars frame-capture The frame-capture skill for Claude Code records web pages to MP4 with frame-by-frame control of time. Use it to capture animations, page scrolls, or a comparison of two clips. CX Codex +1 ★ 448repo stars scroll-film The scroll-film Claude Code skill builds film-like page sections controlled by scrolling. It covers clip joins, caption pauses, frame loading and mobile versions. CX Codex +1 ★ 448repo stars threejs-scene This Claude Code skill builds interactive three.js scenes from code, without model files. It activates for 3D websites, WebGL hero sections and real-world objects rendered in 3D. CX Codex +1 ★ 448repo stars open-3d-skills The open-3d-skills Claude Code plugin adds skills for 3D scenes and animated websites. Its eight skills cover three.js builds, scroll-controlled films, and browser checks. CX Codex ★ 448repo stars

Project sponsors

Companies that keep this analytics open