Anatomy Reveal skill
The skill builds any object as an isometric figure of many parts and renders a reveal film that takes it apart
- 96 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Runs Node.js scripts and a browser to render and writes files and images into the project folder
- The build needs `ffmpeg` and ImageMagick installed, and the agent may offer to install them
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/anatomy-revealDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs Node.js scripts and a browser to render and writes files and images into the project folder
- The build needs `ffmpeg` and ImageMagick installed, and the agent may offer to install them
This is third-party code. Review the repository files before installing.
What it does
The skill assembles an object from its real dimensions out of many small convex parts: panels, screws, dials, glass, boards. The figure is drawn in ink on white paper, and the paint order is solved from separating planes. That model yields two outputs: an interactive page where the object is turned by dragging and taken apart on hover, and an MP4 film at 30 frames per second. The film comes in four ratios, 9:16, 4:5, 1:1 and 16:9, from 3 to 60 seconds long, 10 by default. The object tumbles in, the camera whips to macro shots of details, one feature is shown working, then the figure explodes into parts and snaps back with adaptive motion blur. The input is a photo of the object or just its name. A finished example ships with it: a dual-boiler espresso machine with a built-in grinder made of 82 parts.
Who it is for. Designers and product marketers who need an object teardown for social media, a landing page or a deck without a 3D editor.
Good fit when
- You need a 9:16 teardown film of an espresso machine or a sneaker for Reels and Shorts
- A product page would benefit from an interactive figure whose parts spread apart on hover
- You only have a photo of the object and no drawing, and the figure must be built from geometry
- You need a square 1:1 eight-second clip for Instagram
Not a fit when
- You need a photorealistic 3D model for a render: the skill draws a stylized ink figure
- Chrome, ffmpeg and ImageMagick 7 are missing and cannot be installed
- The subject is a living thing or abstract and does not break down into convex parts
Example request
Make a 10-second teardown film of my coffee grinder in 1:1 from the photo in the refs folderLimitations
- Node.js 20 or newer, Google Chrome, Chromium or Edge (otherwise set `CHROME_PATH`), `ffmpeg` and ImageMagick 7 with the `magick` command are required.
- The skill runs shell commands and a browser for rendering, so the agent needs terminal access.
- Rendering motion-blur frames takes noticeable time and disk space, especially for long films.
- The figure is built from convex solids using dimensions estimated from a photo or a name, so detail accuracy depends on how the agent reads the object.
How to disable. Delete the skill folder from the agent skills directory, for example `~/.claude/skills/anatomy-reveal`. Projects created by `scripts/new-project.mjs` live elsewhere and are removed with their own folder.
FAQ
How do I install Anatomy Reveal in Claude Code?
Clone the repository into `~/.claude/skills/anatomy-reveal` with the README command and open a new session. The skill loads from `SKILL.md`, after which you can ask for a teardown film.
Do I need a 3D model or a drawing of the object?
No, a photo or just a name is enough. The object is rebuilt from geometry using real dimensions and is never traced from a picture.
What video formats does it produce?
MP4 at 30 fps in 9:16 (1080 by 1920, the default), 4:5, 1:1 and 16:9. Length is set from 3 to 60 seconds, 10 by default.
Can I run the pipeline by hand without an agent?
Yes. `node scripts/new-project.mjs my-object` creates a project and `node motion/build.mjs --duration 10 --ratio 1:1` builds the film page. Then `npm run render` and `npm run encode` produce the MP4.
What is the interactive page in the output?
An HTML page with the figure: drag to turn it, hover to take it apart, press keys to work its features. A light version sits next to it as `figure-light.html`.
Discussion
No questions or reviews yet.
Related
SkillsA skill gives the agent 38 recipes of shots from launch films, rebuilt in code, and joins them into a product film.
A Claude Code skill for short animated videos drawn in code: seven styles, story and storyboard sign-off, voice-over and an MP4 render
A skill that turns your narration and real assets into a 20–60 second video in the style you pick, rendered locally as MP4.
A skill for a SaaS demo film in Remotion: brand intake, UI rebuilt from your site, beat-locked cuts and checked renders
A Claude Code skill that builds a Remotion film of your product from its own components, tokens and logo, cut to music
A skill that draws interactive isometric illustrations in SVG, with WebGL shaders and React output, explaining an idea as a working machine
README in short
The repository describes a skill that turns any object into a stylized figure and films it. The README lists requirements, installation into the skills directory, sample prompts and a by-hand script run. The references folder holds notes on look, shots and object composition, and template is a ready project with the geometry kit.
README badge
Original SKILL.md
--- name: anatomy-reveal description: Build any physical object (a product, a tool, furniture, an instrument, a shoe, a vehicle, a piece of jewellery, kitchenware, a toy, even a fruit or a flower) as a crafted isometric "anatomy" figure made of many small convex parts, then turn it into (1) an interactive dissection page you can drag, turn and take apart, and (2) a product-reveal film (MP4, 9:16, 4:5, 1:1 or 16:9, 30 fps, motion blur, white paper look, 10 s by default, any length from 3 to 60 s). The film tumbles in, whips to macro shots of the object's details, shows one feature working, explodes into its parts and snaps back together for a hero shot. Works from a photo of the object or from just its name. Use it when someone asks for an exploded view, a teardown or dissection drawing, an anatomy figure, or a product reveal or product motion video of an object. license: MIT compatibility: Node.js 20+, Google Chrome / Chromium / Edge (set CHROME_PATH if it is not found), ffmpeg, ImageMagick 7 (magick). Any agent that can run shell commands and write files. --- # Anatomy Reveal The object is never a stock 3D model or a traced picture. It is built part by part from its real dimensions, with the Anatomy kit's 3D mode (`template/kit`): - every panel, screw, dial, glass element and board is its own convex solid; - each part is shaded in four tones by how it faces the light; - parts are painted in an order solved from separating planes. Because the object is real geometry, the same model turns through any angle, comes apart, and drives both outputs. `template/` is a complete working project. Its worked example is a dual-boiler espresso machine with a built-in grinder (82 parts), but nothing in the pipeline is specific to espresso machines: any object the user names or shows works the same way. Start every job from the template and replace the object. Read before building: - `references/inputs.md`: getting from a photo or a name to dimensions, features and a parts list. - `references/objects.md`: how any kind of object comes apart, and how to build curved, organic, soft and large shapes from convex parts. - `references/object.md`: how to build the object so it turns through every angle and comes apart cleanly. - `references/shots.md`: the film's beats, the timeline format, eases and framing. - `references/look.md`: the paper look, materials and line weights. ## Inputs: two cases **A. The user uploads an image of the object.** - Study it for silhouette, proportions, materials, colours, surface decoration, visible controls, ports and markings, and anything that moves. - If you can tell what product it is, also look up its real dimensions and internals as in case B. Otherwise estimate the size from a feature of known size and say what you assumed. - The image is a reference only. Rebuild every shape, colour and ornament as geometry: never trace it, embed it, or map its pixels onto anything. **B. The user only names the object.** - Research the real product: - overall dimensions in millimetres, and the main sub-dimensions; - materials and colourways; - every visible control, port and marking; - how it opens, folds, slides or turns; - what is inside (teardowns are the best source). - Use web search when you have it. Without it, use what you know and list your assumptions. - If the name is ambiguous (a model family, several generations), pick the most common variant and say which. Either way, finish with a short spec before any geometry: the dimensions, the feature list, the parts list grouped by assembly, and the one or two features that will move in the film. Show it to the user if anything is uncertain. ## Workflow