viz3d ยท diff
git:20261104.bc2fde5 to git:20261104.b2e77d0
25 added, 5 removed. Audit A to A.
---
name: viz3d
description: Start the visualize-in-3d skill from a command, with an optional mode and look first and then the subject, for example "/viz3d film white model the 1906 San Francisco earthquake". With no request it shows the menu of modes and looks.
- argument-hint: "[app|lesson|prototype|embed|film|action|showcase|book|game] [look] <subject>"
+ argument-hint: "[app|lesson|prototype|embed|film|doc|action|showcase|book|game] [look] <subject>"
disable-model-invocation: true
---
# viz3d
The user started viz3d with this request:
$ARGUMENTS
In tools that do not fill in the line above, the request is the rest of the user's message.
1. If the request is empty or is `help`, show the menu below as it is, then ask one question: what do you want to
make 3D? Stop there.
2. Otherwise load the `visualize-in-3d` skill and follow it from the start. It is installed next to this one
(`../visualize-in-3d/SKILL.md`).
- 3. If the first word is a mode, use that shape and drop the word from the subject. Otherwise pick the shape from the
- subject with the skill's table.
- 4. If the request names a look, use the matching section of `references/looks.md`. Otherwise use the default look for
- the shape (looks.md, Choosing).
+ 3. Read the request from the left: an optional mode word, then an optional look word (one or two words, from the
+ table below), then the subject. A look word may also come first when there is no mode. Drop the mode and look
+ words from the subject. Match whole words, in any case, and take the longest match (`dark documentary` is one
+ look). Text in quotes is always subject, so `/viz3d "film noir city"` is a subject, not a mode.
+ 4. With no mode word, pick the shape from the subject with the skill's table. A named look that fits only one shape
+ settles it (`plate` is a book). When the subject still fits more than one shape, ask one question that names
+ them, for example: watch it, play it, learn how it works, or open it up?
+ 5. A look the user names always wins over the default. With no look word, use the default look for the shape
+ (`references/looks.md`, Choosing).
+
+ | Look word | Section of `references/looks.md` |
+ |---|---|
+ | `ops` | Clean ops world |
+ | `toy` | Toy isometric |
+ | `lived-in` | Lived-in isometric |
+ | `terrain` | Photoreal terrain analysis |
+ | `documentary`, `dark` | Dark documentary |
+ | `white model` | White model documentary |
+ | `layer build` | Layer build film |
+ | `point cloud` | Point-cloud survey |
+ | `plate`, `cutaway` | Illustrated cutaway plate |
+ | `pixel` | Pixel diorama |
+ | `ASCII` | Dither + ASCII showcase |
+ | `glow` | Gradient glow ASCII |
## Menu
**Modes**, by what you want people to do with it:
| Watch it | Explore it | Put it in your product |
|---|---|---|
| `film` or `doc`: documentary film of a story or event | `app`: live 3D app with a dashboard and a 30 s film | `prototype`: quick prototype from primitives, no Blender |
| `action`: action short, things fighting, chasing, launching | `lesson`: a real object built and explained step by step | `embed`: live 3D view inside your dashboard, on your data |
| `showcase`: a film or stills that show off one object or model | `book`: illustrated cutaway plate, or a book with quizzes | |
| | `game`: playable browser game | |
**Looks**, in four families:
| Clean product | Real and cinematic | Technical | Stylized art |
|---|---|---|---|
| ops, toy, lived-in | terrain, documentary, white model, layer build | point cloud, plate | pixel, ASCII, glow |
Examples: `/viz3d app a container port`, `/viz3d film white model the Chernobyl accident`,
`/viz3d showcase glow a cockroach`, `/viz3d game pixel a worm that eats a city`.