gotchi-3d-custom-render

Use this skill when the user wants a custom 3D gotchi render from selected traits, wearable IDs, wearable names, or a named preset.

Plain-language requests should also route here, for example:

• - "render an ETH gotchi with common eyes, aagent hat, shades, shirt, headset, and pistol"
• "show me a custom gotchi portrait on a cream background"
• "make a gotchi outfit preview with wizard hat and blue wand"
• "give me a headshot of a hypothetical gotchi with shades and a fedora"

Do not wait for the user to explicitly say gotchi-3d-custom-render.

What this skill does

• - writes a structured render request JSON
• uses the hosted Aavegotchi renderer by default for official-style output
• falls back to the local Unity batch worker when hosted assets are unavailable
• returns:

• - supports friendlier presets, slot aliases, themed backgrounds, and render-mode selection
• wearable flags accept either numeric IDs or quoted wearable names
• supports plain-language outfit requests after routing picks this skill

Constraints

• - requires a local Unity editor installation
• hosted mode matches the existing Aavegotchi renderer look much more closely, but may ignore custom local-only pose behavior
• Unity fallback is still useful for hypothetical combinations or local debugging
• hosted mode can run on non-Unity hosts as long as node, jq, and python3 with Pillow are available
• intended for local development first, then AAi/Telegram integration through hosted mode

Routing Notes

• - Prefer this skill when the user describes a look, outfit, traits, wearables, background, portrait, headshot, or hypothetical gotchi.
• Prefer aavegotchi-3d-renderer instead when the user gives a tokenId or inventory URL for an existing gotchi.
• If the user gives both a tokenId and custom outfit instructions, clarify whether they want the real token render or a hypothetical custom loadout.

Entry points

• - main wrapper: INLINECODE5
• preset gallery helper: INLINECODE6
• direct Unity runner: INLINECODE7
• Unity project: INLINECODE8

Quick usage

From the skill root:

CODEBLOCK0

Default mode is hosted. Use --render-mode auto if you specifically want hosted-first with Unity fallback, or --render-mode unity for local-only rendering.

Outputs land in:

• - INLINECODE12
• INLINECODE13
• INLINECODE14

Input contract

Supported flags:

• - INLINECODE15
• INLINECODE16
• INLINECODE17
• INLINECODE18
• INLINECODE19
• INLINECODE20
• INLINECODE21
• INLINECODE22
• INLINECODE23
• INLINECODE24
• INLINECODE25
• INLINECODE26
• INLINECODE27
• INLINECODE28
• INLINECODE29
• INLINECODE30
• INLINECODE31
• INLINECODE32
• INLINECODE33
• INLINECODE34
• INLINECODE35
• INLINECODE36
• INLINECODE37
• INLINECODE38
• INLINECODE39
• INLINECODE40

Wearable flags can take either:

• - numeric IDs like INLINECODE41
• quoted names like INLINECODE42

Friendly Examples

CODEBLOCK1

Natural-language request examples this skill should handle:

• - "render a custom ETH gotchi with common eyes and an aagent pistol"
• "show me a gotchi with aagent hat, shades, shirt, and headset"
• "make a portrait gotchi on a studio cream background"
• "preview this outfit on an ETH gotchi with common eyes"

If you need to inspect the request shape or adjust it manually, read references/request-schema.md.
If you need the preset list or alias vocabulary, read references/presets.md.

When to read extra files

• - read references/request-schema.md when you need the exact JSON payload layout
• read references/presets.md when you need preset names, background aliases, or friendlier slot names
• read references/wearables.tsv when you need the built-in wearable name catalog used on non-Unity hosts
• read unity/GotchiCustomRenderer/Assets/Editor/GotchiCustomRenderCLI.cs only when changing the Unity render behavior