gotchi-3d-custom-render

Render custom Aavegotchi 3D images from arbitrary trait and wearable combinations. Use when the user describes a synthetic or hypothetical gotchi look in plain language, asks for an outfit preview, headshot, or full-body image, and is not asking for an existing onchain token by tokenId or inventory URL.

3,891 stars

Best use case

gotchi-3d-custom-render is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Render custom Aavegotchi 3D images from arbitrary trait and wearable combinations. Use when the user describes a synthetic or hypothetical gotchi look in plain language, asks for an outfit preview, headshot, or full-body image, and is not asking for an existing onchain token by tokenId or inventory URL.

Teams using gotchi-3d-custom-render should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/gotchi-3d-custom-render/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/aaigotchi/gotchi-3d-custom-render/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/gotchi-3d-custom-render/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How gotchi-3d-custom-render Compares

Feature / Agentgotchi-3d-custom-renderStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Render custom Aavegotchi 3D images from arbitrary trait and wearable combinations. Use when the user describes a synthetic or hypothetical gotchi look in plain language, asks for an outfit preview, headshot, or full-body image, and is not asking for an existing onchain token by tokenId or inventory URL.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# 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:
  - full-body PNG
  - headshot PNG
  - manifest JSON
- 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: `scripts/render-custom-gotchi.sh`
- preset gallery helper: `scripts/render-preset-gallery.sh`
- direct Unity runner: `scripts/run-unity-render.sh`
- Unity project: `unity/GotchiCustomRenderer`

## Quick usage

From the skill root:

```bash
bash scripts/render-custom-gotchi.sh \
  --preset aagent-eth
```

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:

- `Renders/<slug>-full.png`
- `Renders/<slug>-headshot.png`
- `Renders/<slug>-manifest.json`

## Input contract

Supported flags:

- `--preset`
- `--slug`
- `--haunt-id`
- `--collateral`
- `--eye-shape`
- `--eye-color`
- `--skin-id`
- `--background`
- `--pose`
- `--body`
- `--face`
- `--eyes`
- `--head`
- `--pet`
- `--hand-left`
- `--hand-right`
- `--left-hand`
- `--right-hand`
- `--slot`
- `--wearables`
- `--print-presets`
- `--write-only`
- `--render-mode`
- `--hosted-only`
- `--unity-only`
- `--find-wearable`

Wearable flags can take either:
- numeric IDs like `--head 59`
- quoted names like `--head 'Aagent Fedora Hat'`

## Friendly Examples

```bash
bash scripts/render-custom-gotchi.sh --find-wearable aagent
bash scripts/render-custom-gotchi.sh --preset portrait-eth
bash scripts/render-custom-gotchi.sh --preset aagent-eth
bash scripts/render-custom-gotchi.sh --preset aagent-eth --render-mode auto
bash scripts/render-custom-gotchi.sh --body 'Aagent Shirt' --face 'Aagent Headset' --eyes 'Aagent Shades' --head 'Aagent Fedora Hat' --hand-right 'Aagent Pistol'
bash scripts/render-custom-gotchi.sh --wearables 'head=56,hand-right=58' --bg gotchi-radio --pose hero
bash scripts/render-custom-gotchi.sh --slot hat=56 --slot weapon=58 --background transparent
bash scripts/render-preset-gallery.sh
bash scripts/render-preset-gallery.sh --preset aagent-eth --preset portrait-eth --gallery-name quicklook
bash scripts/render-preset-gallery.sh --preset aagent-eth --preset portrait-eth --gallery-name quicklook --skip-failures
bash scripts/render-preset-gallery.sh --preset aagent-eth --gallery-name quicklook --open
```

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

Related Skills

Customer Onboarding

3891
from openclaw/skills

Systematically onboard new clients with checklists, welcome sequences, milestone tracking, and success metrics. Reduce churn by nailing the first 90 days.

Workflow & Productivity

Customer Support Command Center

3891
from openclaw/skills

Enterprise-grade customer support system: ticket triage, response templates, escalation workflows, CSAT tracking, knowledge base management, and churn prevention. Turns your AI agent into a support team lead.

Workflow & Productivity

Customer Success Playbook

3891
from openclaw/skills

Build and run a customer success operation for B2B SaaS. Covers the full lifecycle: onboarding, health scoring, QBRs, churn prevention, and expansion revenue.

Workflow & Productivity

Customer Journey Mapping

3891
from openclaw/skills

Map every touchpoint from first click to loyal advocate. Identify drop-off points, emotional peaks, and automation opportunities across your entire customer lifecycle.

Customer Analytics & Strategy

Customer Acquisition Cost (CAC) Optimizer

3891
from openclaw/skills

Analyze, benchmark, and reduce your customer acquisition cost across every channel.

Business Analytics & Strategy

render-agent

3891
from openclaw/skills

生成图片、画图、出图、AI绘画、图像生成。当用户要求生成图片、画一张图、出几张图、AI绘画时,必须使用此技能调用本地ComfyUI生成,不要使用任何在线服务或API。

agent-render-linking

3891
from openclaw/skills

Create zero-retention agent-render.com links for markdown, code, diffs, CSV, or JSON artifacts. Use when an agent needs to share a nicely rendered artifact in the browser instead of pasting raw content into chat. Trigger for requests like "share this as a link", "make a diff link", "render this markdown/code/csv/json", or when chat rendering is weak. Agent Render is open source, hosted on Cloudflare Pages, and self-hostable. Use platform-specific linked-text syntax only on surfaces that support it cleanly, such as Discord Markdown links, Telegram HTML links, or Slack mrkdwn links; otherwise send a short summary plus the raw URL.

customer-support-autopilot

3891
from openclaw/skills

Classify customer support tickets, draft accurate responses, suggest macros, and route escalations based on risk, SLA, and business impact.

renderkit

3891
from openclaw/skills

Render structured data as beautiful hosted web pages, and create hosted forms for data collection, using the RenderKit API. Use this for visual pages, surveys, RSVPs, feedback forms, or any structured data.

acumatica-customization

3891
from openclaw/skills

Manage Acumatica ERP customization projects via the CustomizationApi web API. Use this skill whenever the user wants to export, import, publish, validate, unpublish, or delete Acumatica customization projects, check publish status, toggle maintenance mode, or automate any customization lifecycle task against an Acumatica instance. Trigger even when the user mentions "Acumatica", "customization project", "publish", "unpublish", or "acumaticahelper".

customer-success-manager

3891
from openclaw/skills

Monitors customer health, predicts churn risk, and identifies expansion opportunities using weighted scoring models for SaaS customer success. Use when analyzing customer accounts, reviewing retention metrics, scoring at-risk customers, or when the user mentions churn, customer health scores, upsell opportunities, expansion revenue, retention analysis, or customer analytics. Runs three Python CLI tools to produce deterministic health scores, churn risk tiers, and prioritized expansion recommendations across Enterprise, Mid-Market, and SMB segments.

desktop-control-custom

3891
from openclaw/skills

Advanced desktop automation with mouse, keyboard, and screen control