Transparent Visual Assets logo

Transparent Visual Assets

Community
DwDestiny
transparent-visual-assets

Generate transparent-background raster assets with Codex image generation plus deterministic cleanup. Use when the user wants a PNG sticker, icon, mascot, sprite, UI asset, or web-ready visual element with transparent background, or asks to remove/avoid a generated image background while preserving the subject.

Overview

PublisherDwDestiny
Repositorycodex-visual-asset-skills
Skill nametransparent-visual-assets
Stars
62
Forks
3
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by DwDestiny on GitHub. Read the source before you install it.

Installation

Install the Transparent Visual Assets AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/DwDestiny/codex-visual-asset-skills/tree/main/skills/transparent-visual-assets
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/DwDestiny/codex-visual-asset-skills.git /tmp/codex-visual-asset-skills
mkdir -p .claude/skills
cp -r /tmp/codex-visual-asset-skills/skills/transparent-visual-assets .claude/skills/transparent-visual-assets
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Transparent Visual Assets in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Transparent Visual Assets on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Transparent Visual Assets is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Transparent Visual Assets

核心判断

先让 Codex 生图得到“容易抠干净”的图,再用脚本做确定性清理。不要要求模型直接画棋盘格透明背景;棋盘格会变成图像内容。优先让模型使用纯色背景,例如 #FF00FF 或 #00FF00,并明确主体不能使用接近背景的颜色。

适合输出:透明 PNG、网页素材、贴纸、图标、单帧 sprite、角色/物体素材。

不适合输出:多帧动画、spritesheet、视频;这些转给 $sprite-animation-assets。

典型使用场景

  • 网站设计素材:Landing page、产品官网、博客插画、功能区装饰、空状态插画。
  • PPT / 汇报图表:路演页、数据页、业务复盘、图表旁的视觉解释元素。
  • App / 产品引导:onboarding、权限说明、功能引导、发布说明里的产品插画。
  • 电商 / 社媒贴纸:商品页角标、促销贴纸、社媒封面、公众号配图元素。
  • 游戏 / 互动 UI:小角色、道具、背包图标、按钮素材、单帧 sprite。
  • 视频 / 海报叠加:封面人物、栏目贴片、透明 logo-like 装饰、片头片尾元素。

工作流

  1. 明确素材用途、尺寸、主体边界和禁用元素。
  2. 调用 Codex 生图能力生成带纯色背景的候选图。
  3. 目视检查:主体完整、没有阴影地面、没有漂浮杂点、主体颜色不接近背景色。
  4. 用 scripts/prepare_transparent_asset.py 清理纯色背景、裁切透明边缘、输出 PNG。
  5. 打开结果或检查报告,确认透明角落、主体不被误删。

生图提示词要点

使用简短、强约束的提示词:

text
Create a single centered web asset of <subject>.
Use a perfectly flat #FF00FF background for later chroma key removal.
The subject must not contain magenta, pink, or colors close to #FF00FF.
No shadows, floor, scenery, text, labels, checkerboard pattern, glow, blur, or detached decorative particles.
Keep the full subject inside the canvas with clear spacing.

如果主体天然包含粉色或品红,换成 #00FF00、#00FFFF 或其他不会出现在主体里的纯色。

更多提示词和 QA 细节见 references/prompt-and-cleanup.md。

清理脚本

bash
python "${CODEX_HOME:-$HOME/.codex}/skills/transparent-visual-assets/scripts/prepare_transparent_asset.py" \
  --input /absolute/path/source.png \
  --output /absolute/path/asset.png \
  --background "#FF00FF" \
  --threshold 24 \
  --feather-threshold 48 \
  --trim \
  --padding 8 \
  --report /absolute/path/report.json

参数说明:

  • --background:要移除的纯色背景;不传时用四角颜色估算。
  • --threshold:颜色容差。背景边缘残留就调大;主体被吃掉就调小或重生图换背景色。
  • --feather-threshold:可选的边缘柔化容差,用来淡化生图抗锯齿留下的背景色毛边。
  • --trim 和 --padding:裁掉透明边缘并保留一点安全留白。

脚本只做背景清理,不会补画、重绘、扩图或创造新素材。

验收标准

  • 输出必须是 .png,并带 alpha 透明通道。
  • 四角应透明,主体边缘不缺块。
  • 主体外没有阴影、地面、光晕、漂浮符号、文字或背景色残留。
  • 素材在深色、浅色、棋盘格背景上都能读清。
  • 如果清理后主体明显破损,重新生图或换背景色,不要靠脚本硬修。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Transparent Visual Assets AI skill do?

Generate transparent-background raster assets with Codex image generation plus deterministic cleanup. Use when the user wants a PNG sticker, icon, mascot, sprite, UI asset, or web-ready visual element with transparent background, or asks to remove/avoid a generated image background while preserving the subject.

Why use Transparent Visual Assets on TypingMind?

Because you install it once and use it with any model. Transparent Visual Assets is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Transparent Visual Assets in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/DwDestiny/codex-visual-asset-skills/tree/main/skills/transparent-visual-assets. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Transparent Visual Assets?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Transparent Visual Assets?

As many as you like. As long as a model supports skills, you can use Transparent Visual Assets with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Transparent Visual Assets AI skill free?

Yes. It is published on GitHub by DwDestiny under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇