Native Transparent Imagegen logo

Native Transparent Imagegen

Organization
ZSeven-W
native-transparent-imagegen

Generate new raster assets that must contain native pixel transparency, then verify the untouched PNG or WebP before delivery. Use for transparent stickers, sprites, character cutouts, product assets, and furry or fine-edged subjects where background removal would be unacceptable. Do not use to remove a background from an existing opaque image, repair an opaque generation by masking or chroma key, or create ordinary opaque images.

Overview

PublisherZSeven-W
Repositorycraft-skills
Skill namenative-transparent-imagegen
Stars
233
Forks
33
Bundled files
6
LicenseApache-2.0
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.

  • 6 bundled files

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

  • Open source

    Published by ZSeven-W on GitHub. Read the source before you install it.

Installation

Install the Native Transparent Imagegen 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/ZSeven-W/craft-skills/tree/main/skills/native-transparent-imagegen
  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/ZSeven-W/craft-skills.git /tmp/craft-skills
mkdir -p .claude/skills
cp -r /tmp/craft-skills/skills/native-transparent-imagegen .claude/skills/native-transparent-imagegen
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Native Transparent Imagegen 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 Native Transparent Imagegen 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 Native Transparent Imagegen 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.

Native Transparent ImageGen

Generate the asset with native alpha. Treat a visible checkerboard, a prompt that says "transparent," and a successful tool call as unverified until the original file passes alpha inspection.

Keep the boundary strict

  • Use this skill only for a newly generated asset whose deliverable must contain native transparency.
  • Treat supplied images as identity, subject, composition, or medium references unless the user explicitly requests an edit.
  • Do not invoke background removal, segmentation, chroma-key extraction, masks, or local alpha synthesis to rescue an opaque output.
  • Do not call a rendered checkerboard "transparent." An RGB checkerboard is a failed asset.
  • If the user instead wants a background removed from an existing opaque image, route to a background-extraction workflow and disclose that it is an edit, not native generation.

Generate conservatively

  1. Preserve the user's subject, identity, style, composition, and text constraints.
  2. Add one concise output requirement: return a PNG or WebP whose area outside the subject is genuine pixel transparency with a real alpha channel.
  3. With a prompt-only built-in image tool, issue native-alpha deliverables one at a time. Do not parallelize unless the current tool exposes an explicit per-request background control and concurrent native-alpha behavior has been verified.
  4. When the user explicitly chooses an API path that exposes output controls, request background: "transparent" and output_format: "png" or "webp".
  5. Preserve the original returned bytes. Validation must not rewrite, optimize, composite, resize, or otherwise alter the deliverable.

Read references/prompting-and-retry.md when preparing a prompt, retrying a failed output, generating more than one asset, or reporting limitations.

Validate the untouched file

Install the validator dependency only when it is missing:

sh
python3 -m pip install -r \
  "${CODEX_HOME:-$HOME/.codex}/skills/native-transparent-imagegen/scripts/requirements.txt"

Run the read-only validator on every requested deliverable:

sh
python3 \
  "${CODEX_HOME:-$HOME/.codex}/skills/native-transparent-imagegen/scripts/validate_alpha.py" \
  --require-transparent-corners \
  /path/to/original-output.png

The file passes the technical gate only when:

  • its decoded pixels contain an alpha channel;
  • at least one pixel is fully transparent and at least one is visible;
  • required padding corners are transparent when the asset is meant to be isolated; and
  • the validator exits successfully on the original output.

Then inspect the actual edges against contrasting viewer backgrounds. Alpha metadata cannot prove that fine fur is clean or that the image lacks a broad translucent haze. Reject visible checkerboards, matte halos, colored fog, unintended shadows, clipped strands, or missing details even when the metadata gate passes.

Retry without faking success

  • On an RGB or opaque output, keep all subject invariants and retry only the native-alpha output instruction.
  • Make at most three total generation attempts per distinct asset unless the user requests more.
  • Validate after every attempt. Do not edit the failed image into compliance.
  • If all attempts fail, stop and report the original modes and validation failures. Offer an explicit API route only when available and authorized; never silently change models or use background extraction.

Report evidence

For every accepted asset, report:

  • generation route and model when known;
  • original file path, format, dimensions, mode, and SHA-256;
  • alpha extrema, fully transparent pixel count, corner alpha values, and validator verdict;
  • visual edge-QA result; and
  • the exact final prompt or the native-alpha clause added to the user's prompt.

Keep generated, alpha-validated, edge-inspected, user-accepted, and published as separate states.

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 Native Transparent Imagegen AI skill do?

Generate new raster assets that must contain native pixel transparency, then verify the untouched PNG or WebP before delivery. Use for transparent stickers, sprites, character cutouts, product assets, and furry or fine-edged subjects where background removal would be unacceptable. Do not use to remove a background from an existing opaque image, repair an opaque generation by masking or chroma key, or create ordinary opaque images.

Why use Native Transparent Imagegen on TypingMind?

Because you install it once and use it with any model. Native Transparent Imagegen 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 Native Transparent Imagegen in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ZSeven-W/craft-skills/tree/main/skills/native-transparent-imagegen. 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 Native Transparent Imagegen?

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 Native Transparent Imagegen?

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

Is the Native Transparent Imagegen AI skill free?

Yes. It is published on GitHub by ZSeven-W under the Apache-2.0 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 👇