zelda-style-image-prompt skill
A skill that writes a ready image prompt in the look of a Zelda screenshot: a real place, character or object in the game world.
- 88 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill only writes prompt text and runs no commands.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/zelda-style-image-promptDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill only writes prompt text and runs no commands.
This is third-party code. Review the repository files before installing.
What it does
The `zelda-style-image-prompt` skill for Codex turns a short description of a place or scene into a finished prompt for an image generator. The result looks like a frame from a Nintendo Switch game: stylized graphics, area captions in the game manner and interface elements. The prompt is assembled from a template of 10 to 13 lines: style, map block, key elements, gameplay moment, list of game details, region caption and interface rules. All on-image text is in Chinese. Style rules live in `references/zelda-visual-style.md`. The skill returns only the final prompt block and does not draw the picture itself.
Who it is for. Designers and content authors who make picture series about cities, landmarks and objects in a game style and do not want to rework the wording every time.
Good fit when
- A picture of a familiar city is needed, as if it were an area of a game world.
- A real product should appear as an item from an adventure.
- A series of pictures must keep one style and one caption structure.
- Only one hero stays in frame, and the second character is removed from the prompt.
Not a fit when
- The picture itself is needed: the skill outputs prompt text and the generator is connected separately.
- A different game style is required: the rules are written only for this game series.
- On-image text is needed in Russian: the template leads to Chinese text.
Example request
Use zelda-style-image-prompt and write a prompt for a view of Red Square in Moscow, without generating the image.Limitations
The skill works with text only and draws nothing, so picture quality depends on the chosen generator. Rules, captions and examples are written in Chinese, so a Russian-speaking user will need a translator to read the final prompt. The repository holds no game models, fonts or assets and has no tie to Nintendo; rights to the resulting pictures and platform rules are the author's own concern. Installation is documented for Codex, with no instructions for other agents.
How to disable. Delete the `zelda-style-image-prompt` folder from the Codex skills directory and restart Codex.
FAQ
How do I install the skill?
Clone the repository and copy the `skills/zelda-style-image-prompt` folder into `~/.codex/skills/` or the project `.codex/skills/`. After restarting Codex the skill appears in the list.
Does the skill draw the image itself?
No. It outputs prompt text in a code block and a separate image model makes the picture.
What scenes can it describe?
Real places in the game style, scenes with characters, and objects or products.
What language is the on-image text?
Chinese: the template requires all readable interface text in that language.
Can one of the heroes be removed?
Yes. If you ask for a prompt without one of the two, the skill keeps a single hero.
Discussion
No questions or reviews yet.
Related
Skillsimage-prompt-reverse analyzes an uploaded picture and writes a generator prompt together with a negative-term list.
A set of skills for Claude Code and Codex that assemble detailed image prompts from an element library and composition schemes
A Claude Code skill that compiles a vague request into a finished gpt-image-2 prompt and checks it with a validator script
A skill that assembles ready image prompts in hand-drawn styles from a set of tested recipes: kids drawing, minimal line, crayon, Ghibli look and more
Codex skill that turns a portrait, photo or text description into a retro illustration in the style of an early CRT interface.
Fifty-one Codex skills that turn a photo into a poster, avatar, comic or illustration in a chosen visual style.
README in short
In the README: Codex installation, an example request and a statement that the project is unaffiliated with the rights holder. Style rules sit in the skill reference file.