Nuyoah Image Reverse Prompt skill
nuyoah-image-reverse-prompt
A skill that breaks a picture into frame, light, color and materials and assembles a ready Chinese prompt for image generation.
- 104 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- Reads the supplied image and may pass its content to the agent model.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/nuyoah-image-reverse-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.
- Reads the supplied image and may pass its content to the agent model.
This is third-party code. Review the repository files before installing.
What it does
The skill takes a reference image, decides its dominant type, then breaks down frame size and ratio, composition, subject, light, color, materials and processing traits. Details backed by the picture are assembled into one Chinese prompt and a swatch palette. It does not claim to recover the author's original prompt and generates nothing in the normal mode. Separate flows cover calibration against a generated return and updating the skill itself. The repository holds image type references, the output contract and sets of eval cases.
Who it is for. Designers and content makers who turn a reference image into a Chinese prompt for an image generator.
Good fit when
- You have a reference and need a prompt ready to paste into a generator.
- You need a color swatch palette from an image.
- A poster or photo is analyzed for light and materials.
- You compare a generated result with the original and refine wording.
Not a fit when
- You want an image generated without analysis.
- There is no reference, only an idea.
- You need plain image editing.
- You expect an exact copy of someone's original prompt.
Example request
Use Nuyoah Image Reverse Prompt: break down this image and give me the palette and a full generation prompt.Limitations
Descriptions and prompts target Chinese. The result relies on what is visible in the picture, so hidden details and model settings are not recovered. The agent must be able to read images, and long descriptions can be shortened by hand because not everything visible reaches the prompt. The manifest version is 0.1.0, so the project is young. If the picture contains third-party material, check usage rights before generating from the resulting prompt.
How to disable. Delete the skill folder from the agent's skills directory or remove it through `npx skills`.
FAQ
What does it output?
A field-by-field structural breakdown, a swatch palette and one coherent Chinese prompt.
Does it generate images?
No. The normal mode only analyzes; generation runs only when the user explicitly asks for calibration.
How do I update the skill?
Ask the agent to update it or run `npx skills update nuyoah-image-reverse-prompt -g -y`, then open a new task.
Does it recover the original prompt?
No. It only describes what is visible and makes no claim of matching the original.
What license is it under?
MIT.
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 skill that turns a picture into a generator prompt: frame breakdown, an enhanced version, three variants and platform editions.
Nuyoah Xiezhen Prompt
南鸢写真提示词
Portrait photography in Chinese: prompts, series, gacha keywords and reshoots with a new subject from the same plan.
A set of skills for Claude Code and Codex that assemble detailed image prompts from an element library and composition schemes
Five image-generation skills: Qwen-Image prompts, logos with shared geometry, diary comics, transparent PNGs and process dioramas
Qwen-Image 2.1 Prompter
qwen-image-2.1-skill
A skill that rewrites prompts for Qwen-Image-2.1 by Alibaba's official rules: text-to-image and multi-image editing
README in short
The README briefly covers installation through `npx skills`, updating and the repository layout: rules, agent interfaces and eval cases.