Story Cover builds a full cover for a web novel that carries the title and the pen name. It reads the book’s genre and target platform from the project files, picks a genre style from a style library, and assembles an English image prompt from a text layer, a style layer and a scene layer. You choose between two or three composition options before anything is drawn.
It can stop at the prompt, or generate the image with the built-in image tool of Codex or Antigravity, or call the GPT-Image-2 API when no built-in tool exists. It saves numbered versions, crops and scales a copy to the platform’s upload size, and checks that the title and pen name stay readable and uncut.
What You Get
- One to three complete cover prompts, ready for any image generator
- A generated cover saved as numbered versions with its prompt file beside it
- A cropped upload copy at the platform size, such as 600 by 800 for Fanqie, Qidian and Qimao
- A short report with the design idea and two or three directions to change
Common Use Cases
- Making a cover for a new web novel before publishing
- Getting only a prompt to use in another image tool
- Producing a platform-size upload file from a generated image
- Redoing a cover with a different composition, color or title font
What Makes It Unique
It is tied to the novel’s own files: genre, platform and title come from the project, and platform aspect ratios and safe areas are built into the prompt. It prefers the image tool already in your coding agent, and it does not switch to a paid API without telling you.
Under The Hood
The skill is instructions plus two reference files, a style library and an API fallback guide. For images it calls the built-in image tool of the host agent when there is one. Otherwise the guide has the agent run shell commands with curl and jq that send your prompt, and a reference image if you give one, to the OpenAI image API or a compatible proxy using the GPT_IMAGE_API_KEY environment variable, then decode the result to a PNG. It may download a reference image from a URL. It writes cover images and prompt text files into the book’s cover folder and runs ImageMagick or sips to crop and resize a copy.