Skip to content
SkillModel-led3,585 tokens in use

Story Cover

Design a web novel cover prompt from title, pen name and genre, and optionally render the cover image and resize it to the platform upload size.

8,793 stars on the repository MIT Licensezenstory-ai/oh-story-claudecode · skills/story-cover
npx skills add zenstory-ai/oh-story-claudecode -y -g
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Story Cover costs

118tokens idle
3,585tokens in use
9,502tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure25/25
  • Examples12/15
  • Output0/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 101
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 111

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity28
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers