Mono Color gives an agent a fixed visual language for printed editorial images: a white, gray or pale-beige paper, at most two inks, open negative space, halftone or risograph-style image treatment and strong type. It resolves every request into a recipe (palette, layout, type role, empty paper share, focal event) from JSON catalogs in the repository.
The agent returns a final image-generation prompt, the generated image and a short recipe note. Exact text you supply is kept in its original language, and the skill carries rules that keep each result original and away from any reference’s layout.
What You Get
- A final image-generation prompt written in five ordered paragraphs: canvas and ink, composition, subject, typography, material
- A generated raster image saved to a Mono Color folder on your Desktop when a file path is available
- A short recipe note naming mode, inks with hex values, layout family, type pairing and print process
- Catalogs of palettes, compositions, typography roles, carriers, rhythm and print imperfections the recipe is drawn from
Common Use Cases
- Make a monochrome or duotone poster from a one-line theme
- Convert a photograph into a halftone, one-ink editorial cover
- Produce a series of risograph-style event or zine visuals with consistent ink and spacing rules
- Turn an article idea into a single printed-looking visual with a short English headline
What Makes It Unique
Most image-prompt skills describe a mood. This one resolves a manifest of concrete choices before writing the prompt: a named substrate hex, an approved ink pair with plate roles, a layout picked by a top-to-bottom decision list, a stated share of empty paper and one focal event. The same input resolves to the same recipe, and an originality rule requires changing at least four structural features from any reference you supply.
Under The Hood
The skill is almost entirely instructions: SKILL.md tells the agent to read the relevant JSON catalog in design-system/ for each decision, build the recipe and compile the prompt. It then asks the agent to call whatever image-generation capability it has, inspect the result at full and thumbnail size and regenerate once if a check fails. It writes the output image and files to a folder on your Desktop. The Python scripts in the repository build the design-system board and validate the catalogs for the maintainer; the agent does not need them to make an image.