Skip to content
SkillMixed7,149 tokens in use

Mono Color

Turn a theme, sentence or photo into an original one- or two-ink editorial print, with the image prompt and the generated image.

3,709 stars on the repository MIT Licenseyanliudesign/mono-color-skill
git clone https://github.com/yanliudesign/mono-color-skill.git ~/.claude/skills/mono-color
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Mono Color costs

197tokens idle
7,149tokens in use
11,861tokens, 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 Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/build_design_system_board.py, scripts/build_vibe_coding_poster.py, scripts/validate_design_system.py, scripts/validate_evals.py.

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
  • Frontmatter12/15
  • Structure19/25
  • Examples12/15
  • Output10/15
  • Size11/15
  • Resources7/15

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

    scripts/build_design_system_board.py, line 265
  • Writes files−8

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

    scripts/build_vibe_coding_poster.py, line 98

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Fair
  • Development activity68
  • Maintenance52
  • Community44
  • Maturity20
  • Momentum40

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.

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