Skip to content
SkillMixed900 tokens in use

replica-design

Rebuilds an app's design system for a clone as tokens and component specs, with open icons and fonts and a WCAG contrast checker.

10,140 stars on the repository MIT LicenseJakeschincariol/replica-skill · replica-design
/plugin install replica-skill@replica-skill
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing replica-design costs

112tokens idle
900tokens in use
1,500tokens, 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: contrast.py.

Touches

shelldetected

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 →
Excellent
  • Frontmatter12/15
  • Structure15/25
  • Examples9/15
  • Output15/15
  • 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 20

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Needs attention
  • Development activity32
  • Maintenance4
  • Community64
  • Maturity12
  • Momentum40

replica-design measures the recon screenshots into design tokens: colour roles, a type scale, a spacing scale, radius, shadow and motion. It then writes a spec for every component with its states and builds the primitives in isolation.

It rebuilds the system, never the original’s assets. Icons come from open sets, fonts from open families, and the brand colour is kept as a neutral role for the brand skill to replace.

What You Get

  • tokens.json and tokens.css with colour roles, type, spacing, radius, shadow and motion
  • A Tailwind theme mapping so components use role names and never raw hex
  • A components.md with variants, sizes, states, tokens, accessibility notes and the screens each is used on
  • Primitives built in isolation on a design route or Storybook
  • A contrast report with zero AA failures

Common Use Cases

  • Turning screenshots of an app into a token file with colour roles and a type scale
  • Checking text and background pairs for WCAG AA after a palette change
  • Writing component specs including focus, disabled, loading, error and empty states

What Makes It Unique

It works in roles, so the brand step only changes values and keeps names. It lists what is never taken (logos, icons, illustrations, licensed fonts, copy, the brand colour) and gives open replacements, and its contrast script exits with an error so it can gate a build.

Under The Hood

contrast.py is a standard-library Python script. It reads your tokens JSON, computes WCAG 2 contrast ratios for each listed pair and exits with an error code on a failure. It makes no network calls. The skill’s instructions also have the agent read screenshots, write token and CSS files, edit the Tailwind config and build components in your project, so it reads and writes files and runs commands.

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