Skip to content
SkillScript-led1,725 tokens in use

Design System

Three-layer design tokens, component specs and token-compliant slide decks, with scripts that generate CSS and flag hardcoded values.

152,128 stars on the repository MIT Licensenextlevelbuilder/ui-ux-pro-max-skill · cli/assets/skills/design-system
npm install -g ui-ux-pro-max-cli uipro init --ai claude
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Design System costs

52tokens idle
1,725tokens in use
20,797tokens, 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 Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/embed-tokens.cjs, scripts/fetch-background.py, scripts/generate-slide.py, scripts/generate-tokens.cjs, scripts/html-token-validator.py, scripts/search-slides.py, scripts/slide-token-validator.py, scripts/slide_search_core.py, scripts/tests/test_utf8_io.py, scripts/tests/test_validate_tokens.py, scripts/validate-tokens.cjs.

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 →
Excellent
  • Frontmatter11/15
  • Structure22/25
  • Examples15/15
  • Output15/15
  • Size10/15
  • 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 59
  • Writes files−8

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

    scripts/generate-slide.py, line 751

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community76
  • Maturity36
  • Momentum40

Design System teaches an agent to structure tokens in three layers: primitive values, semantic aliases and component tokens. Scripts generate CSS variables from a JSON token config and scan source folders for hardcoded colors and fonts that should be tokens.

The skill also carries a slide system. A BM25 search over CSV data picks a deck strategy, layouts, typography, colors, backgrounds, copy formulas and chart types, and a validator checks generated slide HTML for token compliance.

What You Get

  • A token generator that turns a JSON config into a CSS file of variables
  • A validator that scans a folder for hardcoded values that should be tokens
  • Seven reference documents on token layers, component specs, states and Tailwind integration
  • A starter token JSON with the primitive, semantic and component structure
  • Slide tooling: BM25 search over strategies, layouts, copy and charts, plus a token validator for slide HTML

Common Use Cases

  • Setting up primitive, semantic and component tokens for a new product
  • Finding raw hex values and font names in source files and replacing them with variables
  • Defining hover, active and disabled states for each component
  • Building an investor or marketing deck that uses the brand tokens and Chart.js charts

What Makes It Unique

It combines token architecture with a data-driven slide system. Slide recommendations come from searchable CSV tables that encode deck structures, emotion arcs and layout logic, and every slide must import the token CSS and use variables only. Most token skills stop at naming conventions; this one adds generation, scanning and validation scripts.

Under The Hood

The model reads SKILL.md and references, then runs Node and Python scripts from the skill folder. Token scripts read a JSON config or scan a source directory and write a CSS file. Slide scripts search local CSV data, generate slide HTML and validate it, reading and writing project files such as the brand guidelines and token files. A background script returns curated Pexels image links and search pages for each slide type. Generated slides load Chart.js from a public CDN.

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