agentleFS
Sign inStart free
ai-enhanced-engineerai-enhanced-engineer/aiee-skills/skills/design-system-workflow/SKILL.md

design-system-workflow

Skill4 starsChanged 5 months agoMITView on GitHub

Human-in-loop design system workflow using AI generation (Gemini) for brand identity exploration, dual-format token output (CSS + Swift), and WCAG contrast validation. Use when establishing a brand identity for a new product, generating design tokens for web and iOS, or validating a color palette against WCAG contrast requirements.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When product positioning pivots, stale claims often persist in invisible locations — meta tags, OG descriptions, JSON-LD structured data, …

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Design System Workflow

Human-in-loop workflow for AI-assisted brand identity exploration and design token generation.

When to Use

  • Creating brand identity for a new product
  • Exploring visual directions with AI generation (Gemini)
  • Producing design tokens for cross-platform projects (web + iOS)
  • Validating color palettes against WCAG accessibility requirements

For CSS-only design systems, see frontend-design-systems. For SwiftUI color/font patterns, see swift-swiftui (Asset Management section).

Three-Phase Workflow

  1. AI-Assisted Direction Exploration — Batch Gemini prompts across multiple directions using natural language color descriptions. Sequential prompt-per-artifact generation with founder review between each.
  2. Founder Selection — Consolidated HTML review page with annotations and decision boxes. Generation of next phase gates on approval.
  3. Dual-Format Token Production — Single design direction produces CSS custom properties (web) and Asset Catalog + Swift extensions (iOS/watchOS). The design direction is the source of truth; each format is a translation.

WCAG Contrast Validation

Specifying WCAG contrast ratios as explicit acceptance criteria (4.5:1 body text AA, 3:1 large text/UI AA) catches failures before merge. ~25% of AI-generated colors typically fail on first pass. A complete brand identity exploration typically requires ~15 crafted prompts (logo, palette, screens, app icon, watchOS).

Strategic Pivot Copy Audit

When product positioning pivots, stale claims often persist in invisible locations — meta tags, OG descriptions, JSON-LD structured data, alt text, and app store descriptions. Auditing all copy (not just visible text) after a pivot prevents search engines and social previews from showing outdated messaging.

See reference.md for the pivot copy audit checklist.

Anti-Patterns

Anti-PatternPattern
CSS tokens as sole output for iOS/SwiftUI appsDual-format: CSS for web + Asset Catalog + Swift extensions for native
Hex codes in Gemini/Imagen promptsNatural language only ("sage green", "deep navy") — hex renders as literal text
Batch generation without founder gatesSequential prompt-per-artifact with review between each
Skipping dark mode variantsDark variants needed when any app context forces dark mode
Updating visible copy but leaving meta/OG/JSON-LD staleInclude meta tags, OG tags, and structured data in copy audit scope

See reference.md for detailed phase descriptions, pre-implementation validation patterns, and SVG hand-coding guidance.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free