agentleFS
nassaj2011nassaj2011/claude-skills-for-chatgpt/skills/theme-design-system/SKILL.md

theme-design-system

Skill0 starsChanged 25 days agoMITView on GitHub

Define and evolve a cohesive web or mobile design system with accessible tokens, typography, color, component variants and usage rules.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Read brand identity, screenshots and the existing token/component stack.

    line 8
  2. Distinctive:

    Ensure minimum readable contrast, visible keyboard focus, reduced-motion support, RTL/localization and responsive breakpoints where …

    line 12
  3. Distinctive:

    Do not claim WCAG compliance without measured checks.

    line 17

≈ “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

Theme and design-system factory

  1. Read brand identity, screenshots and the existing token/component stack. Preserve established brand rules unless redesign was requested.
  2. Describe 2 viable visual directions with rationale rooted in audience and domain; choose one after considering accessibility and technical cost.
  3. Specify semantic color tokens (surface, text, border, focus, danger, success), light/dark variants, typography scales, spacing, radius and motion preferences.
  4. Map tokens to actual component primitives (buttons, inputs, nav, dialogs, tables, alerts) and their hover/focus/disabled/error/loading states.
  5. Ensure minimum readable contrast, visible keyboard focus, reduced-motion support, RTL/localization and responsive breakpoints where relevant.
  6. Provide a migration map for existing styles; avoid generating a parallel design system that conflicts with shipped components.
  7. Validate representative screens at mobile, tablet and desktop widths and collect visual regression evidence.

Output: theme rationale, token table or CSS variables, component state matrix, sample usage and integration notes. Do not claim WCAG compliance without measured checks.

Token reference

Inspect examples/frontend-rtl/tokens.css for semantic light/dark tokens, logical layout properties, focus outlines and reduced-motion preference. This is a testable starting point rather than a general-purpose component library. Measure actual contrast and RTL behavior in a browser before certification.

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.