agentleFS
dylantarredylantarre/design-system-skills/CLAUDE.md

design-system-skills

CLAUDE.md50 starsChanged 11 months agoMITView on GitHub

This is a Claude Code plugin marketplace for design system development. It provides skills (markdown-based prompt templates) that guide Claude through generating design tokens, components, and accessibility patterns. Installation: /plugin https://github.com/dylantarre/design-system-skills Each skill is a SKILL.md file with YAML frontmatter: All token skills share these conventions: - Output formats: CSS custom properties, Tailwind config, JSON tokens - Naming: T-shirt sizes (xs, sm, md, lg) or numeric (100, 200, 300) - Process: Gather input → ask format → generate → output

The file

We split this CLAUDE.md into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All token skills share these conventions:

    line 59
  2. Very specific:

    Create directory under appropriate category: skills/{category}/{skill-name}/

    line 68
  3. Very specific:

    Add SKILL.md following the format above

    line 69
  4. Distinctive:

    Update README.md to list the new skill

    line 70

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a Claude Code plugin marketplace for design system development. It provides skills (markdown-based prompt templates) that guide Claude through generating design tokens, components, and accessibility patterns.

Installation: /plugin https://github.com/dylantarre/design-system-skills

Architecture

.claude-plugin/
├── plugin.json      # Plugin metadata (name, version, author)
└── marketplace.json # Marketplace registry configuration

skills/
├── tokens/          # Design token generators
│   ├── color-scale/SKILL.md
│   ├── spacing-scale/SKILL.md
│   └── type-scale/SKILL.md
├── frameworks/      # Framework-specific patterns (planned)
├── tools/           # Design tool integrations (planned)
├── accessibility/   # WCAG compliance skills (planned)
└── documentation/   # Doc generators (planned)

Skill File Format

Each skill is a SKILL.md file with YAML frontmatter:

---
name: skill-name
description: Use when [trigger conditions]. Supports [output formats].
---

# Skill Name

## Overview
[What it does - 1-2 sentences]

## When to Use
[Bullet list of scenarios]

## Quick Reference
[Tables with key information]

## The Process
[Numbered steps Claude follows]

## Output Formats
[Code examples for CSS, Tailwind, JSON]

Token Skills Patterns

All token skills share these conventions:

  • Output formats: CSS custom properties, Tailwind config, JSON tokens
  • Naming: T-shirt sizes (xs, sm, md, lg) or numeric (100, 200, 300)
  • Process: Gather input → ask format → generate → output

Color scale uses OKLCH by default (perceptually uniform). Spacing/type use ratio-based exponential scales.

Adding New Skills

  1. Create directory under appropriate category: skills/{category}/{skill-name}/
  2. Add SKILL.md following the format above
  3. Update README.md to list the new skill
  4. Skills are auto-discovered by Claude Code from the skills/ directory

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.