Skip to content
Agentmart
Submit a tool

design-system

Extract, normalize, and sync design system tokens into DESIGN.md.

Skill by r3dlex

IndexedMIT
Write a review

Chalk Labs

Need help deploying design-system?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/r3dlex-design-system

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Extract, normalize, and sync design system tokens into DESIGN.md. Use when the user wants to create, import, or update design tokens.

Use cases: design

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/design-system

What's inside

Skill name
design-system
Description
Extract, normalize, and sync design system tokens into DESIGN.md. Use when the user wants to create, import, or update design tokens.
License
MIT
Instructions
54 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Design System Skill (oh-my-antigravity)

## Quick Start

- Choose a source, extract tokens, map semantic names, then update DESIGN.md.

Use this skill when the user wants to extract, create, or synchronize design system tokens.

## Quick Start

1. **Token Extraction** — Extract design tokens from:
   - Live URLs (color palette, typography, spacing from computed styles)
   - Existing CSS/SCSS/Tailwind config files
   - Figma exports or design specs
   - Screenshot images (via multimodal analysis)

2. **DESIGN.md Sync** — Update DESIGN.md sections:
   - Color Palette & Roles (Section 2)
   - Typography Rules (Section 3)
   - Layout Principles (Section 5)
   - Depth & Elevation (Section 6)

3. **Token Format Generation** — Output tokens as:
   - CSS custom properties (`--color-primary: #hex`)
   - Tailwind config extensions
   - SCSS variables
   - JSON token files (Style Dictionary compatible)

## Workflow

1. **Source** — Identify where tokens come from (URL, file, image, manual spec)
2. **Extract** — Parse and normalize token values
3. **Map** — Assign semantic roles (primary, secondary, accent, surface, etc.)
4. **Write** — Update DESIGN.md and/or generate token config files
5. **Verify** — Check contrast ratios, validate completeness

## Token Categories

| Category | Required Tokens |
|----------|----------------|
| Colors | primary, secondary, accent, background, surface, text, border, error, success, warning |
| Typography | heading (h1-h6), body, caption, overline font specs |
| Spacing | scale from 4px base (4, 8, 12, 16, 24, 32, 48, 64, 96) |
| Elevation | shadow-sm, shadow-md, shadow-lg, shadow-xl |
| Radius | sm (4px), md (8px), lg (16px), full (9999px) |

## Rules

- Always output tokens with semantic names, never raw values only
- Validate color contrast ratios (WCAG AA: 4.5:1 for text, 3:1 for large text)
- Preserve existing DESIGN.md sections when updating — only modify relevant sections
- Generate both human-readable (DESIGN.md) and machine-readable (CSS/JSON) outputs

From r3dlex/oh-my-antigravity, MIT.

More from r3dlex/oh-my-antigravity

Signals

Stars
0
Forks
0
Open issues
2
Last commit (this folder)
May 25, 2026 (5 months ago)
Last release
May 25, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from r3dlex

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get design-system running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying design-system?

CallGet help
Cite this page

design-system skill. Agent Mart. https://agentmart.dev/skills/r3dlex-design-system (last updated 2026-10-24)