Skip to content
cccskills
FreePublished on GitHub

design-md

Create DESIGN.md files that combine exact design values with explanations for coding agents. Validate file structure and color contrast, compare versions, and export shared design settings to Tailwind or a standard design-token JSON format.

OriginalShow the original description

Author/validate/export Google's DESIGN.md token spec files.

See how to install

Good for

  • Turning a style guide into a specification for agents
  • Sharing consistent design settings across projects
  • Checking color contrast and token references
  • Comparing revisions and exporting to Tailwind

Files included (2)

  • SKILL.md8.3 KB
  • templates/starter.md2.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

DESIGN.md Skill

DESIGN.md is Google's open spec (Apache-2.0, google-labs-code/design.md) for describing a visual identity to coding agents. One file combines:

  • YAML front matter — machine-readable design tokens (normative values)
  • Markdown body — human-readable rationale, organized into canonical sections

Tokens give exact values. Prose tells agents why those values exist and how to apply them. The CLI (npx @google/design.md) lints structure + WCAG contrast, diffs versions for regressions, and exports to Tailwind or W3C DTCG JSON.

When to use this skill

  • User asks for a DESIGN.md file, design tokens, or a design system spec
  • User wants consistent UI/brand across multiple projects or tools
  • User pastes an existing DESIGN.md and asks to lint, diff, export, or extend it
  • User asks to port a style guide into a format agents can consume
  • User wants contrast / WCAG accessibility validation on their color palette

For purely visual inspiration or layout examples, use popular-web-designs instead. For process and taste when designing a one-off HTML artifact from scratch (prototype, deck, landing page, component lab), use claude-design. This skill is for the formal spec file itself.

File anatomy

---
version: alpha
name: Heritage
description: Architectural minimalism meets journalistic gravitas.
colors:
  primary: "#1A1C1E"
  secondary: "#6C7278"
  tertiary: "#B8422E"
  neutral: "#F7F5F2"
typography:
  h1:
    fontFamily: Public Sans
    fontSize: 3rem
    fontWeight: 700
    lineHeight: 1.1
    letterSpacing: "-0.02em"
  body-md:
    fontFamily: Public Sans
    fontSize: 1rem
rounded:
  sm: 4px
  md: 8px
  lg: 16px
spacing:
  sm: 8px
  md: 16px
  lg: 24px
components:
  button-primary:
    backgroundColor: "{colors.tertiary}"
    textColor: "#FFFFFF"
    rounded: "{rounded.sm}"
    padding: 12px
  button-primary-hover:
    backgroundColor: "{colors.primary}"
---

## Overview

Architectural Minimalism meets Journalistic Gravitas...

## Colors

- **Primary (#1A1C1E):** Deep ink for headlines and core text.
- **Tertiary (#B8422E):** "Boston Clay" — the sole driver for interaction.

## Typography

Public Sans for everything except small all-caps labels...

## Components

`button-primary` is the only high-emphasis action on a page...

Token types

TypeFormatExample
Colorany CSS color (hex, rgb(), oklch(), named)"#1A1C1E", "oklch(62% 0.18 250)"
Dimensionnumber + unit (px, em, rem)48px, -0.02em
Token reference{path.to.token}{colors.primary}
Typographyobject with fontFamily, fontSize, fontWeight, lineHeight, letterSpacing, fontFeature, fontVariationsee above

Component property whitelist: backgroundColor, textColor, typography, rounded, padding, size, height, width. Variants (hover, active, pressed) are separate component entries with related key names (button-primary-hover), not nested.

Canonical section order

Sections are optional, but present ones should appear in this order. The linter flags out-of-order sections (section-order, warning) and duplicate headings — consumers per the spec reject duplicates, so fix both before returning the file.

  1. Overview (alias: Brand & Style)
  2. Colors
  3. Typography
  4. Layout (alias: Layout & Spacing)
  5. Elevation & Depth (alias: Elevation)
  6. Shapes
  7. Components
  8. Do's and Don'ts

Unknown sections are preserved, not errored. Unknown token names are accepted if the value type is valid. Unknown component properties produce a warning.

Workflow: authoring a new DESIGN.md

  1. Ask the user (or infer) the brand tone, accent color, and typography direction. If they provided a site, image, or vibe, translate it to the token shape above.
  2. Write DESIGN.md in their project root using write_file. Always include name: and colors:; other sections optional but encouraged.
  3. Use token references ({colors.primary}) in the components: section instead of re-typing hex values. Keeps the palette single-source.
  4. Lint it (see below). Fix any broken references or WCAG failures before returning.
  5. If the user has an existing project, also write Tailwind or DTCG exports next to the file (tailwind.theme.json, tokens.json).

Workflow: lint / diff / export

The CLI is @google/design.md (Node). Use npx — no global install needed.

# Validate structure + token references + WCAG contrast
npx -y @google/design.md lint DESIGN.md

# Compare two versions, fail on regression (exit 1 = regression)
npx -y @google/design.md diff DESIGN.md DESIGN-v2.md

# Export to Tailwind v3 theme JSON (`tailwind` is a back-compat alias)
npx -y @google/design.md export --format json-tailwind DESIGN.md > tailwind.theme.json

# Export to a Tailwind v4 CSS @theme block (--color-*, --text-*, --radius-*, ...)
npx -y @google/design.md export --format css-tailwind DESIGN.md > theme.css

# Export to W3C DTCG (Design Tokens Format Module) JSON
npx -y @google/design.md export --format dtcg DESIGN.md > tokens.json

# Print the spec itself — useful when injecting into an agent prompt
npx -y @google/design.md spec --rules-only --format json

All commands accept - for stdin. lint returns exit 1 on errors (warnings alone exit 0). export exits 0 on a successful export regardless of lint findings in the source — run lint separately to gate on those. Output is JSON by default; parse it if you need to report findings structurally.

On Windows, the design.md bin name can collide with the .md file association (silent no-op or the file opens in an editor). Use the dot-free alias: npx -y -p @google/design.md designmd lint DESIGN.md.

Lint rule reference (the 9 rules, as of CLI 0.3.0)

  • broken-ref (error) — {colors.missing} points at a non-existent token
  • contrast-ratio (warning) — component textColor vs backgroundColor below WCAG AA (4.5:1)
  • missing-primary (warning) — colors defined but no primary token
  • missing-typography (warning) — colors defined but no typography tokens
  • orphaned-tokens (warning) — color tokens never referenced by a component
  • section-order (warning) — sections out of the canonical order
  • unknown-key (warning) — top-level YAML key that looks like a typo of a schema key (colours: → colors:); custom extension keys stay silent
  • token-summary, missing-sections (info) — counts and absent optional sections

When the user cares about accessibility, call this out explicitly in your summary — WCAG findings are the most load-bearing reason to use the CLI.

Pitfalls

  • Don't nest component variants. button-primary.hover is wrong; button-primary-hover as a sibling key is right.
  • Hex colors must be quoted strings. YAML will otherwise choke on # or truncate values like #1A1C1E oddly.
  • Negative dimensions need quotes too. letterSpacing: -0.02em parses as a YAML flow — write letterSpacing: "-0.02em".
  • Section order matters even though the linter only warns. If the user gives you prose in a random order, reorder it to match the canonical list before saving — spec-compliant consumers expect it.
  • Typography sub-property typos are silently dropped. As of CLI 0.3.0 a typo like fontwight: produces no finding and the value vanishes from exports — double-check sub-property names against the schema (fontFamily, fontSize, fontWeight, lineHeight, letterSpacing, fontFeature, fontVariation).
  • version: alpha is the current spec version (as of Jul 2026, CLI 0.3.0). The spec is marked alpha — watch for breaking changes.
  • Token references resolve by dotted path. {colors.primary} works; {primary} does not.

Spec source of truth

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

1password

FreeSummary

Set up the 1Password CLI and use stored passwords or API keys in commands and configuration templates. Choose an authentication method, retrieve secret references, and pass credentials to processes through environment variables.

  • Installing and configuring the 1Password CLI
  • Running commands with stored API keys
  • Filling configuration templates with stored secrets
NousResearch/hermes-agent255KUpdated Oct 18, 2026

Build an Excel workbook linking the income statement, balance sheet, and cash flow statement. Populate historical figures, create formula-based forecasts, compare scenarios, and check that balances and cash totals agree across all three statements.

  • Populating a financial model template with historical data
  • Building linked forecasts across three financial statements
  • Comparing base, upside, and downside scenarios
NousResearch/hermes-agent255KUpdated Oct 18, 2026

accelerate

FreeSummary

Adapt existing PyTorch training scripts to use multiple GPUs or machines with limited code changes. The skill guides configuration, launch commands, mixed precision, which uses lower-precision numbers, and DeepSpeed or FSDP settings for distributing training work and memory.

  • Move a single-GPU training script to multiple GPUs
  • Configure mixed precision training
  • Set up DeepSpeed or FSDP to reduce memory use
NousResearch/hermes-agent255KUpdated Oct 18, 2026

actual-setup

FreeSummary

Configure Hermes to run AI models through Actual Computer on your own hardware. Set up either the hosted relay or a local connection, select models, verify responses, and troubleshoot request errors or empty output.

  • Connecting Hermes with an Actual inference key
  • Running models through a local Actual daemon
  • Downloading and loading local models
NousResearch/hermes-agent255KUpdated Oct 18, 2026

Test an app from the perspective of a frustrated, less technical user. Find confusing steps and barriers, separate actionable usability problems from personal complaints, and produce screenshots, suggested fixes, and prioritized tickets.

  • Reviewing usability before a launch or demo
  • Checking the experience of a new user
  • Finding friction in signup and subscription flows
NousResearch/hermes-agent255KUpdated Oct 18, 2026

Resolve Git merge conflicts between two agents by comparing both changes and their stated goals. Combine compatible work, explain choices where designs differ, and verify the merged result with project builds or tests.

  • Resolving conflicts between branches edited by two agents
  • Integrating changes from parallel worktrees
  • Reviewing reasons for conflicting design choices
NousResearch/hermes-agent255KUpdated Oct 18, 2026

See all skills by NousResearch

Report a problem with this skill