design-md
Author, consume, and enforce a DESIGN.md design system spec (Google Labs open format, package @google/design.md). This skill should be used when the project has a DESIGN.md at the root or under docs/, when the user mentions "design tokens", "design system spec", "DESIGN.md", "tokens.json", needs to translate a design system into Tailwind theme config, export tokens to DTCG, lint token consistency, diff design system revisions, or check WCAG contrast on component color pairs. Acts as the upstream source of truth for impeccable-colorize, impeccable-typeset, impeccable-audit, impeccable-critique, web-design-guidelines, and shadcn.
What this skill does
# DESIGN.md — Design System Source of Truth
DESIGN.md is an open format (repo: `google-labs-code/design.md`, package `@google/design.md`) for describing a visual identity to coding agents. It combines **machine-readable design tokens** (YAML front matter) with **human-readable rationale** (Markdown prose). Tokens are normative; prose provides application context.
When this skill loads, the design system stops being something the agent guesses at and becomes something the agent *reads*. Every sibling design skill in the frontend plugin should defer to DESIGN.md when it exists.
## MANDATORY PREPARATION
The spec is `alpha` and under active development. Before any non-trivial authoring work, fetch the authoritative spec and linting rules:
```bash
npx @google/design.md@latest spec --rules
```
Treat that output as canonical. Do not paraphrase the schema from memory for high-stakes changes — re-verify.
## Detection & Mode
Before acting, decide which of three modes you are in.
1. **Consume mode** — `DESIGN.md` exists at the project root or `docs/DESIGN.md`. Read it first, internalize `## Overview` and `## Do's and Don'ts`, and ground every downstream suggestion in its tokens.
2. **Author mode** — user asks to "create a design system", "write design tokens", "generate a style guide", or wants to seed one alongside a shadcn init.
3. **Propose mode** — neither file nor explicit ask, but the user is picking colors/typography from scratch. Use `AskUserQuestion` to ask whether to commit to a DESIGN.md before scattering ad-hoc hex values.
Detect with `ls DESIGN.md docs/DESIGN.md 2>/dev/null` or `Glob("{DESIGN.md,docs/DESIGN.md,design/DESIGN.md}")`. Do not assume.
## Spec Essentials
Section order is fixed. Sections can be omitted, but the ones present must follow this order (the `section-order` lint rule is a warning):
| # | Section | Aliases |
|:--|:---------------------|:-------------------|
| 1 | Overview | Brand & Style |
| 2 | Colors | — |
| 3 | Typography | — |
| 4 | Layout | Layout & Spacing |
| 5 | Elevation & Depth | Elevation |
| 6 | Shapes | — |
| 7 | Components | — |
| 8 | Do's and Don'ts | — |
YAML front matter schema (abbreviated — verify against `spec --rules` for edge cases):
```yaml
---
version: alpha
name: <string>
description: <string> # optional
colors:
<token-name>: "#RRGGBB" # sRGB hex, required start with "#"
typography:
<token-name>:
fontFamily: <string>
fontSize: <Dimension> # px | em | rem
fontWeight: <number> # 100..900
lineHeight: <Dimension | number> # unitless = multiplier of fontSize (preferred)
letterSpacing: <Dimension>
fontFeature: <string> # optional, maps to font-feature-settings
fontVariation: <string> # optional, maps to font-variation-settings
rounded:
<scale>: <Dimension> # sm, md, lg, xl, full, ...
spacing:
<scale>: <Dimension | number>
components:
<component>:
backgroundColor: "{colors.primary}" # references via {path.to.token}
textColor: "{colors.on-primary}"
typography: "{typography.body-md}" # components may reference composite typography
rounded: "{rounded.md}"
padding: <Dimension>
size|height|width: <Dimension>
---
```
Valid component properties: `backgroundColor`, `textColor`, `typography`, `rounded`, `padding`, `size`, `height`, `width`. Variants are expressed as sibling keys (`button-primary`, `button-primary-hover`, `button-primary-active`).
Recommended (non-normative) token names:
- **Colors:** `primary`, `secondary`, `tertiary`, `neutral`, `surface`, `on-surface`, `error`
- **Typography:** `headline-display`, `headline-lg`, `headline-md`, `body-lg`, `body-md`, `body-sm`, `label-lg`, `label-md`, `label-sm`
- **Rounded:** `none`, `sm`, `md`, `lg`, `xl`, `full`
## CLI Workflow
All commands accept a file path or `-` for stdin. Default output is JSON, exit code `1` on error/regression.
### `lint` — validate structure and token resolution
```bash
npx @google/design.md@latest lint DESIGN.md
```
The linter runs eight rules:
| Rule | Severity | Meaning |
|:----------------------|:---------|:----------------------------------------------------------|
| `broken-ref` | error | `{path.to.token}` does not resolve |
| `missing-primary` | warning | Colors defined but no `primary` — agents will auto-synth |
| `contrast-ratio` | warning | Component bg/text pair below WCAG AA 4.5:1 |
| `orphaned-tokens` | warning | Color token defined, never referenced by any component |
| `missing-typography` | warning | Colors present, no typography — agents fall back to defaults |
| `section-order` | warning | Sections out of canonical order |
| `token-summary` | info | Per-section token counts |
| `missing-sections` | info | Optional sections absent when other tokens exist |
Fix `error` rows first. Surface `contrast-ratio` warnings to the user — promote them to ship blockers if the project commits to WCAG AA+.
### `diff` — regression detection between two revisions
```bash
npx @google/design.md@latest diff DESIGN.md DESIGN.next.md
```
Exits `1` when the candidate has more errors or warnings than the baseline. Use before committing any token schema change.
### `export` — emit consumable token shapes
```bash
npx @google/design.md@latest export --format tailwind DESIGN.md # v3 theme.extend JSON
npx @google/design.md@latest export --format dtcg DESIGN.md # W3C DTCG tokens.json
```
### `spec` — inject spec into an agent prompt
```bash
npx @google/design.md@latest spec # full markdown spec
npx @google/design.md@latest spec --rules # + lint rules table
npx @google/design.md@latest spec --rules-only # only the rules table
npx @google/design.md@latest spec --format json # programmatic
```
### Programmatic API (when scripting)
```ts
import { lint } from '@google/design.md/linter';
const report = lint(markdownString);
report.findings; // Finding[]
report.summary; // { errors, warnings, info }
report.designSystem; // parsed DesignSystemState
```
## Tailwind v4 Adaptation (critical)
`export --format tailwind` emits **Tailwind v3** shape (JS `theme.extend` object with `colors`, `fontFamily`, `fontSize`, `borderRadius`, `spacing`). The frontend plugin targets **Tailwind v4** with CSS-first `@theme { ... }`. Do not drop the raw JSON into `tailwind.config.*`.
Apply this transform when emitting into `app/globals.css` (or wherever `@theme` lives):
| DESIGN.md token | Tailwind v4 CSS variable |
|:-------------------------------------|:--------------------------------------|
| `colors.<name>` | `--color-<name>` |
| `typography.<name>.fontFamily` | `--font-<name>` |
| `typography.<name>.fontSize` | `--text-<name>` |
| `typography.<name>.lineHeight` | `--text-<name>--line-height` |
| `typography.<name>.letterSpacing` | `--text-<name>--letter-spacing` |
| `typography.<name>.fontWeight` | `--font-weight-<name>` |
| `rounded.<scale>` | `--radius-<scale>` |
| `spacing.<scale>` | `--spacing-<scale>` |
Example:
```css
@theme {
--color-primary: #1a1c1e;
--color-neutral: #f7f5f2;
--font-h1: "Public Sans", sans-serif;
--text-h1: 3rem;
--text-h1--line-height: 1.1;
--text-h1--letter-spacing: -0.02em;
--radius-smRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.