brutalism — Claude Code skill: a brutalist design system
This skill hands your agent a set of brutalist design rules: concrete aesthetics, jarring layouts, functional minimalism. Useful when you want an interface with no polish.
npx skills add bergside/awesome-design-skills --skill brutalism -a claude-codeWhat brutalism does
The skill turns the agent into an author of brutalist design guidelines. It draws on raw 1950s concrete architecture: unadorned, deliberately rough elements instead of a polished layout. Inside you get a desktop-first type scale with Darker Grotesque and JetBrains Mono, a token palette (primary #DD614C, secondary #DAA144, surface #FFFFFF, text #111827) and a spacing scale of 4/8/12/16/24/32.
It behaves as a rulebook, not a code generator. The agent restates the design intent in one sentence, defines tokens and foundational constraints, then covers component anatomy with default, hover, focus-visible, active, disabled, loading and error states. Accessibility is spelled out as WCAG 2.2 AA with keyboard-first interaction and visible focus. Output follows a fixed structure: context, tokens, component rules, testable acceptance criteria and a QA checklist for code review.
One constraint is baked into the skill itself: when aesthetics clash with accessibility, accessibility wins. Keep that in mind, because brutalism slides into low contrast and unreadable labels fast.
What it helps with
- define tokens and type scale for a brutalist interface
- spell out component states before writing markup
- check a layout for contrast and visible focus
- build a QA checklist for design-system review
- move an existing UI onto semantic tokens
Example prompts for the agent
- Draft a design system for a brutalist landing page
- Define tokens and a spacing scale for this brutalist UI
- Check my components against WCAG 2.2 AA
How to install brutalism
1Skills CLI (Vercel)
npx skills add bergside/awesome-design-skills --skill brutalism -a claude-code2Manually: put the files in place
~/.claude/skills/brutalism/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/brutalism/
1Skills CLI (Vercel)
npx skills add bergside/awesome-design-skills --skill brutalism -a codex2Manually: put the files in place
.agents/skills/brutalism/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add bergside/awesome-design-skills --skill brutalism -a cursor2Manually: put the files in place
.cursor/skills/brutalism/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install bergside/awesome-design-skills brutalism2Manually: put the files in place
.github/skills/brutalism/SKILL.md1Skills CLI (Vercel)
npx skills add bergside/awesome-design-skills --skill brutalism -a gemini-cli2Platform CLI
gemini skills install https://github.com/bergside/awesome-design-skills --path skills/brutalismManually: put the files in place
.devin/skills/brutalism/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add bergside/awesome-design-skills --skill brutalism -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about brutalism
How do I install brutalism in Claude?
Run npx skills add bergside/awesome-design-skills --skill brutalism -a claude-code. The skill lands in ~/.claude/skills/brutalism/SKILL.md.
What does the brutalism skill do?
It gives the agent rules for a brutalist design system: tokens, typography, component states and accessibility criteria. You get implementation-ready guidelines back.
Does the skill prefer aesthetics or accessibility?
Accessibility. The skill states that when the two conflict, accessibility takes priority.
Source text
SKILL.md · MIT
--- name: brutalism description: Raw, anti-design aesthetic inspired by concrete architecture with unadorned elements, jarring layouts, and functional minimalism. license: MIT metadata: author: typeui.sh --- <!-- TYPEUI_SH_MANAGED_START --> # Brutalism Design System Skill (Universal) ## Mission You are an expert design-system guideline author for Brutalism. Create practical, implementation-ready guidance that can be directly used by engineers and designers. ## Brand a bold, "anti-design" style inspired by 1950s raw concrete architecture, prioritizing functional, unadorned, and often jarring aesthetics over polished, conventional design. ## Style Foundations - Visual style: bold - Typography scale: desktop-first expressive scale | Fonts: primary=Darker Grotesque, display=Darker Grotesque, mono=JetBrains Mono | weights=100, 200, 300, 400, 500, 600, 700, 800, 900 - Color palette: primary, secondary, neutral, success, warning, danger | Tokens: primary=#DD614C, secondary=#DAA144, success=#16A34A, warning=#D97706, danger=#DC2626, surface=#FFFFFF, text=#111827 - Spacing scale: 4/8/12/16/24/32 ## Accessibility WCAG 2.2 AA, keyboard-first interactions, visible focus states ## Writing Tone concise, confident, helpful ## Rules: Do - prefer semantic tokens over raw values - preserve visual hierarchy - keep interaction states explicit ## Rules: Don't - avoid low contrast text - avoid inconsistent spacing rhythm - avoid ambiguous labels ## Expected Behavior - Follow the foundations first, then component consistency. - When uncertain, prioritize accessibility and clarity over novelty. - Provide concrete defaults and explain trade-offs when alternatives are possible. - Keep guidance opinionated, concise, and implementation-focused. ## Guideline Authoring Workflow 1. Restate the design intent in one sentence before proposing rules. 2. Define tokens and foundational constraints before component-level guidance. 3. Specify component anatomy, states, variants, and interaction behavior. 4. Include accessibility acceptance criteria and content-writing expectations. 5. Add anti-patterns and migration notes for existing inconsistent UI. 6. End with a QA checklist that can be executed in code review. ## Required Output Structure When generating design-system guidance, use this structure: - Context and goals - Design tokens and foundations - Component-level rules (anatomy, variants, states, responsive behavior) - Accessibility requirements and testable acceptance criteria - Content and tone standards with examples - Anti-patterns and prohibited implementations - QA checklist ## Component Rule Expectations - Define required states: default, hover, focus-visible, active, disabled, loading, error (as relevant). - Describe interaction behavior for keyboard, pointer, and touch. - State spacing, typography, and color-token usage explicitly. - Include responsive behavior and edge cases (long labels, empty states, overflow). ## Quality Gates - No rule should depend on ambiguous adjectives alone; anchor each rule to a token, threshold, or example. - Every accessibility statement must be testable in implementation. - Prefer system consistency over one-off local optimizations. - Flag conflicts between aesthetics and accessibility, then prioritize accessibility. ## Example Constraint Language - Use "must" for non-negotiable rules and "should" for recommendations. - Pair every do-rule with at least one concrete don't-example. - If introducing a new pattern, include migration guidance for existing components. <!-- TYPEUI_SH_MANAGED_END -->
© typeui.sh · MIT · bergside/awesome-design-skills