packages/skills-catalog/skills/(design)/frontend-design/SKILL.md
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications. Generates creative, polished code that avoids generic AI aesthetics. Do NOT use for design review or audit (use web-design-guidelines or web-quality-audit).
npx skillsauth add tech-leads-club/agent-skills frontend-designInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices.
Commit to a BOLD aesthetic direction:
CRITICAL: Choose a clear conceptual direction and execute it with precision. Bold maximalism and refined minimalism both work—the key is intentionality, not intensity.
Then implement working code that is:
→ Consult typography reference for scales, pairing, and loading strategies.
Choose fonts that are beautiful, unique, and interesting. Pair a distinctive display font with a refined body font.
DO: Use a modular type scale with fluid sizing (clamp) DO: Vary font weights and sizes to create clear visual hierarchy DON'T: Use overused fonts—Inter, Roboto, Arial, Open Sans, system defaults DON'T: Use monospace typography as lazy shorthand for "technical/developer" vibes DON'T: Put large icons with rounded corners above every heading—they rarely add value and make sites look templated
→ Consult color reference for OKLCH, palettes, and dark mode.
Commit to a cohesive palette. Dominant colors with sharp accents outperform timid, evenly-distributed palettes.
DO: Use modern CSS color functions (oklch, color-mix, light-dark) for perceptually uniform, maintainable palettes DO: Tint your neutrals toward your brand hue—even a subtle hint creates subconscious cohesion DON'T: Use gray text on colored backgrounds—it looks washed out; use a shade of the background color instead DON'T: Use pure black (#000) or pure white (#fff)—always tint; pure black/white never appears in nature DON'T: Use the AI color palette: cyan-on-dark, purple-to-blue gradients, neon accents on dark backgrounds DON'T: Use gradient text for "impact"—especially on metrics or headings; it's decorative rather than meaningful DON'T: Default to dark mode with glowing accents—it looks "cool" without requiring actual design decisions
→ Consult spatial reference for grids, rhythm, and container queries.
Create visual rhythm through varied spacing—not the same padding everywhere. Embrace asymmetry and unexpected compositions. Break the grid intentionally for emphasis.
DO: Create visual rhythm through varied spacing—tight groupings, generous separations DO: Use fluid spacing with clamp() that breathes on larger screens DO: Use asymmetry and unexpected compositions; break the grid intentionally for emphasis DON'T: Wrap everything in cards—not everything needs a container DON'T: Nest cards inside cards—visual noise, flatten the hierarchy DON'T: Use identical card grids—same-sized cards with icon + heading + text, repeated endlessly DON'T: Use the hero metric layout template—big number, small label, supporting stats, gradient accent DON'T: Center everything—left-aligned text with asymmetric layouts feels more designed DON'T: Use the same spacing everywhere—without rhythm, layouts feel monotonous
DO: Use intentional, purposeful decorative elements that reinforce brand DON'T: Use glassmorphism everywhere—blur effects, glass cards, glow borders used decoratively rather than purposefully DON'T: Use rounded elements with thick colored border on one side—a lazy accent that almost never looks intentional DON'T: Use sparklines as decoration—tiny charts that look sophisticated but convey nothing meaningful DON'T: Use rounded rectangles with generic drop shadows—safe, forgettable, could be any AI output DON'T: Use modals unless there's truly no better alternative—modals are lazy
→ Consult motion reference for timing, easing, and reduced motion.
Focus on high-impact moments: one well-orchestrated page load with staggered reveals creates more delight than scattered micro-interactions.
DO: Use motion to convey state changes—entrances, exits, feedback DO: Use exponential easing (ease-out-quart/quint/expo) for natural deceleration DO: For height animations, use grid-template-rows transitions instead of animating height directly DON'T: Animate layout properties (width, height, padding, margin)—use transform and opacity only DON'T: Use bounce or elastic easing—they feel dated and tacky; real objects decelerate smoothly
→ Consult interaction reference for forms, focus, and loading patterns.
Make interactions feel fast. Use optimistic UI—update immediately, sync later.
DO: Use progressive disclosure—start simple, reveal sophistication through interaction (basic options first, advanced behind expandable sections; hover states that reveal secondary actions) DO: Design empty states that teach the interface, not just say "nothing here" DO: Make every interactive surface feel intentional and responsive DON'T: Repeat the same information—redundant headers, intros that restate the heading DON'T: Make every button primary—use ghost buttons, text links, secondary styles; hierarchy matters
→ Consult responsive reference for mobile-first, fluid design, and container queries.
DO: Use container queries (@container) for component-level responsiveness DO: Adapt the interface for different contexts—don't just shrink it DON'T: Hide critical functionality on mobile—adapt the interface, don't amputate it
→ Consult ux-writing reference for labels, errors, and empty states.
DO: Make every word earn its place DON'T: Repeat information users can already see
Critical quality check: If you showed this interface to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.
A distinctive interface should make someone ask "how was this made?" not "which AI made this?"
Review the DON'T guidelines above—they are the fingerprints of AI-generated work from 2024-2025.
User says: "Build a landing page for a developer tools product, something that doesn't look like every other SaaS." Actions: Pick a bold direction (e.g. brutalist or editorial); choose a distinctive type pairing and a cohesive palette; implement with fluid spacing and one clear focal point; avoid cards-in-cards and hero-metric clichés. Result: A single-page layout with clear hierarchy, memorable typography, and no generic AI tells (no purple gradients, no rounded cards with thick accent borders).
User says: "Create a dashboard for viewing analytics with a dark theme." Actions: Commit to a specific dark aesthetic (e.g. refined dark with tinted neutrals, not default glow-on-black); use container queries for panels; add one considered motion moment (e.g. staggered list load); ensure empty states are helpful. Result: Functional dashboard that feels intentionally designed—distinct palette, no cyan/purple glow, clear data hierarchy and responsive behavior.
User says: "Make a poster for a conference talk about frontend performance." Actions: Choose a strong typographic or visual concept; use a modular type scale and limited palette; avoid generic stock-photo + headline layout. Result: A poster that could stand alone as a designed artifact—memorable type and composition, not a template fill-in.
Match implementation complexity to the aesthetic vision. Maximalist designs need elaborate code with extensive animations and effects. Minimalist or refined designs need restraint, precision, and careful attention to spacing, typography, and subtle details.
Interpret creatively and make unexpected choices that feel genuinely designed for the context. No design should be the same. Vary between light and dark themes, different fonts, different aesthetics. NEVER converge on common choices across generations.
Remember: the AI is capable of extraordinary creative work. Don't hold back—show what can truly be created when thinking outside the box and committing fully to a distinctive vision.
development
Generate Excalidraw diagrams from natural language descriptions. Outputs .excalidraw JSON files openable in Excalidraw. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", "generate an Excalidraw file", "draw an ER diagram", "create a sequence diagram", or "make a class diagram". Supports flowcharts, relationship diagrams, mind maps, architecture, DFD, swimlane, class, sequence, and ER diagrams. Can use icon libraries (AWS, GCP, etc.) when set up. Do NOT use for code architecture analysis (use the architecture skills), Mermaid diagram rendering (use mermaid-studio), or non-visual documentation (use docs-writer).
tools
Browser debugging, performance profiling, and automation via Chrome DevTools MCP. Use when user says "debug this page", "take a screenshot", "check network requests", "profile performance", "inspect console errors", or "analyze page load". Do NOT use for full E2E test suites (use playwright-skill) or non-browser debugging.
development
Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Use when the user asks to threat model a codebase or path, enumerate threats or abuse paths, or perform AppSec threat modeling. Do NOT use for general architecture summaries, code review, security best practices (use security-best-practices), or non-security design work.
development
Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Use when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do NOT use for general maintainer lists, non-security ownership questions, or threat modeling (use security-threat-model).