plugin/skills/design-system-patterns/SKILL.md
Use this skill when designing UI, defining or auditing a design system, reviewing UX deliverables, specifying components, evaluating accessibility, or producing redlines and tokens for engineering handoff — the UI/UX knowledge base covering user research, personas, jobs-to-be-done, user journeys, usability testing, information architecture, wireframing, prototyping, visual design, typography, color theory, grid systems, visual hierarchy, micro-interactions, animation, design systems, atomic design, design tokens, Figma workflows, WCAG 2.2 accessibility, responsive and mobile-first design, Material Design 3, Apple HIG, Nielsen heuristics, Gestalt principles, conversion-centered design, and design-to-code handoff.
npx skillsauth add avav25/ai-assets design-system-patternsInstall 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.
Human-centered design knowledge: user research, IA, visual + interaction design, design systems, accessibility, responsive behavior, platform guidelines, and design-to-code handoff. Combines cognitive psychology (Gestalt, Nielsen heuristics) with platform conventions (Material 3, Apple HIG) to produce accessible, conversion-optimized interfaces. Use this knowledge when applying the ui-ux-designer role or any workflow that needs UX rigor.
Design Thinking phases: Empathize → Define → Ideate → Prototype → Test.
End-to-end touchpoints with emotions, pain points, and opportunities mapped per stage. Reveals friction invisible at the single-screen level.
Interviews, contextual inquiry, card sorting, tree testing, surveys, A/B testing, heatmaps. Choose by question: discovery (interviews), structure (card sort), validation (A/B).
Task-based, think-aloud protocol. 5 users surface ~85% of issues (Nielsen). Test on real devices, not desktop simulations.
Establish importance order via size, color, contrast, spacing, position, typography weight. Apply Gestalt principles:
Consistent shadow scale (sm → xl). Shadows encode hierarchy, not decoration.
Trigger → Rules → Feedback → Loops. Visible feedback within 100ms keeps users oriented.
Design every state: default, hover, focus, active, disabled, loading, error, success, empty. Skipping any state = bug.
150–300ms. Ease-out on enter, ease-in on exit. Motion supports comprehension, never decoration alone.
Interactive elements must look interactive. Clear clickability, editability, draggability cues.
Larger targets faster to acquire; nearer targets faster still. Touch targets ≥44×44px; WCAG 2.2 minimum 24×24px.
Constraints over confirmations. Undo over warnings. Inline validation on blur, not on every keystroke.
Essentials first. Details on demand. Reduces cognitive load.
Skeletons over spinners. Optimistic UI for predictable success. Progress indicators when >1s.
Atoms (tokens, icons, buttons) → Molecules (input groups, cards) → Organisms (headers, forms) → Templates → Pages.
blue-500: #3B82F6).color-primary: {blue-500}, color-error: {red-500}).button-bg: {color-primary}).Token categories: color, spacing, typography, elevation, border-radius, motion duration + easing.
Document props, variants, sizes, all states, accessibility requirements, usage guidelines, do/don't examples. Every component has anatomy + behavior + a11y + code example.
Semantic versioning per release. Changelog every update. Breaking changes require migration guide.
clamp(min, preferred, max) scales smoothly between breakpoints.Dynamic color (user-themable palette derived from a seed), expressive motion, adaptive layouts. Primary reference for Android + cross-platform web.
Clarity, deference, depth. SF Symbols for iconography. Primary reference for iOS + macOS. Respect platform conventions (swipe-back gesture, safe areas, status bar contrast).
Depth, motion, material, scale. Reference for Windows surfaces.
Underlined links, top-left logo → home, search/cart top-right. Violate only with deliberate cause.
Proximity, similarity, continuity, closure, figure-ground, common region — see Visual Hierarchy.
--color-primary, --spacing-4, --font-size-lg.| Workflow | Apply this knowledge |
|---|---|
| Agent(ui-ux-designer) invocation | Auto-loaded |
| /feature-design Wave 2 UX-FLOW | Spawned designer loads this |
| /architecture (UX-FLOW step) | Architect references for IA + flows |
| /seo-review (accessibility section) | SEO reviewer references WCAG checks |
| /content-creation (visual direction) | Content designer references tokens + hierarchy |
| /code-review (UI changes) | Reviewer checks tokens + states + a11y |
ui-ux-designer (primary), frontend-engineer (implementation handoff), content-designer (visual direction), seo-engineer (a11y + Core Web Vitals), content-writer (UI microcopy).development
Use this skill when running the recurring (daily) knowledge-base rescan for a repo that already has knowledge/.knowledge-sync.yml — the main-thread dispatcher that reads the config, computes the git delta since last_scanned_sha, maps changed paths to affected doc areas, early-exits cheaply when nothing changed, then fans out one Agent(content-writer) per affected area, applies the propose/direct update policy, advances the baseline only on success, and writes an L4 run log — all with the G1 untrusted-content choke-point, secret-scan, deny-list, and budget controls woven in. For first-time setup use /knowledge-sync-init.
development
Use this skill when bootstrapping scheduled knowledge-base sync for a repo that has no knowledge/.knowledge-sync.yml yet — to run one-time setup that detects the knowledge_root from CLAUDE.md/AGENTS.md, maps doc areas to source globs, records opt-in external sources (Linear/Notion/WebFetch, all disabled by default), captures a baseline last_scanned_sha, sets the per-area update policy, generates or seeds knowledge/CONVENTIONS.md, provisions the L4 memory dir, and offers to register the daily routine. Routes ongoing recurring sync operations to /knowledge-sync.
tools
Use this skill when bootstrapping a target repository to be ai-skills-aware — on the first run of any ai-skills workflow in a fresh repo, when adopting the ai-skills plugin in an existing repo, or after upgrading to a plugin version that adds new memory paths or templates, including when the user does not say "init" but asks to "set up" or "onboard" the repo — to detect codebase type, create CLAUDE.md + AGENTS.md scaffolding, initialize the .ai-skills-memory/ directory tree from L1 templates, and configure .gitignore. Idempotent — safe to re-run. Accepts `--codebase-type <type>` and `--overwrite`. Not for re-initializing only memory — use `/memory-init` instead.
tools
Use this skill when extending, repairing, or improving plugin assets, when ingesting a `/feedback` report as a fix-cycle backlog, or when you do not remember which lower-level command is right for the job — the umbrella workflow for ai-skills plugin-asset authoring and maintenance: creating, auditing, fixing, improving, refactoring, and migrating skills, agents, rules, hooks, prompts, schemas, and rubrics inside the plugin. Auto-classifies the request, loads the right knowledge skills (`@prompt-engineering`, `@context-engineering`, `@team-protocols`), and spawns the right subagents (`prompt-engineer`, `system-architect`, `python-engineer`, `software-engineer`, `qa-engineer`, `eval-judge`) via the `Agent` tool.