Design & Media

ch4570 Bundle

Refine a product screen's color composition, layout, hierarchy, grouping, spacing, typography, density, and responsive structure while preserving its brand and behavior. Use for weak palettes or placement, visual cleanup, inconsistent layouts, cramped content, or narrow styling fixes; leave workflow logic and copy rewrites to their specific skills.

hoangnb24 Skill

Repo-local bridge skill for shadcn/ui work. Use when a dedicated agent is composing UI, extending the design system, or adding shadcn components in a Next.js frontend.

egoisutolabs Skill

Bias Figma design output toward 2030-aligned radical aesthetics and explicitly reject generic 2022 SaaS defaults. Use when the designer asks for "2030", "futuristic", "radical", "anti-polish", "cyberpunk", "spatial UI", "HUD", "editorial", "brutalist", "maximalist", "Y2K", "AI-native", "make this less generic", "not another SaaS landing", or signals a clear preference for forward-looking design. Works in concert with the `design-system` skill — this skill filters the style pool and enforces anti-patterns, design-system produces the Figma output.

egoisutolabs Skill

Add premium ambient glow / atmospheric depth to dark-mode Figma screens using blurred alpha ellipses. Use when the designer asks for "ambient depth", "premium feel", "glow behind hero number", "iOS-style atmosphere", "aurora background", "dark mode with depth", or similar. Works on any frame; no component dependency.

egoisutolabs Bundle

Turn a product brief into a Figma design system — color palette, type pairing, aesthetic/style, layout spine, and component scaffold — as real Figma Variables, Paint Styles, Text Styles, and Components. Use when the designer asks to "set up a design system", "pick colors and fonts for a new app", "build a brand foundation in Figma", "give me a palette and type scale", "start a new project", "scaffold a design system", or anything that needs a coherent visual foundation before screens get built. Reads from bundled reference data (161 palettes, 57 type pairings, 85 styles, 161 product-type rules) to make opinionated recommendations, not defaults.

egoisutolabs Skill

Rename Figma layers semantically based on their content, role, and position. Use when the designer asks to "rename layers", "clean up layer names", "fix Rectangle 1234 names", "give these semantic names", or similar. Operates on the current Figma selection by default.

egoisutolabs Skill

Create a multi-variant Figma component correctly. Use when the designer asks to "make this a variant", "add size/state variants", "build a button with primary/secondary/ghost", "turn this into a component set", or any task that needs VARIANT properties. Covers the full promote → clone → combine → add properties sequence and avoids the "variant properties require component set" trap.

jangles-byte Bundle

Establish a deliberate aesthetic point of view before building anything visual. Use this skill FIRST whenever starting any visual work — a website, landing page, app UI, dashboard, data visualization, slide deck, game screen, generative art piece, poster, or component library — even if the user only says "make it look good", "build me a page", or "design a UI". Also use it when the user complains that a design looks generic, bland, "AI-generated", or like a template. This skill produces a short written design philosophy that every other design decision follows.

jangles-byte Bundle

Typography & Layout

mrwogu Skill

UI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces, including pages, components, design systems, accessibility, interaction, responsive layout, typography, color, charts, and stack-specific UI implementation. Searchable local data: 79 searchable styles (50 active), 192 product palettes and reasoning profiles, 74 font pairings, 119 UX guidelines, 105 icons, 17 GSAP presets, 25 chart types, and 22 stacks.

pixelvault-dev Skill

Generate an image with an AI model (via OpenRouter — e.g. Gemini image / "Nano Banana") and host it on PixelVault, getting a permanent CDN URL back. Use when you need to CREATE an image and then embed it somewhere durable — a blog hero, an OG/social card, a README diagram, a docs illustration — and a temporary model URL or a base64 blob won't do. Prompt in, permanent https://img.pixelvault.dev/... URL out.

jrajasekera Bundle

Z.ai API integration for building applications with GLM models. Use when working with Z.ai/ZhipuAI APIs for: (1) Chat completions with GLM-4.7/4.6/4.5 models, (2) Vision/multimodal tasks with GLM-4.6V, (3) Image generation with GLM-Image or CogView-4, (4) Video generation with CogVideoX-3 or Vidu models, (5) Audio transcription with GLM-ASR-2512, (6) Function calling and tool use, (7) Web search integration, (8) Translation, slide/poster generation agents. Triggers: Z.ai, ZhipuAI, GLM, BigModel, Zhipu, CogVideoX, CogView, Vidu.

kaustavr19 Bundle

Critique and audit the visual aesthetics of any existing UI from screenshots and/or URLs. Evaluates six dimensions: typography & type hierarchy, colour system & palette harmony, spacing/rhythm/layout, motion & microinteractions, iconography & illustration style, and overall visual personality & brand cohesion. Benchmarks against design systems (Material, Apple HIG, Fluent), design movements (Swiss, Bauhaus, Brutalism), and industry peers. Outputs diagnosis + specific fix values (hex, type scale, spacing) + inspiration refs. Adapts output: written brief, design tokens, or critique report as needed. Trigger when user shares screenshots or URL and asks about visual quality, aesthetics, look and feel, or design critique. Also trigger for "roast my design", "aesthetic audit", "visual critique", "does this look good", "what's off", or "how do I make this feel more premium/modern/cohesive".

kjooncho Skill

Figma 또는 디자인 정보를 받아 개발자용 사양서를 생성한다. 엣지케이스 11종 + 토큰 + Analytics 이벤트 포함. Trigger in any language — e.g. "create a developer handoff spec", "edge case spec", "開発者向けの仕様書を作って", "ハンドオフ資料まとめて".

aditya-ariosity Bundle

Audit, diagnose, score, and recommend fixes for a design system, design tokens, token architecture, component library, Figma library, Storybook, or design-ops model. Evaluate product-wide consistency, accessibility, adoption, and governance. Trigger on "audit our design system", "review these components", "assess token drift", "review our design tokens", or "improve design ops". Use ux-ui-audit for a product screen or flow. Do not create a visual brand from scratch.

alfredxw Skill

Generate one spoiler-free illustration for the current or specified chapter and save it under workspace assets/illustrations.

alvinindra Bundle

Direction for image-led, typography-disciplined pages that read like designed articles — design journals, architecture magazines, hospitality brands, fashion houses, cultural institutions, studios, and premium service brands whose pages should feel printed, not scrolled. Enter through the parent pack at ../SKILL.md.

alvinindra Bundle

Direction for grid-led, type-disciplined pages with Swiss-modernist rigor and institutional confidence — design-forward brands, portfolios, systems products, cultural institutions, archive interfaces, B2B technical platforms, and any work where typography, grid, and precision must do all the work. Enter through the parent pack at ../SKILL.md.

receptron Bundle

Create a conversation practice chat MulmoScript with speech bubble UI and character illustration (voiceover approach). Use when the user wants to create English conversation practice content.

rommapp Skill

Argosy design tokens system. Use BEFORE adding colors, dimensions, typography, motion specs, or component defaults to ensure they go in tokens.json (the single source of truth), not as hardcoded literals in Composables.

theexperiencecompany Skill

Design language and visual conventions for the GAIA web app (apps/web). Use when building new components, pages, tool call sections, chat bubbles, or any UI element in GAIA. Covers the design philosophy, color system, typography, spacing, icons, animations, and all patterns needed to make anything look native to GAIA.

theexperiencecompany Bundle

Create high-quality Remotion video animations for GAIA product commercials. Use when building, modifying, or creating new scenes for the GAIA promotional video (apps/video), creating Apple-style motion design commercials in Remotion, or when working on any video animation in the GAIA monorepo. Covers scene architecture, animation patterns, typography, transitions, sound design, and aesthetic rules derived from 72 production conversations. Also use when the user asks to create a new video, add scenes, fix animation timing, or improve visual quality of Remotion compositions.

theexperiencecompany Skill

Use when reverse-engineering a codebase's implicit design system, creating a DESIGN.md style guide, documenting design tokens, or establishing visual language standards. Also use when asked to audit UI consistency, rationalize ad-hoc styling into a system, or prepare a design reference that enables one-shotting new components.

vercel-labs Bundle

Builds UI components using the Blok design system for Sitecore Marketplace apps. Use when the user wants to create UI, add components, build a page layout, or work with Blok/shadcn components in a marketplace app.

sriwitsumo Bundle

Draft, revise, and quality-check Thai official correspondence, project proposals, research writing, and APA 7 references, including Thai typography and document layout. Use for หนังสือราชการ, โครงงาน, reports, theses, or academic manuscripts; defer to an institution's required template when supplied.

ssheleg Bundle

Use when designing or improving HOW users move through the product - task analysis, user flows (screens, branches, error paths), screen states, low-fi wireframes, Figma mockups, heuristic UX evaluation and redesign proposals. A paid-acquisition funnel is one of these flows - its step chain and branches, onboarding, the paywall step and the activation funnel, read against reference screens from the same category. Maintains docs/ux/flows.md between foundation (stories) and scenarios. Triggers - "user flow" / "юзер флоу", "screen flow" / "флоу экранов", "user path" / "поток пользователя", "improve UX" / "улучши UX", "fix UX" / "почини UX", "wireframe" / "вайрфрейм", "design a screen" / "нарисуй дизайн", "mockup" / "мокап", "task analysis", "redesign flow", "reference screens" / "референсы", "funnel" / "воронка", "onboarding" / "онбординг", "paywall" / "пейволл", "activation funnel" / "активация". Visual system and Figma variables belong to sheleg-design.

t4sh Bundle

CI-anchored code-to-Figma token export pipeline for keeping Figma aligned with the codebase. Use when the user asks to "sync code to Figma", "export design tokens to Figma", "set up a Figma sync pipeline", "wire up the tokens-sync-to-figma plugin", "generate a figma-export.json", "create a page walker", or "keep Figma up to date with the codebase".

t4sh Bundle

Repo-first Figma-to-code workflow for implementation, design tokens, design-system rules, and Code Connect. Use when the user asks to "implement this Figma design", "turn this Figma into code", "build from a Figma link", "match this Figma mockup", "extract Figma design tokens", "create Figma design system rules", "set up Figma guidelines", "code connect this component", or "map this Figma component to code"; or when a Figma URL/selection must become repository code, code tokens, agent rules, or Code Connect mappings.

yu-369 Skill

Hero-section pipeline for building Awwwards/FWA-tier hero sections. Extracts design direction from reference images, provides six hero architectures with implementation blueprints, and enforces the fundamentals that separate award-winning heroes from generic AI output - viewport-scale typography, single focal point, extreme whitespace, tight palette. Hero-only. Pair with other skills for full pages.

yu-369 Skill

Motion design pipeline for building Awwwards/Apple-tier animations, micro-interactions, scroll sequences, page transitions, and kinetic typography. Enforces the principles that separate award-winning motion from generic CSS transitions - intentional easing, scroll-linked choreography, staggered reveals, magnetic interactions, text splitting, parallax depth, morphing state transitions, and the invisible micro-animations that make interfaces feel alive. Every animation must justify its existence, respect reduced-motion, and run at 60fps. Motion is choreography, not decoration.

yu-369 Skill

Surgical aesthetic upgrade pipeline for existing React codebases. Takes ugly, functional code (Bootstrap defaults, generic Tailwind, amateur CSS) and transforms it to Awwwards-tier quality WITHOUT touching or breaking the underlying JavaScript logic - states, effects, API calls, event handlers, routing, and data flow are sacred and untouchable. Audits the existing code across 7 layers (tokens, typography, spacing, color, components, atmosphere, motion), classifies every element as Sacred (JS logic - do not touch) or Slop (visual cruft - upgrade), then executes precise CSS-only surgery layer by layer. The skill that turns a developer's "make this look better" into a controlled, non-destructive visual transformation.

zeiynz Bundle

Audit a React/Next.js component or codebase for accessibility, performance, and consistency issues before shipping — checks re-render patterns, prop drilling depth, missing memoization, unhandled loading/error states, and WCAG violations. Use whenever the user shares a component file and asks to "review this", "is this production-ready", "why is this slow", "check this for accessibility", or before merging a PR that touches shared UI components. Also trigger proactively when generating new components if the user's codebase context suggests these standards apply (TypeScript strict mode, existing design system usage).

zhangxiansheng-888 Bundle

Generate realistic AI portrait photography prompts by translating photo references, portrait ideas, photography judgments, or style articles into executable shooting-brief prompts. Use when the user asks for 真人写真提示词, AI人像写真, 上传真人照片生成写真, 保留本人长相, 脸部细节, 五官锚点, 妆容, 滤镜, 质感词, 摄影感prompt, 焦段/光圈/景深/光线/色调怎么写进人像prompt, 单人写真, 情侣写真, 九宫格写真, 职业写真, 头像, 生活方式人像, 人像变量库, 填空模板, prompt for realistic portrait photos, or a reusable portrait prompt framework. Do not use for non-human illustration, product/scene/poster prompts without real-person portrait intent, video prompts, storyboards, or purely illustrated characters.

zhiming33416 Bundle

Create, revise, audit, render, and export publication-ready computer-science paper figures using a Python-first, corpus-calibrated workflow. Use for manuscript figures, multi-panel experimental charts, comparison plots, scaling curves, heatmaps, embeddings, network diagrams, method schematics, executable YAML/CSV figure render specs, figure-brief handoffs, caption/callout alignment, SVG/PDF/PNG/TIFF export bundles, and visual QA for WWW, ICLR, ICML, NeurIPS, CVPR, ACL, or generic top-CS submissions. Do not use for interactive dashboards, Plotly/Altair/web apps, Illustrator/Figma-first layout, AI-generated graphical abstracts, or result-table writing.

lotfb86 Skill

Responsive web design sub-skill. Provides mobile-first layout patterns, CSS Grid/Flexbox strategies, responsive images, fluid typography, container queries, and breakpoint systems. Pull this in whenever building or reviewing UI that must work across mobile, tablet, desktop, and large screens. Triggers on: "make it responsive", "responsive design", "mobile-first", "breakpoints", "fluid layout", or any request involving cross-device layout.

lotfb86 Skill

Generate a structured DESIGN.md file for any business or project. Produces a machine-readable design system specification that build pipelines consume during code generation. Based on VoltAgent/awesome-design-md format.