Design & Media

desquared Bundle

Annotate Figma UI screens with accessibility annotations — reading order, tab/focus order, Button, Image alt, Role/Value/Label and More info callouts — using the annotation library configured for the project. Use when asked for accessibility annotations, AX annotations, a11y markup in Figma, reading or focus order, screen reader labels for designs, or to continue an accessibility annotation handoff.

deedlefake Bundle

Design and build polished, non-generic UI for this TanStack Start + React + Tailwind v4 + shadcn/Radix app. Use whenever you create or restyle any interface surface — pages, landing pages, dashboards, forms, modals, nav, and game overlays (start screens, HUD, menus). Covers design tokens, layout, typography, color, spacing, motion, and the anti-"AI-slop" rules that keep output from looking generic. Triggers on "design", "UI", "make it look good", "polish", "landing page", "theme", "style", "redesign", "ugly", "clean up".

devenkhatri Skill

Brand DNA extractor for paid advertising. Scans a website URL to extract visual identity, tone of voice, color palette, typography, and imagery style. Outputs brand-profile.json to the current directory. Run before /ads create or /ads generate for brand-consistent creative. Triggers on: "brand DNA", "brand profile", "extract brand", "brand identity", "brand colors", "what is the brand voice", "analyze brand", "brand style guide".

devskale Bundle

Improve UI/UX of web interfaces by grounding every change in curated example sites and design references. Use when polishing a component, page, or design system - visual hierarchy, spacing, motion, empty states, accessibility, copy.

xonika9 Bundle

Use when the user explicitly invokes x9-diagrams, needs a choice between diagram formats, converts or reviews diagrams across formats, or needs one visual method with native creation and verification in Excalidraw, Mermaid, or draw.io/diagrams.net. Also use for requests such as “choose the right diagram format”, “convert this Mermaid diagram to editable draw.io”, «выбери формат схемы», «проверь и улучши диаграмму». A Mermaid-only syntax request may remain with an installed specialized Mermaid skill. Do not use for data charts, UI mockups, raster illustration, or unsupported diagram formats.

paretofilm Bundle

Apple-canon design system for SwiftUI projects: produces DESIGN.md + a Swift Package starter (semantic colors, SF Pro, Liquid Glass, motion, accessibility). Use when starting or refreshing a SwiftUI design system.

ikatkov Bundle

Generate Ian-style English article illustrations. Use for user requests that need weird, clean, hand-drawn body images, article illustrations, shot lists, or edit/remove-title tasks for English articles, posts, blogs, Notion docs, workflows, methods, structures, states, metaphors, or viewpoints. Default to the Xiaohei IP, pure white hand-drawn look, sparse red/orange/blue annotations, and a clean but imaginative visual style. Do not use for generic illustration, PPT, commercial brand art, children's cartoons, or non-Xiaohei image requests unless the user explicitly asks for Ian/Xiaohei style.

waynesutton Skill

Full-stack Convex development guidelines covering React, Vite, TypeScript, mutations, auth, design system, and documentation practices. Use when building features, writing Convex functions, or making code changes in this project.

shashidharbabu Bundle

Select export formats from Jitter (jitter.video) — the browser-based motion design tool ("Figma for motion") — and integrate its MP4/GIF/Lottie exports into Next.js 14 + Tailwind 3.4 + motion v13 (`motion/react`). Use this whenever a task involves Jitter in any form, a motion-designed asset needs to be produced by a designer and played on a page, a Lottie file (.json or .lottie) needs to be rendered in React, someone asks "how do I play this animation export", an animated logo/loader/product-demo clip needs embedding, a Figma design needs to become an animation, or when deciding between a Lottie export and a hand-coded CSS/framer-motion animation. Also use it to pick the right Lottie player package — the verified comparison (lottie-react vs @lottiefiles/dotlottie-react) and the reduced-motion/lazy-loading patterns live in references/integration.md.

shashidharbabu Bundle

Embed and integrate Spline (spline.design) 3D scenes — the collaborative browser-based 3D design tool — into Next.js 14 + Tailwind 3.4 + motion v13 (`motion/react`) via the verified @splinetool/react-spline + @splinetool/runtime packages, or decide against a live embed and use an image/video export instead. Use this whenever a task involves Spline in any form, a 3D scene/hero/product visual needs embedding in a web page, a *.splinecode or prod.spline.design URL appears, someone asks for an "interactive 3D hero", "3D landing page", "rotating product model", or "that floaty 3D blob thing", or when weighing the real cost of 3D on a landing page (the runtime is ~582KB gzipped — measured). Also use it for Spline pointer-events layering under hero copy, Suspense/poster fallbacks, reduced-motion and mobile fallbacks, and free-tier watermark questions — code and tradeoffs live in references/integration.md.

shashidharbabu Bundle

Install and integrate Componentry (componentry.dev — componentry.fun redirects there) — an MIT-licensed, Vercel-OSS-backed library of ~60 animated React components by Harsh Jadhav (@harshjdhv), distributed as copy-in source via the shadcn registry (npx shadcn@latest add @componentry/<name>) and built on framer-motion, Tailwind, and canvas/WebGL — into Next.js 14 + Tailwind 3.4 + motion v13 (`motion/react`). Use this whenever a task involves componentry.dev/componentry.fun or an @componentry/ install command, a landing page needs a spectacle background (matrix rain, dither gradient, aurora, liquid chrome, particle galaxy, circuit board, noise), an interactive set-piece (magnetic dock, eye tracking, image trail, spotlight card, split-flap display, mac keyboard), kinetic typography (letter cascade, text repel, particle typography, hyper text, text morph), or a scroll set-piece (sticky scroll cards, scroll split card, scroll velocity text, scroll choreography) — and whenever choosing between componentry and motio

shashidharbabu Skill

Stay visually current using Recent (recent.design), a daily curated feed of fresh design work across web, interfaces, branding, product, typography, motion, illustration, 3D, editorial, print, and packaging — judge whether a design "reads 2026" versus templated, run trend triage (adopt / adapt / skip) on what the feed surfaces, and translate a fresh reference into named decisions for Next.js 14 + Tailwind 3.4 + motion v13 (`motion/react`). Use this whenever someone asks "what does modern design look like right now", "does this look dated", "make it feel current/2026", "is this trend worth adopting"; whenever a recent.design URL appears in conversation; whenever a redesign brief includes freshness as a goal; or whenever you need to check what working designers are shipping this month before committing to a direction.

shashidharbabu Skill

Master router over the Design Lab's 21-skill design stack — maps any design need (direction, identity, typography, color, components, glass surfaces, texture, backgrounds, motion, 3D, video, audio, logo) to the right skill and sequences them into a complete design-system build for an application. Use this whenever a task is bigger than one asset — "build a design system", "do a full design pass", "make this app look premium", "set up the visual identity", "redesign this whole product" — or when unsure which design skill applies, or when starting design work on a new repo and deciding what to load in what order. Also owns the glass/glassmorphism recipe (no single site-skill covers it) and the aggregated licensing pre-flight for commercial launches.

shashidharbabu Bundle

Add polished, pre-built animations to React/Next.js apps using the motion-primitives component library (motion-primitives.com) — animated text reveals, number tickers, morphing dialogs, marquees, scroll reveals, hover effects. Use this whenever a task involves animating UI, making a landing page or hero section feel alive, animating numbers/KPIs on a dashboard, adding entrance/reveal animations, marquee/logo sliders, animated dialogs or popovers, shimmer/loading text states, or when someone says an interface feels "static", "flat", or "needs polish". Also use it to decide when NOT to animate. Always consult references/component-api.md for exact prop names before writing any motion-primitives code — the APIs here are extracted from source and several differ from what you'd guess.

desquared Skill

Use when implementing a Flutter feature from scratch or completing one in progress. Covers file structure, design system compliance, state management setup, error handling, testing, and build_runner requirements.

maybemonad Bundle

Aesthetic direction workflow for greenfield UI, brandless screens, new visual systems, redesign concepts, or designs that need a concrete typography, color, density, component, imagery, and motion thesis before hi-fi work.

maybemonad Bundle

Source-map extraction for design systems, brands, UI kits, screenshots, Figma files, existing codebases, reference sites, tokens, components, layout grammar, and visual vocabulary. Use before matching or extending an existing design.

stoica-mihai Bundle

Apply the Futurism Design System — a Paper-Futurist web aesthetic (bold italic display type, a single red accent, square corners, solid offset shadows, and fast directional motion) with paired light and dark themes. Use this skill whenever the user asks to build, style, or restyle any web UI — a page, component, landing hero, dashboard, form, or full app — AND wants it to follow the Futurism look, OR invokes /futurism-design, OR references "futurism", "futurist", "paper futurism", "the red/cream design", or "our design system" in this repo. Trigger it even when the user only says "make a page" or "build a component" in a project that has adopted this system, so the output stays on-brand instead of defaulting to generic styling. This is an explicit, web-only design language — do not use it for terminal/CLI output.

thearmagan Skill

Use real icon sets instead of emoji when building or editing UI. Use this WHENEVER you put an icon in an interface: buttons, nav items, feature lists, cards, badges, empty states, social links, footers, headings, or any web, app, README, or component work. Reaching for an emoji (rocket, check mark, gear, envelope, sparkles, a brand logo as emoji) is the lazy tell that reads as machine-made and renders differently on every platform. For brand and company logos use Simple Icons (https://simpleicons.org). For every other UI icon use Lucide (https://lucide.dev). Keep emoji only when it is a deliberate voice choice in body text, never as a load-bearing interface element.

gridaco Bundle

Design, review, and debug visual rendering tests: reftests (independent oracle), golden/snapshot regression tests, probe tests (pixel assertions without vision), SVG reftest suites, and Figma refig suites. Use when adding pixel diffs, choosing an oracle strategy, or comparing renderer output against a ground truth.

ironbee-ai Skill

Visual testing, UI verification, and design comparison using screenshots and Figma integration. Use when the user wants to verify UI appearance, compare with Figma designs, test responsive layouts, check for visual regressions, or validate design implementation.

jezweb Skill

Use when prompting an image-generation model: a hero image, icon set, product shot, illustration, OG image, scene, or any generated visual. Covers concrete specifics over quality adjectives, specifying the world not just the subject, describing presence not absence, reference images over style prose, anchoring sets, iterating by editing, and designing for the image's job. The image sibling of write-prompts.

yzfly Bundle

将参考图或文字描述的主体转换为低分辨率像素插画 / 像素图标（Low Resolution Pixel Sprite）。当用户上传一张图并说「做成像素风 / 像素画 / pixel art / 8-bit / 16-bit / sprite / 游戏图标 / 像素头像」，或想把 logo、吉祥物、产品、宠物、人物变成复古游戏像素素材时使用。严格保留原主体设计，只转换表现形式；输出 32×32 规格、硬边像素、有限色板、纯白背景的单主体居中图。不适用于像素风海报排版、点阵印刷海报或需要文字 / 场景的整图设计。

yzfly Bundle

出海 / 国际化品牌的极简呼吸感视觉全案。当用户说要做品牌 VI、品牌视觉、logo 与周边、独立站视觉、社区 / 组织 / 产品的品牌形象，或抱怨自己的品牌「看起来廉价」「太满太乱」「不够国际化 / 高级」，或想要「留白」「呼吸感」「高级感」的品牌设计时使用。产出定位洞察、色彩 + 留白系统、线条链接母题、线条 Emoji 表情集、应用物料（独立站 UI、名片、帆布袋、PIN、社媒封面）的生图提示词与全案展示文案。不适用于单张海报、照片风格化或纯 UI 页面编码（后者用 hallmark 等）。

yzfly Bundle

把照片做成上下 1:1 的 3:4 高级设计海报：上半原图轻调色，下半「真实物象穿越几何情绪窗口」的极简几何色块海报，自动从画面提炼标题与文案排版。当用户上传照片想要「高级感海报」「几何色块 + 留白」「像高端地产 / 奢侈品 / 美学杂志 / 节气视觉」的编辑设计，或提到「几何情绪窗口」「主体越界破框」时使用。每张照片单独输出，不拼图。不适用于手绘重绘、像素风或纯抽象色块（分别见 xxd-panel-070、pixel-sprite、photo-abstract-editorial）。

ddtcorex Bundle

Use when creating UI components, pages, design systems, or converting Figma/mockups to code. Covers Tailwind + shadcn/ui + Radix primitives, design tokens, responsive, a11y (WCAG 2.2), motion, and Figma→code workflow. Use for scaffolding a design system or generating production-ready UI. Triggers: figma, tailwind, shadcn, design system, a11y, responsive, component, landing page, dashboard, scaffold UI.

belos-street Bundle

Collection of distinctive UI design templates. Each template provides a complete design system with colors, typography, components, and layouts. Use these when building production-ready interfaces.

spacezephyr Bundle

帮助用户通过交互式问答创建自定义批量生图 Skill。用户不需要写代码，只需回答问题即可生成完整可用的生图 Skill。当用户说"帮我创建生图Skill"、"我想做一个配图技能"、"创建批量出图的Skill"、"生成图片的Skill怎么做"、"帮我做一个AI画图技能"时触发。支持文章配图、Logo设计、分镜故事、社交媒体图、海报等任意图片场景。

spacezephyr Bundle

分析文章结构并批量生成AI配图，调用Gemini API为每个段落创建专业逻辑图/概念图。当用户说"批量配图"、"给文章配图"、"生成文章插图"、"为这篇文章配图"时触发。支持两种风格：简约手绘风和建筑蓝图编辑风。自动保存到Obsidian图片目录并插入文档。

team-commonly Skill

3D Morph PPT — extends morph-ppt with GLB model insertion, cinematographic camera, model-content layout, and enriched visual design system.

xiaolai Skill

Test-driven CSS design system modifications. Run checks before/after CSS changes to verify token usage, variable definitions, fallbacks, and consistency. Use when modifying CSS tokens, fixing design inconsistencies, or auditing CSS architecture.

cometchat Skill

Add in-call messaging using CometChat Chat SDK and UI Kit. Use when implementing chat during calls, chat button, unread badge count, or group messaging linked to call session. Triggers on "in-call chat", "chat during call", "chat button", "in call messaging", "setChatButtonUnreadCount".

discourse Bundle

Write and repair HTML/CSS/SCSS for Discourse core, plugins, themes, and theme components. Use when authoring or modifying templates (.gjs/.hbs), stylesheets (.scss), component markup, class names, responsive layout, FormKit/select-kit styling, or CSS regressions. Covers Discourse's BEM-with-standalone-modifiers naming, the CSS custom-property color palette (theming + dark mode), template/HTML conventions, CSS repair patterns, and where stylesheets live.

novoads Bundle

Generate one or more standalone Meta image-ad creatives via ChatGPT Image 2 (gpt-image-2) through the Novoads API. Locks the model, auto-strips platform chrome, enforces edge-safe layouts and glyph-safety inside body text. Use when the user asks for a "gpt-image-2 ad", "ChatGPT Image ad", "Image 2 ad creative", "make a static image ad with GPT", or anchors on a need for typography-heavy / dense-text / UI-mimicry ad creatives (chat threads, comparison tables, fake search results, iOS dialogs, Slack snapshots, ChatGPT-conversation ads, Apple Notes lists). Does NOT trigger on Nano Banana cues — use nano-banana-image-ad for those.

pablostanley Skill

Build brand identities -- visual systems, color palettes, typography, voice/tone, brand guidelines. Activate for branding projects, rebrands, or when brand consistency is needed.

pablostanley Skill

Activate for color systems, typography, composition, imagery direction, and visual identity work.