Design & Media
Design agent skills guide AI agents through visual and UX work: UI mockups, design systems, image and asset workflows, and design reviews. A skill keeps the agent aligned with your design language instead of improvising a new style each session.
-
full-stack-skills Bundle Pencil UI Design System ElementInitialize Element Plus. design system components in Pencil variables and component overview.
-
full-stack-skills Bundle Pencil UI Design System UchartsInitialize uCharts. design system components chart placeholders and data-viz tokens in Pencil.
-
full-stack-skills Bundle Pencil UI Design System UviewproInitialize uView Pro. design system components in Pencil variables and component overview.
-
full-stack-skills Bundle Pencil UI Design System BootstrapInitialize Bootstrap. design system components in Pencil variables and component overview.
-
garveyhu Bundle Sound Gen本地生成背景音乐(BGM) + 音效(SFX)——一句文字描述直接合成,离线、免费、可商用。当用户/agent 要「配 BGM / 背景音乐 / 配乐 / 底床 / 氛围乐 / 生成音效 / whoosh / ping / 转场音 / 出场音 / 打击音 / sonic logo / text-to-music / text-to-sfx / background music / sound effect / generate BGM」,且未指定其他音频后端时使用。两个子命令:music(文生纯器乐·ACE-Step 1.5·MIT·Apple MLX·48kHz·最长10min·M3 约与实时同速) / sfx(文生短音效·Stable Audio Open Small·Stability 社区许可·≤11s·8步蒸馏·每个<1s 极快)。是媒体生态 media/audio 层继 voxcpm(人声 TTS)之后的第二条音频后端——**voxcpm 管人声、sound-gen 管音乐+音效**。产物喂进 video-polish(音效落点/BGM ducking) 与 produce-pipeline 的音频设计层。区别 stock-sourcing(下现成 CC0):本 skill 是「生成」不是「下载」,防同质化、要什么造什么。
-
genericservice Skill Print CSSWrite production-ready print stylesheets. Covers @page rules, page breaks, visibility, color management, typography, images, links, tables, and framework-specific gotchas for Next.js/React/Tailwind. Use when the user asks to add print styles, make a page printable, or create a print-friendly layout.
-
genericservice Bundle Kitchen Sink Design SystemScript-First design system workflow. Uses a deterministic auditor script to detect frameworks, inventory components, and detect design drift (hardcoded hex, arbitrary Tailwind). Provides a clear report for the agent to judge and implement a Kitchen Sink page.
-
fanlw0816 Skill Evaluate DesignUI/UX design evaluation skill that assesses visual hierarchy, responsiveness, and accessibility. Evaluates layout, contrast, typography for visual design; mobile/tablet/desktop for responsiveness; WCAG compliance for accessibility.
-
innei Bundle Generate Design MdGenerate a DESIGN.md file for any brand or website by analyzing its visual design system. Use when the user asks to "generate a DESIGN.md for [brand/URL]", "create a design system doc for [site]", "extract the design tokens from [URL]", or "make a DESIGN.md like [brand]". Triggers on any request to document a website's design language in DESIGN.md format.
-
innei Bundle Acg Character SetteiUse when generating an ACG (anime/manga) character settei sheet (キャラ設定資料) — multi-view full-body lineup, expression list, detail callouts, color palette — from a template settei image plus a single character reference image. Built on top of gemini-image-generation; this skill encodes the layout-locking + identity-locking prompt pattern that reliably produces settei-style output.
-
fivetaku Bundle Pumasi ImageImage-generation companion skill for the pumasi plugin family. Use when the user asks for an image, thumbnail, poster, logo, illustration, banner, profile image, cover, icon, or any visual artifact — including casual phrasing like "그림 하나 뽑아줘", "비주얼 만들어줘", and Codex-named requests like "코덱스로 이미지 만들어줘"; this skill owns every image request. In Codex it maps to the native image generation/editing tool (gpt-image-2), with an optional Grok image_gen backend through the bundled scripts. Korean triggers — "이미지 만들어줘", "그림 생성해줘", "썸네일 만들어", "로고 만들어줘", "일러스트 그려줘", "포스터 만들어", "배너 만들어", "아이콘 만들어", "표지 이미지". English triggers — "create image", "make thumbnail", "make logo", "make illustration", "draw image". DO NOT trigger on code-generation requests like "함수/컴포넌트/페이지/배너 컴포넌트 만들어줘" — those go to the pumasi skill.
-
fivetaku Bundle Insane DesignDesign system analyze / apply / build router plus the analysis engine. Extracts a deterministic design system from any URL by fetching real CSS, parsing custom properties, and writing a 19-section design.md (schema_version 3.2 with medium + archetype detection) plus an interactive report.ko.html. Also exports design.md frontmatter to a W3C DTCG tokens.json. Pairs with insane-apply and insane-build via the §18 DON'T hex-grep contract. Korean triggers — "디자인 분석해줘", "이 사이트 디자인 시스템 뽑아줘", "CSS 뜯어봐", "design.md 만들어줘", "레퍼런스 리포트 만들어줘", "사이트 분석", "디자인 토큰 추출", "tokens.json 내보내줘". English triggers — "analyze design", "extract design tokens", "rip the design system", "what CSS does this site use", "export DTCG tokens".
-
1c7 Skill Liquid GlassImplement, refactor, or review modern macOS SwiftUI UI for the new design system and Liquid Glass. Use when adopting Liquid Glass, updating NavigationSplitView, toolbars, search, sheets, and controls, removing custom backgrounds that fight system materials, or building custom glass surfaces with glassEffect, GlassEffectContainer, and glassEffectID.
Audited -
lukehle Skill Design TokensBuild a small token system for a page or a pack - colour roles, spacing and type scales, radii, elevation, and chart-specific tokens (categorical series, sequential ramps, semantic up/down) so every artifact reads as one system instead of a series of one-offs. Trigger on "design system", "tokens", "CSS variables", "palette", "colour scheme", "consistent styling", "series colours", "make these pages match".
-
lukehle Skill Data TypographyTypography for numbers and data-dense interfaces - tabular figures, alignment, precision and rounding, units, negative-number conventions, type scale, and the label/value pairing that makes a table or dashboard readable at a glance. Trigger on "typography", "font", "numbers don't line up", "type scale", "how many decimals", "format the numbers", "table formatting", "tabular figures", "text is hard to read".
-
commontoolsinc Skill Figma To CodeTranslate a Figma design selection into cf-* Lit component code. Use when implementing a design from Figma, reviewing component alignment, or checking how Figma properties map to code. Triggers include "implement this design", "translate from Figma", "what cf- component matches this", or having a Figma node selected to implement.
-
decocms Skill Figma To DecoImplement a complete Figma design into a Deco storefront — from reading pages and sections, downloading assets, configuring loaders, to QA with Playwright and performance auditing. Use when the user provides a Figma link and wants it built as a Deco site.
-
huang-sir1 Bundle Radiology FigureProduce publication-quality white-background academic figures for Radiology (RSNA), Nature-portfolio/npj, European Radiology, NEJM, Science, or Lancet-family venues with Python (matplotlib): ROC curves, calibration plots, decision-curve analysis, forest/SROC plots, Kaplan-Meier curves with numbers-at-risk, Bland-Altman, heatmaps, radiogenomics plots, graphical/visual abstracts, and annotated imaging panels. Uses The Lancet Digital Health guide as the default Lancet-series proxy. Use when the user wants figures, plot cleanup, figure-set planning, journal-specific figure formatting, or overlap/crowding QA. Outputs editable vector (.svg/.pdf) plus 300+ dpi raster, enforces de-identification and journal typography, and never invents data points.
-
iflytek Bundle Frontend DesignGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
-
itsjavi Bundle Design Guide AuthoringCreate or update a design guide or design system specification, usually DESIGN.md, for web or mobile interfaces. Use when asked to document visual direction, design tokens, typography, component patterns, or interaction guidelines for developers and agents. Ground the guide in the project's existing design and stack.
-
piyushverma0 Skill Design SystemGlobal-level design system for Android AI agents — Material 3 Expressive. Use this skill for visual consistency: spacing tokens, 8dp grid, M3 typography scale (15 styles), HCT color system, dynamic color Material You, shape system with morphing, motion tokens, physics-based spring animations, design tokens, AppButton/AppCard/AppTextField components, loading/error/empty states, dark mode, surface containers, tonal elevation, or when any two screens look visually different. Always apply when starting any new screen — without this skill AI agents produce apps where every screen looks designed by a different person. Apply immediately alongside compose-ui, material3, and adaptive-ui skills.
-
piyushverma0 Bundle Design TokensMaterial 3 design system foundation for Android apps. Use this skill for ANY theming, color, spacing, shape, or elevation work — MaterialTheme, colorScheme, ColorScheme roles, lightColorScheme, darkColorScheme, dynamicColorScheme, primary/secondary/tertiary/surface/background tokens, onSurface, onBackground, surfaceContainer, outline, spacing scale, 4dp grid, shape tokens, RoundedCornerShape, Shapes, elevation, tonalElevation, shadowElevation, dark mode, isSystemInDarkTheme, Material You, dynamic color, brand colors, semantic colors, Theme.kt, Color.kt. Applies to ALL app categories: fintech, edtech, healthtech, ecommerce, social, proptech, enterprise, productivity, entertainment, food, travel.
-
lichtblick-suite Skill ThemeDeep theme system knowledge: createMuiTheme factory, dark/light palette tokens, typography scale, ThemeProvider color-scheme application, and tss-react/mui styling conventions.
-
melvynx Skill FigmaFigma Code Connect CLI - connect design components to code, publish connections, parse Figma files. Use when user mentions 'figma', 'code connect', 'figma cli', or wants to link Figma designs to code.
-
black-yt Bundle Markdown To DOCXUse when converting Markdown documents into Microsoft Word .docx deliverables, including articles, reports, announcements, release notes, project documentation, image-rich explainers, meeting materials, and public-facing drafts that need embedded local images, captions, readable headings, Chinese/English typography, visible word counts, and a deterministic Python conversion workflow.
-
digitaldreams Bundle Design SystemAnalyzes the project and generates a custom, opinionated design system with Tailwind CSS CSS-first configuration (@theme), writing tasks/design_system.md from requirements, wireframes, information architecture, and the frozen architecture. Use whenever the user says "design system", "design tokens", or "set up the Tailwind theme".
-
dlazy-ai Bundle Remove Watermark去水印去文字。带水印 / 文字 / logo 的图 → 干净图,背景纹理自然补全。当用户说「去水印」「去文字」「擦掉 logo」「把字去了」时使用。
-
sallaapp Bundle Salla Embedded UIOwns native look-and-feel for a Salla app's EMBEDDED (dashboard) UI — the Partner-dashboard iframe on the Embedded SDK design system. Use WHENEVER an embedded/dashboard page draws visible UI (settings, analytics, addon flows). Its five binding gates must all pass — none skippable — and the final gate is a live demo-store screenshot. Not done until verified. Storefront UI → salla-storefront-ui; SDK/auth wiring → salla-embedded-app.
-
sallaapp Bundle Salla App UI BuilderThe Salla app's App Store listing page (the page merchants see before installing). Use when customizing that listing page. Build it via the `app_page_builder` MCP tool as an ordered list of blocks; editing a block's elements writes shared listing content (name, description, logo, screenshots, benefits) into the app's draft publication. Prerequisite: call `app_publish action=open` first to create the draft — the builder is disabled until then. Upload media with `salla_upload`. Draft/publish flow and `short_description` → salla-publication-consistency. Schemas → salla-docs.
-
seldonframe Skill Cinematic LandingDark cinematic landing system — looping Pexels MP4 background + liquid-glass UI + Instrument Serif italic typography + Framer Motion choreography. Auto-applied to agency + cinematic-aspirational (coaching, medspa, wellness, luxury) archetypes during create_full_workspace. The marketplace-forkable "fat skill" that captures the entire Aura / Velorah / Aethera / Asme aesthetic family.
-
skillatlas Skill Movie Poster GraphicsCreate generative movie-poster style graphics for products, apps, brands, campaigns, and abstract concepts. Use when a task needs poster-quality key art, archetype selection, title treatment guidance, or strong prompting for an image model.
Audited -
jinning6 Skill Frontend Layering Specificity DebugDiagnose and fix frontend controls whose typography or dimensions ignore component CSS, and React Three Fiber/Drei projected HTML labels that paint above opaque drawers, dialogs, or navigation. Use for inconsistent button sizes, element-type-dependent styling, unexpected wrapping, z-index escalation failures, or WebGL labels leaking through DOM overlays.
-
mane087 Skill Auto Size TextGuide for using Flutter AutoSizeText in a consistent, responsive, and maintainable way, including sizing constraints, scaling rules, AutoSizeGroup usage, Theme integration, and testing considerations. Trigger: Use when the task involves `AutoSizeText`, `AutoSizeGroup`, responsive text sizing, preventing text overflow in constrained layouts, adapting typography for long or translated strings, or reviewing whether auto-resizing text is being used correctly without abusing it for layout logic or global styling decisions.
-
mane087 Bundle Tailwind CSS PatternsProvides comprehensive Tailwind CSS utility-first styling patterns including responsive design, layout utilities, flexbox, grid, spacing, typography, colors, and modern CSS best practices. Trigger: When styling components, building responsive layouts, implementing design systems, or optimizing CSS workflow.
-
yousefnabil-soc Bundle ImpeccableCreate distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for shape-then-build, 'teach' for design context setup, or 'extract' to pull reusable components and tokens into the design system.
-
archibate Bundle Zhlint中文排版规范(全角标点、中英文空格)+ zhlint 校验工具。Use whenever writing or editing formal Chinese document content — Chinese markdown docs, README 中文版, blog posts, WeChat articles, translation output, announcements, tutorials — or when the user mentions 排版, 全角/半角, punctuation or spacing issues in Chinese text. Apply even if the user doesn't explicitly ask for typography checking.
Frequently asked questions
What are Design & Media agent skills?
Design agent skills guide AI agents through visual and UX work: UI mockups, design systems, image and asset workflows, and design reviews. A skill keeps the agent aligned with your design language instead of improvising a new style each session.
Which Design & Media skills are most installed?
Popular Design & Media skills on SkillMD right now include pencil-ui-design-system-element, pencil-ui-design-system-ucharts, pencil-ui-design-system-uviewpro. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Design & Media skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.