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.
-
zhanlincui Bundle Wechat WritingUse when generating a complete WeChat article from a topic, with optional source research, evidence tracking, illustration, HTML conversion, and draft-box publishing.
-
zhylq Bundle Zhy Wechat WritingUse when generating a complete WeChat article from a topic, with optional source research, evidence tracking, illustration, HTML conversion, and draft-box publishing.
-
tutti-os Bundle ImagegenGenerate or edit raster images in AI Media Canvas when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, ads, storyboards, UI mockups, product images, or cutout-style assets. Use when the assistant should create a brand-new image, transform an existing image, derive visual variants from references, or prepare a production-ready prompt for the generate_image tool. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.
-
tutti-os Bundle Canvas DesignCreate beautiful visual art as .png and .pdf files using design philosophy. Use when the user asks to create a poster, visual artwork, design piece, or static visual output via code generation. Requires the execute tool and Python with Pillow/reportlab.
-
uxjoseph Skill Supanova Premium AestheticTeaches AI to design landing pages that feel like $150k agency work. Defines exact fonts, spacing, shadows, card structures, animations, and Korean typography standards that make Supanova-generated pages feel expensive and intentional. Blocks all common defaults that make AI designs look cheap or generic.
-
uxjoseph Skill Supanova Design EngineSupanova Landing Page Design Engine. Generates premium, conversion-optimized landing pages using pure HTML + Tailwind CSS (CDN). Overrides default LLM biases toward generic templates. Enforces metric-based design rules, Korean typography standards, and hardware-accelerated motion for standalone HTML output.
-
vamseeachanta Skill Website QualityProfessional-grade quality bar for aceengineer.com — the design system as it actually ships, plus the accessibility, typography, layout and consistency criteria every page is held to. Use when reviewing or changing any page under content/**, when adding a capability page, or when asked whether the site "looks professional".
-
vdelacou Bundle AtelierSenior-engineer coding standard for Bun/TypeScript, Next.js, and Java (Quarkus) repos. Enforces strict TDD (primary-port SUT, hand-written fakes, no mocks), Clean Architecture (`src/{domain,use-cases,infra,presenter,composition}`), `Result<T, E>` at IO boundaries, branded types at trust boundaries, Bun-only or Maven toolchains (no `class`/`function` declaration/`interface`/`console.*` in TS), Atomic Design, a logic-free design system (no Tailwind in app code), and production disciplines covering privacy (no PII in logs/URLs), tenant isolation, IO deadlines, soft-delete, expand-contract migrations, optimistic locking, observability, AI ports with evals, delivery, accessibility. Use for ANY code task in a Bun, Next.js, or Java repo, covering writing, scaffolding, testing, refactoring, review, React components, APIs, persistence, debugging, security. Consult even when conventions are not mentioned; rules are non-negotiable; violations are rewritten.
-
veritasian Bundle Image Prompt GuidePrompt engineering and tool routing for AI image generation and editing. Use for: creative generation, product photo editing, e-commerce platform image sets, and specialized scenes (white background, authorized watermark/element cleanup, HD upscale, scene swap, model showcase, selling point, logo design, tech pack, etc.). Do NOT use for: full product development workflows (use ai-product-designer), or non-AI operations like resize/crop/compress/format-convert (use native tools).
-
victorzhong0110 Bundle Frontend DesignProduce a distinctive, subject-grounded UI plan and implementation notes. Use when the user asks for a new page, landing, dashboard, or restyle — including requests that never say "design system" but clearly need visual direction.
-
raffaelecamanzo Bundle Md2pdfConvert Markdown files to professional PDF documents using Pandoc + XeLaTeX. Use when the user asks to generate a PDF, export a document, create a PDF from markdown, or produce a printable version of any .md file. Supports two templates: "sourcesense" (corporate branding with logo, red/orange palette, copyright footer) and "standard" (clean professional layout, blue/gray palette, no branding). Also use when asked to convert documentation, specs, sprint docs, or any project markdown to PDF.
-
spacezephyr Bundle Article Cover And Batch Illustration分析文章结构并生成公众号视觉素材,默认使用 Codex 内置 image_gen/image2。当用户说"制作封面图"、"生成封面"时输出一张 2.35:1 白底工程风封面图;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"时为段落批量生成多张专业逻辑图/概念图。自动保存到Obsidian图片目录并按需插入文档。
-
locusyuri Bundle General Paint By Py编写 Python + matplotlib 绘图脚本,生成教材级(教科书排版风格)的数学/物理教学插图与数据图——包括网格/表格式图形、数学结构示意图、物理场景图、函数曲线图,并渲染输出 PNG 或 SVG。当用户提出"画/绘制/生成/做一张图、figure、chart、示意图、diagram、illustration"等请求、给出一段需要转为图片的详细视觉规格、或要求修改一个现有绘图脚本时使用。
-
locusyuri Skill Physics Model FiguresGenerate physics-textbook figures pairing a conceptual model diagram with the governing function curves (e.g. electric field + potential vs. distance). Use when drawing a physics concept illustration that needs a model/scene panel beside one or more function plots.
-
novuhq Skill Figma To CodeUse when given a Figma URL and asked to make a component or section match the Figma design. Covers fetching Figma data, mapping design tokens to Tailwind/CSS, and updating component code.
-
sapiens-ostracism678 Bundle Generative UIDesign system and guidelines for Claude's built-in generative UI — the show_widget tool that renders interactive HTML/SVG widgets inline in claude.ai conversations. This skill provides the complete Anthropic "Imagine" design system so Claude produces high-quality widgets without needing to call read_me first. Use this skill whenever the user asks to visualize data, create an interactive chart, build a dashboard, render a diagram, draw a flowchart, show a mockup, create an interactive explainer, or produce any visual content beyond plain text or markdown. Triggers include: "show me", "visualize", "draw", "chart", "dashboard", "diagram", "flowchart", "widget", "interactive", "mockup", "illustrate", "explain how X works" (with visual), or any request for visual/interactive output. Also triggers when the user wants to display financial data visually, create comparison grids, or build tools with sliders, toggles, or live-updating displays.
-
spatie Skill Tailwindcss DevelopmentAlways invoke when the user's message includes 'tailwind' in any form. Also invoke for: building responsive grid layouts (multi-column card grids, product grids), flex/grid page structures (dashboards with sidebars, fixed topbars, mobile-toggle navs), styling UI components (cards, tables, navbars, pricing sections, forms, inputs, badges), adding dark mode variants, fixing spacing or typography, and Tailwind v3/v4 work. The core use case: writing or fixing Tailwind utility classes in HTML templates (Blade, JSX, Vue). Skip for backend PHP logic, database queries, API routes, JavaScript with no HTML/CSS component, CSS file audits, build tool configuration, and vanilla CSS.
Audited -
xe Bundle Xe Design SystemXe Iaso Design System — Skill
-
callmeming Bundle Design LinterA design specification linter that automatically detects code violations against design system specifications. On startup, it fuzzy searches for design system documentation in the project and lets users select the specification source; if none is found, it guides users to select a CSS variables file or uses built-in rules. | 设计规范走查器,自动检测生成的代码是否违反设计系统规范。启动时模糊搜索项目内的设计系统文档(支持多种命名),让用户选择规范来源;未找到时引导用户选择 CSS 变量文件或使用内置规则兜底。
-
callmeming Bundle Component GuideAn intelligent component management assistant that automatically determines whether to create new components, reuse existing ones, or ask users for decisions based on their instructions. Ensures component consistency and compliance based on design system specifications. | 智能组件管理助手,根据用户指令自动判断是否创建新组件、复用现有组件,或在需要时询问用户创建决策。基于设计系统规范,确保组件一致性和合规性。
-
castor6 Bundle Design StyleUse this skill whenever the user asks to build, create, design, develop, improve, or style any frontend interface or visual element. This includes: - Landing pages, websites, web apps, dashboards, portfolios, or any web UI - UI components (buttons, forms, cards, navbars, modals, etc.) - React, Vue, Next.js, Svelte, or other frontend frameworks - CSS, Tailwind, styled-components, or styling help - Visual improvements or aesthetic upgrades - Requests mentioning frontend, UI, UX, interface, web design, or styling - Adjectives like beautiful, modern, clean, professional, minimalist, dark, brutalist, etc. This skill loads the appropriate design system prompt (Neo-brutalism, Modern Dark, Bauhaus, Cyberpunk, Material, etc.) to generate distinctive, production-grade frontend code instead of generic UI. IMPORTANT: Trigger proactively for ANY frontend/UI-related request, even if no style is specified.
-
hosseinkm89 Bundle Figma Rename LayersBatch-renames Figma layers from their design content instead of leaving default names like "Frame 1" or "Rectangle 23". Walks every frame and its child layers on the current page, derives a readable Title Case name from the most prominent text, a contained component, or an image fill, and applies the names in batches the designer can undo. Triggers when a designer wants to clean up generic layer names — phrasings like "rename all my layers", "my layers are all called Frame 1, Frame 2", "auto-rename these frames based on what's inside them", "clean up the layer names on this page", "name my layers from their content", "batch rename layers", "rename layers by content", or "fix these default layer names". Renames frames plus their generic-named children, preserves names the designer set on purpose, and chunks large pages so each batch is one undo step. The skill also documents Figma's built-in AI "Rename layers" command as a manual fallback for nuanced cases — that feature is editor-UI only and cannot be trigger
-
hosseinkm89 Bundle Accessibility Contrast AuditAudits color contrast on a Figma page against WCAG 2.1 AA and AAA, then writes a clean, designed report onto a brand-new page in the same file. For every top-level frame it scores text contrast (1.4.3 AA and 1.4.6 AAA, with the large-text exception) and flags low-contrast UI strokes/borders (1.4.11, 3:1), giving each frame a PASS/FAIL verdict. The report lists one row per frame with pass/fail badges and a clickable link that jumps straight to that frame, plus its node address printed underneath — so findings are easy to act on without cluttering the layout. Triggers when a designer wants to check contrast or accessibility before handoff — phrasings like "check the color contrast on this page", "run a WCAG contrast audit", "is this design AA compliant?", "which frames pass AA and AAA?", "audit contrast and write up the results", "are my text colors accessible?", "find low-contrast text", "contrast check before handoff", or "make me an accessibility contrast report". Reads the designs and creates a report page
-
joe-simo Bundle Apple Design SystemCommunity skill for designing, redesigning, reviewing, and polishing Apple-style interfaces using official Apple Human Interface Guidelines and Apple Developer design resources only. Use for platform-native and Cupertino-style UI across iOS, iPadOS, macOS, watchOS, tvOS, visionOS, SwiftUI, UIKit, AppKit, and web translations; typography, semantic color, layout, materials, Liquid Glass, SF Symbols, app icons, navigation, controls, components, accessibility, motion, platform adaptation, responsive behavior, asset/licensing boundaries, screenshots, and Apple-quality UI polish. Community-authored, not official Apple. Trigger for Apple HIG, Apple design, Apple-style UI, iOS UI, macOS UI, visionOS UI, Cupertino UI, SF Pro, SF Symbols, Liquid Glass, or native-feeling Apple-platform product design. Skip non-visual work unless it materially changes rendered UI.
-
joe-simo Bundle Vercel Geist Design SystemCommunity skill for applying the Geist design system to Vercel-inspired rendered frontend UI across React/Next.js/Vite/Astro/Svelte/Vue/HTML/CSS, Tailwind, shadcn, and Radix. Use for typography, spacing, color, materials, components, app shells, dashboards, forms, tables, dialogs, states, responsive layout, and UI polish. Community-authored, not official Vercel. Trigger for Geist, Vercel-style UI, or generic clean/modern/premium/polished SaaS/developer-product visuals when no other final visual system is requested. Skip non-visual work unless it materially changes rendered UI.
-
klionskiy Bundle Swiftui From FigmaThis skill should be used when the user wants Claude Code to convert approved Figma mobile app screens into production-ready SwiftUI code, map Figma components to SwiftUI views, or implement iOS screens based on a Figma file using Figma MCP.
-
klionskiy Bundle Appstore Mvp ReviewThis skill should be used when the user wants Claude Code to review a mobile app MVP, product concept, Figma design, feature list, App Store submission plan, or competitor-inspired app for App Store readiness, differentiation, thin-wrapper risk, and practical release scope.
-
klionskiy Bundle Mobile Figma DesignerThis skill should be used when the user wants Claude Code to create, improve, audit, or structure mobile app interfaces in Figma using Figma MCP. It is best for iOS or Android MVP screens, onboarding, paywalls, home screens, practice flows, settings, empty states, design systems, and handoff-ready mobile UI.
-
mfrostbutter Bundle Figma DesignDesign, build, or edit a Figma file through a design connector (plugin-API calls verified with screenshots). Use whenever the task is to create or change a Figma design, mock up a UI, logo, infographic, or design system, build styles or components, or hand a design to dev. Triggers even if the user does not name Figma but asks to "mock up", "design a screen", or "build a component library". Encodes the hard rule that page structure and layer naming come before any frame.
-
cth9191 Bundle Dom CloneExtract and rebuild the DOM/CSS layer of a web page — layout, typography, colors, spacing, real content, assets, and normal interactions — into clean components, section by section, from exact getComputedStyle() values rather than guesses. This is the DOM/CSS track: it deliberately does NOT handle WebGL/WebGPU/canvas shader surfaces (those go to shader-extract). Usually driven by the clone-site coordinator, but can be used directly when the user wants to rebuild a page's markup/styling and there are no GPU-rendered effects. Trigger on "rebuild this section", "extract the CSS/layout", "clone the markup and styling of this page", or the DOM half of a full site clone.
-
cth9191 Bundle Clone SiteReverse-engineer and rebuild any website — including its WebGL/WebGPU/canvas shader effects — into a clean local codebase. Use this whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy a website or landing page, especially designy sites with animated/shader/3D hero backgrounds. This is the top-level coordinator: it does recon, classifies every page surface as DOM vs GPU-rendered, routes plain layout to the dom-clone sub-skill and shader surfaces to the shader-extract sub-skill, scaffolds a build target on demand, composites the two tracks, and runs automated visual QA. It also produces a human-readable TEARDOWN.md (stack, measured design system, every effect with its exact runtime params and how it works) — pass --analyze-only to stop there. Trigger on "clone this site", "rebuild this page", "make a copy of this website", "reverse-engineer this landing page", "clone this but the background is some WebGL thing", any pixel-accurate site reproduction, AND on analysis asks: "how did the
-
dmccreary Bundle Circuit Diagram GeneratorGenerate clear, beginner-friendly circuit and wiring diagrams for microcontroller projects (Raspberry Pi Pico + NeoPixels, push buttons, rotary encoders, sensors, switches, batteries) using the schemdraw Python library, in the Moving Rainbow house style — red power rail across the top, black ground rail across the bottom, amber signal wires, light component blocks, white background, and PNG + SVG output. Use this skill whenever the user wants to create, draw, generate, redraw, or update a circuit diagram, wiring diagram, schematic, hookup figure, "how the parts connect" illustration, or breadboard wiring picture for a kit or microcontroller project — even if they don't mention schemdraw by name. Also use it when adding a wiring figure to a kit's documentation page.
-
goorm-dev Bundle Token Lint지정한 경로의 vapor 디자인 토큰 CSS 변수 사용을 검사합니다. .css/.scss/.sass/.less/.ts/.tsx/.js/.jsx 파일에서 `var(--vapor-...)` 참조를 스캔하여, 정식 토큰 집합에 없는 이름을 신고하고 세그먼트 정렬 Damerau-Levenshtein 합 거리 2 이내의 가장 가까운 유효 토큰을 최대 3개까지 제안합니다. 사용자가 디자인 토큰 린트, 토큰 오타 검사, vapor 토큰 사용 검증, Figma에서 코드로 변환한 결과의 `var(--vapor-)` 참조 감사를 언급하거나 `/token-lint <path>`를 요청할 때 사용하세요. 디자인 의도 단계의 린트(의미 범위, 사용 가능/금지 여부)는 Figma 단계에서 이미 끝난 것으로 가정합니다 — 이 스킬은 개발자가 토큰을 코드에 옮겨 적는 과정에서 발생하는 전사 오타만 잡습니다. 자동 수정은 하지 않고 제안만 합니다.
-
goorm-dev Bundle Figma Token ReviewFigma 시안에서 vapor 디자인 토큰(색상 + typography)이 올바르게 쓰였는지 4축으로 검증하는 스킬. Figma URL이 등장하고 토큰·색상·폰트·스타일 사용에 대한 질문이 조금이라도 있으면 반드시 이 스킬을 써라. 사용자가 "토큰 검토", "색상 맞게 썼어?", "폰트 위계", "Text Style", "do-not-use", "raw 색", "토큰 사용성", "디자인 토큰 적법성", "fg 배경 맞아?" 같은 표현을 쓰거나, Figma 링크를 던지며 "이거 맞아?", "확인해줘", "리뷰해줘"라고만 해도 이 스킬을 적용한다. 영어로 "check token usage", "review design tokens", "color token audit", "typography hierarchy", "is this token correct" 같이 물어도 마찬가지다. 이 스킬은 4축(raw/바인딩 · semantic 의미 · typography 위계 · 배경-전경 짝)을 결정론(코드)과 의미 판정(LLM)으로 나눠 PASS/FAIL + confidence + 근거 + 대체 토큰을 출력한다. 단, "컴포넌트 가이드라인 ↔ 코드 props 간극" 비교는 design-gap 스킬의 영역이다.
-
hferello Bundle Arch FlowDrafts architecture documentation with ASCII box diagrams and pseudocode (no raw SQL or implementation syntax). Optionally creates an editable FigJam diagram via the Figma plugin when requested. Use when the user asks for architecture diagrams, flow documentation, arch-flow.md, FigJam architecture flows, or documents cron, API, or feature flows.
-
imsus Skill Tailwindcss DevelopmentAlways invoke when the user's message includes 'tailwind' in any form. Also invoke for: building responsive grid layouts (multi-column card grids, product grids), flex/grid page structures (dashboards with sidebars, fixed topbars, mobile-toggle navs), styling UI components (cards, tables, navbars, pricing sections, forms, inputs, badges), adding dark mode variants, fixing spacing or typography, and Tailwind v3/v4 work. The core use case: writing or fixing Tailwind utility classes in HTML templates (Blade, JSX, Vue). Skip for backend PHP logic, database queries, API routes, JavaScript with no HTML/CSS component, CSS file audits, build tool configuration, and vanilla CSS.
Audited
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 circuit-diagram-generator, wechat-writing, zhy-wechat-writing. 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.