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.
-
narumiruna Bundle Author Marp SlidesWrite, revise, structure, or validate Marp/Marpit Markdown slides, including directives, layouts, themes, templates, and rendered-deck checks. Use for slide authoring when palette or illustration design is not the primary task.
-
aktsmm Bundle Visualize As InfographicCreate colorful infographic PNGs from a conversation, topic, file, skill, or workflow. Use when: インフォグラフィック, 図解, 挿絵, 章扉, X投稿用画像, OGP, HTML→PNG, visualize session, poster image. Produces 2-3 self-contained HTML patterns, renders PNGs, and verifies every image visually before reporting.
-
igorwarzocha Skill BrandingApply official brand colors and typography to professional artifacts. Use for presentations, reports, and documents to ensure corporate visual identity. Use proactively when a "client-ready" look-and-feel is requested. Examples: - user: "Brand this report" -> apply corporate colors and fonts - user: "Apply brand guidelines to these slides" -> update colors/fonts in XML - user: "Check if this document is on-brand" -> verify against color/font standards
-
paperclipai Bundle Design GuidePaperclip UI design system guide for building consistent, reusable frontend components. Use when creating new UI components, modifying existing ones, adding pages or features to the frontend, styling UI elements, or when you need to understand the design language and conventions. Covers: component creation, design tokens, typography, status/priority systems, composition patterns, and the /design-guide showcase page. Always use this skill alongside the frontend-design skill (for visual quality) and the web-design-guidelines skill (for web best practices).
-
microsoft Bundle Powerbi Report DesignGenerate Power BI report visual design guidance before PBIR files are written. Use when the user wants to: (1) choose tone, signature, page archetypes, chart types, layout, color, typography, theme direction, or accessibility approach, (2) redesign/restyle an existing report, apply a brand, or critique chart/layout choices, (3) produce a design contract for `powerbi-report-authoring`. For end-to-end requirements, approval, and build sequencing, use `powerbi-report-planning`. Triggers: "design Power BI report", "make dashboard look professional", "choose chart type", "apply brand to report", "redesign report", "create design brief", "Power BI report design archetype".
2.7k -
meitu Skill Video Logo Add使用 meitu-cli 给视频四角叠加 Logo/水印图片,支持透明底 PNG。当用户提到加水印、加 Logo、打 Logo、贴标、加角标、合成水印、叠加 Logo、视频贴牌、品牌标识时触发。
-
meitu Skill Video Element Remove使用 meitu-cli 从视频中消除路人/字幕/水印/Logo 或一键清屏全部文字。当用户提到去路人、去行人、去字幕、去对白、去水印、去 Logo、去角标、消除抖音号、清屏、纯净画面、不要出现任何字时触发。
-
meitu Skill Image Poster Generate文/图生海报,多风格多尺寸带排版,支持参考图/已有海报修改文字/背景/元素。当用户提到海报、宣传图、广告图、Banner、推广图、营销图、活动海报、促销海报、poster时触发。
-
vudovn Bundle Design SpecHow to author a DESIGN.md file — the machine-readable design-token + human-rationale format that must exist before any UI is built. YAML front-matter token schema (colors, typography, spacing, rounded, components), type system, token references, and canonical section order.
-
whawkinsiv Bundle BeautifyUse this skill when the user wants to make their app look better, says it looks like a template, asks how to achieve Stripe/Linear quality, or says something looks off. Covers visual hierarchy, whitespace, composition, color application, and typography in practice.
-
whawkinsiv Skill Brand Identity GeneratorUse this skill when the user needs to create a visual brand identity for their product. Generates a comprehensive BRAND-IDENTITY.md file for the project root. Covers colors, typography, spacing, components, accessibility, and responsive design — with no gaps for AI to fill with generic defaults.
-
danielmiessler Bundle ArtStatic visual content across 20+ formats — diagrams, mermaid, infographics, D3 dashboards, comics, icons, wallpaper — via Nano Banana Pro (default), Nano Banana, and Flux. USE WHEN art, illustration, diagram, flowchart, infographic, header image, blog social thumbnail, visualize, generate image, mermaid, architecture diagram, comic, icon, blog art, framework diagram, D3 chart, remove background, wallpaper. NOT FOR locked house-style YouTube/channel/video thumbnails, video or animation (use Remotion), or web UI design and integrated frontend layout (use Webdesign).
-
danielmiessler Bundle HTMLRenders the current session's output (analysis, research, red team, report, plan) as an extremely well-designed, self-contained HTML artifact via a deterministic renderer — the model distills content into typed JSON, the tool owns all layout/typography/color. USE WHEN /HTML, HTML artifact, render this as HTML, make this an HTML page, artifact of this analysis, designed HTML output. NOT FOR deployed websites or web apps (build the project directly), web UI design systems (use Webdesign), static images or diagrams (use Art), or writing the underlying analysis itself (run the analysis first, then /HTML renders it).
-
danielmiessler Bundle WebdesignDesign and integrate web interfaces via three paths: DirectDesign (write design inline with Anthropic frontend-design philosophy — the default workhorse), native /design + /design-sync Claude Code commands (preferred for code integration and design-system sync), or ClaudeDesign (drive claude.ai/design through Interceptor — experimental visual-review fallback). USE WHEN web design, UI design, create prototype, design system, design sync, redesign site, mockup, landing page, dashboard design, design-to-code, frontend design, polish UI, design audit, brutalist/editorial/retro UI. NOT FOR illustrations/logos (use Art) or video (use Remotion).
-
spencerpauly Skill Using UI StackEnforce a configuration-driven design system when generating UI. Ensures consistent spacing, colors, typography, dark mode, interactions, and accessibility across all AI-generated components.
-
syncfusion-blazor-ui-components Bundle Syncfusion Blazor BarcodeBuild and troubleshoot barcode generation in Blazor using SfBarcodeGenerator, SfQRCodeGenerator, and SfDataMatrixGenerator. Trigger for 1D barcodes (Code39, Code128, Codabar), QR codes with logo and error correction, Data Matrix, checksum validation, and exporting barcodes to images in Syncfusion Blazor apps.
-
steelan9199 Skill Flat Illustration Asset Parser解析纯色平涂插画图片,输出 SAM3 提取提示词与儿童单层绘画顺序的 Markdown 表格。当用户消息中包含「分割图片」或「绘画步骤」关键词时触发此技能。
-
hermeticormus Bundle Design PrinciplesCore visual design principles that underpin all great design. Master gestalt psychology, visual hierarchy, composition, color theory, and typography fundamentals. Use when making design decisions or evaluating designs against proven principles.
-
remotion-dev Bundle Studio CSS ResetDiagnose and fix Remotion Studio UI bugs caused by the global CSS reset. Use when nested text or SVG icons have incorrect color, typography, sizing, hover states, or truncation in packages/studio.
3.9k -
scientiacapital Bundle Frontend UIEnterprise SaaS frontend — Tailwind v4, shadcn/ui, Next.js App Router or Vite SPA, accessibility, responsive design, component patterns. Use when: React component, Next.js page, frontend UI, Tailwind, shadcn, accessibility, a11y, responsive design, form validation, server component, client component, design system, dark mode, SaaS UI, dashboard, pricing page, enterprise UI, data table, landing page, Vite, React Router, SPA, single page app.
-
jiaiyan Skill Element Plus Design ColorColor design specifications for Element Plus. Invoke when user needs to understand the color palette, main colors, secondary colors, or neutral colors used in Element Plus.
8 -
jiaiyan Skill Element Plus Design TypographyTypography design specifications for Element Plus. Invoke when user needs to understand font conventions, font-family settings, or text styling guidelines.
8 -
vm0-ai Bundle InkdabBrush-pen editorial illustration with a single free-floating accent color "dab" sitting underneath loose ink linework. Black hand-wobbled ink on pure white background, ONE flat accent-color shape per prop (painted-first, never outlined in black), scribbled hatched hair, open-outline bodies with zero fill, and one small solid-accent triangle floating freely as a recurring motif. Trigger when user says /inkdab, asks for an "inkdab illustration", a "brush-pen illustration with a single accent color", a "free-floating color block illustration", or briefs in the style of the included reference images.
-
vm0-ai Bundle EndpaperRiso-grain flat-vector collection of chill characters or objects scattered across a fully saturated solid color field — like the inside endpaper of a children's picture book. Two-tone interior shading on every character, closed crescent-eye sleepy smiles, soft hand-drawn line details on props, dense overlapping composition where elements touch the canvas edges. Trigger when the user says /endpaper, asks for an "endpaper illustration", a "scattered animal or object collection on saturated color", a "children's-book endpaper scene", or briefs with a cast + background hue + density + palette.
-
vm0-ai Bundle InkstompInkstomp — a loud, hand-screened indie-packaging poster style. Full-bleed saturated flat color filling the entire canvas, a two-line hand-lettered headline (thin arched caps over chunky drop-shadowed display), and one weird-cute character drawn in thick uniform black brush ink. Trigger when the user says /inkstomp, asks for an "inkstomp poster", a "Ray Fenwick / Hattie Stewart packaging poster", an "indie brush-ink flavor card", or briefs in a "palette + headline + character" shape.
-
vm0-ai Bundle Crowd InkHand-drawn editorial crowd illustration — confident sketchy black ink contours over flat 3-color spot fills on a pure-white background, scene-as-metaphor composition, fine-line backdrop drawn lighter than the foreground, and scattered atmospheric marks in negative space. Trigger when the user says /crowd-ink, asks for a "crowd-ink illustration", an "editorial crowd scene", a "hand-drawn ink-and-spot-color illustration", a "New-Yorker-style crowd vignette", or briefs with a palette + scene metaphor + complexity level.
-
vm0-ai Bundle Folk MuseFlat folk-art gouache portrait illustration in the contemporary editorial style of Carson Ellis, Maja Tomljanovic, and Bodil Jane. A single chest-up figure with an elongated mannerist oval face, tiny almond half-lidded eyes, smooth flat hair, one hand pressed against the face, a patterned robe filling the lower frame, and an asymmetric botanical surround filling the background edge-to-edge. Hand-painted matte gouache texture, flat color blocks, no harsh outlines, no photorealism. Calm, slightly melancholic, contemplative mood. Trigger when the user says /folk-muse, asks for a "folk-art portrait", "gouache portrait", "Carson Ellis style portrait", or any new piece in this contemplative folk-portrait style.
-
vm0-ai Bundle Iso SceneIsometric editorial-magazine scene illustration in a locked flat-vector style — ultra-fine hairline outlines, monochromatic saturated background filling the canvas, and a single composed scene whose props themselves embody the theme. Trigger when users say /iso-scene, ask for an "isometric editorial illustration", a "scene illustration in the editorial machine style", or brief with palette + scene archetype + complexity.
-
vm0-ai Bundle PapernookHand-drawn editorial illustration set in a cozy cluttered personal-studio scene. Loose scratchy black ink outlines that wobble, textured gouache fills with visible brush marks, warm cream paper background, simplified dot-eye face, and a DENSE edge-to-edge composition where a centered character is orbited by thematic props that visually act out the idea. Modern editorial palette (coral / dusty blue / sage / cream) on warm cream — no mustard or burnt-orange. Trigger when user says /papernook, asks for a "papernook illustration", a "cozy cluttered editorial scene", a "warm-cream desk scene", or a new piece in this hand-drawn studio-clutter editorial style.
-
vm0-ai Bundle Mellow PopChill flat-vector editorial poster of a serene recurring character (closed-eye smile, tiny nose hint, short dark bobbed hair) posed inside a scene-as-metaphor composition on a fully saturated solid color background, with a signature pop of bright leaf-green woven into every piece. Trigger when the user says /mellow-pop, asks for a "mellow-pop illustration", "chill flat-vector poster", "saturated color-block scene", or briefs with a scene metaphor + palette + complexity level.
-
vm0-ai Bundle Riso RelicPop-art retro risograph poster of a single nostalgic everyday object — saturated single-color background, bold black ink outlines, halftone/riso grain, hand-drawn doodle accents (sparkles, squiggles, dots, music notes, lightning), tiny white "SMALL OBJECTS IN TIME" banner at top, chunky retro display headline at bottom with offset black drop-shadow. Trigger when user says /riso-relic, asks for a "riso poster", a "small objects in time" illustration, or any new piece in this nostalgic pop-art relic-object style.
-
vm0-ai Bundle Shadow PopBright flat-vector editorial illustration style — every colored shape sits in front of an offset black silhouette of itself (the signature depth trick, no outlines on the fills), with white hand-drawn dashed stitching, scattered palette-colored sparkle confetti, and a fully transparent PNG background so the piece drops cleanly onto any surface. Five dials per brief — palette (default / berry-pop / tropical / citrus-cobalt), scene metaphor, complexity (L1 / L2 / L3), confetti density, and subject domain. Trigger when user says /shadow-pop, asks for a "shadow-pop illustration", a "bright flat-vector illustration with offset shadow", an "in-app illustration with offset shadow trick", or briefs in the style of the included reference images.
-
vm0-ai Bundle Cozy ParlorHand-painted watercolor + ink-line illustration style — one anthropomorphic animal in a quiet domestic interior, on clean cool-white watercolor paper (never amber-tinted), with a neutral cool palette and a single hot accent pop. Cozy, hushed, picture-book mood. Trigger when the user says /cozy-parlor, asks for a 'cozy parlor illustration', a 'watercolor animal scene', a 'picture-book interior', or a new piece in this neutral-palette watercolor style.
-
vm0-ai Bundle Soft VectorAiry flat-vector spot illustration style — square 1:1 pale-blue canvas, delicate ~1.5-2px dark-navy linework with intentionally OPEN / unclosed outlines, flat color fills, one muted accent hue (mustard / lime-sage / warm-orange / violet), centered subject with generous breathing room, scattered thin-navy micro-marks (dots, plus signs, sparkles, or motion ticks). Trigger when the user says /soft-vector, asks for a "soft-vector illustration", a "friendly UI onboarding illustration", a "thin-line flat spot illustration", or briefs a scene metaphor + palette + complexity in this house style.
-
vm0-ai Bundle Grain PosterFlat-vector editorial poster of a serene full-body figure interacting with one hero prop — riso/halftone grain confined to a single textile (skirt or trousers), closed-eye smiling face with a single round red blush, solid black hair, limited 5-6 color palette per piece, and editorial poster framing. Six tunable dials — palette, mood, scene, cast, complexity, framing. Trigger when the user says /grain-poster, asks for a "flat-vector editorial poster", "riso-grain figure poster", "grainy editorial illustration", or briefs with a scene + palette + cast in this house style.
-
vm0-ai Bundle Emboss DebossPoetic editorial posters and covers in sculpted matte paper, with pronounced raised lettering and forms, deeply pressed contours, fine fibers, and intentional negative space. Use for /emboss-deboss, embossed paper posters, debossed typography, letterpress covers, or paper-relief design.
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 author-marp-slides, visualize-as-infographic, branding. 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.