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.
-
presidenteog Skill Design System SpecUse when authoring or updating a DESIGN.md design-system specification — defining color/type/spacing tokens with rationale, component state variants, and WCAG-safe palettes for a codebase or agent to consume. Trigger when a project has no design system file yet, or an existing DESIGN.md needs new components or a dark-mode variant.
-
reaperinvest Skill Style TileCreates style tiles for web design projects with typography, colors, UI elements, textures, and mood references. Use when aligning on visual direction before full design.
-
reaperinvest Skill Brand RefreshBatch updates text and imagery across existing Canva designs when brand elements change, searching for affected designs and applying find-and-replace operations across all confirmed files. Use when a user has updated their brand colors, fonts, tagline, logo, or contact info and needs to propagate those changes across multiple existing Canva designs.
-
yuanhao667 Bundle Red Book为以 AI 产品为主、但不限于软件的产品实测账号,完成热点选题判断、官方卖点核验、五分钟体验引导、轻量产品拆解,并在 Figma 固定生成 8 张画板:7 张小红书/微信小绿书发布图与 1 张双平台文案复制区;也可按需扩写公众号文章。用户说“今天拆什么”“这个产品值不值得做”“按体验做小红书测评”“把产品拆解做成 Figma 八张画板”“转成公众号版本”时使用;不用于纯资讯搬运或未经实测的功能罗列。
-
gkw77 Bundle Paper Ink ChartsRender scientific figures — bar, line, scatter, box, heatmap, multi-panel — as warm-paper single-ink charts. Activate when producing figures for a paper, thesis, lab report, or poster; when a chart needs to read as typeset rather than as default matplotlib; when the user asks for 墨迹/暖纸/单墨/论文插图风格 or complains that a figure looks like default output; when replacing viridis/tab10 defaults, adding error bars, layering significance markers, or laying out shared-scale multi-panel comparisons.
-
reaperinvest Skill Brand Identity GuideCreates comprehensive brand identity guidelines with logo usage, color codes, typography, imagery style, voice, and application examples. Use when documenting your brand standards.
-
talhamah56 Bundle Paper IllustrationGenerate publication-quality AI illustrations for academic papers. Default renderer is Gemini (Paperbanana) image generation; an alternate codex-image2 renderer (local Codex app-server bridge) is available for users without Gemini API access — see "Alternate Renderer: codex-image2". Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
-
talhamah56 Bundle Figure SpecGenerate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图", "pipeline 图", "确定性矢量图", "figure spec", "draw architecture", or needs precise, editable, publication-ready vector diagrams. Preferred over AI illustration for formal architecture/workflow figures.
-
maybackcompany Bundle Design ExtractExtract, analyze, compare, grade, clone, or apply a website design language using Manavarya09/design-extract's designlang CLI. Use when the user asks to extract a design system, inspect colors/fonts/spacing/motion/components from a URL or localhost page, generate design tokens, Tailwind/shadcn/Figma variables, compare two sites, grade a design, run visual diffs, or use "design-extract" / "designlang" on a web page.
-
maybackcompany Skill UI Color SystemApply professional UI color theory to landing pages, websites, and web interfaces — enforcing the 60/30/10 rule, neutral balance, accessible contrast, proper dark mode, element states, and semantic color usage. Use this skill whenever the user asks to design or review a landing page, website, dashboard, app UI, or any web interface and color quality matters. Also trigger when the user asks to "check the colors", "apply the 60/30/10 rule", "make this look more professional", "fix the color palette", "add dark mode", or "make the UI less chaotic." Trigger even on fresh builds — this skill should run alongside frontend-design any time colors are involved. Pairs with the saas-copywriter skill for full landing page production.
-
talhamah56 Bundle Paper Poster HTMLDEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the user says "做海报", "poster", "conference poster", "paper poster", or asks to design/redo a research poster. Supersedes the retired LaTeX /paper-poster.
-
maybackcompany Bundle ImpeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
-
maybackcompany Bundle Kishi Design ArchitectMandatory first-pass skill for branding, UI, UX, frontend design, React/Next.js components, Tailwind, shadcn/ui, landing pages, dashboards, pricing pages, forms, navbars, cards, typography, color systems, design systems, motion, accessibility, responsive behavior, and visual polish. Always use this skill before writing or reviewing user-facing frontend code or brand/design recommendations. Skip only for backend-only, database-only, infrastructure-only, CLI-only, or algorithm-only tasks with no UI/UX/branding impact.
-
ncdevshiv Bundle Brand Guidelines CommunityApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatt...
-
infrasity-labs Skill Frontend Design 2Guidance 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.
-
skillmedev Skill Print LayoutPrepares a design for commercial print - document setup with correct bleed and safe zones, CMYK color management, print typography, image resolution, and a full prepress checklist through PDF/X export and proofing. Use when someone asks "get this file print-ready", "what bleed do I need", "why did my printer reject this PDF", "will these colors print right", or is sending business cards, brochures, posters, or packaging to a print shop. Do NOT use for on-screen design deliverables or developer handoff - use design-handoff-doc instead.
-
akunikkola Bundle Tavaramerkki Ja ToiminimiTavaramerkin ja toiminimen suoja Suomen oikeuden mukaan (tavaramerkkilaki 544/2019, toiminimilaki 128/1979). Käytä tätä skilliä, kun käyttäjä suunnittelee tuotteen, palvelun tai yrityksen nimeä tai logoa, valmistelee tavaramerkin rekisteröintiä (PRH, EUIPO, Madrid), arvioi erottamiskykyä tai sekaannusvaaraa, käsittelee väite- tai mitätöintiasiaa, epäilee merkkinsä tai nimensä loukkausta tai saa varoituskirjeen. Triggeröi sanoista: tavaramerkki, brändi, logo, tuotenimi, toiminimi, yrityksen nimi, rekisteröinti, sekaannusvaara, erottamiskyky, väite, loukkaus, varoituskirje, EUIPO, PRH, verkkotunnus, domain.
-
skillmedev Skill Narration ScriptWrite the spoken voiceover for a tutorial or demo - the actual words, phrased for the ear and synced one-instruction-per-action to what is on screen, with a pacing budget and a confident, jargon-checked tone. Use when someone says "write the voiceover", "script the narration", "what should I say over this", "VO script for my tutorial", "narrate this demo", "the script feels robotic", or "the narration is too wordy". Do NOT use to mix, time, duck, source, or beat-match the audio - VO leveling, SFX, music - that is sound-and-music-sync; do NOT use to decide which scenes exist or their order - that is video-storyboard; do NOT use to direct the on-screen actions themselves (cursor, zoom, callouts) - that is product-demo-director; do NOT use to turn spoken lines into animated on-screen text - that is kinetic-typography.
-
dhruvhkumar Skill Liquid GlassLiquid glass design system skill that guides the implementation of Apple-style translucent, refractive glass effects in web interfaces. Triggers when creating or reviewing any UI that uses glassmorphism, frosted glass, backdrop blur, translucent surfaces, or the liquid glass aesthetic. Covers CSS implementation, SVG filter techniques, performance, accessibility, and when to use (and not use) the effect.
-
skillmedev Skill Captions From TranscriptProduce an accurate, properly timed caption track (SRT or WebVTT) from a video's audio - transcribing or aligning to the voiceover script, timing cues to speech, and enforcing line-length and reading-speed rules so captions are readable and in sync. Use when someone says "generate captions", "make subtitles from the audio", "transcribe and caption this", "export an SRT or VTT", "the captions are out of sync", or "the subtitles flash by too fast to read". Do NOT use to burn-in, style, reframe, or position an existing caption track for a platform (9:16, brand styling, safe areas) - that is social-video-formatter; do NOT use to animate text word-by-word as a motion graphic - that is kinetic-typography; do NOT use to write the spoken script in the first place - that is narration-script.
-
dhruvhkumar Skill Design TokensDesign token system enforcer that ensures every visual value in the UI comes from a defined, consistent token system — never from arbitrary magic numbers. Triggers when creating, reviewing, or modifying any CSS, styling, theming, color usage, spacing, typography, or visual property in a codebase.
-
kerneldroid Bundle Md3 Expressive Androidbuild, refactor, review, and polish android app ui with jetpack compose and material 3 expressive. use when coding agent or another coding agent must implement or redesign compose screens, themes, shapes, shape morphs, motion, typography, adaptive icons, monet or dynamic color, material symbols, grouped large plaques, navigation, carousels, button groups, or exact android dependency blocks; handle android 17 (api 37) defaults like baklava adaptive-by-default, handoff apis, and deliqueue performance; implement navigation 3 state-driven flows, flexbox/grid adaptive layouts, and m3e motion physics; remove ai slop from spacing, gradients, insets, cutouts, typography balance, and hierarchy; generate full import blocks; inspect optional sample app sources placed in Sources to learn better interface patterns; and query droidsearch for exact gradle, agp, maven, kotlin, compose, and androidx versions without rounding or rewriting version strings.
-
godhonggi-cmd Bundle Higgsfield Storyboard GenerationEnd-to-end storyboard-to-image production for Higgsfield. Use when the user gives a storyboard, conte, shot list, Figma board, screenshot, or cut list and wants Codex to create cut-by-cut prompts, run logged-in Higgsfield browser generation, choose quality-first models such as GPT Image 2 or Nano Banana Pro, generate two or more variants per cut, download 4K outputs, build contact sheets, select the best frame per cut, update logs, and package final deliverables.
-
buzzmatic Bundle Chatgpt ImagegenGenerate and edit images with OpenAI's GPT Image models (gpt-image-2 default, gpt-image-1.5/1/1-mini fallbacks). Text-to-image, image editing/inpainting with mask, multi-image composition, transparent backgrounds, branded photo/logo/mockup generation. Up to 3840px, PNG/JPEG/WebP, low/medium/high quality. Use for ChatGPT/OpenAI/DALL-E image generation.
-
gpire Skill Frontend 3dFrontend avanzato: React, Angular, Vite, WebGL, Three.js, GSAP, Unity WebGL, Unreal Engine, GitHub Pages, ecommerce frontend, animazioni avanzate, shader GLSL, fisica 3D, performance 3D, R3F (React Three Fiber), Drei, Cannon.js, Rapier, motion design, scroll-driven animations, CSS avanzato, design system in codice. Attiva quando l'utente vuole Three.js, WebGL, GSAP, animazioni, 3D nel browser, shader, R3F, effetti visivi avanzati, frontend interattivo.
-
bestagentkits Bundle Design SystemCaptures the user's brand identity once via a 10-question onboarding wizard (primary/accent HEX + heading + body Google Fonts + design style editorial/technical/minimal/playful + default output directory + syntax theme + TOC behavior + optional logo/company), validates body-text and link contrast against WCAG 2.2 AA, derives 12 CSS custom properties in HSL space, and stores the result for every markdown-html converter to consume. Use before any markdown-html conversion. Triggers on first-run onboarding ("set up the brand", "configure markdown-html", "run onboarding"), on explicit reset ("reset the design system", "re-onboard"), and is checked by every converter via config_loader.py before rendering. Refuses to save if body-text contrast fails AA 4.5:1 or the output dir isn't writable. Precedence: project (./.markdown-html/) > global (~/.config/markdown-html/) > built-in defaults; MARKDOWN_HTML_NO_CONFIG=1 bypasses.
-
gpire Skill Design SystemDesign system completo: atomic design, component library, token di design, accessibilità WCAG 2.2, tipografia scalabile, spacing system, grid system, motion design system, dark mode, responsive design, Figma variables, CSS custom properties, Storybook, documentazione design system, design per React/Angular/Webflow. Attiva quando l'utente vuole creare un design system, component library, tokens, atomic design, accessibilità.
-
bestagentkits Bundle Gis Cartography DesignerUse when Codex should act as the Cartography Designer specialist from Agency Agents. Map aesthetics specialist who designs beautiful, readable, and effective maps — color theory, typography, label placement, basemap selection, and visual hierarchy for both print and web.
-
bestagentkits Bundle Brand GuidelinesWhen the user wants to apply, document, or enforce brand guidelines for any product or company. Also use when the user mentions 'brand guidelines,' 'brand colors,' 'typography,' 'logo usage,' 'brand voice,' 'visual identity,' 'tone of voice,' 'brand standards,' 'style guide,' 'brand consistency,' or 'company design standards.' Covers color systems, typography, logo rules, imagery guidelines, and tone matrix for any brand — including Anthropic's official identity.
-
bestagentkits Bundle UI Design SystemUI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools. Use when creating design systems, generating design tokens, maintaining visual consistency, or facilitating design-dev collaboration and developer handoff.
-
euxx Skill 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.
-
uitbreidenos Skill No SlopEscape AI-generated aesthetics in UI/frontend: specific typography, color palettes, layouts, and design rules that avoid the generic 'AI look'
-
uitbreidenos Skill Claude Design BrandingCreate consistent brand systems with Claude Design including logos, colors, and typography
-
uitbreidenos Skill Design System CheckerDesign System Checker
-
lxl333 Bundle Xiaolanben HTML LessonCreate source-faithful, beginner-friendly single-file HTML lessons from Xiaolanben math PDFs, scanned pages, images, chapters, sections, examples, or exercises. Use when the user wants only an HTML study handout/page and explicitly does not need video, MP4, cover images, PDF export, or external illustration assets.
-
abooai Bundle Text Image To HTML VisualTurn a text-heavy image, screenshot, poster, chart, table, or reference graphic into a polished HTML visual. Use when the user provides a "文字图", comparison screenshot, dense table image, infographic, or pasted image and asks to extract information, rewrite/polish wording, preserve core facts, create a beautiful HTML page/card/report, optionally use Guizang-inspired styles such as editorial ink, Swiss grid, social card, or launch-slide, ask for confirmation before final screenshot, and export a high-resolution PNG.
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 design-system-spec, style-tile, brand-refresh. 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.