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.
-
aias Bundle Agent BrowserUse when programmatic browser work—navigate, fill forms, click, screenshots, scrape/extract data, login flows, or E2E-style checks without manual driving. Triggers on "open this site", "automate the browser", "take a screenshot", "test in the browser", headless UI verification. Also covers Electron desktop apps (VS Code, Slack, Discord, Figma, Notion), Slack workspace automation, exploratory testing / dogfooding / QA / bug hunts, running inside Vercel Sandbox microVMs, and AWS Bedrock AgentCore cloud browsers. Uses agent-browser.
-
isnoobgrammer Bundle PainterImpeccable UI/UX design skill: visual design, animation, color, typography, layout, interaction design, accessibility, Three.js/WebGL, scroll effects, design systems, and 15+ styles (glassmorphism, brutalism, neumorphism, etc.). Use when the user wants to design, build, fix, or audit UI. Trigger on: '/painter', 'make it look good', 'design this', 'fix the ui', 'hero section', 'dashboard', 'animation', 'three.js', 'shader', 'color palette', 'responsive', 'accessibility audit'.
-
isnoobgrammer Bundle Logo FaviconFind, generate, or create logos, favicons, and SVGs for any project. Cascading strategy: search the web for existing assets first, scrape free logo sites, generate SVGs programmatically with Python, and only use AI image generation as a last resort. Triggers on: "logo", "favicon", "icon", "brand kit", "SVG", "app icon", "og image", "make me a logo", "need a favicon", "brand identity", "project icon", "website icon". Even triggers when the user mentions "new project" or "deploying" — every project needs a logo.
-
stukh Skill Sparq AnalyzeGather and consolidate requirements from Jira, Confluence, Figma, and local files. Use when: (1) analyzing a Jira ticket for testing, (2) extracting requirements from Confluence specs, (3) understanding UI flows from Figma designs, (4) preparing requirements for test generation. Triggers: Jira ticket ID, Confluence page URL, Figma link, or feature description.
-
leihuang23 Bundle Design LanguageDerive or extend a product design system from real context, producing semantic design tokens, component contracts, states, accessibility rules, and implementation mappings. Use for design-system creation or substantial UI work. Do not use to generate an arbitrary trendy palette.
-
leihuang23 Bundle Rednote CarouselTurn a source-backed narrative into an editable Xiaohongshu (小红书) carousel with deterministic Chinese typography, safe-area and overflow checks, caption, contact sheet, and export manifest. Use for RedNote social cards. Do not use image models to render Chinese text.
-
leihuang23 Bundle Pixels To ProductTurn a product brief, screenshot, Figma reference, or existing interface into a coherent design language and visually verified implementation. Use for substantial UI creation or redesign. Do not use for a tiny CSS correction with an existing exact target.
-
rosuh Bundle Display Glasses With Jetpack Compose GlimmerProvides guidelines for developing projected Android XR apps for display glasses using the Jetpack Compose Glimmer UI toolkit. This skill covers foundational Glimmer design principles, workflows for implementing Jetpack Compose Glimmer, and interaction models for the glasses form factor. Use this skill to build an Android XR Augmented Experience app with Jetpack Compose Glimmer that adheres to the Glimmer design system for optimized glasses styling.
-
kingxiaozhe Skill Cm Frontend Engineer前端工程师 Skill,执行前端开发任务,自动适配项目技术栈(React/Vue/Svelte/Next.js 等),支持 Figma/Stitch 设计稿还原
-
kingxiaozhe Bundle Cm Miniprogram Engineer微信小程序开发工程师 Skill,执行小程序开发任务,自动适配项目技术栈(原生小程序/Taro/uni-app 等),支持 Figma/Stitch 设计稿还原与云开发
-
xhqing Skill Commit提交当前暂存区已有的内容到本地仓库并推送到远程(依次 git commit → git push;不执行 git add,只提交用户已自行 git add 到暂存区的内容;无远程仓库则先用 gh repo create --public 创建再推送)。当用户输入 commit 时触发。分支感知(2026-09-07 用户修订:main 不设分支保护、不限制直接 push,2026-09-06 的「main 仅本地提交」模式废止):在 main(或 master)上 → commit 后直接 push 远程 main(普通文件修改、杂事、main 对齐走这条直推通道);在功能分支上(存在测试用例的软件开发项目走 dev-workflow)→ commit → push → 已有 open PR 则复用、没有则创建(标题须具体达意)→ 等 CI 完成(gh pr checks --watch)→ 绿灯 squash 合并+删分支(分支保护已撤,auto-merge 不可用)。git commit 前对暂存区已有内容做敏感内容扫描 + cache 文件/目录检测(cache 命中自动加入 .gitignore),任一命中即彻底终止——不 commit/push,须重新 /commit 走完整流程。push 之后补齐项目标配(README 中英双语+LOGO+标准徽章、版权署名归一 All Contributors、LICENSE.md、CHANGELOG.md 与 VERSION、GitHub About、Sponsors 按钮),缺则自动补、齐则记项目根 .commit-cache.md 缓存跳过重复检测;另做版本滞后检测(VERSION 已在 GitHub Release 发布且其后有新提交 → 报告并指引 /bump,不就地改文件)与版本号一致性检测(以 VERSION 为唯一权威自动同步各文件),均不阻塞、每次必查不缓存。
Audited -
xhqing Skill Icon DesignUse this skill whenever you are about to create or modify ANY icon, logo, favicon, app icon, agent logo, badge-style graphic, or README header image — in SVG, PNG, or any format — for a project, VSCode extension, app, or agent. Read it BEFORE drawing the first shape or picking colors. Enforces rounded-only outlines (no sharp corners), color harmony, composition, and a pre-flight checklist. Triggers on: 'icon', 'logo', '图标', '徽标', 'favicon', 'app icon', '扩展图标', '设计图标', '画个 logo', '做个图标'.
-
yusifeng Bundle Formax Web Style SystemUse for all frontend and web UI tasks by default to apply a business-agnostic desktop web visual style system with medium-strength guardrails; if an existing design system is present, follow it first and use this skill only as a style harmonizer.
-
bonnguyenitc Skill UX DesignerUse when designing UI, creating wireframes, running user research, defining information architecture, or reviewing design decisions — regardless of tool (Figma, Sketch, etc.)
Audited -
zoonk 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.
-
canvascoding Bundle Brand GuidelinesApplies Canvas brand colors, typography, and visual polish to artifacts that benefit from a consistent product look-and-feel. Use it when brand colors, style guidelines, visual formatting, or company design standards apply.
-
fanzr-arch Bundle Acid Depth Poster把主题、文章或标题编译成「前进色×后退色」实验海报提示词:清晰前景层+模糊后景层的双层空间结构,介于实验杂志封面、青年文化海报、地下传单、Y2K 视觉与 Acid Graphics 酸性设计之间。用户提到前进色、后退色、酸性设计、酸性海报、Acid Graphics、Y2K海报、实验海报、地下传单风、青年文化海报、夜晚城市感封面,或要求做一张躁动/粗粝/夜感的实验视觉时使用。先填输入区,再输出一条完整可直接生图的提示词。
-
fanzr-arch Bundle Brand Icon Banner把一条平台观察、政策解读或产品判断编译成「立体品牌图标横幅」生图提示词:近白影棚虚空里悬一枚厚圆角立体 App 图标,图标上是真实品牌 logo,左侧压三层中文文字(小标签 / 反白块大标题 / 灰副标题),5:2 超宽横板。用户提到品牌图标封面、平台观察封面、3D App 图标横幅、logo 立体封面、政策解读头图、brand icon banner,或要给一组平台/产品文章成套做同骨架换品牌的横幅时使用。先调研品牌当前 logo 版本,再编译单条确定性提示词。不用于插画风格、写实摄影、信息图或纯字体海报。
-
fanzr-arch Bundle Neo Brutalist Poster把文章主题、产品介绍或技术项目编译成新粗野主义(Neubrutalism)风格生图提示词:粗黑边框、硬偏移阴影、扁平撞色块、超大标题字、组件感构图。用户提到新粗野主义、粗野主义风格封面、Neubrutalism、neo-brutalism、Gumroad风格、粗黑边框、硬阴影、反精致设计、组件感封面时使用。先判断三个方向(文章封面/产品视觉/开发者视觉)再编译单条确定性提示词;产品和开发者方向默认提醒优先引用真实案例。
-
fanzr-arch Bundle Flat Field Cover Poster把主题、标题或人物概念编译成「平涂色场封面海报」提示词:单一纯平色底 + 写实人像摄影,超大压缩体大写标题横跨上三分之一、第二行穿过头肩被部分遮挡,一个手绘元素压在前景下角桥接照片层与图形层,四周环绕杂志编辑排版系统,2:3 竖版。用户提到色场封面、平涂底封面、杂志封面海报、大标题被遮挡、刊头压人像、写实人像配超大标题、flat field cover、magazine cover poster,或要给一组主题成套做同骨架换色底的竖版封面时使用。先选色场寄存器与桥接元素再编译单条确定性提示词。不用于黑白极简横幅、插画风格、纯字体海报或产品图。
-
fanzr-arch Bundle Craft Diorama Still Life把文章、观点或产品主张编译成「一个实物替一句判断」的手作拟物静物提示词——剪纸质感、微缩场景、轻拟物、克制静物摄影感。用户提到拟物风封面、拟物风章节图、剪纸质感、微缩静物、实物隐喻配图、craft diorama、cut-paper still life、object metaphor cover、diorama illustration,或要为一篇内容做封面加逐章配图时使用。默认输出封面 5:2、章节图 16:9 的完整可直接生图提示词;调色板由用户自填或按内置预设映射。不用于摄影写实、3D 渲染或人物场景插画。
-
fanzr-arch Bundle Outline Figure Explainer把一个概念、流程或对比编译成「粗黑描边简笔人 + 扁平撞色块」风格的说明插图提示词——纯白底、圆头无五官的黑线小人、无描边的饱和色块、块内白色细线图标、细黑连接线与箭头。用户提到说明插图、概念图、流程图配图、扁平插画、简笔小人插图、白底扁平风、explainer illustration、flat vector diagram,或要给一篇文章配一组解释性插图时使用。可单张也可成组,成组时风格基座逐条重复保证一致。不用于写实摄影、拟物质感、纯字体海报或黑白编辑封面(后者走 mono-editorial-banner)。
-
fanzr-arch Bundle Plakatstil Object Poster把文字主题、商品照片、包装照片、物品照片或人物服务主题编译成 Plakatstil / Sachplakat 风格提示词。用户提到 Plakatstil、Sachplakat、德国广告海报、物体海报、商品广告海报、复古广告、拍照重绘成广告海报,或要求判断图片像不像 Plakatstil 时使用。先内部选择模块,再输出一条确定性提示词,不展示模块菜单。
-
fanzr-arch Bundle Swiss Typographic Poster把瑞士国际主义(Swiss International Typographic Style / Swiss Design)海报封面拆成可选配的设计模块,识别用户意图后自动选配并编译成一条确定性、可直接用于图像模型(gpt-image-2 等)的提示词。用户提到瑞士风格/国际主义/Swiss design 海报、文章封面、视觉主图、字体海报,或在视觉创作上下文给出一个标题/主题要做成瑞士风时使用。只输出一条成品提示词,不展示模块菜单。不用于其他设计风格、排版本身、或普通设计史问答。
-
fanzr-arch Bundle Visual Identity Expander把用户上传的 Logo、人物头像、个人形象、IP 角色、插画、产品照片或标志性物件,扩展成一套统一的视觉身份提示词。用户提到一张图做品牌全案、个人品牌视觉、头像延展、IP 设定、品牌主视觉、包装周边、社交媒体视觉,或要求保持参考图一致性生成多场景图片时使用。默认输出视觉 DNA 卡和一组可直接生图的完整提示词;有生图工具且用户明确要求时可继续生成图片。
-
glebis Bundle BrandkitThis skill should be used when EXPLORING a brand identity that does not exist yet. Generates premium brand-guidelines boards for competing directions, and hands the WINNING direction off into the design-tokens brand block (confirm-then-write). Upstream of tokens; for producing assets under an EXISTING token contract use brand-illustrate instead. Carries reference direction for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Triggers on brand kit, brand board, brand directions, identity candidates, identity direction, logo system, brand guidelines deck, visual identity exploration, визуальные направления бренда.
-
glebis Bundle Brand IllustrateTurn design tokens into a coherent, on-brand illustration set through a short step-by-step questionnaire, then generate with whichever image backend is installed (gpt-image-2 / nano-banana). Assembles the prompt scaffold from the token palette + brand block, merges layout-rules de-slop negatives, requests platform preset sizes, saves a reusable recipe, and hands the batch to review. Use when a project already has a token set and needs images that match it, or when an earlier batch should be re-run from its saved recipe. Triggers on brand illustrations, on-brand images, illustration set, generate images matching my brand, illustrate this section on-brand, contact sheet.
-
google-gemini Skill Slide CreatorCreate Google-style presentation slides as standalone HTML files. Use when the user wants to (1) create presentation slides from notes or bullet points, (2) build slide decks in HTML format, (3) recreate or replicate existing slide designs, (4) convert rough notes or talking points into polished visual slides, or (5) needs professional Google-branded presentation materials with clean typography, visual diagrams, code blocks, or data visualizations.
3.8k -
bodish-coder Skill Func UIUse when an EXISTING UI-only / mockup / prototype frontend needs to become a real, working system — the user says their app is "just a UI", "only a mockup / shell", "not functional", "fake / hardcoded data", "no backend", "the buttons don't do anything / just clear", or asks to "make it real / functional", "wire it up", "connect the frontend to a backend / API / database", "make the buttons actually save", "turn this prototype into a working app". Ends at a confirmed plan; does not build. NOT for Figma-to-UI, design / UX / a11y review, visual or styling bugs, debugging a feature that already works, a brand-new app with no existing mockup, or backend-only fixes.
-
bodish-coder Bundle Design ArwenUse whenever the user wants to build, redesign, improve or critique a UI/UX, native or web: a web page/app/component, an iOS or Android screen, a React Native app, a dashboard, landing page, form, data table, settings screen, multi-step flow, onboarding, empty state, or design system; or asks to make something "more unique / bolder / quieter / more polished / less generic / more memorable / less AI-made", pick fonts/colors/layout/motion, fix visual hierarchy, spacing, contrast, a11y or UI performance, write UX copy and error states, or share one design language across native and web. NOT for backend-only or non-UI tasks; `impeccable` covers craft with no aesthetic direction to forge, gstack the headless-browser review of a finished page.
-
fellipeutaka Bundle Figma Raw GeometryRaw Figma node geometry for Figma-to-code work. Use when exact local bounds, page-space bounds, transforms, rotation, visibility, or effective layer opacity are required; when reconstructing Smart Animate across component variants; or when Figma MCP output is unavailable, incomplete, or too large.
-
leandrodslv Bundle UIProduces distinctive, production-grade UI for pages, components, visual interfaces, typography, and screenshot-driven polish. Use when users ask in any language for UI, page, component, frontend, typography, screenshot-grounded visual polish, or complaints that a screen looks unclear, ugly, inconsistent, or visually wrong. Not for backend logic or data pipelines.
-
leandrodslv Skill Figma To CodeFigma → Code (Pixel-Perfect)
-
leandrodslv Skill HTML To FigmaHTML → Figma (Pixel-Perfect)
-
leandrodslv Bundle UI UX Pro MaxUI/UX design intelligence for web and mobile. Searchable local database with 84 styles, 192 color palettes, 74 font pairings, 192 product types, 98 UX guidelines, 104 icon entries, 16 GSAP motion presets, and 25 chart types across 22 stacks (React, Next.js, Vue, Nuxt, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, WPF, WinUI, Avalonia, Uno Platform, UWP, Three.js, and HTML/CSS). Use when designing, building, or reviewing UI: pages, components, color schemes, typography, layout, accessibility, animation, or data visualization.
-
leandrodslv Skill Color Contrast CheckerAnalyse le contraste de couleurs d'une image (maquette, capture d'écran, export Figma, interface web) et produit un rapport d'accessibilité WCAG/RGAA complet. Utilise ce skill dès que l'utilisateur partage une image et veut vérifier les contrastes, l'accessibilité des couleurs, ou la conformité WCAG. Déclenche pour : "vérifie le contraste", "analyse les couleurs de mon image", "est-ce que mes couleurs sont accessibles", "contraste WCAG", "ratio de contraste", "couleurs lisibles", "couleurs accessibles", "check my colors", "audit couleurs", "maquette accessible", "contraste insuffisant", "palette accessible". Toujours utiliser ce skill plutôt qu'une réponse générique dès qu'une image est partagée ET que la question touche au contraste ou à l'accessibilité visuelle.
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 agent-browser, painter, logo-favicon. 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.