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.
-
marcus Skill Create ThemeCreate custom color themes for Sidecar, including base theme selection, color overrides, gradient borders, tab styles, per-project themes, community themes, and programmatic theme registration. Use when creating or modifying themes, adjusting UI appearance, or debugging color/style issues. See references/palette-reference.md for the full color palette with all keys and per-theme values.
-
slogsdon Skill Figure AuditDecide whether a given article should get a figure at all — additive, performative, or none — against a five-type taxonomy where each type has a hard entry requirement. Use when Shane says "should this post have a diagram", "audit these articles for figures", "does this need a chart", or before commissioning any illustration for written work. Do NOT use to build the figure once approved (use the design artifact skills), to audit an existing figure's styling, or for social artifacts, which are decorative by design.
-
slogsdon Skill Design SystemGenerate a brand-agnostic DESIGN.md (Google design.md spec format) plus tokens.css and showcase.html for any branding project. Reads ./design/<brand-slug>/DESIGN-PLAN.md if present, otherwise asks for an inline brief. Use AFTER design-plan and BEFORE design-ui-components. Triggers include "design system for [brand]", "build a DESIGN.md", "generate design tokens", "/design-system".
-
slogsdon Bundle Design Business CardGenerate a printable business card — pixel-exact 1050×600 front canvas + 1050×600 back canvas in a single HTML file. Standard 3.5×2 inch card at 300dpi. Front carries name + title + contact details; back is wordmark-dominant (or brand device) with minimal text. The design system's most reduced artifact — tests whether the brand can speak with almost no text. Print bleed instructions in footer comment. Reads ./design/<brand-slug>/DESIGN.md, tokens.css, and components.html. Triggers include "business card", "calling card", "name card", "/business-card".
-
dkeken Skill Design Url To CodeTurn a live website into a working local frontend you can edit. Fetches the page, extracts its design system and structure, and rebuilds it locally in your stack, then screenshot-compares to the original. Use when the user says "url to code", "clone this site locally", "make it look like linear.app", "rebuild this page", or provides a live URL to recreate. Part of the Product Design set. Uses web-fetch + browser automation.
-
dkeken Skill Design Image To CodeTurn a reference image or mockup into a working local frontend that matches it closely. Inspects the image, extracts the design system (layout, type, spacing, color, components), implements it, then screenshot-compares and iterates to close the gap. Use when the user says "image to code", "build this mockup", "code this screenshot", "make this design real", or provides a UI image to implement. Part of the Product Design set. Uses a browser tool for screenshot verification.
-
dkolba Skill Modern CSSWrite cutting-edge and modern native CSS. Apply this skill whenever writing, reviewing, or refactoring CSS for components, layouts, design systems, or theming, even if the user doesn't say "modern CSS" explicitly. Covers a self-contained design-token scale (color, size, shadow, ease, type), cascade layers (@layer), @scope for component isolation (donut scopes, :scope specificity, scoping proximity), container queries, :has(), OKLCH/color-mix, native nesting, subgrid, fluid typography via clamp(), scroll-driven animations, logical properties, and concrete native replacements for SCSS mixins, maps, and variables.
-
ttttstc Bundle Ni PosterGenerate ZINE-style paper-poster prompts and raster images through one public skill with four internal modes: Standard, Gathered Scenes, Scene Distillation, and Photo Abstract Editorial. Use for themes, sentences, objects, moods, photos, or content briefs that need a tactile editorial poster. Triggers include 「做一张海报」「ZINE 风格」「极简海报」「纸感海报」「拾景纸刊」「保留照片」「撕纸边」「场景提炼」「不保留照片」「视觉隐喻」「单色块模式」「照片抽象编辑」「抽象记忆面板」「poster」「zine poster」「photo abstract editorial」. Style controls are `/ni-poster s`, `/ni-poster g`, `/ni-poster d`, and `/ni-poster a`; full names remain aliases. If no selector, explicit mode, or decisive treatment is given, interview one question at a time until one mode is confirmed before generating. Not for commercial ads, product KV, UI mockups, or article inline illustrations (use ni-article-image-gen).
-
varunr89 Bundle Paper BananaThis skill should be used when the user asks to "generate a scientific diagram", "create an academic illustration", "make a figure for my paper", "generate a plot for my paper", "create a publication-ready diagram", "illustrate my methodology", "visualize my paper's architecture", "draw a pipeline diagram", "visualize my method", or "create a chart for my research". Also triggers when the user mentions "PaperBanana", "paper figure", "NeurIPS diagram", "conference figure", or "academic figure".
-
vlabsai Bundle Logo CreatorGera logos com workflow iterativo de design assistido por IA. Cria variacoes, processa finalistas com crop, remocao de fundo e vetorizacao para SVG. Entrega assets prontos para producao (PNG recortado, PNG transparente, SVG escalavel).
-
vlabsai Bundle PresentationCria apresentacoes HTML navegaveis em 16:9 e documentos visuais em scroll vertical usando o design system da Vector Labs. Use para pitch decks, propostas, workshops, one-pagers e relatorios visuais.
-
vlabsai Bundle Web TypographySistema de decisao tipografica em 7 passos: tipo de app, tom da marca, combo de fontes, biblioteca de icones, escala tipografica, loading e implementacao. Inclui 14 combinacoes pre-curadas por cenario e regras de pareamento fonte-icone.
-
vlabsai Bundle Generative MediaGera e edita imagens usando modelos de IA via OpenRouter (FLUX.2 Pro, FLUX.2 Flex, Nano Banana 2). Suporta geracao texto-para-imagem, edicao, variacoes em lote e pos-processamento. Use para criar ilustracoes, arte e graficos para redes sociais.
-
wikimedia Bundle Codex UsageHow to use the Wikimedia Codex design system in any frontend — prefer Codex Vue components over custom DOM, lean on the bundled tokens / icons / base CSS, match Figma designs by reusing the same Codex assets, and know when (rarely) to write per-app CSS. Use when picking UI primitives, importing Codex, asking "should I write custom CSS?", or matching a Figma design with Codex assets.
-
wikimedia Bundle Codex TokensThe Codex CSS custom-property design tokens (color, spacing, typography, border, shadow, transition) shipped via @wikimedia/codex-design-tokens — what each token name means, how to use them in templates and CSS, and how the light / dark token sets cascade through [data-theme]. Use when picking a colour / spacing / type value, debugging a dark-mode regression, or asking "what's the token for X?".
-
wikimedia Skill Codex TypographyThe single most important text rule in Codex — every piece of text must use exactly ONE of the 9 canonical text styles (Heading 1–4, Body, Small, Figure caption, Block quote, Cite). Each style is a fixed combination of font-family, font-size, font-weight, and line-height; never invent font combinations or mix tokens across styles. Use whenever you add or style any text — a heading, paragraph, label, caption, or quote.
-
wikimedia Bundle Codex Style GuideThe Wikimedia / Codex Style Guide — the design-decision companion to the Codex toolkit. Covers the four design principles (Design with Others, For Curious Humans, Trustworthy, Content First), accessibility, bidirectionality, visual styles (colour usage, typography/readability, icon design, images, illustrations, data visualization), layout guidelines (links vs buttons, forms, content overflow), and content guidelines (voice & tone, writing for copy, machine assistance). Use when making a UX call ("dialog or inline edit?"), choosing colours/type/imagery, laying out a form, writing UI copy, labelling AI-assisted output, or sanity-checking a design.
-
wikimedia Skill Protowiki Update CodexHow to upgrade ProtoWiki to a new version of the Wikimedia Codex design system — bump the three @wikimedia/codex packages in lockstep, diff the upstream design-codex docs between the old and new release tags, propagate documented changes into the codex-* skills, refresh the vendored token snapshot, then verify. Use when asked to "update Codex", "upgrade Codex", "bump @wikimedia/codex", or pull in a new Codex version.
-
kangarooking Bundle Cover SkillUse for the owner's personal creator-content thumbnails and covers for short video, Bilibili, Douyin, WeChat, or similar platforms from a title, summary, established real portrait, kangaroo IP, product Logo, screenshot, or app reference. It enforces the owner's visual signature, runs a four-concept selection stage, then five responsive platform ratios. Do not use for generic clients, book or album covers, slide title pages, generic posters or social cards, article body illustrations, document headers, website hero art, or unrelated image edits unless the user explicitly invokes cover-skill and accepts the personal-signature rules.
-
kangarooking Bundle Shijing Paper ZineTransform ordinary snapshots—including daily moments, portraits, objects, pets, food, interiors, streets, architecture, landscapes, travel, and humanistic scenes—into the restrained Shijing Paper Zine visual style. Use when the user wants any real photo turned into a spacious paper-editorial composition with an irregular photographic fragment, simplified source-derived drawing, one structural print color, tactile torn-paper texture, minimal micro-copy, a consistent multi-image series, or a source-to-poster comparison.
-
kangarooking Bundle Book Illustration Workflow用于处理写书过程中的章节截图与插图工作流。适用于:梳理某一章需要哪些截图、逐步给出 Claude Code 实操提示词、规定截图文件名与图号映射、回填本地 Markdown 中的图片位置、清理作者备注为读者版正文、以及把章节和图片按正确位置同步到 Feishu 文档。用户如果提到“书的截图”“章节配图”“图号对应”“放到原文里”“上传飞书文档”“按刚才那套流程来”,应触发此 skill。
-
juspay Skill Design SystemCreate or modify coherent visual tokens and reusable component rules for color, typography, spacing, radius, elevation, controls, and interaction states.
-
labspangaea Bundle Design FundamentalsSay why a design looks wrong, and what to change. Use this whenever something visual "looks off", "looks cheap", "feels amateurish", or "doesn't look professional" and the person cannot name why — and whenever someone needs colours, fonts or a layout chosen for them. Runs a measured review over colour, type, layout, grouping and hierarchy, then reports concrete fixes ranked by impact with a severity each; or turns a brief into a buildable spec — palette with hex and 60/30/10, a type pairing with real sizes off a scale, a grid. Checks the contrast maths people skip, including borders and other non-text elements (3:1), not just text (4.5:1). Scope is **print and static graphic design**: posters, flyers, packaging, labels, menus, signage, banners, book and album covers, logos and wordmarks, slide decks, social posts and thumbnails. Reach for it on phrasings like "why does this poster look cheap", "our deck cover feels amateurish", "these two brand colours fight each other", "what pairs with Montserrat ExtraBold"
-
le-19-stvn Skill UI SystemBuild a coherent design system — tokens, components, spacing and type scales — from the project's brand and taste. Use when the user needs a design system, component library, style tokens, or consistent UI foundations across a product. Trigger on design system, tokens, component library, style guide (for product UI). Reads TASTE.md and BRAND.md.
-
freecodecamp-universe Skill DesignAdd, update, or theme UI in a project using the freeCodeCamp UIKit copy-source registry. Use when creating or editing any UI - buttons, modals, forms, tabs, badges, toasts, icons, layout - or when touching design tokens, colors, spacing, typography, or dark/light theming.
-
freecodecamp-universe Bundle Command Line ChicfreeCodeCamp's "Command-line Chic" UI design system and aesthetic guidelines. Apply these rules whenever building, styling, or reviewing any UI that should look and feel like a freeCodeCamp product — web apps, dashboards, landing pages, admin tools, component libraries, or themes. Use this skill when the user mentions freeCodeCamp styling, fCC design, "Command-line Chic", dark theme development for fCC, or asks for a UI that follows freeCodeCamp's visual identity. Also use when working on any freeCodeCamp repository, contributing to freeCodeCamp projects, or building tools and dashboards for freeCodeCamp staff, even if the user doesn't explicitly mention the design system.
-
gitt510 Bundle DadsReference knowledge for the Digital Agency Design System (DADS, デジタル庁デザインシステム): pinned design tokens, official dads-* component markup and porting rules, curated usage guidelines, and compliance policy. Use whenever output should look DADS-compliant — building a new page, artifact, or HTML document in DADS style, restyling an existing frontend to DADS (「DADS 風に」「デジタル庁デザインシステム準拠に」「デジタル庁っぽく」), auditing markup against official DADS components, or fetching DADS tokens/components from primary sources. This skill owns only the visual layer — colors, typography, components, usage rules, policy — and composes with whatever owns structure and medium (artifact-design, holy-grail-html, a React app, plain HTML edits). Triggers on "DADS", "デジタル庁デザイン システム", "dads-*", "digital-go-jp", "Japanese government design system".
-
gordon1210 Bundle React Codebase ExcellenceUse this skill when designing, implementing, reviewing, refactoring, debugging, testing, securing, optimizing, upgrading, or preparing CI and releases for a small-to-medium React web application, component library, design system, embedded widget, SSR application, or React Server Components boundary. Apply production-grade React engineering for React 19, with an explicit React 18 compatibility path, without framework cargo cults, speculative abstractions, blanket memoization, unnecessary state libraries, or unrelated rewrites. Preserve the repository's exact React and renderer versions, framework contracts, public component APIs, accessibility behavior, server/client boundaries, browser support, and established architecture unless the task explicitly changes them.
-
gordon1210 Bundle Godot UI Design ExcellenceDesign, implement, critique, and polish distinctive game UI in Godot: visual art direction, HUDs, menus, inventories, strategy dashboards, typography, materials, motion, controller navigation, accessibility, and in-engine visual validation. Use for premium or AAA-quality interface requests, Expedition 33 / Frostpunk 2 references, UI redesigns, and interfaces that work but look generic. Not for website design, general gameplay implementation, or engine migration.
-
jzkk720 Skill Design Md LibraryCurated library of 74 real-world DESIGN.md files (Google Stitch spec) extracted from sites like Apple, Stripe, Linear, Vercel, Notion, Airbnb. USE WHEN the user wants a design system to ground UI generation, says "make it look like [brand]", "use the [brand] design system", wants to build a page matching a known site's visual language, asks for design tokens/colors/typography for a named brand, or references DESIGN.md / Stitch / VoltAgent awesome-design-md. Returns the path to the matching DESIGN.md so the agent can read and apply it. Not a generator itself — it's an index into the fork mirror at ~/dev/forks/JZKK720/awesome-design-md/design-md/.
-
jzkk720 Skill Impeccable BolderAmplify a section within an existing design system to make it bolder and more confident. Use when a specific section reads flat or timid compared to its neighbors, and needs to be raised to the expressive level the rest of the page already reaches — without rebuilding anything outside the named target.
Audited -
sirhamza Skill Graphicdesigner SkillThis skill should be used when the user asks about graphic design principles, typography, color theory, design systems, UI/UX design, logo design, branding, visual hierarchy, grids and layouts, design tools (Figma, Adobe Illustrator, Photoshop, Canva), icon design, illustration, image composition, print design, web design aesthetics, accessibility in design, design tokens, wireframing, prototyping, or any visual design topic. Trigger when the user mentions "figma", "design system", "typography", "color palette", "font pairing", "logo", "branding", "visual hierarchy", "whitespace", "grid layout", "design tokens", "wireframe", "prototype", "UI design", "UX design", "illustration", "icon set", "brand identity", "contrast ratio", "accessibility", or asks for design advice or critique.
-
morphet81 Skill Address TicketEnd-to-end ticket implementation with a multi-agent team using TDD. Retrieves JIRA ticket details and Figma designs, spawns a PO to write requirements, gets developer approval, then proposes a test plan for review. Once tests are approved, implements tests first (red), then production code to pass them (green). Use --no-jira to skip JIRA retrieval and use inline instructions instead. Use --headless for fully autonomous execution where a reviewer agent replaces human approval.
-
morphet81 Skill Create Jira TicketCreate a JIRA ticket from user instructions via acli. Uses project from the current branch when possible, lists project epics, recommends the best epic, asks confirmation before creating, uses ADF descriptions, and can attach Figma designs via the Jira integration.
-
dayvisonassis Bundle Pabx Design SystemFonte-da-verdade do design system do DRCALL PABX (Angular Material M3, aesthetic compacto/profissional). Use ao criar ou revisar qualquer UI do frontend — páginas, tabelas, dashboards, formulários, diálogos — para seguir tipografia, espaçamento, tokens de cor, padrões de página/tabela/dashboard e os anti-padrões proibidos. É também a base do gate styles-frontend e da verificação visual.
-
platformplatform Skill RebrandApply a downstream brand to a PlatformPlatform fork. Edits one config file, drops in eight supplied logo assets, renames the solution and CLI to the new brand, and rotates UserSecretsId across every csproj. Skips all other source files. Use once per downstream fork after cloning, or to re-flip a brand later.
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 create-theme, figure-audit, design-system. 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.