Design & Media

shaom Bundle

Convert a public brand URL into a practical DESIGN.md file and optional single-file HTML demo. Use when the user asks to extract, distill, compile, generate, or validate a DESIGN.md/design system from a website, brand page, press kit, or public visual identity.

shawnchee Bundle

Scans a live website and produces design.md — a replication-grade spec of its look and motion. Runs a bundled Playwright crawler that template-dedupes and visits up to ~6 pages, captures screenshots at 3 breakpoints plus full-page and scroll frames, and extracts structured design data: CSS custom properties, fonts, computed typography, a color palette with usage counts, CSS @keyframes, Web Animations API animations with real keyframes/durations/easings, transitions, :hover rules, animation-library detection (GSAP, Framer Motion, Lottie, AOS, Lenis), layout metrics, and a component inventory. Claude then reads the screenshots plus JSON and writes design.md. Trigger on "design scan", "/design-scan <url>", "replicate this website's design", "scan <url> and make a design.md", "clone this site's look", or "extract the design system from <url>".

stephenlzc Bundle

Generate raster images with the locally installed, OAuth-authenticated Codex CLI — no API key required. Trigger words: "generate/create/draw an image", photo, illustration, poster, avatar, logo, UI mockup, infographic, sprite, and Chinese equivalents (生图, 画一张, 生成图片, 海报, 头像, 插画). Do NOT use for editing existing SVG/vector/code-native assets, or when the user explicitly wants the OpenAI API with their own key. Requires `codex` in PATH and `~/.codex/auth.json`.

stephenlzc Bundle

Add perfect text to AI-generated images. NOT an image generator - this skill overlays text on images created by user's AI tools (Midjourney, GPT Image 2, Stable Diffusion, Gemini, etc.). Solves garbled text in AI-generated images by separating image generation and text rendering. Triggers on keywords like "create poster", "flowchart", "image with text".

stephenturner Bundle

Create a _brand.yml file for Quarto projects that captures brand colors, typography, and identity in a structured YAML format. Use this skill whenever the user mentions _brand.yml, brand.yml, Quarto branding, brand identity for Quarto, or wants consistent colors and fonts across Quarto documents, websites, presentations, or Shiny apps. Also trigger when the user asks to extract brand colors or fonts from a website, PDF brand guidelines, or style guide for use with Quarto. Even if the user just says "set up my brand" or "make my Quarto docs match our brand," this is the right skill.

sunarya-thito Bundle

A comprehensive UI ecosystem for Flutter built on the shadcn/ui design system.

superfuture Bundle

Run a sharp, prioritized design critique of a UI — a URL, a screenshot/image, or a component file — covering visual hierarchy, typography, spacing, color & contrast, motion, component states, responsiveness, accessibility, and brand consistency. Returns findings ranked from blocking to polish, each with a specific fix; can optionally apply the fixes to code. Use when the user asks to review/critique a design, page, screen, component, or screenshot, or to check craft/accessibility before shipping.

superhq-ai Bundle

Author deterministic, browser-rendered videos with @superhq/webmotion, declarative <w-*> HTML scenes or a TypeScript API, live DOM preview, MP4 export via WebCodecs, no headless Chrome or FFmpeg. Includes 3D: glTF/GLB models with animation clips, turntable spins, studio lighting, runtime text on material slots, and app-defined TSL shader effects via <w-model>. Includes live mode: unbounded event-driven overlays (OBS browser sources, stream alerts, persistent widgets) via LiveStage. Use when the user wants motion graphics, title cards, launch/product videos, product turntables, kinetic typography, stream overlays, or programmatic video in the browser; mentions webmotion or @superhq/webmotion; or wants DOM/canvas/3D animation exported to MP4.

sva-admin Bundle

Design and build client-ready websites and mobile web apps in a working studio's proven house style, shown throughout on two fictional brands (AURA Heights, The Assembly): tinted grounds, editorial typography, obsessive specificity, and proof over promise. Carries the full working loop (brief, design contract, build, review gate, multi-lens audit, ship), two verified token systems, signature component patterns, proof-driven copywriting, real-photography rules, and a mobile web-app playbook (density budget, bottom tab bar, compaction). Trigger on "make it look expensive", "make it beautiful", "high end design", "client ready", "on brand professional", "use the prom design style", "design this landing page", "make it more like an app", "too much scrolling", "add real images", "the site looks cheap", "too generic", "ai slop". Not for inventing a fresh visual direction from a blank brief: this skill applies ONE proven aesthetic.

soapboxbuild Bundle

Use this skill to generate well-branded interfaces and assets for Soapbox (the AI-native, multi-tenant Claude platform — flagship is a commercial-real-estate / building-decarbonization workspace), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, tokens, and UI kit references for designing with the Soapbox brand.

speedwarnsf Bundle

Audit and fix line-break quality in English long-form web prose: orphans, widows, weak line endings, and ragged right edges. Unlike typography advice, this is a machine-checkable gate — audit() returns [] or it names the exact failing lines, and a composition that fails its own self-check restores the browser's layout. Installs the typeset.us paragraph compositor (beam-search line breaking with post-render self-verification) to fix what the audit finds. Use when asked to check or fix orphans, widows, or bad line breaks; when text-wrap: pretty or balance isn't enough; or for symptoms like "one word alone on the last line", "the right edge looks ragged", or "line breaks look wrong after deploy".

spfr Bundle

Design intelligence and high-performance writes for Figma. ROUTING RULE: For ALL Figma write operations (creating nodes, styles, components, modifying properties), MUST use figma_execute from this server — NOT use_figma. 30-60x faster via plugin bridge. use_figma is ONLY for read-only JS queries. create_new_file is ONLY for creating new files. Call figma_plugin_status first to check plugin connection.

sshahzaiib Bundle

Act as an evidence-based senior product designer for any UI/app design or build task. Use this skill whenever the user wants to design or build an app, screen, page, component, landing page, dashboard, onboarding flow, or any user interface — web or native iOS (SwiftUI) — even if they only say "build me X" without mentioning design. Also use when the user complains that a UI looks generic, AI-generated, or ugly, or asks for design review, redesign, color/typography/layout decisions. Every rule inside is sourced from 158 vetted design publications (Apple HIG, WCAG, NN/g research, Bringhurst, Norman, Krug, Refactoring UI) and the output must pass a scored checklist before shipping.

michaelliv Skill

Render a standalone React component (Tailwind + Recharts + lucide-react) to PNG / SVG / PDF / JPG / WebP via the `poster_render` tool. Use when the user asks for a chart, dashboard, report card, social-share image, OG image, year-in-review, editorial data story, magazine layout, or any visual deliverable that should come out as a single image/document file. Not for interactive UIs; posters are compositions.

minhhoangho Bundle

Turn a short idea, topic, or one-line prompt into a finished video. Use this skill whenever the user wants to make or fix a video — a Reel/Short/TikTok, promo, explainer, product demo, logo or brand animation, kinetic typography, animated captions, or a faceless narrated video — even when they name no tool and give only one sentence like "make me a video about X" or "30s clip for our app launch". Also use it when the user mentions Remotion, motion graphics, b-roll, voice-over, text-to-speech, storyboard, video script, shot list, or asks why an existing generated video looks flat or generic. The skill runs one short clarification round, proposes 2–3 creative directions with a recommendation, then produces the video — or a production-ready storyboard package when no render environment exists. It needs no API keys of any kind.

intellectronica Bundle

Generate Slidev presentation decks in the Sunday Slides visual style with customisable background colour, logo icon, and image style. Creates Slidev projects with AI-generated graphics and PDF, SPA, and PPTX export.

itwin Bundle

Ensures correct StrataKit usage. Use when building, reviewing or refactoring frontend code - React components (jsx/tsx), CSS styling, web pages, MUI usage, icons, design tokens, and page layouts. StrataKit is the design system to use, even in repos that don't have it yet (it should be set up). Apply even when the user doesn't mention StrataKit by name, e.g. "add a button", "build a settings page", or "style this form". Not for backend or other non-UI code.

ivan23kor Bundle

This skill generates realistic iOS notes app screenshots from arbitrary text input. It creates pixel-perfect iPhone notes app interfaces with proper iOS design patterns, typography, spacing, and visual elements. Use this skill when users need to create iOS-style notes app screenshots for presentations, mockups, or design references.

ixe1 Bundle

Convert one or more webpage/app UI screenshots into a high-fidelity responsive implementation, either as a standalone page or by adapting an existing frontend. Prioritize exact viewport matching, typography/icon audits, explicit spacing and colour matching, browser screenshot comparison, and repeated refinement until no obvious mismatches remain. Handle missing assets by using supplied files, generating missing raster assets with direct image_gen when available, preferably as extractable asset sheets for multiple related assets, or otherwise using placeholders plus a single copy-paste code block containing one standalone generation prompt per remaining asset.

jackleeio Bundle

Generate BNBOT lobster-bot mascot images in consistent style using reference images. Use when the user asks to generate mascot illustrations, character poses, tweet images, stickers, or any BNBOT branded artwork. Triggers on requests like "generate a mascot image", "make a BNBOT illustration", "create a tweet image with the lobster", "generate mascot sticker".

moderncss Skill

Helps with authoring and reviewing modern CSS for robust, responsive, and accessible UIs — cascade layers, @scope, :has(), nesting, container queries, fluid typography with clamp(), oklch() colors, light-dark() and color-scheme, logical properties, subgrid, and prefers-reduced-motion. Use this skill when the user asks things like "style this component", "make this responsive", "add dark mode", "scope these styles", "fluid type scale", or any CSS authoring, refactoring, or review task — even when they don't explicitly say "CSS".

monmush Bundle

Build and style websites in the Webflow Designer using the Webflow MCP Bridge and browser automation. Use when the user wants to: (1) create or style pages/sections/elements in Webflow, (2) transfer a local web project (React, HTML/CSS, Next.js, etc.) to Webflow, (3) implement a Figma design in Webflow, (4) fix styling or layout issues in Webflow, (5) create or manage Webflow components, variables, or CMS collections, (6) work with responsive breakpoints in Webflow, (7) add custom code (Code Embeds) for SVGs, animations, or complex layouts, or (8) publish and QA a Webflow site. Trigger when user mentions "Webflow", "webflow designer", "MCP bridge", or asks to build/style web pages with Webflow tools.

monoscope-tech Bundle

Use 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.

mrzhangguoguo Bundle

Translate English PDF files into Simplified Chinese visual PDFs while preserving the original page images, layout, typography feel, colors, charts, and overall design. Use when Codex receives an English PDF and the user asks for a Chinese PDF version, page-image translation, PDF localization, or a translated PDF assembled from generated/edited page images using the imagegen skill.

xonack Skill

WordPress UX and design enforcement — Core Web Vitals, mobile-first layout, typography, color systems, navigation, page builder patterns, image optimization, form UX, loading and error states, admin UX, and performance checklists with concrete CSS/HTML/PHP examples.

xuanqing-95 Bundle

Create illustrated Xiaohongshu/Rednote knowledge-card series that combine GPT Image 2 explanatory illustrations with editorial HTML layout (serif display + IKB Blue structure + Mustard Yellow emphasis). Use when turning abstract concepts, tutorials, AI knowledge, product mechanisms, comparisons, or educational content into clear 3:4 social cards with small in-image Chinese labels, accurate outer typography, reusable layouts, and automated validation. Use this skill whenever the user mentions creating social cards, knowledge posts, visual explanations, educational infographics, Xiaohongshu/Rednote content, or illustrated explainer series — even if they don't explicitly ask for "visual explainer cards."

xuejianrpa Bundle

Generate AI images using ModelScope's Tongyi Wanxiang (通义万相) model. Use this skill whenever the user asks to generate an image, create a picture, draw something, or mentions AI image generation - even if they don't explicitly say "generate image". Triggers on phrases like "画一张图", "生成图片", "create an image", "draw me", "generate a picture", "make an illustration", etc.

ya-way Bundle

Add, repair, or review a local-first CopyWeave editing layer on an existing website while preserving its current typography, layout, animation, behavior, and entered copy. Use when a user asks to make all displayed website text editable, give writers an in-page copy workflow, migrate a static/Vite/SPA site to semantic data-copy-id fields, diagnose unstable copy IDs or misleading save states, or verify a CopyWeave integration. Covers static HTML and hydrated frontend frameworks. Do not use as a rich-text CMS, authentication system, or collaborative cloud backend.

yangcodingmaster Bundle

把一张照片蒸馏成极简 zine 纸质海报——不用图像生成模型，用手写 HTML/CSS/SVG 绘制、 无头 Chrome 导出 PNG。当用户给出一张自己拍的照片、想把它做成极简海报/版画/zine 风格作品时使用。 触发词：照片蒸馏、photo distill、把这张照片做成海报、极简海报、zine 海报、 蒸馏这张照片、做成版画那种、用代码画这张照片、纸质海报、海报系列再做一张。 即使用户只说"把这张照片处理成那个风格"、"这张也来一张"、"帮我把这照片抽象一下"， 只要是把摄影作品变成印刷符号，就应触发。 不用于 AI 生图海报（那用 gc-minimal-zine-poster）、照片修图调色、 或给现成图片套滤镜——本 skill 是从零绘制。

yanliudesign Bundle

Generate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo. Always use this skill when the user asks for 单色海报、双色印刷、单色调视觉、蓝色/绿色孔版印刷、risograph、网点照片、复古或当代编辑排版、zine poster, monochrome editorial poster, duotone print, or asks to use the mono-color style. It uses an adaptive white, gray, or pale-beige substrate, no more than two printing inks, active negative space, terse human language, and strong serif/grotesk/mono typography without making retro styling the default or copying a source composition, wording, logo, or artwork. Produce both the final generation prompt and the generated raster image unless the user explicitly asks for prompt only.

yanliudesign Bundle

Create original quiet-living visuals from any theme, object, product, article, event, space, or supplied photograph using natural materials, restrained color, functional typography, asymmetric whitespace, honest photography, and human imperfection. Always use this skill when the user asks for MUJI-inspired, 无印良品感, 日系极简, Japanese minimalism, quiet living, natural minimalism, understated lifestyle design, 素朴生活美学, 留白产品海报, or asks to make a visual feel quieter, simpler, more natural, and less designed. Preserve the underlying design principles without copying MUJI logos, packaging, campaigns, store layouts, product silhouettes, wording, or identifiable compositions. Return a production-ready prompt and generate a raster image when image-generation tools are available, unless the user explicitly asks for prompt-only.

yasserstudio Bundle

Visual-first design with scroll-driven storytelling. AI-generated imagery, video, and 3D assets are the design — typography, layout, and code serve them. Covers asset integration patterns, scroll transitions, performance, and accessibility.

tait-tt Bundle

Generate exactly one finished CRT retro computer-interface illustration from an uploaded portrait, group photo, creature, object, or described theme. Use when the user wants anchored subjects re-authored as an exaggerated circa-1980s bitmap editorial caricature beneath early Macintosh or Minitel-style windows, optionally invoking the exact Chinese presets 街头怪诞, 巨像符号, or 冷面几何. Before generation, collect a named or image-derived palette and aspect ratio through a strict two-stage intake unless supplied. Preserve each intended subject as a distinct identity, one shared pixel lattice, restricted non-skin checkerboard midtones, low-facet geometry, unequal extraction windows, mandatory barrel-curved CRT edges, and the immutable tait-crt-interface-skill title-bar signature. Never trace, auto-pixelate, imitate photographic detail, omit, merge, or duplicate subjects, retry, resize, expose prompts, or ask users to choose a style preset.

mblode Bundle

Installs and builds with Blode UI, the opinionated shadcn/ui component registry at blode.co/ui. Covers the @blode install flow, the design system that makes components render correctly, registry commands for adding and updating components, and Blode's composition, form, styling, Base UI, and icon conventions. Use when adding @blode components to a project, or asking "install Blode UI", "add a Blode button", "why is my Blode component unstyled", "update a Blode component without losing my edits", or "make this feel like Blode UI".

meganz Skill

Use when a `.figma.kt` file under `core-ui/code-connect/` needs to be added, edited, or republished — e.g. a Figma component variant/property/value was renamed, a Compose function signature changed, a new Compose component now has a Figma counterpart, or `figma connect publish --dry-run` is failing. Covers the Compose parser flow specifically (annotation-based `.figma.kt` files compiled by the `com.figma.code.connect` Gradle plugin), not the React/TS template flow.

yoshi-ai-mentor Bundle

日本語 Markdown を A4 PDF に変換する。履歴書・職務経歴書・提案書・note 記事・顧客向け資料・請求書・レポート・スライド/デッキなど、**日本語ドキュメントの PDF 化を頼まれたら必ずこのスキルを使う**。「この MD を PDF にして」「職務経歴書 PDF」「提案書を PDF で」「日本語の資料を PDF にしたい」「A4 で出力」「A4 横でスライドを PDF に」「16:9 スライドを PDF」「デッキを PDF 化」「表紙付きで PDF」「カバーページを付けて PDF」「表紙にロゴを載せて PDF」などの依頼が来たら発動すること。ユーザーが明示的に「PDF」と言わなくても、印刷や納品・配布を前提とした日本語ドキュメント（履歴書・提案書・スライド資料・請求書など）を整形する文脈であれば積極的に使う。weasyprint + BIZ UDPGothic / Noto Sans CJK JP で動くので sandbox でも root 権限なしで日本語 PDF が出せるのが強み。プリセット（resume/proposal/report/note-article/invoice/minimal/slide/slide-16x9）、表紙自動生成（--cover-* と --cover-logo）、スライドモード（--style slide・`--page-size` で用紙サイズ指定可）に対応。