Design & Media

cline Skill

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

jvalin17 Bundle

Design system architecture with trade-offs. Keywords: architecture, design, database, API, frontend, backend, security, scaling, decisions, tech stack, patterns

nangongwentian-fe Bundle

Generate AI images (photos, illustrations, concept art, product shots, game assets, UI mockups, posters, textures, sprites, stickers) by delegating to Codex CLI's built-in image_gen tool. Use this skill whenever the user asks to generate, create, or make any AI-generated bitmap image in Claude Code — including requests like 'generate an image', 'create a photo of', 'make an illustration', 'design a poster', 'draw a picture', 'generate a product shot', 'create concept art', 'make a logo', 'create a thumbnail', 'generate a hero image', or any visual asset request that needs AI image generation rather than code-based SVG/HTML. Also trigger when the user says '生成图片', '画一张图', '做个海报', '生成一张照片', '帮我画', '生成插画'. Do NOT trigger for editing existing SVG/vector files, creating HTML/CSS layouts, or generating diagrams/flowcharts (those are better handled by code or other tools).

nicknisi Bundle

Generate or edit images via Google Gemini (nano-banana-pro) or OpenAI gpt-image-2. Trigger on "generate image", "create diagram", "edit image", or "make illustration". Supports 1K/2K/4K resolution, masked inpainting, and text-accurate generation.

owid Skill

Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.

pdugan20 Bundle

Review one completed UI component or bounded surface against the design system evidenced in its repository, classify accidental deviations, intentional exceptions, system gaps, and uncertainty, then apply only approved corrections. Use for post-build UI conformance or normalization. Do not use for UI ideation, repository-wide audits, exact design translation, or general production hardening.

pdugan20 Bundle

Audit one or more code repositories for design-system drift, hardcoded visual decisions, inconsistent token or primitive use, overlapping UI components, missing system capabilities, and enforceable rules. Produce a prioritized read-only health and consolidation report grounded in source and rendered evidence. Do not use for aligning one component, UI ideation, greenfield system creation, Figma-only audits, or automatic refactoring.

rfxlamia Bundle

Brand-aware design system generator that acts as Head of Brand. Translates abstract brand language into a mathematically-validated, implementation-ready design system, writes creative-brief.md as the source of truth for all UI/UX in a project, and optionally compiles it to framework tokens (Tailwind v4 @theme, v3 preset, or plain CSS custom properties). Standalone skill (like bug-hunting and hotfix — no full pipeline required). Trigger on "/brand-design", "design system", "creative brief", "define the brand", "brand identity", "set up UI tokens", "export design tokens", "tailwind theme from brand", or when starting UI work without an existing design authority.

rshvr Bundle

UI/UX quality audit for web implementations. Run after building to verify accessibility, performance, animation quality, touch interaction, forms, navigation, typography, and brand consistency. Checks ~190 rules organized by priority (CRITICAL, HIGH, MEDIUM). When a rule fails, triggers the relevant teaching skill for remediation. Use when asked about: audit, review, check, QA, pre-launch, quality check, accessibility audit, performance audit, verify, validate, or "is this ready to ship". This skill orchestrates fixes by invoking elite-accessibility, elite-performance, elite-gsap, elite-css-animations, elite-layouts, elite-design-core, elite-ux-strategy, or elite-brand-design as needed.

rshvr Bundle

Foundation for elite web design. Covers design philosophy, visual systems, and the design-to-code process. Use when asked about: premium website design, award-winning aesthetics, design systems, visual hierarchy, spacing, typography, color theory, data visualization, or "how to make this look professional". This skill provides the foundational thinking that informs all other elite-web-design skills. When loaded alongside animation skills (elite-gsap, elite-css-animations), provides the token foundation they reference.

ginlix-ai Skill

Design-quality reference for financial-research visual output: typography, color, composition, and avoiding generic AI aesthetics

jal-co Skill

Fetch brand SVG logos and cloud architecture icons (AWS, Azure, GCP) from theSVG. Use when the user asks for a brand logo, company icon, framework mark, service icon, or any "icon/logo for X" where X is a real brand or cloud service. Returns ready-to-use CDN URLs or raw SVG markup.

vobase Bundle

Generate a Voltade-branded 1-page or 2-page demo onboarding guide (Markdown source + print-ready PDF) for a new client demo or sandbox. Use this skill whenever the user says "make an onboarding guide", "write an onboarding doc", "create a 1-pager", "create a 2-pager", "demo handout", "demo onboarding", "client handoff doc", or names a specific client + asks for an onboarding artefact (e.g. "draft the onboarding for the {client} demo"). Also use when the user says "spin up the onboarding PDF", "give me the onboarding doc for {project}", "do the {client} handout", or asks to update an existing onboarding guide. Baked-in: Voltade design system tokens (mauve + purple-9, Source Serif 4 / DM Sans / IBM Plex Mono), the one-italic-accent-word rule, the running-header pattern, the standard sections (ACCESS · TRY THE AI ON WHATSAPP · SUGGESTED PROMPTS · WHAT'S PRE-LOADED · TWO THINGS WORTH NOTICING for 1-pagers; ACCESS · TRY THE AI · "What the system does" cluster for 2-pagers), and a markdown→HTML→PDF pipeline via hea

yakoub-ai Skill

Use this skill when the user wants to design the UX, plan screens, define navigation flows, or establish a design system for a Flutter app — before implementation begins. Trigger phrases: "design Flutter UX", "create screen flow", "plan app screens", "help with mobile UI", "design system Flutter", "what screens do I need", "design the UI for my Flutter app", "define the navigation", "create a component inventory", "help me plan the screens", "what widgets do I need", "design the onboarding flow", "map out the user flows", "define the color palette", "set up the theme for my Flutter app", "plan the accessibility", "design the empty states". Also use when: the product brief is complete and the user is ready to define the visual and interaction design before writing any widget code.

danielimad Bundle

Apple Human Interface Guidelines as a working reference — the visual and structural design system for iOS/iPadOS 26+ (Liquid Glass). Verbatim HIG corpus (171 pages) plus recovered hard specs — Dynamic Type scale, SF Pro tracking, system color hex, device metrics, layout margins. Use when building, reviewing, or converting UI that must look and behave Apple-native, on SwiftUI/UIKit or on the web. Covers components (buttons, sheets, tab bars, toolbars, lists, pickers), foundations (typography, color, layout, materials, icons, accessibility), and patterns (navigation, modality, onboarding, feedback, data entry). Trigger on "make this look like iOS", "Apple design", "HIG", "native iOS UI", "Liquid Glass", "system colors", "Dynamic Type", or any iOS design audit or spec question.

decocms Skill

Build or style React UI with the decocms product design system (@decocms/ui). Use when creating interfaces, pages, or components in a project that should look like decocms products, when the user mentions "design system", "@decocms/ui", "decocms style", or asks to make UI consistent with Studio. Covers installation, Tailwind v4 token setup, component inventory, and usage conventions.

mizchi Skill

Markup from a mock image or screenshot — recreate a page as HTML/CSS when the only input is an exported design image (Figma export, retina screenshot, competitor-site capture) with no reference HTML. Normalizes @2x/@3x exports to CSS pixels (scan mock), then drives the deterministic verify-markup loop to a DONE verdict. Works with any agent model — the agent's own vision is the only VLM required, no API key; Haiku handles structure/spacing cheaply, hard 1px endgames measured to need Sonnet (see Model selection). Use when asked to "implement this mock", "turn this screenshot into HTML", or markup from an image that did not come from this repo's own capture tooling.

sanhuang520-ship-it Skill

中文排版规范助手。当用户要"排版""中文网页样式""文章排版""公众号排版""PDF/Word 排版""字体怎么选""中英混排""为什么我的中文网页很丑"时使用。处理中英间距、标点、行高、字体栈、CJK 断行等中文特有问题，输出可直接用的 CSS 或排版建议。

yang20040317-svg Skill

图形字/合字设计（pictogram typography，以字寄形 + 填字共生）专项方法论。当任务要求"在一个汉字里寄具象图形"或"让真实物品形态承载中文书法文字、文字填充并生长出主体"，或"汉字本身就是视觉主体（而非仅承载信息）"——字即图、字做主视觉、书法构成画面主体——时触发。覆盖：合字字体选型、以字寄形、墨朱三色制、图字共生四型（形嵌字/笔成形/包围形/填字共生）、共享笔画1-2处、设计三轴、系列化延展、双重可识别与物品优先识别验收、红线。触发词：「图形字」「合字」「以字寄形」「墨朱」「画个鸡字」「XX字配XX图形」「节令物产字」「文字填充物品」「物品里填字」「文字长成物品」「书法构成主体」「字即图」「字做主视觉」「汉字是视觉主体」「字是画面主体」。

simonstrumse Skill

Design system for creating premium glass UI using iOS 26 native Liquid Glass APIs (.glassEffect modifier) or fallback gradient-based approaches for older iOS versions. Use when building SwiftUI iOS apps with glassmorphism, premium UI, translucent cards, or modern Apple-style interfaces. Triggers on requests for liquid glass, glassmorphism, iOS 26 design, premium UI, or translucent interfaces.

spec-kitty Bundle

Use this skill to generate well-branded interfaces and assets for Spec Kitty, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.

gabrielcardosodeaguiar45-oss Bundle

Gera notificações extrajudiciais bancárias (RMC, RCC, consignado-não-contratado, Bradesco-encargos/tarifas/capitalização/pagamento-eletrônico) a partir de templates DOCX com placeholders canônicos. Suporta versão COM-escritório (logo Tiago/Eduardo) e SEM-escritório (Patrick/Gabriel/Alexandre, timbrado neutro).

herxinsasa Skill

设计执行。基于 Design-Brief.md 产出原型、设计稿或设计系统。支持 Figma、Pencil、HTML/CSS 原型等多种输出方式。

inspirepan Skill

Create a single wide cinematic scene image with strong atmosphere, mood lighting, and aerial perspective. Use for cinematic scene, narrative illustration, atmospheric scene, wide-angle scene, sci-fi mood, blog hero, podcast wide cover, story configuration. 用于电影感、氛围图、场景插画、宽幅故事图、叙事配图、博客头图、AI/sci-fi 主题首图。Do NOT use for 干货知识卡 / 信息图 / 海报排版 / 产品图 / UI 截图 / 四象限图。

inspirepan Skill

Generates Xiaohongshu (RedNote / 小红书 / 小绿书) and WeChat 图文 image card series — a coherent set of 4-8 cartoon-style infographic cards with 12 visual styles, 8 layouts, and 3 palettes. Use whenever the user mentions 小红书图片 / 小红书种草 / 小绿书 / 微信图文 / 微信贴图 / XHS images / RedNote infographics / image card series / 系列图卡 / 图卡系列 / 多图笔记. NOT for 单张文章封面、PPT 长图、单页海报、长图营销页 (single hero cover or single long poster — pick a different skill).

inspirepan Skill

Generate screen-print and duotone style editorial posters for movie posters, book cover posters, concert posters, cultural commentary covers, and limited-edition art prints. Use whenever the user mentions movie poster, book cover poster, editorial poster, screen-print, silkscreen, duotone, halftone, concert poster, alternative poster art, Mondo style, or 影评海报、书评封面、电影海报、演唱会海报、文化评论封面、丝网印刷海报、双色调海报. Strong visual core is screen-print silhouettes plus duotone color blocks plus halftone grain plus typography-as-composition. Do NOT use for slide decks, flowcharts, infographics, product photography, UI screenshots, or photorealistic key art.

inspirepan Skill

Generate layered 2.5D flat design illustrations with clean shapes, visible depth, cel-shaded planes, soft top-right lighting, balanced spacing, plain backgrounds, and restrained palettes. Use when the user asks for 扁平插画, flat illustration, layered vector illustration, Live2D-like flat character art, simple geometric character/object art, or cute clean icon-like scenes. Do NOT use for UI mockups, product ads, comics, dense infographics, cinematic scenes, realistic photography, logos, or text-heavy posters.

inspirepan Skill

Generate a single dense knowledge card / infographic / concept map / cheat sheet / business analysis report from a topic, outline or article. Trigger on "knowledge card", "infographic", "concept map", "summary card", "cheat sheet", "mindmap card", "quadrant card", "business report infographic", "干货卡", "知识卡", "概念图", "速查表", "信息图", "思维导图卡", "象限图", "商业分析图", "商业报告长图". Style covers notion subtle layered surfaces, sketch-notes hand-drawn, chalkboard, consulting-report. Layout covers dense / list / mindmap / quadrant / flow / report. Do not use for movie posters, single-character illustration, standalone photorealistic scenes, or social-feed cover series.

lora-sys Bundle

Create, edit, replicate, read, and export presentations. For every PPT task, the default deliverables are BOTH (1) a self-contained PPTD project folder containing the .pptd manifest plus pages/media dependencies and (2) a locally generated .pptx with embedded fonts and fade slide transitions. Use for any presentation, PowerPoint, PPT/PPTX, slide deck, PPTD, infographic, or poster task unless the user explicitly requests another format. Deliver with normal local file/folder links using absolute paths.

lufigir Bundle

Use when creating or updating a project entry for felipego.com — the bilingual Notion "Projects" (English) / "Proyectos" (Español) portfolio databases that power the site as a headless CMS. Driven by a single input: a GitHub repo URL. The workflow: generate a Mintlify wiki from the repo, read that wiki as the source of truth, write rich English + Spanish project pages in Notion via Executor, and illustrate them with interactive HTML-block diagrams styled with felipego.com's own design system (falling back to native Mermaid when that's not warranted), plus explicit, easy-to-find image placeholders left for the user to fill in later. Trigger whenever the user mentions adding, publishing, or updating a felipego.com project, a portfolio project item, the Notion Projects/Proyectos databases, generating project documentation, or making a Mintlify wiki for a repo — even if they don't spell out every step. Uses Notion (via the Executor MCP hub) and the Chrome DevTools MCP.

yikart Skill

Image editing using Sharp. Supports compositing (QR codes, logos, watermarks), resizing, cropping, rotating, flipping, brightness/contrast/saturation adjustment, blur, sharpen. 图片编辑、图片合成、添加二维码、添加Logo、添加水印、图片缩放、图片裁剪、图片旋转、图片翻转、亮度对比度饱和度调整、模糊、锐化。

gcwing Skill

Sparo OS Product App UI polish guidance. Use when improving Product App visuals, layout, runtime UI Kit usage, Sparo OS theme variables, density, empty/loading/error states, accessibility, responsive behavior, light/dark QA, zh-CN/en-US QA, or aligning Product App surfaces with existing built-in app design.

igniteui Bundle

Generates and customizes Ignite UI for Angular themes including color palettes, typography, elevations, and component-level styles using the Sass theming system and the igniteui-theming MCP server. Use when users ask to theme, restyle, or style Ignite UI components, change colors or the color palette, switch between light and dark themes, create or apply a global theme, customize typography or elevation shadows, adjust spacing, sizing, or roundness, or configure per-component design tokens. Do NOT use for component behavior, APIs, or data binding — use igniteui-angular-components or igniteui-angular-grids instead.

sonhaicoder Skill

LME Flutter Skill — Build với lme_ui design system

yosemitecrew Bundle

Use when building or changing UI in apps/frontend. Covers the custom design system, component library (Button, Card, Badge, and more), design tokens, and styling conventions so UI stays consistent and on-brand.

crunteam Bundle

Generate multi-panel educational comics, science explanatory cartoon strips, infographic storyboards, concept illustration strips, and step-by-step teaching comics using Crun AI image models and automated panel stitching. Use whenever the user asks for an educational comic, science/tech concept comic, explanatory cartoon, teaching storyboard, multi-panel knowledge strip, infographic illustration, or wants to turn any topic, concept, historical event, physics/math problem, coding logic, or story into a visual comic strip — even if they don't explicitly say "Crun" or "comic".