Design & Media

eigenwise Bundle

Create professional technical diagrams (architecture, sequence, state, flow) in the Tesseron docs visual language — dark slate base with a single amber accent, dotted-grid background, gradient cards, Lucide-style icons, Gaussian-blur glow on the emphasized node, and Inter + JetBrains Mono typography. Use when creating docs diagrams for a Tesseron-style project, any Starlight/Astro docs site that wants a restrained monochrome-plus-one-accent aesthetic, or when the user says "use our Tesseron design system".

jhd3197 Skill

Long-form editorial article — opinionated typography, byline, hero image, generous reading column.

joet203 Bundle

Generate actual images from text, free, no paid API. Use whenever the user wants an image created — illustration, hero/header art, icon, texture, concept art, photo-style render, logo sketch, placeholder, or a picture to drop into a page or doc. Triggers on 'make an image', 'generate a picture of', 'create art', 'I need a graphic for', 'render', 'draw me', or any request that needs a visual rather than prompt text. Three backends: local ComfyUI (private, no limits), pollinations.ai (any size, needs internet), and Codex gpt-image-2 (best quality, uses ChatGPT Plus subscription limits — finals only). NOTE: for writing funny prompt TEXT (not images) use the image-prompts skill instead.

abdul977 Bundle

Rebuild a website (or a single section) from a reference design image so it matches measurably, not approximately — by measuring the reference to derive a numeric spec (viewport, container width, section heights, font sizes, colours, corner radii, gaps), building section by section, then measuring the built DOM and diffing it against the reference until every delta is within a few pixels. Use this skill whenever someone supplies a screenshot, mockup, Figma export, theme demo, or competitor page and wants it "rebuilt", "cloned", "matched", "recreated", "converted to HTML/CSS", or asks for it to look "exactly like", "1:1", "pixel perfect", or "100% the same" — and also when they hand over a design image section by section, or ask you to check whether a build matches a reference. Reach for it even when they just say "make it look like this image", because the measuring loop is what separates a real match from a rough approximation.

abdul977 Skill

Build premium white-background, single-green-accent kinetic-typography motion ads (9:16) with real footage layered behind HTML type — the divyansh.fx_ style. Use when the user wants a "motion graphics ad", "kinetic typography video", "text animation ad", or to turn a voiceover script into a faceless/objects-driven social ad in the workspace under C:\Users\user\Desktop\video-ad. Composites keyed or framed footage (green-screen OR their own Veo clips) with animated HTML/SVG objects, one green accent, italic-serif emphasis, depth/parallax, and a brand end card.

abdul977 Bundle

Build a standalone, Elementor-like page-builder CMS with its own /admin editor as a single self-contained WordPress plugin. Beginner-friendly tap/drag editing, 15+ content blocks (columns, accordion, tabs, testimonial, gallery, pricing, form...), rich text, per-block spacing/animation/typography, undo/redo, duplicate & copy-paste, saved-section library, autosave recovery, global brand theme, page manager (duplicate/delete/rename/publish), and version history. Use when asked to create a WordPress admin panel, a custom client-editable page builder, a no-code CMS editor, or a standalone /admin for editing pages.

backnotprop Bundle

Write and refine production UI code to a high craft bar. Use for building components, polish and detail work (spacing, typography, color, copy, icons, shadows, interaction states), implementing animation and gestures, implementing accessibility (keyboard, screen readers, focus, forms), and hardening for production (real data, failure states, devices, languages, offline, shipping metadata). Triggers on build, implement, polish, refine, tighten, "feels off", animate, transition, gesture, drawer, make accessible, keyboard navigation, production-ready, edge cases, empty states. The deliverable is code. Not for read-only critique (review) or pre-code design work (design).

backnotprop Bundle

Design-process work before production code. Use to capture product and design-system context (PRODUCT.md / DESIGN.md), write a design brief for one feature or flow, set creative direction and taste, build wireframes / mockups / prototypes / diagrams / plans as self-contained HTML, render competing variations of a UI piece behind a picker, design onboarding and first-run flows, or record an approved artifact under .product/approved/. Triggers on design, design brief, "write a brief", "spec this feature", "shape this flow", direction, "how should this look/feel", wireframe, mockup, prototype, mock this up, diagram, "document our design system", DESIGN.md, "show me versions/variations", onboarding, empty states, first-run. The deliverable is a document or artifact — not production code (pe-build) and not a verdict on existing UI (pe-review).

backnotprop Bundle

Create standalone visual assets that stay on brand — SVG illustrations for articles and blog posts, repo and social/OG images, logo and identity work, on-brand concept images for features. Authors SVG in code. Reads the project's brand truth (DESIGN.md, style guides, a brand/ folder) first and refuses to invent brand values. Triggers on brand asset, on-brand, SVG illustration, article image, header image, og image, social card, repo image, logo, brand kit, identity, tagline panel. Not for UI mockups (pe-design), production components (pe-build), or judging existing assets (pe-review).

skillmedev Skill

Put text in motion the right way - title cards, animated captions, lower-thirds, callouts, and word-by-word reveals - with a reading-time-per-word budget so copy holds long enough to read, plus enter/exit timing, weight and size transitions, and type hierarchy in motion. Use when someone asks to "animate this text", "make a title card", "animated captions/subtitles", "kinetic typography", "animate the headline", "lower-third", "word-by-word reveal", "text that pops in", or "how long should this line stay on screen". Do NOT use when the question is the cut, pacing, or easing curve of non-text motion - use motion-design-principles instead; do NOT use to plan which scenes or shots exist - use video-storyboard instead; do NOT use to resize or crop a caption track for a specific platform (9:16 TikTok, 1:1 feed) - use social-video-formatter instead; do NOT use for the color, contrast, or lighting of the type against its background - use motion-color-and-light instead.

skillmedev Skill

Direct the craft of putting a real software UI on screen - cursor choreography, zoom/pan/callout language, screen-recording vs recreated-UI, and making state changes legible with highlights, focus pulls, and slow-downs. Use when filming or recreating an app for a product demo, feature walkthrough, onboarding clip, or release reel and asking "how do I show this click", "where should the camera zoom", "should I screen-record or rebuild the UI", "why does my demo feel confusing", "how do I make the state change readable", or "how do I move the cursor". Do NOT use for the underlying motion grammar (easing, timing) - use motion-design-principles; for the beat-by-beat plan - use video-storyboard; for animating words on screen - use kinetic-typography; for the color/light of highlights and glows - use motion-color-and-light; for sound design or a click/whoosh hit - use sound-and-music-sync; for reframing the demo to 9:16 or 1:1 - use social-video-formatter; for the React/MP4 mechanics of building it - use remotion-c

skillmedev Skill

Choose palette, contrast, and lighting for a moving video - not a static UI - so color survives H.264/VP9 compression, banding, and YouTube/Instagram/TikTok recompression across OLED, LCD, and projectors. Use when picking video colors, building a gradient mesh, adding glow/bloom/depth, setting a dark-background default, asking "why does my gradient band", "why is my neon muddy after upload", "is this contrast video-safe", or "what palette for my video". Do NOT use when laying out scene timing or beats - use video-storyboard instead. Do NOT use for motion-easing or animation-feel decisions - use motion-design-principles instead. Do NOT use to style or animate the on-screen text itself - use kinetic-typography instead (you give it the palette, it sets the type in motion). Do NOT use to structure a product walkthrough or decide what to show - use product-demo-director instead. Do NOT use for audio, beat-matching, or scoring - use sound-and-music-sync instead. Do NOT use to re-crop or re-spec a video for a platfo

skillmedev Skill

Reframe and export a finished video for social platforms - 9:16 ↔ 16:9 cropping, burned-in captions, a platform-native first frame, loop design, and per-platform specs (aspect, length, safe areas) for TikTok, Reels, Shorts, X, and LinkedIn. Use when someone says "make this vertical", "crop to 9:16", "format for TikTok/Reels/Shorts", "add captions/subtitles", "why is my video cut off on mobile", "resize for Instagram", or "export for social". Do NOT use when the question is about the storyboard or shot order before any video exists (use video-storyboard); the animation craft of how elements move (use motion-design-principles); animated word-by-word caption styling (use kinetic-typography); palette, contrast, or lighting (use motion-color-and-light); directing the product-demo content and screen choreography (use product-demo-director); or scoring, beat-syncing, or audio (use sound-and-music-sync) - this is the craft layer that decides WHAT to format for the feed, then hands a concrete spec to remotion-compose

moumen-soliman Bundle

Color systems for digital products. Use when creating or extending a palette, theming light and dark appearances, or auditing the colors in a codebase. Triggers on color palette, palette generation, color ramp, brand color, accent color, gray palette, status colors, color tokens, token naming, theming, dark mode colors, contrast ratio, APCA, gamut, display p3, oklch, color conversion, gradients, color meaning, increased contrast.

moumen-soliman Bundle

Web typography. Use when picking or pairing typefaces, setting up a type scale, or styling and truncating text in components. Triggers on typography, font loading, woff2, variable fonts, opentype features, type scale, heading hierarchy, line-height, letter-spacing, measure, text-wrap, truncation, tabular numbers, underlines, text selection, iOS input zoom, font smoothing, smart punctuation, text-box, drop cap.

nexu-io Bundle

A 1970s European editorial poster in motion — a red rule draws across, a giant tilted figure drops in, a three-line headline rises line-by-line, an italic serif standfirst fades.

picsart Skill

Generate images via the Picsart gen-ai CLI or MCP server. AUTO-TRIGGER whenever the user asks to generate, create, render, make, illustrate, or design an image, hero, product shot, OG image, poster, icon set, avatar, background, thumbnail, illustration, wallpaper, ad creative, social tile, lifestyle shot, or packshot; wants to pick between Flux / Recraft / Nano Banana / Imagen / Seedream / Ideogram / Hunyuan; wants to resize, reframe, upscale, remove background, replace background, or batch-process images.

zrosenbauer Bundle

This skill should be used when the user wants to create, fix, or convert SVG assets in any project — banners, badges, icons, logos, window/IDE mockups, terminal screenshots, or diagram nodes. Common triggers include "create an SVG", "make a banner", "design an icon", "draw a logo", "fix the viewBox", "convert SVG to PNG", and "preview this SVG". Bakes in edge-to-edge viewBox discipline (`viewBox="0 0 W H"` — no padding, no offsets), hardcoded hex colors (SVG cannot read CSS variables), a Node- based local preview server for browser + chrome-devtools MCP screenshot verification, and sharp-based conversion to PNG / JPEG / WebP / AVIF. Skip when the asset is purely raster (no SVG source) or when only an existing PNG needs editing.

automattic Bundle

The full design glow-up toolkit. Turns forgettable interfaces into something that looks like a real designer touched it. Routes to 6 sub-skills for de-slopifying, typography, spacing, gradients, motion, and adding that one detail people actually remember. Use when a UI feels mid, generic, AI-generated, or just painfully beige.

automattic Skill

Upgrade typography from generic SaaS to premium, authored, high-conviction design. Uses distinct display fonts, lighter body weights, tight negative tracking, mono eyebrows, restrained serif accents, and OpenType details to create typography with taste, authority, and emotional signal. Use when a page feels flat, template-y, overly safe, or visually anonymous.

dillonschultz93 Skill

Scaffold a new design token system interactively, or bootstrap one from an existing codebase with `--from-codebase`. Guides the user through brand color, spacing base, type scale, and dark mode choices, then runs `quieto-tokens init` to generate a complete DTCG token system with multi-platform outputs (CSS, Figma, iOS, Android). Use when the user wants to create or bootstrap a new token system.

dillonschultz93 Skill

Add a new token category (shadow, border, or animation) to an existing token system. Prompts for category-specific inputs and generates the token files. Use when the user wants to extend their token system beyond color, spacing, and typography.

gainubi Bundle

为文章生成可截图的扁平化解释配图 HTML 页面。用于用户提供文章、草稿、段落或文件路径，并要求配图、文章插图、图解、公众号配图、生成 illustration 页面、帮我配图。输出是本地 HTML 文件，不直接生成 PNG/JPG，不用于 Logo、图标、海报、封面或非文章内容。

guiloureiromkt Bundle

Cria SITES premium (landing, marca, portfólio, produto) no método "Claude Design 2.0" — engenharia reversa do website-builder do Higgsfield, rodando 100% local com Replicate como motor de assets. Use SEMPRE que o Gui pedir "ultra-site", "cria um site", "landing page premium", "site animado", "site tipo Higgsfield/Claude Design", "site com scroll cinematográfico", "faz o site da marca X", ou quiser um site novo com direção de arte de verdade (não template). O design é decidido como IMAGENS (reference boards gerados por seção), o visual é um kit de assets 100% bespoke (hero, texturas, ícones, logo, OG, vídeo-scrub), o código é fiel aos boards, e nada é "done" sem gate mecânico + review adversarial por screenshot. NÃO é pra landing WP do guiloureiro.com.br (use gndm-novo-material), nem redesign de página WP (gndm-page-redesign), nem clonar app existente (clone-webapp), nem deck (ultra-deck), nem carrossel (ultra-carrossel).

jason904 Bundle

This skill should be used after visual-spec-review passes and before OpenSpec UI update or frontend implementation. It expands screenshot-derived visual specs into a production design system by adding interaction states, responsive behavior, accessibility rules, UX checklist, and implementation constraints without overriding UI type, layout paradigm, component tree, rejected assumptions, or asset strategy.

vaadin Skill

Apply a settled design spec to a Vaadin Aura app's global theme: write only what differs from the theme's defaults, prove it in the browser, and refresh the resolved token values the spec records.

vaadin Bundle

Survey a Figma design against what a Vaadin app already builds, interview the user in rounds on every divergence, and write the project's design spec. Ends in the spec plus a delta in the conversation — never in code, theme CSS, or a ticket.

vaadin Skill

Translate Figma designs into Vaadin Flow (Java) UI code using the Figma MCP and the Vaadin docs tools. Use this skill whenever the user wants to implement a Figma frame, screen, or component as Vaadin Java code — even if they just say "implement this design", "generate Vaadin code from Figma", "convert this frame to Java", or paste a Figma URL. Does NOT apply to React, HTML, web components, or other frontend frameworks — only Vaadin Flow (Java). Does NOT apply to design-only tasks such as editing Figma files or generating Figma components. Does NOT configure themes or visual design tokens — that is a separate skill.

vaadin Skill

Visually verify a Vaadin Flow view against the Figma design it was implemented from, using the Playwright MCP server to render the running app and a Figma screenshot as the reference. Use this after implementing or changing a Vaadin view from a Figma design, when the user asks to "verify against the design", "check it matches Figma", "visually verify the view", or as a follow-up step after figma-to-vaadin. Produces a prioritized, actionable list of visual discrepancies — it does not fix them. Does NOT apply to backend/business-logic testing or general UI test suites — this is visual, design-fidelity verification only.

tuoxie2046 Bundle

Generate, edit, describe, or batch-generate images from the terminal using OpenClaw + OpenAI gpt-image-2 (billed to the ChatGPT/Codex subscription, not the API). Use whenever the user asks to create / draw / generate an image, picture, icon, logo, illustration, poster, diagram, architecture figure, flowchart, or infographic — to produce a set / batch of multiple images from several prompts — or to edit an existing image (inpaint / restyle / combine) or describe what is in an image file.

tuoxie2046 Bundle

Generate images from the terminal with Google's nano-banana (Gemini image model) via the Antigravity CLI (`agy`), billed to the signed-in Google account. Use whenever the user asks to create / draw / generate an image, picture, icon, logo, illustration, poster, infographic, or diagram specifically with nano-banana / Gemini / Antigravity — or wants rich, text-heavy infographics. For the OpenAI gpt-image-2 path use the separate `gpt-image` skill instead.

leonvanzyl Bundle

Generate, fetch, and optimize images via the Get Images MCP server. Use this skill whenever the user asks to create, generate, make, or produce an image, illustration, photo, thumbnail, hero image, banner, asset, or visual — especially when the Get Images MCP tools (getimages_generate_image, getimages_list_images, getimages_get_image, getimages_get_account, getimages_list_usage) are available. Also triggers on requests to "add an image to" a webpage/component, "create a thumbnail for", "generate stock photos", or any visual asset request in a coding project.

getcrew44 Skill

Use to evaluate visual consistency, hierarchy, and design-system adherence — typography, color, spacing, density, tokens.

auldsyababua Bundle

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

rebyteai Bundle

Typeset any professional document: resumes, one-pagers, white papers, letters, portfolios, slide decks. Warm parchment design system with ink-blue accent, serif-led hierarchy, and tight editorial spacing. Trilingual best-effort output: Chinese docs use TsangerJinKai02 + Source Han, English docs use Newsreader + Inter, Japanese currently maps to the CJK template path with JP Mincho first and Tsanger fallback, and requires manual visual QA before shipping, with one shared English reference set. Triggers on "做 PDF / 排版 / 生成报告 / 一页纸 / 白皮书 / 作品集 / 正式信件 / 简历 / PPT / slides / 高质量文档 / 好看的排版", or "build me a resume / make a one-pager / design a slide deck / turn this into a PDF / make this presentable / polish typography", and when raw content is handed over to be "typeset, designed, made presentable".

ch4570 Bundle

Remove generic AI-generated UI and make product experiences clear, calm, and easy to use. Use when asked to remove AI slop, make UI/UX smoother or more user-friendly, or improve a screen across visual design, interaction, and copy. Coordinate only the relevant specialist skills; exclude backend cleanup, prose detection, and standalone illustration.