Design & Media

nafisrayan Bundle

Extract components from Figma, convert designs to React components, sync design tokens, and generate code from designs. Bridge the gap between design and code with automated workflows.

cmolg Bundle

Cognitive Extraction Engine for UI designers — product designers focused on visual system, components, typography, motion, and craft. Use when a user wants to clone a UI designer's taste and judgment — how they make visual decisions, set up systems, critique work, and balance brand with usability. Trigger on phrases like "extract my design taste", "clone our UI designer", "build an AI that critiques mocks like me", "interview me about visual design", "capture my design system philosophy", "make a UI cognitive clone". Outputs are tool-agnostic.

pivoshenko Bundle

Central brand system for Volodymyr Pivoshenko — voice, type, color, layout, iconography. Self-contained; covers any output format (web UI, PDF, slide deck, README, social card, email, terminal/theme port, throwaway mock). Trigger even when the user doesn't say "brand" — any visual or copy decision touching pivoshenko surfaces counts. Also trigger on "make this on brand", "style this", "design a mock", "apply pivoshenko style", "needs to feel like my site", "generate a PDF / slide / poster / card", or any styling work on pivoshenko-adjacent content.

sidiangongyuan Bundle

Use when designing, implementing, reviewing, or improving web and mobile UI/UX. Consults searchable design data for product patterns, styles, palettes, typography, accessibility, charts, icons, and common frontend stacks.

aircury Bundle

Use this skill for frontend UI work that must preserve or extend a product's real design system: new screens/components, high-fidelity rebuilds, restyles, non-trivial forms, role-gated UI, substantial behavior changes, or UI implementation that needs layout, experience, style-guide, clean implementation planning, and final code generation. This is the single frontend skill to install; it is self-contained and routes between lightweight UI edits and the full frontend workflow using bundled references.

andreworia Skill

Restores the correct logo lockup with brand clear space and minimum sizing wherever the wrong logo, color, or crop appears.

archibate Bundle

Render-first visual quality assurance for frontends, slides, diagrams, SVG/canvas, PDFs, generative-AI images, and other visual artifacts. Use after creating or changing a visual artifact, including with image generation, or when asked to review alignment, spacing, typography, connectors, clipping, factual correctness, responsive layout, font fallback, export fidelity, or visual polish. Inspect the actual rendered artifact, verify generated content against its source data and constraints, measure suspicious geometry, fix visible defects, and render again before completion.

b-open-io Bundle

This skill should be used when the user asks to "generate SVG", "create SVG", "make a logo", "create vector graphics", "generate icon", "make vector illustration", "vectorize image", or needs scalable vector graphics generated via AI.

b-open-io Bundle

This skill should be used when the user asks to "generate an image", "create a banner", "make artwork", "create an illustration", "generate a logo", "make a graphic", "design a header", "AI art", "img2img", "social share image", "OG image", "open graph image", "Twitter card", "hero image", "cover photo", "profile picture", "social media graphic", or needs AI image generation. Handles prompt rewriting and Gemini 3 Pro image generation API calls.

beast-ofcourse Bundle

Generate insane, taste-driven PDF documents — reports, proposals, resumes, portfolios, magazines, academic papers, letters — with unbound creative freedom: the AI decides palette, typography, and layout from content semantics. Fuses zinc-backbone + editorial parchment taste (pdf-forge + Kami), HarfBuzz/Knuth-Plass typography (imprint), page-as-canvas budget→compose→QC (beautiful-pdf-mcp), and token-driven doc types (minimax). Every PDF is HTML + Tailwind → Playwright/Paged.js, print-ready, no AI slop. This is THE extreme skill for ANY PDF — distinct from PPTX (slides), DOCX (Word), or SVG charts. Trigger whenever the user asks for pdf, PDF, report, proposal, resume, portfolio, magazine, brochure, whitepaper, or "make it a PDF" — even vague "pretty document" without naming PDF. Do NOT trigger for PPTX or DOCX alone.

beast-ofcourse Bundle

Create, optimize, animate, and restyle publication-grade SVG graphics — icons, logos, illustrations, diagrams, charts, patterns, and text art — with spec-correct W3C SVG 2, five-zone lighting, and geometry-validated layout. Outputs standalone .svg, HTML inline, React JSX, or Vue SFC as native vector. This is THE extreme skill for ANY SVG — distinct from PPTX (slides), PDF (paged docs), or PNG (raster). Trigger whenever the user asks for svg, SVG, icon, logo, illustration, diagram, chart, pattern, gradient, filter, mask, path, or “make it vector” — even vague “draw this” or “make a logo” without naming SVG. Also trigger for “optimize this SVG”, “animate this icon”, “restyle this illustration”. Do NOT trigger for raster JPG/PNG alone, PowerPoint, or Word.

bluzir Skill

Pull design tokens + frame structure from a Figma URL via the Figma REST API. Requires FIGMA_TOKEN env var.

bluzir Skill

Clone a GitHub repo and extract design tokens (colors, fonts, spacing) from its codebase. Use when user gives a github.com URL and wants a design system or design work rooted in the repo's style.

bluzir Skill

Screenshot + console sweep + visual inspection of an artifact for layout/color/typography regressions. Silent on pass, reports only on issues. Use after /done reports clean and before end-of-turn.

bluzir Skill

Explicitly load a design system from the org-level registry at ~/.claude/design-systems/<name>/ for the current project. Use when user says "use the Acme design system", "apply company-x tokens", or similar.

bluzir Skill

Create Design System

chanjing-ai Skill

Visual quality review for FrameVideo compositions. Use when checking or fixing material overlap, text overlap, clipped or overflowing text, low text/background contrast, unsafe title/logo/CTA/caption placement, dynamic text fitting, visual collisions during animation, or final composition QA after creating or significantly editing FrameVideo HTML.

mikkelkrogsholm Bundle

Ekspert i implementering af Glød Design System. Sikrer "Nordic Noir" æstetik via tokens, glassmorphism og sensuel bevægelse.

samulee003 Bundle

Technical reference for writing or editing open-slide pages — file contract, 1920×1080 canvas, type scale, CJK typography guards, diagram design (39 visual patterns), human-writing standards, layout, palette/visual direction, assets, stepped reveals, page transitions, and morph transitions. Consult this whenever you are about to write or modify any file under `slides/<id>/`, including from inside the `create-slide` or `apply-comments` workflows, or for any ad-hoc slide edit. Triggers on phrases like "edit slide", "tweak this page", "fix the layout", "change the palette", "reveal one by one", "add a transition", "morph transition", "investigate the slide framework", "how do slides work here".

yoanbernabeu Skill

Style Slidev slides with UnoCSS and custom CSS. Use this skill for custom colors, typography, animations, and responsive designs.

shelbeely Bundle

Generate Material Design 3 color themes programmatically from a source color using @material/material-color-utilities, the same engine that powers the Material Theme Builder. Use this when the user asks to generate an M3 color palette, create a custom theme from a brand color, or export M3 tokens to CSS, JSON, or framework configs.

shelbeely Skill

Master guide for Material Design 3 — covering the full specification from Material You foundations through M3 Expressive. Explains when to use each Material Design 3 skill subset (color, motion, typography, shape, layout, components, icons). Use this when starting a Material Design 3 project, when you need to understand which M3 skill to apply, or when the user asks about Material Design 3 in general.

shelbeely Bundle

Applies Material Design 3 Expressive typography principles including variable fonts, type scales, and hierarchy. Use this when working on text styling, type hierarchy, readable interfaces, or when the user asks to apply Material Design 3 typography guidelines.

julianoczkowski Skill

Run comprehensive lint checks for React + Vite project to ensure design system compliance, type safety, and code quality. Use when making code changes, before completing tasks, or when the user requests lint checks.

julianoczkowski Bundle

Build production-grade frontend interfaces using the Modus 2.0 Design System with Tailwind CSS. Use this skill when the user asks to build web components, pages, dashboards, or application screens. Enforces the 9-color semantic system, Modus Web Components, Modus Icons, and design system compliance. Framework-agnostic (works with SolidJS, React, Angular, or any framework).

hmbown Skill

Create a kid-friendly learning card with an illustration and narrated audio.

jablonkai Bundle

Remote-control Cavalry (Scene Group's 2D motion-design app) by script: build scenes procedurally, animate with keyframes and magic easing, do per-letter text animation, load image/JSON assets, and render PNG frames or full videos. Use whenever the user wants to create or edit a Cavalry scene (.cv file), a motion-graphics sting, logo animation, animated title, countdown, lower third, or particle-style burst in Cavalry — or says 'Cavalry', 'logo sting', 'make an animation in Cavalry', 'intro animation', 'render from Cavalry' — even if they don't mention scripting. Also use when a video project needs an animated overlay that DaVinci Resolve or ffmpeg alone can't produce.

pietz Bundle

Capture the design at hand into a DESIGN.md file — a semantic design system written in descriptive, designer-friendly language. Use when the user wants to document, preserve, or hand off the visual design of what's currently in view (an HTML/CSS prototype, a component, a website, a screenshot, or a codebase's styles). The output is a single Markdown file intended to serve as the source of truth for future design work and for prompting other tools to generate screens consistent with it.

promovaweb Bundle

Conceitua, cria ou revisa um sistema de logo original. Use quando a marca não possui logo ou precisa corrigir um símbolo inadequado.

promovaweb Bundle

Exporta e organiza variações de logo em SVG e PNG. Use para gerar versões light, dark, monocromáticas, ícones, favicons e manifesto.

promovaweb Bundle

Define o sistema visual da marca além do logo. Use para criar direção de arte, paleta, tipografia, fotografia, ilustração e iconografia.

royvergara Skill

Use when producing a design-system reference from a team's existing components, tokens, and patterns — the reference design-system-enforcement needs to audit against. Triggers on existing UI source (a component file, a codebase, exported tokens) plus a request to extract, document, or produce the design system. Returns an evidence-backed reference with its conflicts named, never an invented system.

royvergara Skill

Use when auditing generated or drafted UI against a team's design system. Triggers on a screenshot, code, or spec plus a reference to the design system. Returns violations, not compliments.

royvergara Skill

Use when a design task spans multiple Figma plugins or steps and needs to be sequenced from one instruction. Triggers on a request to coordinate, sequence, or automate plugin work in Figma. Always names which steps stay human.

linuxfoundation Skill

Central explainer for adding object storage capability to an LFX V2 service. Covers the S3-compatible storage decision, hard requirements (no presigned uploads, private buckets only, 20 MB cap, per-service bucket ownership, metadata/payload separation), Go AWS SDK v2 code patterns, the singleton and collection API shapes, the Helm chart credential-mode contract (static creds for local, IRSA for deployed), the nats-s3 sidecar local backend, the nginx-s3-gateway local CDN model, and the S3_BUCKET/AWS_REGION/S3_ENDPOINT_URL/S3_CREATE_MISSING_BUCKET/ CDN_URL_PREFIX env var contract. Fires on prompts like "object storage", "S3", "file upload", "upload endpoint", "attachments", "logo upload", "bucket", "nats-s3", "nginx-s3-gateway", "CDN_URL_PREFIX", "presigned URL", "PutObject", "IRSA S3", "S3_ENDPOINT_URL", "public_url", "download endpoint", "multipart upload". Read-only; routes implementation work to the owning service repo and provisioning to `/lfx-skills:lfx-object-store-ops`.

lujiaheng-artpivot Bundle

TVC级动态字幕设计。生成与音乐节奏同步的动态文字方案，让字幕本身成为视觉元素而非信息附属。