Create, inspect, convert, apply, replace, verify, troubleshoot, update, publish, or restore reversible CodeDrobe themes for supported Chromium/Electron AI desktop apps, including OpenAI Codex, Tencent WorkBuddy, QoderWork (CN/global), and TRAE SOLO (global/CN). Use when a user asks to turn an attached or local…
Generate a cohesive set of transparent-background icons in a chosen or brand-matched visual style. Use when the user wants custom icons, an icon pack / set, system icons, spot / feature / category icons, or icons matching a specific look (line, filled, colorblock, cartoon, isometric, 3D, sticker, realistic, animal…
Generate a visual property annotation in Figma showing each configurable property axis with component instance previews. Use when the user mentions "property", "properties", "property annotation", "create property", or wants to document a component's configurable properties visually.
Use this skill whenever creating PPTX slides, presentations, or decks with any of these 30 modern design styles: Glassmorphism, Neo-Brutalism, Bento Grid, Dark Academia, Gradient Mesh, Claymorphism, Swiss International, Aurora Neon Glow, Retro Y2K, Nordic Minimalism, Typographic Bold, Duotone Color Split, Monochrome…
OKLCH color space for web projects. Convert hex/rgb/hsl to oklch, generate palettes, check contrast, handle gamut boundaries, and theme with Tailwind v4. Triggers on oklch, color conversion, palette generation, contrast ratio, gamut, display p3, design tokens, hue drift, chroma, dark mode colors.
A cover-design prompt guide for Chinese public-account and Xiaohongshu posts. It offers ten composition styles, a person on camera, and layouts for combining a face reference with interface screenshots or product images.
Audits and upgrades existing websites and apps to premium quality. Diagnoses generic AI design patterns, weak states, and sloppy code, then applies targeted fixes without breaking functionality. Use this skill whenever the user wants to improve, polish, upgrade, refine, audit, fix, or redesign an EXISTING site, page…
Creates C4 architecture diagrams for designing, documenting, or understanding software architecture. Use when working through system design, mapping existing codebases, or visualizing structure at any level from system landscape down to code.
Clones any web app pixel-for-pixel from a URL. Runs as an IN-CONVERSATION workflow — the live Claude orchestrates Task sub-agents and drives the Claude Chrome extension to recon (every view), extract (computed styles = ground truth), design-spec, build, QA (computed-style assertions), and extend. Guided check-ins…
Only to be triggered by explicit /co-design commands. Parallel task executor that routes frontend/design tasks to Claude CLI print mode for superior design output.
Use this skill when users want to add, customize, or troubleshoot UI Beats components in React/Next.js projects. It covers component selection, shadcn registry installation from uibeats.com, the UI Beats MCP server, motion and reduced-motion handling, and integration patterns for animated sections.
A design-system guide for building and reviewing Dig web and product interfaces. It provides rules, page layouts, reusable interface parts, and design tokens such as shared colors and spacing.
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
Help Codex plan, generate, reproduce, and refine editable Microsoft Visio scientific diagrams. Use when users ask Codex to operate local Visio, create VSDX research figures, redraw uploaded paper screenshots or sketches in Visio, convert natural-language method descriptions into scientific diagrams, export preview…
NERV Operations Console aesthetic for web interfaces — Evangelion-inspired instrumentation UI with black void backgrounds, sparse high-contrast color coding (orange headers, green nominal data, cyan wireframes, red alerts), dense monospaced data readouts, measurement overlay grids, hex scanner patterns, CRT/VHS…
Translates an image (or a set of image references — screenshots, mockups, Figma URLs, live websites) into two mirrored design-system artifacts: docs/design.md (YAML tokens + prose, following Google's open design.md format, for the coding agent) and docs/design.html (a self-contained, token-driven style guide rendering…
Design new measurement paths or reconstruct, audit, and revise Blender optical-table systems from measurement requirements, 2D schematics, and provenance-bound CAD. Use for high-fidelity optics-only models, Thorlabs-compatible optomechanics, optical topology, whole-system validation, or publication renders with scoped…
Use when creating, reviewing, or styling charts, graphs, dashboards, sparklines, or any data visualization. Applies to Recharts, ECharts, Chart.js, matplotlib, Plotly, seaborn, D3.js, and SVG. Enforces Tufte principles (data-ink ratio, direct labeling, range-frame axes) plus modern screen-first standards…
Universal visual direction engine for AI image, design, and layout work: model-agnostic decision pipeline (intent, analysis, visual language, planning, recovery/refinement) plus swappable adapters for GPT Image, Flux, Ideogram, and generic image backends. Use for visual concepting, image prompts, photo-to-design…
Creative Designer skill. Takes a post concept, a client product photo, or a real lifestyle photo and produces on-brand social media visuals using the client's brand style guide. Four modes — Generate (AI image from concept), Composite (client product photo anchored in an AI-generated scene), Brand (apply text overlay…
A tool for creating text-based Mermaid diagrams and exporting them as PNG, SVG, or PDF files. Mermaid is a format where diagram structure is written as text and laid out automatically.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: