Design & Media

saifyxpro Bundle

Generate, audit, and optimize system prompts for AI agents using 8 proven architectural patterns extracted from 16+ production systems (Kimi, Cursor, Devin, Kiro, Claude Code, v0, Windsurf, Lovable, Replit, Traycer, Manus). Use when creating new agent system prompts, auditing existing prompts for quality and completeness, optimizing prompt architecture for specific use cases, or designing multi-agent workflows. Covers skill injection, persona replacement, state machine planning, structured scratchpad, todo tracking, XML response protocols, design system enforcement, and prompt structure blueprints.

seanchiuai Bundle

shadcn/ui patterns, game UI components, responsive layouts for classroom use

choxos Skill

Mathematical rendering with MathTex, Tex, tex_to_color_map, custom equation classes, and formula animation patterns.

avinava Bundle

Design editorial-quality diagrams as self-contained inline SVG — architecture diagrams, flows, sequences, state machines, data models, timelines, layer stacks, quadrants, comparisons, and system maps. Use when explaining how a system is arranged, how a process moves, how components depend on each other, or how options compare; when a Mermaid or draw.io diagram needs to be converted into a document's design system; or when an existing diagram looks auto-generated and needs editorial judgment. Do not use for quantitative charts of measured data (use chart-design), for the surrounding report structure (use analytical-document-design), for UI mockups or wireframes, or for producing editable .drawio files.

avinava Bundle

Turn a brand into a working theme for this design system — from a screenshot, a website, a PDF brand guide, a style guide, or a handful of hex values. Use when asked to match a company's brand, apply brand colors or brand guidelines to documents, make reports look like an existing site or product, build a theme from a logo or screenshot, or fill in the brand-template slot; and when an existing theme needs its contrast, accent, or print behavior audited. Do not use for choosing between the themes that already ship (that is a one-line answer in core/tokens.md), for restyling a single document rather than creating a reusable theme, or for general visual design of a report, diagram, chart, or deck — those belong to the skill for that artifact.

darcos-loft Skill

Generate premium brand reference images for a design system, covering logo concepts, color and type boards, and product mockups. Use when a brief needs visual references or a brand kit before or alongside building the UI. Tool-agnostic (works with Nano Banana / Gemini, Higgsfield, Midjourney, or any image model).

darcos-loft Bundle

Generate a unique, production-grade brand design system from a short brief. Use when starting a new site or product, defining or extending design tokens (color, type, spacing, radii, shadows, motion), producing a token file plus Tailwind config plus a brand rules doc plus a storybook, or giving a project a distinct visual identity. Encodes a house DNA and forces per-brand variation so no two systems look alike.

gggodlin Skill

Use BEFORE any Figma MCP tool call during design-to-code work. Enforces context-efficient patterns — screenshot+metadata for planning, per-component get_design_context for implementation, cached design tokens, and Code Connect shortcuts. Complements figma-implement-design by preventing context window explosion.

gonadotrophic-tangent41 Bundle

Review a design system, UI library, token architecture, component inventory, Figma library, Storybook, or implemented product for consistency, coverage, accessibility, maintainability, adoption, and governance. Use when asked to audit components, tokens, spacing, typography, color, theming, variants, states, APIs, documentation, design-code parity, contribution, or migration. Produce evidence-backed system findings, a component and token remediation model, governance decisions, and a sequenced adoption plan. Do not use to police intentional product variation or to create a visual brand from scratch.

hiyeshu Bundle

Designer role. Reads deck.md, generates a single HTML presentation file with CSS design system + JS slide engine + per-slide content. Accepts visual references (URLs, screenshots, design specs) and extracts design signals to inform the isomorphic mapping. Use whenever the user says "design slides", "generate deck", "generate the deck", "build slides", "visual style", "reference this style", "like this design", "design", "generate slides", "visual style", "reference this style", or wants to turn an outline into actual slides.

slb2248 Skill

AI Native Product Designer role - LLM-first workflow, AI code prototyping, Figma as finish line, self-serve research, outcome ownership. Use for leveling, workflow design, and AI readiness reviews. Includes quick reference, full rubric appendix, checklist, role comparison.

soia-team Bundle

将文章、开源项目、品牌 Logo 或公开 X Prompt Deck 编译为可验收的图片与矢量资产，按组合轴生成 Prompt 并完成事实、文字和视觉验收。

stellar Bundle

Bridge Figma MCP output to Stellar Lab code conventions. Invoke after calling get_design_context to translate Figma's reference code into project-appropriate components, classes, and patterns.

switch-dimension Bundle

Molten OS Core — creates a practical Google DESIGN.md–spec visual system at `molten-docs/design/design.md`, plus `molten-docs/design/example.html`. Use for design system, design.md, or translating the brand brief into visual direction. Start by choosing one design surface (landing page, web product, mobile product, or desktop product), then load the matching surface reference and ask whether the user wants a fast draft or detailed pass. Do not use for brand strategy or messaging; use molten-brand for those.

prodazhang Bundle

figma 节点树 → 高保真界面还原 + 可交互 harness。两条产物:全保真 .ui.json(渲染真源,逐节点真样式不折叠)+ DSL .md(语义抽象,喂 aigd/KB)。要把 figma 设计帧导成"可还原/可点/可跑"的客户端、或导成结构化 DSL 时用。文法权威在 references/界面DSL规范-figma2dsl扩展.md;本 skill 只编排、不复制文法。可移植、项目无关。

prodazhang Bundle

Use when you have a figma design frame (or several) and want to turn it into a high-fidelity, runnable HTML client — pixel-faithful rendering plus declared interactions (modals, data binding, guards). For figma-sourced UIs; non-figma authoring (brief/screenshot) goes through the 界面 DSL instead.

prodazhang Bundle

把 figma2html 管线产的 IR(.ui.json 像素快照 + flow.json 交互声明)落到 Cocos Creator 3.x —— TS 运行时解释器(组件加载 ui.json 动态建节点树 + flow 绑定器)+ python 离线校验器(引用完整性 + 资产清单)。要在 Cocos 工程里还原 figma 界面与交互(底屏+弹窗/守卫/列表/勾选)时使用;capture 本身归 figma2html。

prodazhang Bundle

把 figma2html 管线捕获的中间表示(IR:.ui.json 像素快照 + flow.json 交互声明)编译成 Godot 4 文本场景(.tscn)与 GDScript 运行时 flow 绑定器。输入 = figma2html capture 的产物;本 skill 是 Godot 4 编译后端,不含 capture。要在 Godot 工程里还原 figma 界面像素与交互(底屏+弹窗/守卫/列表/勾选)时使用。

prodazhang Bundle

把 figma2html 管线捕获的中间表示(IR:.ui.json 像素快照 + flow.json 交互声明)编译成 Unity UI Toolkit 资产(UXML+USS)与 C# 运行时 flow 绑定器。输入 = figma2html capture 的产物;本 skill 是编译后端,不含 capture。要在 Unity 里还原 figma 界面像素与交互(底屏+弹窗/守卫/列表/勾选)时使用。

timeplus-io Bundle

Build user interfaces that match the Timeplus Console look and feel. Use this skill when generating, styling, or reviewing UI for a Timeplus product or console-aligned app — buttons, inputs, toggles, tables, cards, layouts — and when you need the exact Timeplus colors, Inter typography scale, 4px-radius flat-surface shapes, spacing scale, and component states. Provides a DESIGN.md (google-labs-code/design.md token format) plus ready-to-adapt CSS, Tailwind, and React implementations.

valantic-cec-deutschland-gmbh Skill

Generate branded PDF documents (reports, whitepapers, proposals) following Valantic's Liquid Brand Design with correct colors, typography, and layout.

nsairat Bundle

Persona and expertise framework for a Director of UI/UX Design with deep experience across web, mobile platforms, and marketplace products. Use this skill when providing strategic design leadership, building design teams, creating cross-platform design systems, defining product vision, or advising on design operations. Triggers include: design leadership, UX strategy, design team management, cross-platform design, marketplace UX, mobile app design direction, design operations, design system governance, UX metrics, design org structure.

one-ie Skill

shadcn/ui under the ONE 6-token design system — CSS var tokens only, no hex, add components via the CLI. Invoke when editing src/components/ui/ or adding a primitive.

yniantongtian-oss Skill

将已有视频、录屏、口播、播客或 AI 生成镜头转换为可执行的自动剪辑方案，并优先调用仓库内的 auto-editor Skills。适用于删除静音和黑场、依据声音/运动/字幕筛选片段、按台词剪辑、变速、缩放、叠加 Logo、画中画、音量处理、字幕转写，以及导出 Premiere、DaVinci Resolve、Final Cut Pro、Shotcut 或 Kdenlive 工程。先预览剪辑决策，再输出新文件，不覆盖原素材。

amazingchow Bundle

Turn 3-5 reference websites or a Figma reference board into a reusable design system, AI guardrails, and more original high-aesthetic UI directions. Use when Codex needs to extract visual DNA, scaffold a design-system workspace, write CLAUDE/Cursor rules, generate tasteful pages without copying a source site, or review an existing UI that feels template-like, over-decorated, or too close to a reference. Also use for requests like "做更有审美的 UI", "先沉淀设计系统再出页面", "把参考站整理成 design system", or "用 Figma MCP 提炼风格".

nucliweb Bundle

Intelligent media optimization with automated workflows for images, videos, and SVGs. Includes decision trees that detect LCP images (triggers format/lazy-loading/priority analysis), identify layout shift risks (missing dimensions), and flag lazy loading issues (above-fold lazy or below-fold eager). Features workflows for complete media audit, LCP image investigation, video performance (poster optimization), and SVG embedded bitmap detection. Cross-skill integration with Core Web Vitals (LCP/CLS impact) and Loading (priority hints, resource preloading). Provides performance budgets and format recommendations based on content type. Use when the user asks about image optimization, LCP is an image/video, layout shifts from media, or media loading strategy. Compatible with Chrome DevTools MCP.

icebird1998 Bundle

Connect to, inspect, create, reconstruct, or edit a Microsoft PowerPoint or WPS Presentation deck through Windows COM, Mac PowerPoint Office.js context.sync, or the cross-platform native OOXML bridge. Use as the presentation Drawer on Windows or macOS for editable scientific illustration, native text/shapes/lines/tables, atomic images, exact layout, truthful WPS state detection, checkpointed file refresh, and repeated structure-plus-renderer quality gates.

icebird1998 Bundle

Review and score an existing scientific illustration in visible draw.io, Microsoft PowerPoint, or WPS Presentation without hiding defects through flattening. Use for reference-fidelity checks, layout cleanup, connector review, text-fit checks, deep editability and raster-atomicity inspection, local-region gates, or repeated verification in a Designer-Drawer-Reviewer-Corrector loop.

icebird1998 Bundle

Design a new scientific illustration, graphical abstract, workflow, architecture figure, or mechanism diagram from a brief without a reference image, for visible draw.io, Microsoft PowerPoint, or WPS Presentation. Use when a clean editable layout, planned connector lanes, consistent visual grammar, and Designer-to-Drawer-to-Reviewer-to-Corrector quality gates are required.

icebird1998 Bundle

Convert Reviewer findings for a scientific illustration into minimal, ordered, object-level correction instructions for visible draw.io, Microsoft PowerPoint, or WPS Presentation. Use when layout, text, connector, z-order, reference-fidelity, or raster editability defects must be translated into exact backend operations and measurable regression checks without flattening the figure.

icebird1998 Bundle

Recreate a supplied scientific figure, graphical abstract, workflow, model diagram, or multi-panel schematic as a maximally editable illustration in visible draw.io, Microsoft PowerPoint, or WPS Presentation. Use when a PNG/JPEG/SVG/PDF reference must be rebuilt panel by panel through a Designer, Drawer, Reviewer, and Corrector loop with backend capability detection, atomic raster decomposition, local checks, and repeated whole-figure verification.

innei Skill

Use when adding or modifying colors, spacing, typography, or layout values in demo/ CSS. Complete token reference for the monochrome design system.

uid13 Bundle

生成或编辑矢量/程序化图像（博客封面、Logo、图表、徽章、UI 组件、PPT 封面、社交媒体图片等）。当用户需要基于模板/参数生成具有精确排版、字体控制、尺寸约束的设计类图像时使用。使用 SVG 编写 + ImageMagick 渲染。不适合：照片级写实、复杂纹理、人物肖像等需要生成模型的场景（请改用 imagegen 类技能）。适配 opencode、codex、Claude Code、Cursor、Copilot、Gemini CLI 等 Agent 平台。

vechain Skill

Map of reusable UI components and the design system (Chakra UI v3) in apps/frontend. Catalogs existing components so new code reuses them instead of duplicating, and documents semantic tokens, recipe variants, and style patterns (mobile-first, modal/bottom-sheet split, textStyle, semantic colors). Use when building or editing anything under apps/frontend/src/, when asked to add a page/component/modal/card/form/button, when writing Chakra JSX, when choosing colors/spacing/typography, or when touching apps/frontend/src/app/theme/. Triggers on frontend, UI, component, reusable, Chakra, Chakra v3, theme, recipe, slot recipe, textStyle, semantic color, design token, design system, variant, card, button, modal, bottom sheet, drawer, badge, input, form, empty state, step card, stat card, mobile-first, colorPalette, bg.primary, text.default.

xoshbin Skill

Use when building, modifying, or fixing any frontend UI in the Asyar launcher — new components, new views, layout changes, styling decisions, new built-in features, visual bug fixes, and anything in settings or onboarding. Answers "what do I use here?" for fonts, colour, typography, spacing, motion, components, and layout.

zhanlincui Bundle

[WHAT] Generate or edit images using AI via OpenRouter API (Gemini) [WHEN] User needs to create images, edit existing images, or generate visual content [TRIGGERS] generate image, create image, accompanying image, illustration, edit image