Image, video & design

Design & UI agents

465 agents · most starred first

Design & UI agents, page 2 of 5

codex-openpencil★ 153

Codex plugin for OpenPencil — an interactive Rust/WASM canvas for AI-assisted UI design. Create editable .op files from prompts, refine selected elements, generate image assets, and install with one prompt on macOS, Windows, and Linux.

Flovart★ 146

Open-source agent-native visual production workspace where humans and coding agents edit the same live canvas — local-first, BYOK image/video models.

loora★ 144

A canvas design tool your agent can edit. Arrange structured UI nodes on the canvas; connect Claude, Codex, Cursor, or opencode over MCP

oa-design★ 135

The Open Analytics design language as an agent skill: component recipes with type-checked source, token CSS, and a CLI. Works with Claude Code, Cursor, or any agent.

photo-abstract-editorial★ 132

Turn photos into source-faithful editorial artworks with an Agent Skill — adaptive layouts, controlled abstraction, and a Strict Fidelity composition path.

AutoIllustrate★ 132

Generate publication-ready, editable draw.io figures for research papers from a methods section, using LLM agents.

OpenDesign★ 130

Open-source Canva alternative — design editor for social media graphics. Fabric.js + Preact + Hono + SQLite. Part of the OpenClaw ecosystem.

dsh-design-studio★ 123

DSH 设计工作台:模型画的界面摆上画布,点一下就改,还有设计市场。 · Design canvas for DeepSeek Harness (DSH): web, app, mini program and desktop screens in device frames, click or draw to edit, a design market of templates, export and code handoff (React / Vue / uni-app).

b-end-design-system-skill★ 118

B端设计系统与组件规范 AI 执行级 Skill (UI/UX Design System Skill for AI Agents, Cursor, Claude Code & Windsurf)

brand-design-md★ 117

A Claude Code Skill that gives your AI agent the design language of 62 world-class brands — on demand.

gridgeist★ 116

Gridgeist turns product intent into a rigorous visual system—without the generic AI SaaS aftertaste.

bruce-drawio★ 115

跨平台的 draw.io (diagrams.net) 图表生成技能,适用于 Claude Code、codex、zcode、workbuddy、OpenClaw 等各类 AI 编程 Agent。Agent 直接生成 drawio XML,校验后通过 CLI 导出图片;没有桌面版时自动降级为 draw.io 官网打开链接。

PaperBanana-Pro★ 114

Production-ready multi-agent academic illustration system with Chinese GUI, background generation, plot workbench, and portable result bundles. Extended from PaperBanana.

spotkit★ 110

Spotkit — a Claude Code skill that turns a feature description into minimal, abstract SVG product illustrations that all belong to one design system.

Quilt★ 106

AI-native infinite-canvas design tool: describe an app, get multi-screen HTML designs on an infinite canvas, click through them as a prototype, and let your local coding agent read and write the canvas over MCP.

ui-ux-design-pro-skill★ 105

AI spairings, 150+ reasoning rules, CLI, and 18 platform templates. Works with Claude, Cursor, Windsurf, Copilot, Antigravity, Cline & more.kill for premium UI/UX design — 107 styles, 127 palettes, 107 font

PostEx★ 102

Evidence-linked Palette Fusion for distinctive, editable, and print-ready academic posters.

design-skills★ 100

Opinionated UI constraints extracted from the best design systems. Use with AI agents to build pixel-accurate interfaces.

skills★ 100

Agent skill to extract color palettes from images — screenshots, Figma exports, design mockups. Installable via npx skills add pascalorg/image-analysis

brand-design-skill★ 100

Brand Design Skill 是一个 image-first 的 Codex 品牌设计 Skill。它通过对话式流程引导 Agent 完成苏格拉底式需求澄清、Logo 图像探索、最终图像 Logo 资产、行业化 VI 应用场景,以及高质量 HTML 品牌手册。|

markdy-com★ 100

🎬 Open-source animated architecture diagrams as code. Diagram-native DSL, 17 layout engines, Web Animations API, and MCP server for AI agents.

logo-designer-skill★ 99

An agent skill for creating and refining SVG logos through guided exploration and iteration.

awesome-design-md-cn★ 98

Stitch 提出的设计系统文档格式 —— 用纯文本 Markdown 记录设计系统,让 AI 编码 Agent 能够生成风格一致的 UI。

shader-for-interfaces★ 98

Agent Skill for designing, building, debugging, and validating focused GPU effects in product interfaces.

desktop-agent-ui★ 98

现代桌面 Agent / AI 应用的设计规范、交互物理学与深度工程实践指南

refactoring-ui-skill★ 97

Agent skill for professional UI design based on Refactoring UI principles. Covers hierarchy, typography, color, spacing, dark mode, forms, accessibility, and animation.

lieflat-html-design★ 96

Agent-ready HTML design skill collection for decks and Xiaohongshu cards

design-bites★ 96

Curated DESIGN.md files for inspiring websites — design systems decoded for AI agents. By Sparkbites.

store-screenshots★ 96

🖼️ AI agent skill for Claude Code & Codex — turns raw app screenshots into store-ready App Store & Google Play marketing images: device frames (iPhone·iPad·Galaxy·Fold·Flip), app-matched backgrounds, marketing copy, exact store sizes. 앱스토어·플레이스토어 마케팅 스크린샷 자동 생성

opencalque★ 96

Open-source 2D architectural editor with a Figma-like interface, a local CLI, and practical workflows for humans and AI agents.

picture-it★ 95

Photoshop for agents

stop-describing-ui★ 95

An agent skill that strips explanatory copy out of user interfaces.

slab★ 94

A design language for agents

super-prototyping★ 94

A product-validation system for AI agents: idea → logo → product → brand → launch video in two hours. Desktop app + skills for Claude Code and Codex.

figmosha2★ 93

Let Claude edit your Figma file for you — bulk-rename layers, swap variants, bind colour variables, pour in real copy. Describe the change in plain words, watch it land in the file in seconds. A small plugin keeps Figma talking to your terminal.

mira-animator★ 92

Agentes e templates para criação de slides animados com D3.js em HTML

npface★ 92

会表情的 AI头像 — expressive, zero-dependency helmet avatar for AI agents (MIT)

dot-matrix-animations★ 91

28 hand-designed 5x5 dot-matrix loader animations as standalone animated SVGs and a React component. ~4KB each, no JS runtime, agent-themed patterns.

open-screenshot-generator★ 91

Open source Canva for App Store and Play Store screenshots. Free alternative to AppScreens, AppLaunchpad and Previewed. Device mockups, 3D poses, preview videos and an AI agent that designs your listing for you. 100% client side, no account, nothing leaves your machine

archlang★ 89

【Every star you give feeds a hungry developer's motivation! ⭐️】Floor plans as code. Your AI writes ArchLang; the compiler draws a precise, dimensioned plan (SVG, DXF, PDF) and tells it what's wrong. Open source, MIT.

sci-box★ 88

sci-box 提供一组可直接调用的科研绘图复刻模板,帮助 Agent 快速生成高质量图表。sci-box provides a set of directly callable scientific drawing replication templates to help Agents quickly generate high-quality charts.

brand-system-skill★ 88

An open-source, agent-guided creative-direction workflow for turning one visual reference into a connected brand system with Lovart Agent.

chinese-font-selector★ 84

全网首个中文字体专业知识包:可商用中文字体库(授权三级分类)、场景×气质选字矩阵、中英混排与排版规则。让 AI 选中文设计字体不再甩给你一堆 Inter / Chinese font selection agent skill: license-safe free commercial CJK fonts, scene-based selection matrix, CJK-Latin pairing rules. Works with Claude Code / Cursor / Kimi / Codex.

wobnimo★ 83

Give your app a face. Ten living 3D mascots on one ~25 KB web animation engine. React, web component, agent-ready.

layr★ 79

A modular UX, design, and product optimisation system for turning AI-built interfaces into production-grade apps, turning proven principles into enforceable constraints that reduce friction, build trust, and drive action. Works with Claude, Codex, Cursor + all other agentic AI models.

design-jarvis★ 78

An AI-native design team for VS Code — one orchestrator routes your requests to specialist agents (UX, UI, research, content) that collaborate autonomously. Design Lead reviews every output and drives next steps until the project is complete. Memory persists decisions across sessions. Just talk to @Design Jarvis and it handles the rest.

asc-screenshots★ 78

AI agent skill that generates production-ready App Store screenshots for iPhone and iPad. Exports in asc-client compatible format.

Design-Jarvis★ 78

An AI-native design team for VS Code — one orchestrator routes your requests to specialist agents (UX, UI, research, content) that collaborate autonomously. Design Lead reviews every output and drives next steps until the project is complete. Memory persists decisions across sessions. Just talk to @Design Jarvis and it handles the rest.

get-web-design★ 77

将任意线上网站的设计风格提取为一份结构化 `DESIGN.md`。本 skill 是 design-extractor Chrome 扩展的命令行 / AI Agent 移植版。

designmd★ 77

Production-grade design context for AI coding workflows. Extract a real design system from any URL — colors, typography, spacing, breakpoints — as a portable DESIGN.md.

kami★ 75

tiny AI copilot for origami studio

iso-topology★ 73

Isometric architecture diagrams as code — text DSL in, design-grade 2.5D SVG out. Agent-first: LLMs can discover, generate, and validate the DSL.

code-transformer-for-Figma★ 71

Figma plugin to generate code using OpenAI API

comic-ip-onboarder-skill★ 70

把照片、头像、玩偶或吉祥物转成可复用漫画 IP 档案的 AI Agent Skill

OpenDiagram★ 70

AI diagram generator for software architecture - the open-source Eraser.io alternative. Describe your system in plain English, get editable system design, sequence, ERD & cloud diagrams on an Excalidraw canvas. Self-hostable, bring your own key. Vibe diagramming for engineers.

SCALES-Design-Tokens-Starter-Set★ 67

Design tokens starter set for your design system

agent-robot-avatar★ 67

A lightweight, expressive robot avatar Web Component for AI agents and interactive applications.

feishu-whiteboard-pro★ 66

A Claude Code / agent skill for building genuinely designed, editable Feishu / Lark (飞书) whiteboards — deliberate composition, real hierarchy, a gated pipeline with pre-render fit-check and independent design critique.

rhp★ 65

rhp (reactive html plots): charts built from HTML elements and CSS with SolidJS, with a skill and MCP server for AI agents

omit-design★ 63

Let AI agents design with you.

anyviz★ 62

面向 AI 时代的数据可视化规范与工作流库 — specification & workflow library for AI-era data visualization

chatgpt-figma-plugin★ 60

Experimental Chat GPT plugin for Figma

MuseUI★ 60

MuseUI is a browser-only AI interface and image design generator. It helps you create UI mockups, social images, covers, infographics, stickers, logos, and other visual drafts from prompts and reference images.

zuoge★ 57

zuoge — open-source AI design workspace with a document-derived SoA infinite artboard and Design Agent

designpull★ 55

Generate Google Stitch compatible DESIGN.md files from any website using AI vision. Bring your own Gemini, OpenAI, Claude, or Ollama key. No backend, no cost.

getdesign★ 55

On-demand design systems from any URL. Five surfaces, one agent: web, API, CLI, TypeScript SDK, and a portable agent skill that runs inside Claude Code, Codex, and Cursor.

ux-wise-agent★ 52

AI skill pack for senior UX and Product Designers. Runs on Claude Projects or any LLM. Strategic, Direct, and Provocative reasoning modes. Copy, paste, done.

iso-topology★ 50

Isometric architecture diagrams as code — text DSL in, design-grade 2.5D SVG out. Agent-first: LLMs can discover, generate, and validate the DSL.

design-skill-os★ 50

The elite design intelligence layer for AI agents, synthesized from 10+ legendary design books. It primes your AI with the collective strategic wisdom of master designers to generate high-intent UI/UX with zero "schtick."

yuzudraw★ 50

visual ASCII editor for both humans and agents

c-shop★ 50

Graphic editor supporting agentic workflows with deep learning modules.

thinking-logos★ 50

Your logo, as your agent's loading animation. Bake any SVG into a dot cloud and play it as seven AI loading states.

eve-design-template★ 50

An eve agent to act as your design collaborator

web-design-studio★ 50

Three free agent skills for websites people remember: cinematic-scroll builds distinctive scroll, 3D and motion sites; scroll-audit scores any page; launch-page-strategy decides what the page must say. 28 live examples. Formerly Cinematic Scroll.

diagram-design-zh★ 50

agent 零指令产出中文图表的技能——单文件 HTML、断网可开、CJK 排版全内置

style-pack-skill★ 49

从参考图提取视觉风格 DNA,强制生成标注与纯色双版色卡的 AI Agent Skill

design-skills★ 49

AI agent skills for the designer's craft — brand audit, strategy, creative direction, logo, and application across web, collateral, and motion.

poster-style-transfer★ 49

An open Agent Skill for extracting poster design systems and transferring them to original poster concepts.

grok-ball★ 49

会看你的 AI 表情球:25 组眼环、32 种情绪、3D 彩带,纯 SVG、零依赖,支持 JavaScript / TypeScript 与 Agent 状态接入。

deskstudio★ 48

Your own design studio inside the coding agent you already use.

architecture-drawer★ 47

Skill for Claude Code & Codex: describe your system architecture in text → get an editable PowerPoint diagram (native shapes, not a flat image).

drawcms★ 47

The animated diagram editor AI agents can draw on. Animated technical diagrams (architecture, sequence, BPMN, cloud icons) built by you and your agent together on the same live canvas, via WebMCP. Open-source, local-first.

ui★ 47

Halaska UI: a single-file React UI kit for AI products, built on shadcn/ui. 40 AI UX patterns and 90 components for agents, chat and generative UI.

benday★ 46

Turn your logo into an animated thinking indicator for agent UIs and more.

DeepUIDesigner★ 46

An AI agent UI designer based on QT designer and DeepCode cli, refined to UI elements. Inheriting the concise pages of QT designers and the specialized optimization for Deepseek in DeepCode cli. Greatly reducing token costs, simplifying the work required of front-end designers, and making the entire front-end process controllable, and efficient.

codesign★ 46

CoDesign gives AI agents like Claude Code, Codex and PI a real design engine for genuine, editable designs, not flat images. Bring in what you have: InDesign, Photoshop, PowerPoint and PDF files stay editable. Exports print PDFs (CMYK, bleed) and videos. Every design opens in a built-in editor for manual fixes. Runs on your machine, no account.

AUI★ 45

Computer-Use Agents as Judges for Generative UI

perceptual-protocols★ 45

A family of small protocols for the perceptual side of designer-agent collaboration.

agentic-visualization★ 44

CoDA is a multi-agent framework that turns natural language queries into publication-quality visualizations.

humane-agentic-design★ 44

Humane Agentic Design — a human-centric design method cycle for people and agents

open-claude-design★ 43

Claude Design access and UI workflows for coding agents, part of QualityLayer. Create and review designs in QualityLayer without a Claude subscription, or use the standalone Claude Design connection.

Nodesign★ 40

与 Agent 共用一块画布:以画布为中心的 Agent 工作台。网站、演示稿、Word 文档、图像与视频集中在同一块画布上,用户指定、整理与修改,Agent 制作、检查与说明。支持 Windows 桌面版与自有密钥(BYOK)。

mobbin-skill★ 40

AI skill for structured UI/UX research using Mobbin MCP. Works with Claude Code, Cursor, Gemini CLI, Lovable, and any MCP-compatible agent.

recombyn★ 39

Open-source infinite vector canvas and AI Design Agent — shape, text, media, and path editing with realtime collaboration; self-host with Docker Compose.

CartoAgent★ 38

The official repository for "CartoAgent: a multimodal large language model-powered multi-agent cartographic framework for map style transfer and evaluation".

eda-copilot★ 37

嘉立创EDA & EasyEDA 多模态大模型 AI 助手

DesignCode★ 36

Agent 驱动的专业级平面设计工作台 / Agent-powered graphic design workbench that uses HTML/CSS/SVG as the design medium, supporting vector-quality output, editable elements, multi-layer PSD export, lossless text rendering, and other production-grade features.

SmartHopper★ 35

SmartHopper is an open-source project that implements third-party AI APIs to provide advanced features for Grasshopper3D.

design-agent-skills★ 35

Design Skills for Agents

Store-Screenshot-Studio★ 35

Agent skill + Claude Code plugin: bold, art-directed App Store and Google Play screenshots from your own app screens, in every store size.

More in Image, video & design