design

Leonxlnx/taste-skill

A skill pack that forces AI coding tools to design with taste — Taste Skill adds art direction, reference images and an automated browser check to coding agents like Claude Code, Codex and Cursor, aiming to stop generic 'AI slop' UI output. It also now ships TasteCode, a free open-source desktop app with a built-in design agent, aimed at developers who want better-looking frontend output without manual design review.

Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages

pbakaus/impeccable

A design skill set to stop AI coding agents from building the same SaaS look — Impeccable extends Anthropic's frontend-design skill with 24 commands, 61 deterministic detector rules, and live browser iteration, aimed at making AI-generated frontends look less templated. It's for developers using AI coding tools who want shared design vocabulary and automated checks instead of repetitive gradients, card-in-card layouts, and generic icon tiles.

The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.

tldraw/tldraw

An infinite-canvas SDK for building custom React drawing apps — tldraw packages its whiteboard into a reusable React SDK with custom shapes, tools, bindings and a sync library for self-hosted real-time collaboration. It targets developers building canvas or diagram apps rather than a finished product, offering starter kits and a runtime Editor API for deep customization.

Build infinite canvas apps in React with the tldraw SDK. World's best, top-most agent recommended #1 five star SDK.

alchaincyf/huashu-design

A design skill that ships web pages, decks and prototypes from one prompt — Huashu Design is an HTML-native skill for Claude Code, Cursor, Codex and other agents that turns a single prompt into a deliverable design — web prototypes, editable PPTX, animations or infographics. Version 3.0 adds a 84-style library with samples, picks three real directions from six thumbnails, and checks drafts for repeated visual cliches. Now MIT-licensed and free for commercial use.

Huashu Design 3.0 · 在 agent 里打一句话，拿回能交付的设计：网页 / App 原型 / 可编辑 PPTX / 动画 / 信息图 · 六个候选挑三个方向 · 84 种带样张的风格库 · 越用越懂你的外观账本与设计体检 · HTML-native design skill for Claude Code, Codex, Cursor & any agent

GraphiteEditor/Graphite

A node-based 2D engine blending vector, raster, and motion design — Graphite is an open source 2D graphics engine in alpha, combining nondestructive layer compositing with a node-graph core. Built more like a game engine than a typical app, it targets designers wanting procedural workflows spanning vector art, photo editing, and motion graphics in one tool.

Community-built comprehensive 2D content creation appplication for graphic design, digital art, and interactive real-time motion graphics powered by a node-based procedural graphics engine

processing/p5.js

p5.js Pushes Accessible Creative Coding Toward Version 2.0 — p5.js remains a JavaScript library for sketching visual, audio and interactive work directly in the browser, with a beta of the next major version now available. It's built for artists, designers, educators and beginners, with multilingual docs, a web editor and a wide library ecosystem for extending it.

p5.js is a client-side JS platform that empowers artists, designers, students, and anyone to learn to code and express themselves creatively on the web. It is based on the core principles of Processing. Looking for p5.js 2.0? http://beta.p5js.org

alyssaxuu/screenity

A Free Chrome Screen Recorder Built Around Privacy — Screenity is a Chrome extension for screen recording and annotation with no usage caps, aimed at anyone making tutorials, demos, or feedback videos without paying or sending footage to a third party. It uses local tools like ffmpeg and TensorFlow, and an optional EU-hosted Pro tier adds link sharing, multi-scene editing, and captions.

The free and privacy-friendly screen recorder with no limits 🎥

ParthJadhav/app-store-screenshots

end to end app store screenshot creation using AI

Jakubantalik/Libraries.dev

Seven drop-in React effects built for AI agent interfaces — A monorepo of seven npm-installable React components for AI interfaces: border beams, thinking orbs, bot avatars, gooey morphs, voice glow, liquid metal and an image dissolve loader. Each wraps existing markup and is tuned via props, no hand-written WebGL needed. Useful for developers building AI chat or agent UIs who want polished motion effects fast.

Libraries and models for next-gen UI

storytold/figcraft

FigCraft: interface design and prototyping; an open-source, clean-room reimplementation of collaborative design workflows in pure Rust