AI agents for designers
72 AI agents and agent tools that suit designers: graphic, UI, and visual work. Ranked by momentum this week, with setup difficulty for each.
Ranks for week 44 (Oct 26 to Nov 1, 2026). Data as of Nov 2, 2026.
In short
- Gaining the most momentum this week: Impeccable, Lemo-Opuscar, and design-agent.
- Easiest to start with (nothing to install, or adds to an AI app you already use): Impeccable, doop, and logo-design-skill.
- #1
Impeccable
Impeccable is a set of design commands for coding agents that steers, reviews, and polishes interfaces to avoid generic AI-looking design.
- #2
Lemo-Opuscar
Lemo-Opuscar is a Claude Code skill that makes short films entirely in code, with 66 film styles, for people who want a finished video without filming.
- #3
design-agent
Design-agent is an open-source design agent that makes on-brand stills, decks, diagrams, charts and motion graphics from a Slack thread for teams.
- #4
Blender Skills
Blender Skills is a pack of 94 instruction sets that lets Cursor, Claude Code, Kiro, or Codex build and export 3D models in Blender for game and art projects.
- #5
baoyu-design
baoyu-design is an Agent Skill that produces UI mockups, prototypes, wireframes and slide decks as HTML files inside a local coding agent, for designers and builders who want to skip a hosted design website.
- #6
skills
Skills is a collection of agent skills that reviews and improves user interfaces for designers and developers building screens and apps.
- #7
Anatomy
Anatomy is a skill that builds interactive isometric illustrations of machines and systems to explain technical ideas for anyone using Claude or Codex.
- #8
anymove
anymove is a tool that turns one AI video of a creature into a 3D animation file for games and animation software, for game developers and animators.
- #9
doop
doop is a multiplayer design canvas where people and AI agents design together live, for teams who want an open-source alternative to Paper.design.
- #10
logo-design-skill
Logo-design-skill is a skill that guides Claude and other AI agents through logo design, from brief to SVG files, for people creating brand identities.
- #11
Huashu Design
Huashu Design is a skill that turns a one-line request into finished designs like web pages, app prototypes, editable slides, animations, and infographics for people using Claude Code, Codex, or Cursor.
- #12
dsh-image-gen
dsh-image-gen is a plugin that adds image generation, editing and side-by-side comparison to the DSH agent app for people making visuals.
- #13
text-to-cad
text-to-cad is a plugin that lets an AI agent design physical products as 3D CAD models from text descriptions for makers and engineers.
- #14
skills
Skills is a set of instruction files that teach AI coding agents to create images, video, audio, and 3D assets through the Scenario MCP server for games and creative work.
- #15
CozyClay
CozyClay is an open source browser tool that plans shots in 3D and sends them to an AI video model for filmmakers and video creators.
- #16
img2threejs
img2threejs is a skill that rebuilds an object from a reference image as Three.js code for 3D web scenes, without downloading models.
- #17
AI Website Cloner Template
AI Website Cloner Template is a skill that recreates an existing website as a Next.js app for people who want a copy of a site's design and layout.
- #18
brand-identity-skill
Brand-identity-skill is a skill that designs a logo, fonts and colour palette together from one brief for small businesses and creators.
- #19
Context Attachment Manager
Context Attachment Manager is a plugin that keeps long image chats in Codex and Claude fast by loading only the images the model needs.
- #20
EAC design world
EAC design world is a local video and design plugin that edits, grades, and exports videos and slides for creators.
- #21
Agent Sprite Forge
Agent Sprite Forge is a skill that turns one approved character still into a full set of game-ready animated sprites for indie game makers.
- #22
dsh-blender-plugin
dsh-blender-plugin is a skill that lets an AI agent model, check, and export 3D scenes in Blender for DSH users.
- #23
Open Design
Open Design is a local-first, open source design workspace where teams and AI coding agents build prototypes, slides, images, and videos together.
- #24
Blender Agent Skills
Blender Agent Skills is a set of instruction packs that teach AI coding agents to do 3D modeling, rigging, and export work in Blender.
- #25
vvv
vvv is a skill that turns photos and text into an editable video template for a new film, run by a coding agent for people making wedding or memory videos.
- #26
OpenPencil
OpenPencil is a vector design tool that turns text prompts into UI on a canvas, with AI agent teams working in parallel for designers and developers.
- #27
Superhero Skills
Superhero Skills is a skill plugin that gives AI agents structured ways to run product discovery and design work for product builders.
- #28
MCP for Blender
MCP for Blender is a connector that lets AI apps like Claude control Blender 3D modeling software from a text prompt.
- #29
openreality
Openreality is an MCP server that turns phone videos into 3D scenes an AI assistant can measure, plan paths in, and export for robot training.
- #30
BeefTV
BeefTV is a desktop video creation workspace where an AI agent helps plan and generate storyboards, clips, and narration on an infinite canvas for video creators.
- #31
motion-design-skill
Motion-design-skill is a skill that teaches AI agents to choose timing, easing, and choreography for UI animations.
- #32
anidoodle
anidoodle is a skill that makes illustrations, animations and films from code for people who want the same hand-drawn look every time.
- #33
Figma-Context-MCP
Figma-Context-MCP is an MCP server that gives AI coding tools like Cursor access to Figma layout data so they can build designs accurately.
- #34
opus-video-skills
opus-video-skills is a set of Claude Code skills that make complete videos in set visual styles for people who want animated or motion-graphics video without video software.
- #35
Pinvou Agent
Pinvou Agent is a desktop AI agent workspace that turns work, design, and coding requests into finished files for people who want results, not just chat replies.
- #36
rossark-motion-skill
rossark-motion-skill is a Claude Code skill that turns SVG drawings into smooth 60 fps animations for designers and app builders.
- #37
awwwards
Awwwards is a skill that builds polished, award-style websites from a one-line brief for people who want a distinctive site without design work.
- #38
iphone-duo-skills
iphone-duo-skills is a set of skill files that teach an AI coding agent how to build iOS apps for the iPhone Duo foldable.
- #39
Aseprite AI Artist
Aseprite AI Artist is an MCP server that lets a coding agent paint and animate pixel art directly in your open Aseprite window.
- #40
Figwright
Figwright is an MCP server that lets AI coding agents read Figma designs into code and write changes back to the canvas.
- #41
Scenario for Blender
Scenario for Blender is an add-on that brings AI image, video, 3D and material generation into Blender for 3D artists and game asset makers.
- #42
IP as Logo
IP as Logo is a skill that generates simple, cute mascot characters on solid backgrounds for businesses that need a friendly brand character.
- #43
refactoring-ui-skill
Refactoring UI skill is a Claude skill that reviews web interface designs against a rulebook and generates design tokens for people building web UI with AI.
- #44
awesome-gpt-image-2
awesome-gpt-image-2 is a prompt library and agent skill that helps users write reusable prompts for GPT Image 2 image generation.
- #45
RuiC-card-skill
RuiC-card-skill is a skill that turns one sentence or a reference image into an interactive 3D holographic trading card web page for people who want custom collectible cards.
- #46
designer-skills
Designer Skills is a collection of skills and commands that teach Claude Code and Gemini CLI to help with design work from research to delivery for designers.
- #47
Skills
Skills is a collection of agent skill folders that teaches Codex, Claude, and Cursor how to build landing pages, 3D scenes, and UI prompts for designers and builders.
- #48
drawio-skill
drawio-skill is an agent skill that turns text, code, and system sources into editable draw.io architecture diagrams for technical teams.
- #49
threejs-architecture-effects
threejs-architecture-effects is a skill that makes an agent build an orbitable 3D building in Three.js that assembles itself for web designers and developers.
- #50
html-anything
html-anything is an agent app that turns notes, data, or Markdown into a ready-to-share HTML page for people who want clean web-style output without writing HTML.
-
Next AI Draw.io
Next AI Draw.io is a tool that draws and edits draw.io diagrams from chat instructions for people who need diagrams without drawing them by hand.
-
Onlook
Onlook is an open-source visual editor that lets designers build and edit Next.js websites with AI, directly in the code.
-
Pascal Editor
Pascal Editor is an open-source 3D building editor that lets people and AI agents design floorplans and buildings through MCP tools.
-
waoowaoo
waoowaoo is a self-hosted agent app that helps creators develop a brief and generate images and videos on a canvas.
-
Kami
Kami is a skill that gives AI agents layout rules and templates to export polished PDF, PNG, and editable PowerPoint documents for writers and business users.
-
stitch-skills
Stitch-skills is a library of skill add-ons that teach coding agents to turn Google Stitch designs into code, design systems, and assets for designers and developers.
-
Open CoDesign
Open CoDesign is a desktop app that turns prompts into prototypes, slide decks, and PDFs using the AI model you already pay for.
-
GPT-Image2-Skill
GPT-Image2-Skill is a prompt library and agent skill that helps you generate and edit images with OpenAI's GPT Image models.
-
design-extract
design-extract is a command-line tool that reads a website's design system and exports tokens and code for designers and developers building matching interfaces.
-
make-interfaces-feel-better
Make-interfaces-feel-better is a skill that adds small interface polish details like animations, spacing, and hover states for developers and designers building web interfaces.
-
effective-html
Effective HTML is a set of skills that helps AI agents create self-contained HTML wireframes, prototypes, plans, and diagrams for designers and developers.
-
mono-color-skill
Monocolor Editorial Print is a skill that turns a theme, sentence, or photo into a one-ink or two-ink editorial print image for posters, zines, and packaging.
-
UX/UI Agent Skills
UX/UI Agent Skills is a skill that helps coding agents design interfaces to a professional standard and checks the result with 52 gates for developers.
-
Oil Motion
Oil Motion is a skill that builds scroll and mouse-driven web animations for people making web pages with an AI agent.
-
TypeUI
TypeUI is a set of design skills and UI prompts that helps AI coding tools build better user interfaces for websites and apps.
-
photoshop-mcp
photoshop-mcp is an MCP server that lets Cursor, Claude, or a built-in chat window control Adobe Photoshop from plain-language requests.
-
genjutsu
genjutsu is a set of skills for Claude Code that adds motion, micro-interactions and design systems to web, Android and iOS interfaces for developers and designers building apps.
-
Awwwards-mcp
Awwwards-mcp is an MCP server that lets AI coding agents search award-winning websites for design inspiration and rebuild their layouts for people building websites.
-
Motion2Code
Motion2Code is a skill that teaches coding agents to rebuild a motion design video as editable SVG and GSAP code for designers and developers.
-
BeatDesign
BeatDesign is a local-first canvas and video editor that lets AI image and video tools and MCP agents build media projects for creators.
-
skills
skills is a collection of agent skills that shoot cinematic UI videos and framed app screenshots for marketing and docs.
-
design.how
design.how is a set of agent skills that turns an app's existing UI into a design system and keeps new screens consistent with it.