Agent Academy

Agent Academy is a free, source-linked library of skills, prompts, MCP servers and bot templates, organised into courses by profession, for people who hand real work to AI agents: 1,467 live resources, each with its original link, license and safety tags.

Case

Multimodal Design Agent Team

A Streamlit application that provides comprehensive design analysis using a team of specialized AI agents powered by Google's Gemini model.

No credentialsDoes not send
Open the original

https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/advanced_ai_agents/multi_agent_apps/agent_teams/multimodal_design_agent_team

Original content

Full originalApache-2.0Source

Republished in full under its license, with attribution. The source is authoritative.

Multimodal AI Design Agent Team

🎓 FREE Step-by-Step Tutorial

👉 Click here to follow our complete step-by-step tutorial and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.

A Streamlit application that provides comprehensive design analysis using a team of specialized AI agents powered by Google's Gemini model.

This application leverages multiple specialized AI agents to provide comprehensive analysis of UI/UX designs of your product and your competitors, combining visual understanding, user experience evaluation, and market research insights.

Features

  • Specialized Design AI Agent Team
  • 🎨 Visual Design Agent: Evaluates design elements, patterns, color schemes, typography, and visual hierarchy
  • 🔄 UX Analysis Agent: Assesses user flows, interaction patterns, usability, and accessibility
  • 📊 Market Analysis Agent: Provides market insights, competitor analysis, and positioning recommendations
  • Multiple Analysis Types: Choose from Visual Design, UX, and Market Analysis
  • Comparative Analysis: Upload competitor designs for comparative insights
  • Customizable Focus Areas: Select specific aspects for detailed analysis
  • Context-Aware: Provide additional context for more relevant insights
  • Real-time Processing: Get instant analysis with progress indicators
  • Structured Output: Receive well-organized, actionable insights

How to Run

  1. Setup Environment

```bash

# Clone the repository

git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git

cd advanced_ai_agents/multi_agent_apps/agent_teams/multimodal_design_agent_team

# Create and activate virtual environment (optional)

python -m venv venv

source venv/bin/activate # On Windows: venv\Scripts\activate

# Install dependencies

pip install -r requirements.txt

```

  1. Get API Key
  1. Run the Application

```bash

streamlit run design_agent_team.py

```

  1. Use the Application
  • Enter your Gemini API key in the sidebar
  • Upload design files (supported formats: JPG, JPEG, PNG)
  • Select analysis types and focus areas
  • Add context if needed
  • Click "Run Analysis" to get insights

Technical Stack

  • Frontend: Streamlit
  • AI Model: Google Gemini 2.0
  • Image Processing: Pillow
  • Market Research: DuckDuckGo Search API
  • Framework: Phidata for agent orchestration

Tips for Best Results

  • Upload clear, high-resolution images
  • Include multiple views/screens for better context
  • Add competitor designs for comparative analysis
  • Provide specific context about your target audience

Related

Design systemDesign

Apple Human Interface Guidelines

Apple's platform design guidance: foundations, patterns, components, inputs, technologies.

Sourcedeveloper.apple.com/design/human-interface-guidelines

No credentialsDoes not sendApple terms; link only
Style libraryDesign

UI Hub (Incidental AI UI resource hub) — llms.txt / api

Curated multilingual directory of ~2,391 public UI resources with visual-style (vs) facets, design KB (specs, skills), JSON endpoints and a recommended design-skill workflow.

Sourcesiinxu.github.io/ui-resource-hub/llms.txt

No credentialsDoes not sendaggregator; per-item license
WorkflowDesign

UI Hub skills.json (recommended design workflow)

Workflow: pick ONE direction skill (frontend-design or taste-skill) → search resources by style/kind → build with emil-design-eng → audit with impeccable + web-design-guidelines + accessibility → verify in browser light+dark, mobile.

Sourcesiinxu.github.io/ui-resource-hub/api/skills.json

No credentialsDoes not sendaggregator
SkillDesign

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Sourcegithub.com/anthropics/skills/blob/main/skills/algorithmic-art/SKILL.md

No credentialsDoes not sendApache-2.0
SkillDesign

canvas-design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Sourcegithub.com/anthropics/skills/blob/main/skills/canvas-design/SKILL.md

No credentialsDoes not sendApache-2.0
SkillDesign

banner-design

Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon,…

Sourcegithub.com/nextlevelbuilder/ui-ux-pro-max-skill/blob/main/.claude/skills/banner-design/SKILL.md

No credentialsDoes not sendMIT