agents-design-visual-identity

Generate square icons, avatars, and logos for AI agents using the Google AI Studio image generation API.

Updated Jan 28, 2026
One-click install
npx skills add https://github.com/scanady/nexus-skills --skill agents-design-visual-identity-scanady
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agents-design-visual-identity
Source: https://github.com/scanady/nexus-skills/tree/main/skills/agents-design-visual-identity
Command: npx skills add https://github.com/scanady/nexus-skills --skill agents-design-visual-identity-scanady

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Creating consistent, production-ready visual identity assets for AI agents and apps requires design expertise and tooling that most developers lack, resulting in generic or off-brand icons and avatars. ## Core Features & Use Cases - Guided Concept Design: Defines the visual metaphor, color palette, and composition for the agent's identity before any image is generated, with user approval built in. - API-Driven Generation: Produces 1:1 aspect ratio icons, avatars, and logos via the Google AI Studio Nano Banana (Gemini) image generation model using structured prompt templates. - Multi-Size Delivery: Generates at the largest target size and downscales to platform-ready variants (512px down to 32px favicons) with a consistent file naming convention. - Use Case: You are shipping a new code review bot and need a GitHub profile avatar plus a favicon. The skill designs a magnifying-glass-over-bracket concept, generates it at 512×512, and delivers all required sizes. ## Quick Start Ask the agent to create an icon for your AI agent, describing its name, function, and preferred style and colors.

Frequently Asked Questions about agents-design-visual-identity

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate an icon for an AI agent?▼

Define the agent's identity, choose a style direction and 2-3 colors, then approve the visual concept. The skill builds a structured prompt and calls the Google AI Studio Gemini image generation API to produce a square PNG at 512×512 and smaller sizes.

What image model does this skill use for generation?▼

It uses the Google AI Studio Nano Banana model, identified as gemini-2.0-flash-exp, via the generativelanguage.googleapis.com endpoint. No other image generation models are supported by this skill.

Do I need an API key to generate avatars with Google AI Studio?▼

Yes, a Google AI Studio API key is required. Set it as the GOOGLE_AI_STUDIO_API_KEY environment variable or provide it when prompted; keys are never hardcoded in prompts or files.

What sizes are produced for icons, avatars, and logos?▼

Icons and avatars are generated at 512×512 and downscaled to 256, 128, 64, and 32 pixels. Logos are generated at 1024×1024 and downscaled to 512, 256, and 128 pixels, saved as separate PNG files.

Why does image generation return text instead of an image?▼

The model sometimes returns a text-only response without an inlineData part. Retry with a more explicit prompt that begins with "Generate an image:" and confirms the responseModalities include IMAGE.

When should I not use this skill for agent design?▼

Do not use it to define an agent's persona, backstory, or behavioral guidelines, or when you need non-square artwork. It only produces 1:1 aspect ratio visual assets through Google AI Studio.