image-gen

Generate on-brand images via the Gemini API using brand visual identity files.

31|5|Updated Mar 12, 2026

Search Tags:#prompt engineering #image generation #brand identity #gemini api #marketing visuals #blog header #social graphic

Ready to run

npx skills add https://github.com/MoizIbnYousaf/marketing-cli --skill image-gen-moizibnyousaf

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: image-gen
Source: https://github.com/MoizIbnYousaf/marketing-cli/tree/main/skills/image-gen
Command: npx skills add https://github.com/MoizIbnYousaf/marketing-cli --skill image-gen-moizibnyousaf

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, Pillow, and includes references (resource) components.

What problem does it solve? Marketing teams need visuals for blog headers, social posts, and product shots, but generic AI image prompts produce off-brand results that ignore the company's defined visual identity. ## Core Features & Use Cases - Brand-Aware Prompt Crafting: Reads brand/creative-kit.md, voice-profile.md, and positioning.md to weave colors, lighting, mood, and composition constraints into narrative prompts. - Gemini API Generation: Generates images via gemini-3.1-flash-image-preview or gemini-3-pro-image-preview with aspect ratio and resolution control, plus multi-turn iterative refinement. - Use Case: A user asks for a 16:9 blog header; the skill applies the brand's Visual Brand Style, generates the image at 2K resolution, saves it as PNG, and logs it to brand/assets.md. ## Quick Start Ask the agent to generate a 16:9 blog header image for your latest article using your brand style.

Frequently Asked Questions about image-gen

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

FAQPage Schema

How do I generate on-brand images with the Gemini API?▼

Set the GEMINI_API_KEY environment variable, then request an image with its purpose such as blog header or social graphic. The skill reads brand/creative-kit.md for visual style, crafts a narrative prompt, and calls the Gemini image model with the correct aspect ratio.

What aspect ratios and resolutions does Gemini image generation support?▼

The skill maps use cases to defaults: 16:9 for blog headers, 1:1 for social squares, 9:16 for stories, 21:9 for heroes, and 4:3 for product shots. Resolutions range from 1K to 4K depending on the use case.

Can I edit an existing image with Gemini instead of generating a new one?▼

Yes, pass the existing image with an edit instruction to the Gemini API. It supports style transfer, background replacement, object removal, color grading, and text overlay while preserving the original structure.

Why does image generation fail with an API key error?▼

Generation requires the GEMINI_API_KEY environment variable to be set before activation. If it is missing, the skill stops and directs you to ai.google.dev to obtain a key.

What happens if no brand style files exist yet?▼

The skill still works at a lower enhancement level using discovery questions and prompt craft alone. Running the visual-style skill first to define a Visual Brand Style section produces fully on-brand results.