image-gen

Generate AI images from text prompts via OpenAI and Google AI SDK providers.

Updated May 19, 2026

Search Tags:#image generation #openai #reference images #google gemini #aspect ratio #prompt-to-image #quality presets

Ready to run

npx skills add https://github.com/sarkcesscrewpay/trading-intelligence-system --skill image-gen-sarkcesscrewpay

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: image-gen
Source: https://github.com/sarkcesscrewpay/trading-intelligence-system/tree/main/skills/image-gen
Command: npx skills add https://github.com/sarkcesscrewpay/trading-intelligence-system --skill image-gen-sarkcesscrewpay

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps you turn text ideas into finished images without manual design work, while letting you control style, aspect ratio, quality, and (optionally) reference-based edits.

Core Features & Use Cases

Prompt-to-image generation: Create new images from prompt text, including optional prompt files for more detailed scenes.
Provider + model flexibility: Uses AI SDK-backed OpenAI and Google APIs with auto-selection (or forcing a provider) and configurable model IDs.
Deterministic command execution via scripts: Run a single CLI entry point to generate single or multiple images with output as PNG paths or JSON.

Quick Start

Run the Skill’s CLI to generate an image from a prompt by creating an output file like cat.png using the scripts/main.ts entry point in this skill.

Frequently Asked Questions about image-gen

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

FAQPage Schema

How do I generate images from text prompts using OpenAI or Google Gemini?▼

You can generate images from text prompts by executing the local scripts/main.ts entry point, which uses AI SDK-backed OpenAI and Google Gemini APIs to output PNG files or JSON responses.

Can I use reference images for multimodal edits when generating AI images?▼

Yes, the image generation process supports optional reference-based edits for multimodal use cases, allowing you to modify existing images alongside text prompts.

How do I control aspect ratio and quality when generating prompt-to-image outputs?▼

You can control aspect ratio, explicit image size, and quality presets by configuring the parameters within your prompt files before running the CLI execution script.

Do I need API keys to use OpenAI and Google AI providers for image generation?▼

Yes, API-key-based provider selection is required, allowing you to auto-select between OpenAI and Google AI SDK providers or force a specific provider with configurable model IDs.

What is the best way to batch create images from detailed prompt files?▼

Batch creation of AI images is handled through promptfiles-driven execution, processing multiple text prompts via a single deterministic CLI entry point to generate several visual assets.

Does this image generation approach output PNG files or JSON data?▼

The script execution supports both output paths for saving PNG image files and JSON formatting, returning structured data when generating single or multiple visual assets.