image-gen

Automate image generation and editing via OpenRouter with vision-enabled models.

15|1|Updated Feb 17, 2026

Search Tags:#openrouter #image-generation #presets #prompt-engineering #style-references #gpt-5-image

Ready to run

npx skills add https://github.com/buildoak/fieldwork-skills --skill image-gen-buildoak

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Image generation and editing workflows are complex and error-prone; this skill encapsulates end-to-end runbooks for consistent results via OpenRouter, GPT-5 Image, or NanoBanana, with presets, references, and on-demand scripts.

Core Features & Use Cases

Supports text-to-image and image editing with multiple models and style references.
Includes a preset system to ensure visual consistency across a series of images.
Provides an integrated quick-start and references for installation and troubleshooting.

Quick Start

Instruct the agent to generate an image using a chosen model and prompt, optionally supplying a style reference to anchor visuals.

Frequently Asked Questions about image-gen

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

FAQPage Schema

How do I automate image generation with consistent styles across multiple prompts?▼

Automate image generation with consistent styles by using a preset system that anchors visual outputs. This skill applies preset-based styling and style references to OpenRouter models, ensuring repeatable visual consistency across varied prompts and creative illustrations.

Can I use style references for image editing in a zero-dependency CLI workflow?▼

Style references work with image editing in a zero-dependency CLI workflow by leveraging vision-enabled models through OpenRouter. This skill supports text-to-image and image editing, anchoring visuals with supplied references for rapid concept exploration and branding.

What's the best way to handle errors and estimate costs for OpenRouter image generation?▼

Handle errors and estimate costs for OpenRouter image generation using robust error handling and deterministic cost estimates. This skill encapsulates end-to-end runbooks that provide reliable outputs with deterministic naming and integrated troubleshooting references.

Does this image generation approach support GPT-5 Image and NanoBanana models?▼

This image generation approach supports GPT-5 Image and NanoBanana models via OpenRouter. It applies vision-enabled models for text-to-image generation and editing, applying prompt enhancements and quality review for consistent results.

Why do my image generation prompts produce inconsistent outputs across a series?▼

Inconsistent image generation outputs occur when prompts lack preset-based styling and structured prompt engineering. This skill provides a preset system and prompt enhancements to ensure visual consistency, robust error handling, and repeatable results across varied prompts.