How do I install the Image Gen skill?

Run npx skillmds@latest add scaryrawr/image-gen in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Image Gen safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Image Gen?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Image Gen free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Image Gen?

scaryrawr (@scaryrawr) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Image Gen by scaryrawr — Agent Skill

Name: Image Gen
Author: scaryrawr

Image Gen

Use this skill to create, generate, draw, or edit images/photos into saved PNG files with OMLX image models. Covers text-to-image and image-to-image edits. Do not use for text-only image explanations, screenshot summaries, or non-generative image processing scripts.

scaryrawr ffe1d9c 10 files · 32.2 KB Updated Sep 17, 2026

File contents

OMLX Image Generation and Editing

Workflow

Use this skill only for image creation or generative image editing. Use ordinary tools for analysis, screenshot summaries, resizing, conversion, or other non-generative processing.
Turn the request into a finished visual prompt. For edits, state what must change and explicitly preserve important subject details such as pose, clothing, crop, camera angle, text, and privacy blur.
Call omlx_image once with an absolute path for a new output file. Omit sources for text-to-image generation; include absolute read-only source paths for image-to-image generation. Sources are never modified. Pass an absolute mask path only for selective edits. Let the tool select a loaded capable model unless the user named one.
Inspect the saved result. Retry only when it needs a deliberate change; adjust the prompt, strength, or advanced steps and guidance instead of repeating an identical call accidentally.
Report the saved path and selected model.

If omlx_image is unavailable because this skill was installed without the plugin, use the bundled Python helper documented in references/generation.md or references/editing.md. Do not load those references during the native-tool path.

Frequently asked questions