Skills for Real Engineers. Straight from my .agents directory.
oma-image
Agent skill fromfirst-fluke/oh-my-agent
Generate raster images or reference-guided variations through the
How to install oma-image
npx skills add first-fluke/oh-my-agent# or add only this skill to Claude Code: copy the folder
skills/oma-image/
# into
~/.claude/skills/oma-image/ (all projects)
.claude/skills/oma-image/ (one project)
1# Image Agent - Multi-Vendor Image Router23## Scheduling45### Goal6Generate images and visual assets through authenticated multi-vendor routing while preserving prompt clarity, reference-guided regeneration, cost controls, and reproducible output manifests.78### Intent signature9- User asks to generate images, visual assets, illustrations, product photos, concept art, mockups, or AI art.10- Another skill needs shared image-generation infrastructure.11- User provides reference images for a new generated variation or asks for vendor comparison.1213### When to use1415- Generating images, visual assets, illustrations, product photos, concept art16- Comparing output between multiple image models for the same prompt17- Producing images from prompts within editor workflows (Claude Code, Codex, Gemini CLI)18- Other skills needing image generation infrastructure (shared invocation)19- Regenerating a new image that follows a supplied reference's subject, style, lighting, or composition2021### When NOT to use2223- Pixel-level editing, masking, inpainting, object removal, compositing, cropping, resizing, or format conversion -> out of scope; use an image editor or a tool that explicitly supports that operation.24- Generating videos or audio -> out of scope25- Inline vector art / SVG composition from structured data -> use a templating skill26- Simple asset resizing or format conversion -> use a dedicated image library2728### Expected inputs29- Image prompt or creative brief30…
Excerpt shown under the repository's MIT license.
More skills in oh-my-agent
Similar skill repositories
Public repository for Agent Skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
