Image Poster

Generates a single poster, key art, or editorial illustration per turn using whatever image model your project specifies (gpt-image-2, Flux, Imagen, etc.). It takes your brief, builds a structured prompt covering composition, lighting, palette, and camera feel, then dispatches through the unified media contract and saves a PNG or JPEG straight to your project folder. The workflow is tight: no artifacts, no extra variations unless you ask, and it respects the aspect ratio in your metadata so you don't waste a rerender. If you need one hero image and you already know roughly what it should look like, this is faster than assembling the prompt yourself.

skills.sh installs: 225
GitHub stars: 106.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add nexu-io/open-design --skill image-poster --agent claude-code

Installs into .claude/skills of the current project.

Files

Image Poster Skill

Produce one finished image asset per turn unless the user asks for variations. Image generation rewards a tight, structured prompt — your job is to assemble that prompt from the user's brief, then dispatch.

Resource map

image-poster/
├── SKILL.md         ← you're reading this
└── example.html     ← what the resulting card looks like in Examples

Workflow

Step 0 — Read the project metadata

The active project carries imageModel, imageAspect, and (optional) imageStyle notes. Use them as the upstream model + canvas + style anchor. When a value is not provided, infer a safe default from the brief and media contract. Ask only when the choice would materially change the requested result and no safe default can be inferred.