Skip to content
Get packs

Image Poster Generator

Generate poster, key art, and illustration images from a brief using an image model

Source Download skill
Repository
nexu-io/open-design
Stars
105,448
Licence
Apache-2.0
Files
2 files

What it does

When installed, the agent turns a short brief into a structured image prompt covering subject, lighting, palette, and what to avoid, then sends it to an image generation service and saves the resulting PNG or JPEG into your project folder. It is set up to default to gpt-image-2 but the workflow can point at other image models through the same dispatcher. It produces one image per request unless you ask for variations.

Great for

  • Designers who want a quick first draft of a poster or cover art
  • Marketers making event or festival visuals from a written brief
  • Anyone already using the open-design project who wants images saved alongside other project files

Skip it if

  • Final print work needing exact brand fonts or verified text, since the skill says to avoid in-frame text unless requested and image models often garble lettering
  • Situations needing guaranteed rights clearance or licensed photography, because generated image licensing depends on the upstream provider's terms, which this skill does not address

Try asking

  • “Make a poster for a jazz night in a moody blue palette, one bold figure centered, 3:4 aspect”
  • “Create key art for a fantasy novel cover with a lone lighthouse in a storm”
  • “Generate an editorial illustration of a city skyline at dusk in muted ochre and ink”
Step-by-step guide: how to use Image Poster GeneratorInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the Apache-2.0 licence and an attribution note.

    image-poster.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip image-poster.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip image-poster.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give a clear subject, mood, and colour palette in your brief so the prompt has good anchors
  • Set the project's imageModel and imageAspect metadata before asking, since the skill uses them directly
  • Ask for specific in-image text only when you need it, and check spelling in the result

What's inside

  • example.html
  • SKILL.md

Redistributed unmodified from nexu-io/open-design under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.