القائمة
Single-image generation skill for posters, key art, and editorial illustrations. Defaults to gpt-image-2 but is provider-agnostic — the same workflow drives Flux, Imagen, or Midjourney via the active upstream tooling. Output is one or more PNG/JPEG files saved to the project folder.
Use this plugin when the user wants a dark, premium 3D-creator / designer portfolio landing page: a full-viewport hero with a gradient-text headline and a mouse-following magnetic 3D portrait, a scroll-driven horizontal image marquee, an About section with corner 3D decorations and character-by-character scroll-reveal text, a white Services list, and sticky-stacking project cards. Invoke for '3D creator portfolio', 'designer landing page', 'creative portfolio with magnetic hero', or when the user references the Jack 3D Creator template.
Use this plugin when the user wants a premium precision-farming / agritech landing page: dark/light alternating sections, a fullscreen hero video background, an animated stats grid, an infinite logo marquee, and image-backed service cards. Invoke for 'farming landing page', 'agritech marketing site', 'precision agriculture site', or when the user references the Acreage Farming template.
Use this plugin when the user wants a premium dark-to-light aerospace / propulsion marketing site: a scroll-driven gradient hero with parallax wordmark and an engine still, a film-card that grows from a mission thumbnail into a fullscreen sticky video, a pinned tabbed showcase, a bento capabilities grid with looping video cards and a tool marquee, an animated dark stats chart with category tabs, a horizontal video-story rail, and a starfield footer. Invoke for 'aerospace landing', 'engine / propulsion site', 'EngineTech', 'scroll-cinematic hero', or when the user references the AeroCore template.
Use this plugin when the user wants a premium single-page creative-studio / designer portfolio landing page on a white background: serif-accented hero, an infinite GIF marquee, parallax testimonial, two-card pricing, an auto-scrolling testimonial carousel, vertical project showcase, a mouse-trail partner CTA, and a fixed floating bottom nav. Invoke for 'designer portfolio', 'creative studio landing page', 'agency one-pager', or when the user references the Viktor Oddy / AI Designer Portfolio template.
Use this plugin when the user wants a premium, GSAP-driven cinematic B2B landing page: a scroll-driven full-screen video slider hero with clip-path ellipse transitions, SplitText char-reveal headlines, a masonry product gallery, scroll-reveal about text, a partner marquee, Lottie-style feature cards, and a multi-office footer. Invoke for 'cinematic landing page', 'video hero landing', 'bakery / food-service landing', 'GSAP scroll site', or when the user references the Cinematic Landing Page template.
Use this plugin when the user wants a high-end, dark cinematic hero section for a coding-education / bootcamp landing page (CodeNest): full-screen HLS background video, liquid-glass card, green-accent typography, and a working mobile hamburger menu. Invoke for 'coding bootcamp hero', 'dev course landing page', 'liquid glass hero', 'video background hero', or when the user references the CodeNest template.
| name | image-poster |
| description | Single-image generation skill for posters, key art, and editorial illustrations. Defaults to gpt-image-2 but is provider-agnostic — the same workflow drives Flux, Imagen, or Midjourney via the active upstream tooling. Output is one or more PNG/JPEG files saved to the project folder. |
| triggers | ["poster","key art","illustration","image","cover art","海报","插画"] |
| od | {"mode":"image","surface":"image","scenario":"design","preview":{"type":"html","entry":"example.html"},"design_system":{"requires":false},"example_prompt":"Editorial poster for an indie film festival — one bold abstract\nsilhouette over a warm, slightly grainy paper background; hand-set\nsans serif title at the top, festival dates and venue at the bottom\nin monospace. Muted ochre + ink palette.\n"} |
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.
image-poster/
├── SKILL.md ← you're reading this
└── example.html ← what the resulting card looks like in Examples
The active project carries imageModel, imageAspect, and (optional)
imageStyle notes. Use them as the upstream model + canvas + style
anchor; only ask the user to fill them in if they're marked (unknown — ask).
Plan in this exact order before calling any tool:
Use the unified dispatcher — do not call upstream provider APIs by hand. Run from your shell tool:
"$OD_NODE_BIN" "$OD_BIN" media generate \
--project "$OD_PROJECT_ID" \
--surface image \
--model "<imageModel from metadata>" \
--aspect "<imageAspect from metadata>" \
--output "<short-descriptive-name>.png" \
--prompt "<the full assembled prompt from Step 1>"
The command prints one line of JSON: {"file": {"name": "...", ...}}.
The daemon writes the bytes into the project folder; the FileViewer
picks it up automatically.
Reply with a one-paragraph summary of the prompt you used and the
filename returned by the dispatcher (e.g. I generated hero-poster.png
with gpt-image-2 at 1:1.). Do not emit an <artifact> tag.
imageAspect exactly — the upstream cost is the same; matching
the aspect avoids a re-render.