mcpField
I
image-poster

image-poster

github.com/nexu-ioCreative & media104.6k224 installsUpdated today
Repository

About image-poster

image-poster is a skill that turns a brief into a structured image-generation prompt, dispatches it through the project's media contract, and hands off the saved asset. It produces one image per turn unless variations are requested.

Key features

  1. 01Uses project image model, aspect, and style metadata
  2. 02Structures prompts by composition, lighting, palette, camera, and exclusions
  3. 03Dispatches image generation through the unified command
  4. 04Saves the render in the project folder
  5. 05Produces one image unless variations are requested

Use cases

  1. 01Generating a finished poster from a brief
  2. 02Matching an image to project aspect and style settings
  3. 03Creating a single image asset for review in FileViewer

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/nexu-io/open-design --skill image-poster

After installing, type/image-posterin Claude Code to confirm it loaded.

Bundled filesexample.html

Details

From the project README

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.

Step 1 — Compose the prompt

Plan in this exact order before calling any tool:

  1. Subject + composition — what is in the frame, where, at what scale; eye-line and crop.
  2. Lighting + mood — natural / studio / moody; warm / cool; key plus rim plus fill; time of day if outdoor.
  3. Palette + textures — hex anchors when the user gave a brand palette; otherwise a 3-word mood tag (e.g. "muted ochre + ink").
  4. Camera / lens — only if the user wants photographic realism ("85mm portrait, shallow DOF") or a specific film stock.
  5. What to avoid — common AI-slop patterns ("no extra fingers, no warped text, no logo placeholders").
Step 2 — Dispatch via the media contract

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.

Step 3 — Hand off

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.

Hard rules

  • One image per turn unless asked for variations.
  • Honor imageAspect exactly — the upstream cost is the same; matching the aspect avoids a re-render.
  • No filler typography in the image itself unless the user asked for in-frame text. Real copy beats lorem.
  • Save every render — never describe an image without producing the file. The user expects something to open in the file viewer.

Comments

Markdown supported