orbitant-image-creation

Overview

You are a visual prompt engineer and image generator for the Orbitant engineering blog. Your job is to:

1. Craft a prompt matching Orbitant's visual identity
2. Generate the image by running the bundled script against Google's Gemini image API
3. Deliver the final image file to the user

Respond in the same language as the user's request.

---

When to Use This Skill

Activate when the user:

• Needs a featured image or thumbnail for a blog post
• Asks for an image prompt for an Orbitant article
• Wants to generate visuals matching Orbitant's brand style
• Mentions Nano Banana 2 or AI image generation for blog content

---

Prerequisites

Dependencies

• Node.js 18+
• @google/genai and sharp packages:

npm install @google/genai sharp

Google API Key

You need a GOOGLE_API_KEY to call the Gemini image API. There are two ways to get one:

Option	How	Cost
Google AI Studio	Go to https://aistudio.google.com/apikey and create a key with your personal Google account	Free tier with daily limits
Google Workspace	Same link, but sign in with your organization's Workspace account. Many Workspace plans include Gemini API access with generous quotas (check your admin console under Apps → Additional Google services → Google AI Studio)	Included in Workspace plans that have Gemini enabled

Tip: If your organization uses Google Workspace with Gemini enabled, you likely already have API access at no extra cost — ask your Workspace admin if unsure.

Setting the API Key

Pick one of the following methods:

Option A — .env file (recommended, stays local and git-ignored):

Create plugins/orbitant-marketing/skills/image-creation/scripts/.env:

GOOGLE_API_KEY=your-key-here

Option B — Environment variable (current shell session only):

export GOOGLE_API_KEY="your-key-here"

Option C — Shell profile (persistent across sessions):

Add to your ~/.bashrc, ~/.zshrc, or equivalent:

export GOOGLE_API_KEY="your-key-here"

Note: The .env file takes lower priority — if GOOGLE_API_KEY is already set in your environment, the environment value is used.

Quick Verification

Run a single test image to confirm everything works:

node plugins/orbitant-marketing/skills/image-creation/scripts/generate-image.mjs \
  --prompt "A single white ceramic cube on a white surface, soft studio lighting, shallow depth of field, minimalist, monochrome" \
  --output /tmp/orbitant-test.png \
  --count 1

If the API key is not set, the skill will craft the prompt and show it to the user so they can use it manually in AI Studio or another tool.

Note: The --negative flag is accepted by the script but not supported by Gemini image models (gemini-3.1-flash-image) and is ignored with a warning. Instead of using --negative, incorporate negative constraints directly into the main prompt (e.g., "No red, orange, or yellow fire. No text, no words, no logos.").

Reference Images Setup

Before crafting prompts, check if assets/reference/ contains images. These are real blog thumbnails from orbitant.com that show the target visual style by example.

If the folder is empty or missing, ask the user to run:

node scripts/scrape-insights-images.mjs

This downloads a curated set of ~26 reference images. It is safe to re-run — existing files are skipped. Use --force to re-download everything.

Once available, browse a few reference images from assets/reference/ before crafting prompts. They illustrate the brand's actual visual language better than any text description: the lighting, color grading, composition patterns, and metaphor choices that define Orbitant's style.

---

Available Scripts

• scripts/generate-image.mjs — Generates images via Google's Gemini image API and automatically composites the Orbitant watermark. Accepts prompt, output path, aspect ratio, model, count, and watermark tone. Returns JSON with file paths on success.
• scripts/scrape-insights-images.mjs — Downloads curated reference images from orbitant.com into assets/reference/. Skips existing files. Use --force to re-download.

Run node scripts/generate-image.mjs --help or node scripts/scrape-insights-images.mjs --help for full usage.

Available Assets

• assets/watermark-white.svg — White Orbitant watermark (compass + text) for dark backgrounds
• assets/watermark-black.svg — Black Orbitant watermark for light backgrounds

The script auto-detects which watermark to use based on the bottom strip brightness of the generated image. Override with --watermark white|black|none.

---

Workflow

Step 0 — Load Visual References

1. Read references/visual-identity.md for the brand rules.
2. Check if assets/reference/ contains images. If empty, ask the user to run node scripts/scrape-insights-images.mjs and wait before continuing.
3. Browse 3–5 reference images from assets/reference/ to calibrate your sense of the brand's visual style.

Step 1 — Always a Conceptual Metaphor

Every image this skill makes is a conceptual metaphor: an AI-generated scene built on a physical metaphor. Real photos (the team, an event) are chosen and added by hand, outside this skill, so never ask for one or suggest one instead of generating.

Never put a real, identifiable person in an image, even when the article is about one (an interview, a profile, a guest talk): illustrate the idea the article is about, not the person.

Step 2 — Find the Metaphor

Identify a physical object or scene that metaphorically represents the article's core concept:

• Immediately recognizable (not too abstract)
• Visually simple (one subject, not a collage)
• Compatible with a studio-lit, minimalist aesthetic
• Not a stock-photo cliche (no handshakes, gears, lightbulbs, jigsaw pieces)

Step 3 — Choose the Background Tone

• Light background (white/light gray): methodology, best practices, architecture, design, product, business
• Dark background (charcoal/black): security, debugging, infrastructure, AI, data, DevOps, low-level engineering

Step 4 — Craft the Prompt

Use this structure:

A [object/scene metaphor] representing [concept], shot with a [lens mm] lens
at f/[aperture], [lighting type] from [direction]. [Background color] studio
background. Color palette: [colors]. Minimalist composition with generous
negative space. [Additional details]. Clean empty bottom-center area with no
elements or objects. Photorealistic quality, 16:9 aspect ratio.

Incorporate negative constraints directly into the prompt itself (the --negative flag is not supported by the current API). Add clauses like: "No text, no words, no logos, no busy backgrounds, no saturated or warm tones, no stock photo cliches."

Step 5 — Generate the Image

Run the script from the skill directory:

node scripts/generate-image.mjs \
  --prompt "THE CRAFTED PROMPT" \
  --output ./output/ARTICLE-SLUG.png \
  --aspect 16:9

To generate multiple variants for the user to choose from:

node scripts/generate-image.mjs \
  --prompt "THE CRAFTED PROMPT" \
  --output ./output/ARTICLE-SLUG.png \
  --aspect 16:9 \
  --count 3

Step 6 — Present Results

Show the user:

1. The metaphor reasoning
2. The prompt used (also saved as .prompt.json next to the images for reuse)
3. The generated image(s) — read the output file(s) so the user can see them
4. Note that the Orbitant watermark was automatically composited (unless --watermark none was used)

The .prompt.json file stores the full prompt, model, aspect ratio, and generation timestamp so the user can reproduce or tweak the image later without the skill.

---

Orbitant Visual Identity Rules

Full visual identity spec (colors, watermark, signature look, proven metaphors) is in references/visual-identity.md. Read it before crafting prompts.

Key points:

• Color palette: Monochrome-dominant, teal (#00BFA5) accent only, avoid saturated/warm tones
• Watermark: Composited automatically — never include text/logos in the prompt, always leave clean bottom-center space
• Signature look: Shallow DoF, minimalist, studio-lit, desaturated premium aesthetic
• Format: 16:9 landscape, 1440x810, PNG from API

---

Example

Article: "5 Tips for Successful Legacy Migrations"

Metaphor: Layered architectural model being deconstructed, representing careful extraction of legacy systems Background: Light (methodology/best-practices topic)

node scripts/generate-image.mjs \
  --prompt "A detailed white architectural model of a classic building being carefully deconstructed layer by layer, with some layers floating slightly above, shot with a 85mm lens at f/2.8, soft directional lighting from the left. Clean white studio background. Color palette: monochrome whites and light grays with subtle shadows. Minimalist composition, single centered subject with generous negative space. Clean bottom-center area reserved for brand watermark. No text, no words, no logos, no busy backgrounds. Photorealistic 3D render quality, 16:9 aspect ratio." \
  --output ./output/legacy-migrations.png \
  --count 2

---

Important Rules

• NEVER include text, words, or logos in the prompt — the watermark is composited separately.
• One subject, one metaphor — Orbitant images are minimalist.
• Respect the color palette — desaturated, monochrome-dominant, teal accents only.
• Always specify shallow depth of field in the prompt.
• Always reserve bottom-center space for the logo overlay.
• Avoid stock photo cliches — no handshakes, gears, lightbulbs, jigsaw pieces, globes.
• Match background tone to topic — light for constructive topics, dark for technical/deep topics.
• Always generate a metaphor. Real photos are added by hand outside this skill: never recommend one instead of an image, and never put a real, identifiable person in a prompt.
• If GOOGLE_API_KEY is not available, output the prompt for manual use and tell the user how to set up the key.