Image Prompt

Writes the prompt for an image: in the project's brand, in the right size for the platform, with a don't list. It writes text only. It never generates an image, so it costs nothing.

The prompt then goes to an image generator. When the higgsfield-studio skill is installed, hand it over there: it quotes the price before anything is spent. Otherwise the user pastes it into any web tool.

Who you are doing this for

Assume the person asking has never opened a terminal. You run the commands; they never do. Show them the prompt in plain words and say what happens next. If they are clearly comfortable with a terminal, let them drive.

Before anything else: check the dependencies

sh scripts/setup-deps.sh --check

Non-zero exit means Node is missing or older than 18. sh scripts/setup-deps.sh (Windows: .\scripts\setup-deps.ps1) prints the right install command for the machine and asks before running it; --yes skips the question.

Commands

node scripts/prompt.mjs --subject "..." [--type editorial] [--platform instagram_post] [--variant portrait]
     [--size 1080x1350] [--reference] [--people] [--headline "..."] [--scene "..."]
     [--brand FILE] [--brand-mode full|minimal|none] [--paste "Tool name"] [--out DIR] [--force]
node scripts/prompt.mjs sizes        every platform, variant, pixel size and ratio
node scripts/prompt.mjs brand        which brand file is used and what was read from it

• --subject is what the image shows, in plain words: "a tan leather tote bag".
• --type is the direction: editorial (default), clean-studio, detail or branded-overlay. See references/prompt-craft.md.
• --platform and --variant set the size from the table below. --size WxH sets it directly.
• --reference when the user has a photo of the real product to attach. The prompt then tells the model to keep the subject exactly and build a new scene.
• --people adds a person styled with the subject. --headline sets one short line of text on a branded-overlay.
• --paste "ChatGPT" also writes PASTE.md: short, general steps for pasting the prompt into that web tool.

Each run writes a folder with prompt.txt (the prompt alone, ready to copy) and prompt.json (the prompt, size, ratio, don't list, the brand file used, and a suggested Higgsfield model with its ratio and any crop needed).

Platforms

The brand

The brand comes from a Markdown file the project owns: --brand FILE, else BRAND_FILE, else brand.md, BRAND.md, brand/brand.md or docs/brand.md in the folder the command runs from. Its sections (palette, look, studio, motion, tone, don't) are found by their headings. The full contract and an example are in references/brand-file.md.

• No brand file is fine: the prompt carries no brand style, and the tool says so. Offer to write one with the user. Ask for their colours, how their photos look, their tone, and what they never want.
• Never invent brand values, and never copy them into this skill. Read the file every time.
• --brand-mode minimal keeps only the look and the don't list. none ignores the brand.

Handing it to Higgsfield

prompt.json has a higgsfield block: the model, the aspect ratio, the size to crop to when the model cannot make the exact ratio, and how to hand it over. With the higgsfield-studio skill installed, use its create command with --prompt-file pointing at prompt.txt, that model and ratio, and --image for a reference photo. It quotes the price first. Check the model's parameters there before guessing.

Rules

• Read the brand file every time. Never write a brand value from memory.
• One prompt, then look. Make one image from it before writing variations. Fix with one change at a time (references/prompt-craft.md lists the usual fixes).
• Respect the log. Exit code 3 means a similar prompt was already written in this project. Show the user the earlier one. Use --force only when they want a new one.
• Vary the type across a series, so a feed does not repeat itself.
• Disclosure. Generated images count as AI-generated material on most platforms. Tell the user to use each platform's AI label when they publish.

Updates

This skill is versioned. Its version is metadata.version in the header of this file. CHANGELOG.md in this folder lists what changed in each version, newest first.

To check for a newer version, open the address on the Latest: line of CHANGELOG.md and compare its top version with the installed one. If the newer one is ahead, read every entry between the two and tell the user what changed before anything is updated. A Breaking section means the user has to do something. To update, reinstall the skill from its source repository, the same way it was installed.