Hire an AI image prompt engineer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• One main prompt in layers, covering subject, setting, light, camera and look.
• Two variations, each changing one thing, such as the light or the angle.
• A list of what to leave out, in the form your tool uses.
• Notes on which layer to change if the result misses.
• Gaps and checks still needed before you use the picture.

How it does the job well

• Do not say what a tool will produce. You cannot test it. Say what to look for.
• Do not describe or imply real people from a name. If the user asks for a real person's likeness, say the tool may refuse and that rights and consent need checking.
• Say what an image tool costs before the user signs up or connects it. Midjourney needs a paid plan, Higgsfield is a paid service, and OpenAI and Google keys bill each picture.
• Start from the user's task and the content, then the layout. Decoration comes last.
• Design every state: empty, loading, error, long text and mobile.
• Keep one visual system. Reuse spacing, type and colour tokens instead of one-off values.
• Check text contrast (at least 4.5:1 for body text) and keyboard focus as you go.

Mistakes it avoids

• Designing only the happy path at desktop width.
• Copying a reference's logo, text or claims instead of learning from its structure.
• Handing over a picture without the sizes, tokens and behaviour a developer needs.

What a good result looks like

An example, not your task: You want a product photo for a store page or ad and your first prompts keep coming out flat.

• Brief and assumptions. The use, tool and shape it understood, what it assumed and what is missing.
• Main prompt. One prompt ready to paste into your image tool.
• Layers. The subject, setting, light, camera and look broken out so you can change one at a time.
• Leave out. The things to exclude, written for your tool's negative field.
• Variations. Two more prompts that each change one thing, such as the light or the angle.
• If it misses. Which layer to change for common problems, and wording to try.

How the work is checked

• Every screen has its states, breakpoints and interactions written down.
• Colour pairs and type sizes pass the stated contrast checks.
• The handoff names components, tokens and open questions.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Jakob Nielsen would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Take the brief. It asks for the use, the subject, the tool, the shape and the look, and marks what is missing.
• Read your references. If you share photos or links, it names the light, angle, colour and mood that make them work.
• Build the layers. It writes subject, setting, light, camera and look as separate parts, using plain photo terms.
• Fit your tool. It adjusts the wording and settings for Midjourney, DALL-E, Flux or Stable Diffusion, and says when it is unsure of the syntax.
• Add the leave-outs. It lists unwanted things and puts them in the negative field when the tool has one.
• Plan the next try. It gives two variations and tells you which layer to change if the first picture misses.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id design-image-prompt-engineer only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/design-image-prompt-engineer/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• What the picture is for, such as a product page, an ad or a blog header.
• What it should show, in your words, with any must-have details.
• The image tool you will use, such as Midjourney, DALL-E, Flux or Stable Diffusion.
• The look you want, such as moody, bright or editorial, with the shape you need, like square or tall.
• Reference photos or links, and anything that must not appear (optional).

Helpful context (optional)

• A reference photo that has the light and mood you want.
• Your brand colours or a short style note.
• A list of things that must never appear, such as logos or text.

Tools and access

• Midjourney, DALL-E, Flux or Stable Diffusion: The prompt layout is built for these tools. Tell the agent which one so it uses the right settings. Midjourney needs a paid plan, and most of the others limit or charge for pictures.
• Claude, ChatGPT or Gemini with image upload: You can attach reference photos, and the agent reads the light and angle from them.

Functions and deliverables

• Image prompt engineer agent: Describe the photo you want. Get an image prompt that sets subject, light, camera and style, plus a leave-out list, for Midjourney, DALL-E or Flux.
  • One main prompt in layers, covering subject, setting, light, camera and look.
  • Two variations, each changing one thing, such as the light or the angle.
  • A list of what to leave out, in the form your tool uses.
  • Notes on which layer to change if the result misses.
  • Gaps and checks still needed before you use the picture.
  Source: Michael Sitarzewski and Agency Agents contributors.
• Midjourney image prompt writer: Turn one image idea or reference into four different Midjourney prompts, each a new treatment, plus four directions to try next.
  • A one-line reading of your idea, with what it assumed marked apart from what you asked for
  • Four Midjourney prompts, each with a short label, in one block you can copy
  • Four directions to try next, each a real change
  • A MISSING line if your idea or reference was not clear enough
• Reference-style product photo maker: Make product photos that match a look you like. Attach your product and one reference photo. Get an image prompt and ranked pictures.
  • A five-part reading of the reference photo
  • A keep, swap or drop line for each part
  • The finished image prompt, ready to paste
  • If your chat can make images, the pictures ranked with a score out of 100, and a reject list
  • If it can't, any of the four checks the prompt still missed
• Overhead portrait image maker: Describe an overhead adult portrait and share reference photos. Get a camera-and-light prompt, with an image if an image tool is available.
  • One prompt paragraph, ready to paste
  • The role of each photo you attached
  • For an edit, a one-line change and a list of what stays the same
  • If your chat makes images, the picture with a pass or fail line for each check
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Jakob Nielsen: Review a website, app or form through Jakob Nielsen’s recorded approach. Find likely usability problems and plan small rounds of realistic user tasks.
  • Your problem worked on the way Jakob Nielsen would: their questions, their method, their push-back
  • The answer or the work, in Jakob Nielsen's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You want a product photo for a store page or ad and your first prompts keep coming out flat.
• Your team needs one prompt layout, so pictures look alike across a campaign.
• You have a mood board or a photo you like and want its look put into words.
• You need the same scene in a different tool, such as moving from DALL-E to Midjourney.

Limits to check before starting

• You want one quick prompt for an ad image, with a size and a file name. Use the Marketing image prompt writer.
• You use Midjourney and want four different directions to compare. Use the Midjourney image prompt writer.
• Your picture came out wrong and you want to fix the prompt. Use the Image and video prompt director.
• Faces, skin or hands look fake. Use the Skin realism image prompt checker.
• You want to change a photo you already have, or need final artwork. Use the Nano Banana image and edit prompt planner for edits, and a designer for final work.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack from this page and add it to your AI as a skill. Or paste SKILL.md into a new chat, then paste references/source-agent.md after it.
• Describe the picture, its use and your image tool. Attach reference photos if your AI accepts images.
• Answer the questions it asks once. Anything you skip is marked MISSING or ASSUMED in the result.
• Copy the main prompt into your image tool first. Check the picture against your list of must-have details.
• If it misses, change the layer the notes name, or try a variation. Change one thing at a time.
• Check any real product, logo or text in the picture yourself before you publish.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/design-image-prompt-engineer for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.