Hire an AI product gallery image designer

Everything it can hand back

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

• A product truth sheet, and the photos you still need
• A scored plan of about 8 images, each with its question, words and sources
• The images, named in upload order, each with alt text
• A pass or fail for every image, with one fix for each fault

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

Mistakes it avoids

• Skipping a check step to save time.
• Drawing a part, a pack or a close-up that no real photo shows.
• Publishing, uploading or spending money without the person's clear yes.
• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.
• Roadmaps with dates but no owners or confidence levels.

What a good result looks like

An example, not your task: Your product page gallery is mostly packshots and shoppers keep asking the same questions.

• Truth sheet. Shape, colours, printed words, how it opens, what is in the box, what never to draw, and missing photos.
• Gallery plan. A score for each shopper question, about 8 image cards with every word and its source, and a list of gaps.
• Doubts. Your reviews sorted into five fears, with the biggest one placed in image slot 2.
• Gallery images. Each image in its own shapes, named in upload order, with alt text.
• Image check report. 13 checks in three passes, with a Stop, Fix or Polish rating and one fix per fault.
• Hand-back summary. Each step's file, any step not run and why, and every missing item in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• No pilot image was made before approval of the plan and words. The remaining set was made only after approval of the pilot look and words. No image was made from a described photo without actual reference files.
• Every word on every image is in the plan with a source, and every figure matches the facts. Every health, nutrient or results claim was flagged CLAIM CHECK: and approved with proof.
• No two images answer the same question.
• 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

• Records the real product. Uses the product truth sheet skill to keep only photos of the exact variant and write down its shape, colours, printed words, how it opens and what to never draw.
• Plans the gallery. Uses the gallery plan skill to score each shopper question from 0 to 6 and write a card for each of about 8 images. A question with no proof goes on the gaps list.
• Makes the images. Uses the gallery image set skill to sort your reviews into five fears, put the biggest one second, and stop for your yes on the plan and on the first two images.
• Checks every image. Uses the gallery image check skill to run 13 checks in three passes, from thumbnails to a one-second glance at phone size to every word zoomed in.

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 photo-product-gallery 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/photo-product-gallery/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

• Real photos of the exact product, as many angles as you have, ideally one in use
• Your product facts, including amounts, size and what's in the box
• Your brand file, with your colours, fonts, claims and guarantee terms
• Customer reviews, to find the worry that stops most sales (optional)

Helpful context (optional)

• A photo of one daily pack, or one unit, whole and opened, so the how-to-use image can be made
• A photo of everything in the box laid out, so the what-you-get image is honest
• The label panel shot flat and sharp, so every amount is read, not guessed
• Return reasons and questions shoppers ask before buying, so the worst worry is counted right
• Your current gallery files in upload order, so it can say what to keep, fix or drop

Tools and access

• Claude: Keeps track of a long run with two stops for your OK, and holds every fact and source.
• Nano Banana: Takes many reference photos at once and handles shiny packs such as foil pouches.
• GPT Image: Lets you point at one word or part of an image and fix it, which suits the one-change remake rule.
• Figma: Sets ingredient panels and small print as real type, so no word gets redrawn.
• Claude: Reads several product photos at full size and quotes printed words line by line with the photo they came from.
• Google Sheets: Keeps one row per variant, so the sheet and its lock lines are easy to find and update.
• Any good chat AI: The scoring is simple sums, so any current chat AI can run it. Attach the photos so it can sort them by job.
• Google Sheets: Keeps the score table in rows, so you can re-sort it when a new photo or fact arrives.
• Nano Banana: Built for brand consistency and handles words and layout well, which suits images with short lines on them. Paid plans or credits may apply.
• GPT Image: Lets you point at one word or part on an image and fix it, which suits the one-change remake rule. Paid plans or credits may apply.
• Shopify: Lets you add alt text to each product image in the admin, so the alt lines go straight in.
• Any good chat AI: Any current chat AI that reads images can run the checks. Attach each file at full size, then zoom in yourself too.
• Google Merchant Center: Its Diagnostics page flags product images that break Google's rules, such as promo text or a missing AI label.

Functions and deliverables

• Product gallery image designer: Share exact product photos, facts and buyer questions. Get a gallery plan, pilot images and a checked final set where image tools are available.
  • A product truth sheet, and the photos you still need
  • A scored plan of about 8 images, each with its question, words and sources
  • The images, named in upload order, each with alt text
  • A pass or fail for every image, with one fix for each fault
• Product image spec writer: Check your product photos and write a product image spec: a sourced truth sheet, lock lines for every prompt and the next photo to take.
  • A photo check saying which photos to trust and why the rest are out
  • A one-page truth sheet in seven parts, with a source on every line
  • Three to five lock lines that every prompt repeats word for word
  • The shots that can't be made yet, and the one photo to take next
  • Any check the sheet still missed, one line each
• Product page gallery planner: Plan your product page gallery image by image. Give it product facts, reviews and photos. You get an 8-image plan with sourced words and a gaps list.
  • A score table showing why each image made the cut, or didn't
  • One card per image in upload order (question, message, photo, layout, words with sources)
  • A gaps list of every missing fact and photo, and which image waits on each
• Product gallery image planner: Share exact product photos, brand facts and customer feedback. Get a gallery review, image plan and checked files when image tools are available.
  • An audit of your current gallery and the questions it leaves open
  • Customer worries grouped by fear, counted, with real quotes and the image that answers each
  • The image-by-image plan and a gaps list
  • Finished images in upload order, in each shape, with alt text and check results
• Product page image checker: Check your product page images before you upload. Get a pass or fail for each image, one fix per fault and a score out of 100 for the set.
  • PASS or FAIL for each image
  • One line per fault, with the check, severity, where it is, what was planned, what came out and the fix
  • A verdict for the whole set, and a list of any check that couldn't run
  • A score out of 100 for the set, now and after the fixes, with the sum shown
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.
• 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

• Your product page gallery is mostly packshots and shoppers keep asking the same questions.
• You're launching a product and need a full set of gallery images.
• You've tried AI product images and the pack came out wrong.

Limits to check before starting

• You have no real photos of the product yet: take photos first, or make wordless images with the Product image ad prompt writer.
• You want one ad image, not a full gallery: use the Product image ad prompt writer.
• You only want to check images you already have: use the Product page image checker.

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 handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md". It needs an image tool connected to make the images.
• Have your inputs ready. Your product photos (full size, the exact variant you sell), your product facts with amounts, your brand file and, if you can, your reviews.
• It works step by step and saves each result. Read the truth sheet's missing photos first. Each one is an image it can't make honestly.
• Approve the plan and every word on it when it asks, then approve the first two images. Nothing gets made before you say yes, and the words don't change after.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/photo-product-gallery 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.