Hire an AI product photo styling planner

Everything it can hand back

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

• A brand file with your colours, look and product details
• A style sheet and nine matching photo prompts
• Six flash snapshot prompts from one real occasion
• A prompt that matches the look of your reference photo, with the pictures ranked
• A check list for every picture at full size

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

• 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: You only have phone photos and need many more for ads and your shop.

• Brand file. Your colours, look, prices and product details, each tagged with where it came from.
• Styled photo set. A style sheet and nine frames on a grid, each with a prompt for your image tool.
• Flash snapshots. The flash look, one real occasion in time order, and six prompts.
• Reference look. What is kept, swapped and dropped from your reference photo, one prompt, and the pictures ranked.
• Checks. A list for looking at each picture at full size next to your real product.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line 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.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• 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 and April Dunford would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Builds your brand file. Uses the brand file skill to read your site and tag every colour, product detail and claim with where it came from.
• Plans a styled photo set. Uses the shoot planner to write a style sheet, plan nine frames on a grid and write one prompt for each.
• Makes flash snapshots. Uses the flash snapshot skill to set the flash look, plan one real occasion in time order and write six prompts.
• Copies a look you like. Uses the reference photo skill to read your reference as the set that made it, keep or swap each part, and rank the pictures.

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 three-look-product-photos 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/three-look-product-photos/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

• Your website, as a link or saved pages
• Your product photos: the front, the back of the pack, in use, and a close-up of the print
• A photo whose look you like (optional, needed for the third look)
• Who the photos are for (optional)

Helpful context (optional)

• Full-size photos of your product from the front, back and in use
• A close-up of the print on the pack, so printed words stay spelled right
• Your colour codes, if you have them

Tools and access

• Claude: Keeps the product details the same across all three looks in one run.
• GPT Image: Takes your product photos as references and keeps the pack close to the real one.
• Nano Banana: Takes many reference photos at once and handles shiny packs such as foil pouches.
• Claude: A project keeps the start file as its instructions and the other files as knowledge, even on a free account.
• Gemini: A Gem keeps the start file as instructions that Gemini follows every time you use it.
• Shopify: If you sell on Shopify, it exports your products and variants as a spreadsheet, so offers.md matches every variant.
• Nano Banana: Takes up to 6 product photos plus 3 style references, which suits holding one look across nine frames.
• GPT Image: Keeps the product close to your reference photos, and holds small edits across rounds.
• GPT Image: Follows long scene descriptions well, and its thinking mode plans the frame before it draws.
• Nano Banana: Takes up to 10 object photos and holds the product steady across follow-up edits.
• Veo: For the optional short clip. It can start from your approved frame and add sound if you want it.
• Nano Banana: Takes up to 3 style reference images apart from the product photos, so the look and the product stay separate.
• GPT Image: Keeps the product close to your photo while it takes the light from a second image.

Functions and deliverables

• Product photo styling planner: Share product photos, brand facts and a visual reference. Get styled shot plans, flash-photo ideas and a reference-led look for your own product.
  • A brand file with your colours, look and product details
  • A style sheet and nine matching photo prompts
  • Six flash snapshot prompts from one real occasion
  • A prompt that matches the look of your reference photo, with the pictures ranked
  • A check list for every picture at full size
• 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
• Product photo shoot planner: Plan a product photo shoot where every picture matches. Give it your product photos and colours. You get a style sheet and a prompt for each frame.
  • A six-line style sheet for the whole set
  • A frame list, each with its job, distance, angle and what it shows
  • One prompt per frame, plus a check of the whole set side by side
  • An optional plan for a 6 to 8 second loop clip
  • Any check the set still missed, one line each
• Flash snapshot product photo maker: Plan six flash snapshot product photos from one real occasion. Get the flash settings, a shot roll and one image prompt per photo.
  • The three flash dials, set for your brand
  • A roll of frames from one occasion, for you to approve
  • One prompt per photo, written in a fixed order
  • A check log for each photo, with what was remade and why
  • Any check the roll still missed, one line each, or none
• 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
• 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
• April Dunford: Work out why buyers should choose your product. Use April Dunford's positioning method to find real alternatives, buyer value and a clear sales pitch.
  • Your problem worked on the way April Dunford would: their questions, their method, their push-back
  • The answer or the work, in April Dunford'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 only have phone photos and need many more for ads and your shop.
• You like the look of someone else's photo and want that feel for your product.
• Your product photos all look alike and you need some variety.

Limits to check before starting

• You need real customer pictures: the flash snapshots are staged, so use photos from your own customers instead.
• You only want one plain studio photo set: use the Product photo shoot planner.
• You want to fix flaws in pictures you already made: use the Ad image planner.

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 has HANDOFF.md and four skill files, in the order they run: Brand profile builder, Product photo shoot planner, Flash snapshot product photo maker and Reference-style product photo maker.
• Give the folder to Claude, in Claude Code or as files in a Claude Project, and say "Follow HANDOFF.md".
• Have your inputs ready: your website link, your phone photos and one photo whose look you like.
• Take the prompts to your image tool. You need a tool or account that makes images, and it may be paid.
• Make frame 1 of each look first and check it against your real product before you make the rest.
• Look at every finished picture at full size. Treat the flash snapshots as staged images, not real customer photos. If you use one in an ad, label it AI-generated. Never present it as a customer or event photo.

Read it as data

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