Hire an AI image ad style and concept planner

Everything it can hand back

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

• The traits your winners share, and the ones to drop
• New ad plans that each change one thing
• A brief with every setting locked
• The words, layout and feed copy for each ad
• One image prompt per ad that keeps your real product
• After you pick your images, an upscale plan for each

How it does the job well

• 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 have at least six image ads with results and want more that work the same way.

• Winning style. The traits your best ads share and your weakest ads lack, plus the old words and numbers to drop.
• New ad plans. Each new ad keeps the style and changes one thing, such as the argument or the buyer.
• Locked brief. Every setting filled in one brief, with any clashing settings listed so every ad is made the same way.
• Ad plan for each ad. The one-sentence argument, the words on the image, the layout and the feed copy.
• Image prompts. One prompt per ad and size that keeps your real product, with the job of each reference photo.
• Upscale plan. The target size, the tool settings and any changes found, for the images you pick.

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 Eugene Schwartz and Claude Hopkins would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Finds the style your winners share. Uses the style finder skill to compare your best and weakest ads on five traits, keep the ones that split them, and plan new ads that change one thing each.
• Locks the settings. Uses the settings picker skill to turn the plans into one brief where every choice is filled and no two settings clash.
• Plans each ad. Uses the image ad planner to write the one-sentence argument, the claim, the layout and the feed copy for each ad.
• Writes the image prompts. Uses the product image ad skill to give every photo one job and write a prompt that keeps your real product.
• Waits while you make the images. You make the pictures, look at each at full size and pick the ones to keep.
• Sets up the upscale. Uses the upscale checker to check the original, work out the real size needed and set up a faithful upscale.

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 winning-style-image-ads 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/winning-style-image-ads/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

• Six or more of your image ads, as pictures, with their results (spend, sales or clicks)
• Your product facts and photos
• Your brand file (optional)
• How many new ads you want, and the sizes
• After step 4, the images you picked, for the upscale

Helpful context (optional)

• At least six ads with results, so there is a top and a bottom group to compare
• Full-size photos of your pack from the front and in use
• The date range of each result, so ads are not compared across a sale

Tools and access

• Claude: Holds nine ads, their results and four steps of work in one run.
• GPT Image: Takes your product photos as references and keeps short headline words readable.
• Nano Banana: Takes many reference photos at once and handles shiny packs such as foil pouches.
• Meta Ads Manager: Exports spend, purchases and dates per ad, so the ranking matches your account.
• Google Sheets: Ranks the ads and splits them into thirds, so you can check its counts.
• Any good chat AI: Reading traits works in any strong chat AI that can look at ad images.
• Any good chat AI: Pasting snippets and running the conflict check works the same in any strong chat AI.
• GPT Image: Follows long, structured briefs closely, so each pasted snippet shows up in the picture. Use it in ChatGPT (free plans have limits) or with an OpenAI API key, which is paid.
• Nano Banana: Takes several reference images at once, which the closeness and product choices often need. Use it in the Gemini app (free plans have limits) or with a Google API key, which is paid.
• Any good chat AI: Planning one ad from your facts and counting characters works well in any strong chat AI.
• Nano Banana: Takes many reference images and draws legible text, so the pack and any typed words come out close to real.
• Canva: Sets your three reads as real text over the picture, so you can resize them and run the blur check.
• Meta Ads Manager: Its ad preview shows where the first line and headline get cut on each placement before you spend.
• GPT Image: Takes several labelled reference images and follows exact quoted words for headlines and labels.
• Nano Banana: Mixes many reference images and keeps the pack's shape across new scenes.
• FLUX: Gives tight control when the prompt leads with the subject and ties each hex colour to one object.
• Topaz Gigapixel: Lets you choose a faithful model, including one made for text and logos, and turn face recovery down or off. It is paid software.
• Magnific: Offers a Precision upscaler with plain sharpen and grain sliders, apart from its Creative one. It is a paid service.
• GIMP: Free editor whose Difference layer mode shows any change between the original and the result.

Functions and deliverables

• Image ad style and concept planner: Share ads, results and real product photos. Get a style brief, new ad concepts, image prompts and upscale checks after you choose images.
  • The traits your winners share, and the ones to drop
  • New ad plans that each change one thing
  • A brief with every setting locked
  • The words, layout and feed copy for each ad
  • One image prompt per ad that keeps your real product
  • After you pick your images, an upscale plan for each
• Winning image ad style finder: Find the image ad style your best ads share. Attach six or more ads with results. Get a style list and new ad plans that each test one change.
  • A ranking of your measured ads, top, middle and bottom
  • The style, with each trait's count among winners and losers
  • A do-not-carry list of words, numbers, people and offers that stay with the old ads
  • New ad plans, each saying what is kept and the one thing changed
• Image ad visual brief writer: Choose your ad's look and selling style. Get a ready-to-use visual brief, conflicting choices flagged and a list of missing material.
  • Your brief with the always-on rules and your chosen snippets added, each pasted whole
  • A conflict check that names any two choices that fight, and which wins
  • A MISSING line for any material a choice needs and you didn't send
• Single image ad planner: Paste your facts. Get the layout, image words, feed copy and an image prompt.
  • The one sentence the ad argues, with the claim and where it came from
  • The ad type, the look and the layout, with the types ruled out and why
  • A zone map in reading order, and the words on the image with a word count
  • Feed copy with three headlines, each with its character count
  • A prompt for an image model, and a list of every guess and gap
  • Any of its five checks the plan still misses, one line each
• Product image ad prompt writer: Share your approved ad, product facts and photos. Get an image prompt, photo roles and a checklist for the first image.
  • One prompt in five blocks plus a keep line, with its character count
  • A subject block that says which hand holds what, which hand tears or pours, and how they move
  • A one-line role for every attached photo
  • A six-line pass-or-fail check for the first image, with failure notes for your mistakes list
  • A list of what was left out or added, and a MISSING line for any fact it needed
• Image enlargement quality checker: Check an image upscale before it goes to print. Give it your approved image and target size. You get safe settings, a change check and a score.
  • The real target size in pixels, worked out from where the image will go
  • The kind of upscaler to use and the settings that keep it faithful
  • A plan for keeping your words and logo exact
  • A size check, a difference check and a review of words, faces, hands, product and texture
  • A verdict, either accepted or the original returned with the reason
  • A fidelity score out of 100 for each try, from the share of checked areas that match the original
• 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
• Eugene Schwartz: Match a headline or sales page to what buyers already want and know. Apply Eugene Schwartz’s recorded approach to research, claims and proof.
  • Your problem worked on the way Eugene Schwartz would: their questions, their method, their push-back
  • The answer or the work, in Eugene Schwartz's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Claude Hopkins: Write specific ads or plan a small buyer test using Claude Hopkins’s recorded approach. Replace vague praise with facts and track cost per customer.
  • Your problem worked on the way Claude Hopkins would: their questions, their method, their push-back
  • The answer or the work, in Claude Hopkins'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 have at least six image ads with results and want more that work the same way.
• Your winners all feel alike but you cannot say why.
• You want new ads that test one change at a time, not ten new guesses.

Limits to check before starting

• You have fewer than six image ads with results: use the Single image ad planner to plan new ads from your product facts instead.
• You want a video ad: use the Customer quote video ad writer, or write the script with a person who makes video.
• You want to copy one winning layout exactly: use the Reference layout image ad maker.

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 plus five skill files, in the order they run: Winning image ad style finder, Image ad settings picker, Single image ad planner, Accurate product image ad maker, Image upscale checker.
• 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 ads as pictures with their results, your product facts and photos, and a line on how many new ads you want.
• Check the style list and the new ad plans when it stops. Fix anything that is wrong before it writes the prompts.
• Make the images in your image tool, pick the ones to keep, then bring them back for the upscale step.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/winning-style-image-ads 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.