Hire an AI image ad batch brief writer

Everything it can hand back

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

• What last week's ads taught, one line each
• A batch of about 5 ads, each changing one thing, with image words, feed text and a picture prompt
• A pre-launch result for every ad, and the reasons for any held out
• How to get the pictures made, and what it costs

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

• Naming a style from fewer than six measured ads.
• Testing more than one change in an ad, so next week cannot say what worked.
• Fixing the same ad again and again. Two rounds, then hold it out.
• Reading a high pre-launch score as proof the ad will sell. It says only that little stands in the way of launch.
• Running this when the product is out of stock, the offer is about to change, or there is no budget to test a batch.
• Designing only the happy path at desktop width.

What a good result looks like

An example, not your task: You run image ads every week and want a new batch ready each Monday.

• Path. Whether the batch builds from a winners' style or from reviews, and how many ads have enough results.
• What last week taught. One line per ad from last week: the one change it tested and what happened, or too early.
• The batch. About five ads, each changing one thing, with image words, feed text, a picture prompt and a pre-launch result.
• Held out. Any ad that still failed the pre-launch check after two fix rounds, with the reason and the smallest fix.
• How the pictures get made. The tools you can use, what each costs and the first step. Nothing is made without your yes.
• Files and missing. Each step's saved file, then every MISSING line in one list.

How the work is checked

• Every ad changes one thing from the winners, and says which.
• Every picture prompt repeats the product's lock lines word for word.
• Every ad in the batch has a pre-launch result with no stop-ship item.
• No ad borrows a winner's words, numbers, offer, deadline or people.
• 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

• Read the memory. Opens last week's style traits, the change each ad tested and the never-again list.
• Count the measured ads. An ad counts once it has about 20 purchases, or 100 link clicks. Six or more means it can look for a style.
• Choose the path. With six or more, it finds what your winners share. With fewer, it builds from your reviews and does not pretend to know a style.
• Plan and write each ad. Locks the settings once, plans each ad and scores each first line. A weak line gets one fix and one new score.
• Write the prompts. Gives each ad a prompt that repeats your product's lock lines, so the picture keeps your real pack.
• Check each ad. A stop-ship fault is fixed and checked again, twice at most. An ad that still fails is held out with its reasons.
• Ask, then make. Hands back the prompts first. Pictures are made only on your yes, and each one is checked when it comes back.

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 weekly-image-ad-batch-maker 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/weekly-image-ad-batch-maker/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

• An export of your image ads from Meta Ads Manager or Google Ads, with the image, dates, spend and your result (cost per purchase, return on ad spend or click rate)
• The product this batch is for, with its facts and current offer (paste them, or use your brand brain's products file)
• Clear photos of the exact product, one per angle (pack as sold, in a hand, in use, close-up)
• Customer reviews, if you have them (needed when fewer than six ads are measured)
• Your brand brain, if you have one (optional; without it, paste the claims you may and may not make)

Helpful context (optional)

• A note of what changed in your offer or site this week
• Your product's stock level

Tools and access

• Claude Code: It can keep the image-batch folder, read last week's files and run on a schedule.
• Meta Ads Manager: Export your ads with image, dates, spend and results from here.
• ChatGPT or Gemini: Paste a prompt into either one to get the picture. Free plans have tight daily limits.
• 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.
• Claude: Keeps track of a long workflow with stops, and holds every fact and source you gave it.
• GPT Image: Follows detailed scene prompts and takes several product reference photos at once.
• Nano Banana: Good with many reference images and with lighting on shiny packs.
• Figma: Sets real type over each picture and keeps the batch in one file.
• 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.
• Any good chat AI: Hooks are short and the checks are plain, so Claude, ChatGPT or Gemini all do this well.
• Meta Ad Library: Shows the ads other brands run now, so you can check a hook isn't one buyers already see everywhere.
• Meta Ads Manager: Exports results for each ad, so score mode can be checked against the openings you ran.
• 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.
• Claude: Reads full-size images closely, so it can spell-check the words in the picture and spot the safe zones.
• Meta Ads Manager: Its safe zone guardrail marks the area the app's buttons and labels won't cover, so you see what might get hidden.

Functions and deliverables

• Image ad batch brief writer: Use ad results or customer reviews to plan a new image ad batch. Get copy, prompts, check results and held-out drafts.
  • What last week's ads taught, one line each
  • A batch of about 5 ads, each changing one thing, with image words, feed text and a picture prompt
  • A pre-launch result for every ad, and the reasons for any held out
  • How to get the pictures made, and what it costs
• 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
• Buyer research image ad maker: Share brand facts, customer evidence and exact product photos. Get varied ad arguments, concepts, image files or prompts and a check record.
  • A buyer sheet showing which insights are backed and which are only hunches
  • A list of reasons to buy with the proof for each, and the ones it cut
  • A plan of the set by ad type and look, then a concept per ad with headline options and word counts
  • After your approvals, the finished ads and a table of what each one tests
• 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
• Ad opening writer and reviewer: Share your buyer and product facts. Get ten ad openings, or a scored review of your own.
  • In write mode, about ten hooks across the moves your facts allow, at most three per move
  • For each, what backs it, its next line, a short screen version and what a win would tell you, plus what's seen for video
  • In score mode, each hook's four checks, a score out of 4, the honesty gate and a fix for any under 3
  • A list of what it skipped and why, or the buyers your hooks miss
  • A set score out of 100, the points won on the four checks across all hooks, with gate failures counted as zero
• 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
• Pre-launch ad checker: Share your ad, audience and approved facts. Get located issues, fixes, human checks and a custom score before launch.
  • A version-bound list of observed problems and the smallest fixes
  • The buyer argument checked against the supplied facts and proof
  • A clear list of media, destination, tracking or spec checks still needed
  • A scoped verdict and observed/eligible coverage
  • An internal editing score, with any post-fix score marked provisional
• 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 run image ads every week and want a new batch ready each Monday.
• You have results on past ads but no time to work out what the winners share.
• Your pictures keep coming back with the wrong product, and you want it caught before you pay for them.

Limits to check before starting

• You run video ads. Use the Video ad script and prompt writer.
• You have no ad results yet and want one image ad now. Use the Single image ad planner.
• The product is out of stock, the offer is about to change, or there is no budget to test a batch. Wait until it is settled.
• You want one finished ad checked before launch. Use the Meta ad policy checker on its own.

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.

• Open the agent in Claude, ChatGPT or Gemini, or paste it into a new chat. In Claude Code, add it as a skill or save it in .claude/agents so it can keep a memory folder.
• Attach last week's export, the product photos and the product name. The first time, add reviews too.
• Read the batch. Check that each ad changes one thing, and that each picture prompt names your real pack. Say yes or no to each ad.
• Claude cannot draw. To get the pictures, paste a prompt into ChatGPT or Gemini, or use an image tool you pay for. The agent asks before it uses any credits.
• Run it again next Monday. It reads its memory folder to see what last week's changes taught.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/weekly-image-ad-batch-maker 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.