Hire an AI Meta offer image ad 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 offers, prices and claims word for word
• Clashes between your live offers, flagged
• New offers to try, three picked to go first
• Three offer image ads in two sizes, with one offer block
• An ad rules check with a rewrite for anything that fails

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 are running a sale or a bundle and want image ads that show it clearly.

• Brand file. Your offers, prices, terms and claims, each tagged with where it came from on your site.
• Offer finder result. Your live offers, clashes between them, new offers from your stock, and three picked to try first.
• Offer block. One short set of offer facts that every ad repeats the same way.
• Three offer image ads. Three ads on one offer, each with its own look and a layout for each of two sizes.
• Ad rules check. A verdict, each finding with a rating and fix, and a rewrite of the ads with fixes in.
• 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 Eugene Schwartz and Alex Hormozi 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 price, deal and claim with where it came from.
• Finds offers to try. Uses the offer finder skill to copy down what is live, flag clashes, turn your stock into new offers and pick three to try first.
• Plans three offer ads. Uses the offer image ad planner to split the offer into its parts, write one offer block and lay out each ad for its own size.
• Checks the ads against Meta rules. Uses the ad rules checker to rate each finding, give a verdict and rewrite the ads with the fixes 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 offer-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/offer-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

• Your website, as a link or saved pages
• Your current prices, deals, bundles and what you have in stock
• Real product photos
• Your target countries, for the ad rules check (optional)

Helpful context (optional)

• Your price list, with renewal prices and any text sign-up terms
• Your stock levels, so new offers use stock you actually have
• Your checkout page, so the ads match what a buyer sees there

Tools and access

• Claude: Holds your brand file, price list and four steps of work in one run.
• Meta Ads Manager: Its preview shows where the text above the image gets cut off.
• Any good chat AI: This is careful reading and plain writing, so Claude, ChatGPT or Gemini all do it well with a full brand file.
• Google Sheets: Works out price per day, per pack and cost per order with formulas you can check.
• GPT Image: Sets short price lines better than older models, and you can point at one wrong digit to fix it.
• Nano Banana: Takes up to 3 style references and is built for brand consistency, so each of the three looks stays on brand.
• Meta Ads Manager: Its safe zone guardrail marks where the app's buttons may cover a 9:16 ad, so you can check the offer block stays clear.
• Any good chat AI: Claude, ChatGPT and Gemini all read the rule table well; what matters is pasting the ad exactly as it will run.
• Meta Ads Manager: Its rejection notice and Business Support Home give the reason for each rejected ad, so you can test the skill against real decisions.

Functions and deliverables

• Meta offer image ad planner: Share website facts, real prices and product photos. Get offer ideas, three image-ad plans and a first-pass Meta rules review.
  • A brand file with your offers, prices and claims word for word
  • Clashes between your live offers, flagged
  • New offers to try, three picked to go first
  • Three offer image ads in two sizes, with one offer block
  • An ad rules check with a rewrite for anything that fails
• New offer opportunity finder: Paste your prices and deals. Get clashes flagged and new offers to try first.
  • Your live offers, quoted in your own words
  • Every clash between pages, and the figure to use until you fix it
  • A short list of what you already own that could become an offer
  • New offers, each with plain terms, the buyer it suits and what you'd need to set up
  • Three offers to try first, with the reason for each
  • Any of the prompt's seven checks it still missed, one line each, or none
• Three-way offer image ad planner: Plan three offer image ads in feed and story sizes, one for price, one for the safety net, one for why start now, with one shared offer block.
  • One offer block, the same on every ad, with where each line came from
  • Six ads per product (3 ways x 2 sizes), each with layout, colours, photo and every line with its source
  • A contact-sheet test, so you know the three ads look different
  • What to change when the offer changes
  • Any of the skill's five checks the set still misses, one line each
• Meta ad policy checker: Share ad copy, images or a script. Get possible policy issues, a custom score and changes to review.
  • A verdict (ready to run, fix first, or likely rejected) and the main reason
  • A compliance score out of 100, now and after the fixes, with the sum shown
  • A table of findings with the rule group, the exact spot, the problem and the fix
  • Settings to change outside the ad, such as age targeting
  • Your ad rewritten with every fix in, changed lines marked
  • What passed, and what it couldn't check without more information
• 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
• Alex Hormozi: Improve an offer, price or lead plan using Alex Hormozi’s recorded frameworks. Check buyer needs, costs and honest promises before adding more leads.
  • Your problem worked on the way Alex Hormozi would: their questions, their method, their push-back
  • The answer or the work, in Alex Hormozi'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 are running a sale or a bundle and want image ads that show it clearly.
• You have more than one offer live and suspect they confuse shoppers.
• You want new offers to test, each with ads ready to go.

Limits to check before starting

• You have one price and no offer to test: use the Single image ad planner for one plain ad.
• You have no ad copy yet and want words first: use the Fact-based ad copy writer, then come back.
• You already have finished ads and only want a rules check: use the Meta ad policy 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".
• Have your inputs ready. Your website link, your prices and deals as they stand, and your product photos.
• Answer the one check-in on the brand file, then pick the offer you want ads for.
• Make the pictures with your image tool, and fix anything the ad rules check marks "Fix first".

Read it as data

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