Hire an AI image ad launch reviewer

Everything it can hand back

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

• A score out of 100 with fixes and two rewrites
• The ad's awareness stage, where it does not fit the buyer, and a rewrite for each mismatch
• A pass or fail on attention, gain, proof, case and ask, with fixes in order
• A stop-ship verdict with each fix and a score

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: You have an image ad ready and want it checked before launch.

• outputs/step-01-static-ad-critic.md. The side chosen, eye path, picture and headline pair test, phone view, a score out of 100 and two rewrites.
• outputs/step-02-ad-awareness-stage-checker.md. The awareness stage of the hook, picture and copy, any mismatches, a score and a rewrite for each mismatch.
• outputs/step-03-five-part-ad-checker.md. A pass or fail on attention, gain, proof, case and ask, with fixes ranked from the earliest failing part.
• outputs/step-04-pre-launch-ad-checker.md. The stop-ship check on claims, brand details and sizes, with each fix, a verdict and a score out of 100.
• 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 Victor Schwab would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Critique the ad. Picks a side, traces the eye path, swaps the picture or headline to test the pair, checks the phone view, scores it and writes two rewrites.
• Match it to the buyer's awareness. Classifies the hook, the picture and the copy by awareness stage, checks they agree and keep to one stage, and writes a rewrite for each mismatch.
• Check the five jobs of the ad. Quotes where attention, gain, proof, case and ask sit, scores each for 20 points and ranks the fixes with the earliest failing part first.
• Run the stop-ship check. Checks claims, brand details, sizes and platform rules on the fixed ad, then gives each fix, a verdict and a score.

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 fix-a-static-ad-then-clear-it-to-run 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/fix-a-static-ad-then-clear-it-to-run/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 static ad image
• Its copy (headline, primary text and call to action)
• Where it will run, such as Facebook feed or Instagram story (needed for the last check)
• The page it sends people to (optional)
• Your product facts and brand file (optional)

Tools and access

• Any good chat AI: Any current chat AI that reads images can run the checks. Attach the ad as a file.
• Meta Ads Manager: Where you test the two headlines side by side.
• Any good chat AI: Any current chat AI that reads images and video can do this. Attach the file itself.
• Meta Ads Library: It lets you see competitor ads and judge their stage the same way.
• Any good chat AI: The work is sorting and writing from facts you supply, which any strong chat AI does well with this skill.
• 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 launch reviewer: Review a finished image ad, rewrite its pitch for the buyer and check the actual revised ad before launch.
  • A score out of 100 with fixes and two rewrites
  • The ad's awareness stage, where it does not fit the buyer, and a rewrite for each mismatch
  • A pass or fail on attention, gain, proof, case and ask, with fixes in order
  • A stop-ship verdict with each fix and a score
• Image ad reviewer: Check your static ad before you spend. Attach the image, headline and primary text. You get a score out of 100, ranked fixes and two rewritten headlines.
  • A score out of 100 across nine checks, now and after the fixes, with the sum shown
  • A clarity-or-curiosity verdict, with the middle zone flagged
  • The eye path: what is seen first, second and third
  • A ranked list of fixes, a note on the page match and two rewritten headlines, one clear and one curiosity-led
• Ad awareness stage reviewer: Check your ad's awareness stage. Attach the ad and get a score out of 100, the clashes between image and copy, and rewrites to fix them.
  • The stage of each ad, with the evidence
  • Mismatches between image, copy and video
  • A score out of 100, with each part shown, and rewrites
  • A mix check against the target split, if you gave your other ads
• Five-part ad checker: Paste your finished ad. Get a pass or fail on its five jobs, a score and ranked fixes.
  • A pass or fail on each of the five parts, with the quoted text
  • A score out of 100
  • A verdict on length for this product
  • Fixes in the order that pays
• 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
• Victor Schwab: Review ad headlines and openings using Victor Schwab’s recorded approach. Name the reader, support the promise and plan how to track responses.
  • Your problem worked on the way Victor Schwab would: their questions, their method, their push-back
  • The answer or the work, in Victor Schwab'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 an image ad ready and want it checked before launch.
• An image ad is getting clicks but few sales and you suspect the pitch.
• You have several drafts and need to pick one to fix.

Limits to check before starting

• You only have copy and no finished image: write the picture first, then come back. For a quick single critique, run the Single image ad planner on its own.
• You want to check a Meta ad against policy rules only: use the Meta ad policy checker.
• You want a final stop-ship check and nothing else: use the Pre-launch ad 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".
• Attach the final image, not a sketch, and paste the exact copy.
• Give only facts you can prove. The rewrites never add numbers you did not supply.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/fix-a-static-ad-then-clear-it-to-run 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.