Hire an AI low-response ad repair planner

Everything it can hand back

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

• A finding on each of seven checks, with the evidence, and causes ranked by likelihood and cost
• What your winners share, found from your own results
• A fixed version with a change list beside each cause, and a new key
• A ready-to-send check with a ship, fix or rewrite call
• A split-run test plan of old against new

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: An ad, email or page is seen but not answered and you want to know what to change first.

• Step 1: Likely causes. A finding on each check, with evidence, and causes ranked by how likely and how cheap to fix.
• Step 2: Winners and losers. What your better ads share that your weaker ads lack, and a rule to test.
• Step 3: Fixed ad. The full fixed ad, a change list beside each cause, what was left alone, and a new key.
• Step 4: Ready check. A ship, fix or rewrite call, a score, and the three fixes that matter most.
• Step 5: Test plan. One difference between old and new, a code on each, a winner rule and a read date.
• Hand-back summary. Each step's file, any step not run and why, and every missing item 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 John Caples and Eugene Schwartz would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Find the likely cause. Checks the ad is counted, reads the headline alone, then checks the appeal, belief, offer, reply path and place. Ranks causes by likelihood and cost.
• Compare your winners with your losers. Ranks your ads on a fair number, fills in a checklist for each and finds what the winners share. Checks the pattern is not just a place or season.
• Write the fixed ad. Fixes the top three causes with one change each and keeps the rest. Moves the winning reason into the headline, puts the offer where it is seen, makes the reply easy and swaps vague words for facts.
• Check the fixed ad is ready. Checks the opening names the reader and their gain, claims are specific and believable and the next step is clear. Gives a ship, fix or rewrite call.
• Plan the test of old against new. Runs old and fixed at the same time with a code on each, a reply target and a winner rule set before launch.

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 ad-not-working-fix 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/ad-not-working-fix/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

• The ad as the reader sees it, including the reply path
• Results for the ad over a set start and end date, and for your other ads if you have them
• Your offer and what counts as a reply (optional)

Helpful context (optional)

• Results for the same ad in other places
• Results for your other ads, with their text
• The exact code or link tag on each ad

Tools and access

• Any good chat AI: Reading, weighing causes and rewriting are text jobs a strong chat AI does well in one run.
• Your ad platform or email tool: Exports replies by ad and runs the split test.
• Any good chat AI: Reading an ad and weighing causes is text work any strong chat AI does with this skill.
• Your ad platform or email tool: Exports replies by ad for the results input.
• A spreadsheet: Holds the checklist as a table and counts values for each group.
• Your ad platform or email tool: Exports replies and spend by ad.
• Any good chat AI: Rewriting to a short list of causes is text work any strong chat AI handles with this skill.
• Any good chat AI: Any current chat AI can run the 12 checks. Paste your facts so the facts gate can mark items held.
• Hemingway Editor: Gives a reading grade and marks hard sentences, so you can confirm the two measures.
• Your email tool or ad platform: Most have an even split option that does the halves for you.
• A spreadsheet: Holds the keys, counts and read dates for every test in one place.

Functions and deliverables

• Low-response ad repair planner: Review a weak ad against its results and your past ads. Get ranked likely causes, a revised draft, readiness checks and a test plan.
  • A finding on each of seven checks, with the evidence, and causes ranked by likelihood and cost
  • What your winners share, found from your own results
  • A fixed version with a change list beside each cause, and a new key
  • A ready-to-send check with a ship, fix or rewrite call
  • A split-run test plan of old against new
• Ad response troubleshooter: Find why your ad gets few replies. Paste the ad and your results to get likely causes ranked, with the cheapest fix first.
  • What a stranger would say the headline offers
  • A finding for each of seven checks, marked fine, suspect or broken, with its evidence
  • Causes ranked by likelihood and cost to fix
  • What it could not judge and what would settle it
• Ad results comparison analyst: Find what your best ads have in common. Give it results for five or more ads and get them ranked, with a rule to test and the counts behind it.
  • The ads ranked on a fair number
  • A completed checklist for each ad
  • What the winners share, with counts for winners and losers
  • A check that the pattern is not a place or season effect
  • A rule to test and a lesson record
• Ad response copy editor: Fix a weak ad: paste it with its diagnosis and get a new version that changes only the top three causes, with a change list to test.
  • The fixed ad in full
  • A change list with each change beside the cause it answers
  • A list of what was not touched and why
  • A new key for the fixed version
• Sales copy readiness checker: Check your sales copy before it goes out. Paste the finished piece and your facts. Get ship, fix or rewrite, up to three fixes and a score.
  • A verdict, blocked, rewrite, fix or ship, with the part or lines named
  • Every number and claim marked held, contradicted or unverified
  • The reading grade and the longest sentence, against a target
  • Twelve yes or no answers, each with the line behind it, and up to three fixes
  • A readiness score out of 100 (the share of the 12 checks and 2 measures it passes), now and with the fixes made
• A/B test design planner: Plan a fair split-run test of two ads, emails or pages. Get one change, a key on each, the audience size and a winner rule.
  • The one difference being tested
  • What must stay equal and how the audience is split
  • A key (code) for each version
  • The audience size needed, with the sum shown
  • A winner rule with a read date, plus a plan for more than two versions
  • The traps to avoid
• 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
• John Caples: Write headlines and plan a fair ad test through John Caples’s recorded approach. Lead with the reader’s gain and count replies by version.
  • Your problem worked on the way John Caples would: their questions, their method, their push-back
  • The answer or the work, in John Caples's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• 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

Tasks you can use it for

• An ad, email or page is seen but not answered and you want to know what to change first.
• You have a list of ideas for what is wrong and no order to try them in.
• You want to fix the cheapest likely cause before you redesign anything.

Limits to check before starting

• You have no ad yet: write one first with the Fact-based ad copy writer, then come back to fix it.
• You want to know why sales dropped overall, not why one ad gets no replies: use the Ad sales drop analyst.
• You only want the likely causes, with no rewrite or test: run the Ad response troubleshooter 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.

• 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".
• Give it the ad and your results. Add the results for your other ads if you have them.
• It works step by step and saves each result. Read the ranked causes before the fixed ad.
• Run the test it plans, then read the result with "Test two ads head to head and read the winner".

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/ad-not-working-fix 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.