Hire an AI advertorial claims and story reviewer

Everything it can hand back

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

• A one-line big idea, ranked pain points, a root cause, a named mechanism and a why-now line
• A list of claims that still need proof before the page goes live
• A story-led advertorial with an ad label, a button plan and an image list
• Every spot where the story turns into a pitch, with a rewrite, and a story score out of 100
• A proof map and a 30-point page check with a score out of 100

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: Your ads send cold visitors to a page that does not explain the product well enough to sell it.

• Big idea and mechanism. Ranked pain points, a one-line big idea, a root cause, a named mechanism, a why-now line and claims needing proof.
• Advertorial draft. A long story-led page with an ad label, a button plan, a testimonial table and an image list.
• Story and belief check. Each sentence where the story turns into a pitch, with a rewrite, plus eight checks and a score out of 100.
• Proof placement. Real reviews matched to the doubts in the draft, a layout map and a list of proof it dropped.
• 30-point page check. A short verdict, 30 checks with evidence, the five fixes to make first 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 Robert Cialdini and Clayton Makepeace would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Big idea and mechanism builder. Lists what is truly unique about the product, ranks the pain points, names a mechanism that matches what the product does, writes the why-now and lists claims needing proof.
• Store advertorial writer. Writes a long page for one named person from the big idea, with the pains, the mechanism, two closing options and an image list.
• Advertorial story and belief checker. Marks every sentence where the story turns into a pitch, checks the mechanism, the risk and the honesty, and rewrites the weak spots for you to apply.
• Store social proof placer. Matches each real review or press quote to a doubt in the draft, puts proof where readers hesitate and lists what it dropped. It works on the page with the rewrites applied, and you apply its proof map.
• Landing page 30-point checker. Runs 30 yes-or-no checks on the finished page and lists the five fixes to make first. It checks the page with the rewrites and proof applied.

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 write-an-advertorial-that-turns-cold-traffic-into-sales 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/write-an-advertorial-that-turns-cold-traffic-into-sales/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

• Product facts, such as parts or materials, how it works, price and guarantee
• Customer reviews or support questions, each with its source
• Three to five rival products and the claims they make (optional)
• The ad that sends traffic to this page (optional)
• Proof you hold, such as studies, test results and review counts (optional)

Tools and access

• Any good chat AI: Any current chat AI can run the steps. One that can read many reviews at once helps with the pain ranking.
• Any good chat AI: Any current chat AI can write the page in sections. One with a long context window keeps the whole page in view.
• Shopify: A custom Liquid or custom HTML section in your theme can hold the page copy, so it lives on your own store.
• Any good chat AI: Any current chat AI can run the checks. Attach screenshots as files for the button and image checks.
• Any good chat AI: Any current chat AI can sort reviews by doubt and buyer type. Paste reviews with their source.
• Shopify: Your theme's review and testimonial sections can show an open grid in place of a carousel.
• Any good chat AI that reads images: It can judge the first-screen and phone checks from your screenshots instead of guessing from text.
• PageSpeed Insights: Free from Google. It gives the phone speed numbers check 30 needs from just the page's address.

Functions and deliverables

• Advertorial claims and story reviewer: Share product facts, reviews and supporting evidence. Get an advertorial draft, story fixes, proof placement and a structured page check.
  • A one-line big idea, ranked pain points, a root cause, a named mechanism and a why-now line
  • A list of claims that still need proof before the page goes live
  • A story-led advertorial with an ad label, a button plan and an image list
  • Every spot where the story turns into a pitch, with a rewrite, and a story score out of 100
  • A proof map and a 30-point page check with a score out of 100
• Product message and explanation planner: Share product facts, buyer words and rival claims. Get a central sales idea, a clear product explanation and claims needing proof.
  • Ranked pain points, with the one to lead with
  • A one-line big idea and a root cause as a picture the buyer already holds
  • A mechanism name, how it works in two lines, and the specs behind it
  • A why-now line and a list of claims that still need proof
• Store advertorial writer: Write a story-led advertorial for your store that continues your ad and is labelled as an ad. Give it your angle, facts and buyer doubts.
  • Advertorial copy in section order, with an ad label and an honest author line
  • The pains and desires used, and where each one repeats
  • A testimonial-to-objection table and a button plan
  • An image list with each image tied to its paragraph, and a list of claims to check
• Article-style ad story checker: Share an article-style ad draft. Get story breaks, missing reasons to believe, targeted rewrites and a checklist score.
  • A list of sentences where the story turns into a pitch, with a rewrite for each
  • A pass, part or fail for each of eight checks
  • Button and image fixes
  • A score out of 100 with the sum shown, and the fixes in order
• Store testimonial placement planner: Share customer concerns and reviews. Choose credible evidence for each concern and decide where it belongs in your store.
  • A proof list matched to each doubt and buyer group
  • A layout map showing where each proof item sits
  • Hot-spots where proof goes first
  • A list of proof dropped as not real, not sourced or not similar to the buyer
• 30-point landing page checker: Share your page and screenshots. Get a 30-point audit, a score and five fixes to make first.
  • A two-line verdict naming the stop where the page loses buyers
  • All 30 checks with yes, no or can't tell, the evidence and a one-line fix
  • A count of no's at each stop, so you see where the trouble clusters
  • The five fixes to make first, deal-breakers at the top, and what it couldn't judge
  • A checks score out of 100 (the share of checks the page passes), now and with the five fixes made
• 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
• Robert Cialdini: Review a pitch, page or request using Robert Cialdini’s recorded principles. Use real proof, honest expertise and genuine limits without pressure or tricks.
  • Your problem worked on the way Robert Cialdini would: their questions, their method, their push-back
  • The answer or the work, in Robert Cialdini's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Clayton Makepeace: Plan or review a sales page using Clayton Makepeace’s recorded approach. Understand the reader’s concern, outline the argument and find proof for claims.
  • Your problem worked on the way Clayton Makepeace would: their questions, their method, their push-back
  • The answer or the work, in Clayton Makepeace'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

• Your ads send cold visitors to a page that does not explain the product well enough to sell it.
• Your product needs explaining, such as a new type of product or one with a real mechanism.
• Your ads get clicks from people who do not know the problem your product solves.

Limits to check before starting

• You have no customer reviews yet: write a plain product page with the Ad-matched landing page writer, then collect reviews first.
• You want a short page that matches one ad: use the Ad-matched landing page writer.
• You sell a product that needs health claims checked by a rules expert: get a compliance review first, then come back.

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".
• Paste your product facts and reviews. Add rival claims if you know them.
• Read the big idea after step 1. Everything is written from it, so change it now if it feels wrong.
• Find proof for every claim on the list, then make the five fixes the last check gives.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/write-an-advertorial-that-turns-cold-traffic-into-sales 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.