Hire an AI Amazon product gap and viability reviewer

Everything it can hand back

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

• Five to ten gap ideas ranked, each with what page 1 shows now and how yours would be better
• The three ideas worth a full check, and the ones dropped, each with a reason
• A score out of 100 for the idea you pick, built from ten tests, with the weakest test named
• A go, test first or no-go call, the cheapest next test and a first order sized to your cash

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

Mistakes it avoids

• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.
• Roadmaps with dates but no owners or confidence levels.

What a good result looks like

An example, not your task: You want to sell on Amazon but only have an interest or a category, and need a product to start from.

• Gap ideas. Five to ten searched phrases that page 1 serves badly, ranked, with the one change that would beat page 1.
• Top 3 and dropped ideas. Which ideas deserve a full check, and each dropped idea with its reason.
• Verify by hand. Phrases to type into Amazon yourself, and what to look for on page 1.
• Viability score. A score out of 100 from ten tests, with the weakest test and any hard stop.
• Verdict and next test. Go, test first or no-go, a first order sized to your cash and the cheapest next test.
• Hand-back summary. Each step's file 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.
• Step 2 used the idea the person picked and the page 1 evidence from step 1.
• Nothing was invented to fill a gap. Every gap is a MISSING: line, and no volume, revenue or review figure is made up.
• Where the sources disagree on a threshold, such as the price floor, both views are shown.
• 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.

Capabilities

• Find the search gaps. Notes what you can make and what cash you have, reads your keyword and page 1 data, drops crowded niches and ranks the gaps. Names three to check and lists what to verify by hand. Hands step 2 the shortlist and the page 1 evidence.
• Pick one and get a quote. A pause. You choose one idea from the shortlist and get a supplier quote with its cost, size, weight and your selling price.
• Score the idea. Applies five hard stops that end an idea, then scores ten tests, including price band, margin, page 1 weakness, brand giants and shipping. It sizes the first order to your cash and gives a go, test first or no-go.

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 find-an-amazon-product-gap-and-check-it-will-pay 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/find-an-amazon-product-gap-and-check-it-will-pay/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

• A hobby, problem or Amazon category, and whether you will make the product or only brand it
• How much cash you can put into a first order
• A keyword tool export with monthly searches, such as one from Helium 10, which has a free tier with capped lookups (optional)
• What page 1 shows for your ideas, such as prices, ratings and review counts, pasted in (optional)
• After the pause, a supplier quote with unit cost, size, weight and your selling price

Helpful context (optional)

• Your cash limit and the most you can afford to lose on a first order
• A supplier quote with landed cost, size and weight
• A paste of page 1 for your best phrase

Tools and access

• Helium 10: A keyword and product database with a title-competition filter and reverse ASIN lookup. It has a free tier with capped lookups, so check current limits. A paid plan is optional.
• Google Trends: Free. Shows whether interest in a topic is rising before you check the same phrase on Amazon.
• Seller Central fee calculator: Amazon's own tool shows current referral and fulfilment fees for your size and weight.
• Helium 10: A keyword and product database with a title-competition filter and a reverse ASIN lookup, which the source uses. It has a free tier with capped lookups, so check current limits.
• Amazon search box: Free. Type each letter of the alphabet after your seed word to read the autocomplete suggestions.
• Helium 10: A research database with the filters the sources use (ungated, price, revenue, review count, listing age, image count). It has a free tier, so check current limits.
• Seller Central fee calculator: Amazon's own revenue calculator shows current referral and fulfilment fees for your size and weight.
• Any good chat AI: Runs the score from your pasted numbers and page 1 text.

Functions and deliverables

• Amazon product gap and viability reviewer: Review what Amazon search results miss, then score a selected idea using supplier cost, size, weight and selling price.
  • Five to ten gap ideas ranked, each with what page 1 shows now and how yours would be better
  • The three ideas worth a full check, and the ones dropped, each with a reason
  • A score out of 100 for the idea you pick, built from ten tests, with the weakest test named
  • A go, test first or no-go call, the cheapest next test and a first order sized to your cash
• Amazon product opportunity finder: Share an interest, category and any search data. Get ranked product-gap ideas and the evidence needed to test them.
  • A ranked list of 5 to 10 gap ideas, each with the phrase, the volume, what page 1 shows and the gap
  • The 3 ideas worth a full viability check, and which ideas were dropped and why
  • A short list of search phrases for you to verify by hand
• Amazon product viability scorer: Share a product idea and costs. Get a score, the weakest test and a go or no-go.
  • A score out of 100, with the points for each of the ten tests and how it was worked out
  • Any hard stop that ends the idea, and the weakest test
  • A go, test first or no-go call, and the cheapest next test
• Amazon fee and margin checker: Share price, costs, size and fee figures. Get profit per unit, break-even ad cost and a score against the source’s rules.
  • Profit per unit with every fee listed
  • Break-even ad cost per sale, a start-up cash estimate and a price check
  • A score out of 100 for how well the numbers meet the rules, with the sum shown
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.

Tasks you can use it for

• You want to sell on Amazon but only have an interest or a category, and need a product to start from.
• You have a supplier quote in hand and want to know if the margin and the competition still make sense.
• You are about to pay for a first order and want a second opinion on whether your cash can carry it.
• A product idea looks good on page 1, but you have not worked out fees, shipping and ad cost.

Limits to check before starting

• You already have a product and want fees and profit per unit. Use the Amazon seller profit calculator.
• You resell other brands through wholesale or arbitrage. The scoring covers private label only.
• You sell a service, an app or something off Amazon. Use the Target market and pricing reviewer workflow.
• You have a go and want to launch. Use the Amazon product launch preparation workflow.

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 is a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to your AI, such as Claude, and say "Follow HANDOFF.md". Use one that can read files.
• Tell it what you can make or brand and how much cash you have. Add a keyword export and page 1 notes if you have them.
• When it pauses, pick one idea from the shortlist. Check the phrase on Amazon yourself, then get a supplier quote and write down cost, size, weight and your price.
• Give it the quote. Read the weakest test before the verdict, and check current fees in Seller Central before you order.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/find-an-amazon-product-gap-and-check-it-will-pay 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.