Hire an AI Amazon margins, stock and claim review

Everything it can hand back

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

• Profit per unit and the most each product can pay for ads per sale, against last month
• One path per product, from margin fix, listing refresh, ad rebuild or hold
• Restock sizes and send-by dates
• Refund claims with the proof for each

How it does the job well

• Work from the real catalogue, prices, stock and policies. Check variants and currencies.
• Judge changes by contribution margin, not revenue alone.
• Change one thing at a time on a live store and keep a way to roll back.
• Keep product claims consistent with supplier data and labels.

Mistakes it avoids

• Using old fee tables as if they were current.
• Raising a price in the same month as a listing change, so the effect can't be told apart.
• Rebuilding ads for a product that is out of stock.
• Treating one slow month as a trend. Use four weeks.
• Editing live products, prices or themes without approval or a backup.
• Ignoring shipping, returns and fees when judging profit.

What a good result looks like

An example, not your task: You sell on Amazon and want the same checks every month.

• The month. Units, net margin after ads and ad cost per sale for each product, against last month.
• Path per product. One choice per product: margin fix, listing refresh, ad rebuild or hold, with the reason.
• Actions to approve. Up to ten actions ranked by money, each with its product, size, source step and reason.
• Restock. Units to send, send-by date and cash tied up for each low-stock product.
• Claims to file. Each refund claim with its type, amount and the proof you have.
• Watch next month. One to three numbers that decide next month's path.

How the work is checked

• Every margin call uses this month's fee figures, and says where they came from.
• No price rise is proposed without the skill's test plan.
• No listing or ad action is proposed for a product that is out of stock.
• No claim is listed without the proof it needs, or it says proof is missing.
• 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

• Check each margin. Works out profit per unit with this month's fees, and the most each product can pay for ads per sale.
• Choose a path per product. Margin fix if net margin is under the floor or fell a lot. Listing refresh if sales fell and margin is healthy. Ad rebuild if ad cost is above what the product can pay. Hold otherwise.
• Size the restock. Sizes how much to send and when for any product with about three months of stock or less, counting stock on the way.
• Look for money owed. Checks units sent against units received, size tiers, fee lines and lost or damaged stock, and lists claims with proof.
• Hand back one list. Merges every action, ranks it by money and stops for your yes.

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 amazon-monthly-account-keeper 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/amazon-monthly-account-keeper/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

• Price, landed cost, size and weight for each product, the first time
• The month's fee, sales, ad and returns reports
• Stock in Amazon, stock on the way and your maker's lead time
• Shipment records and receipts, and a keyword export if a listing needs work (optional)

Helpful context (optional)

• Maker receipts, packing lists and bills of lading for each shipment
• A keyword export for any product whose sales fell

Tools and access

• Claude Code: It can keep the amazon folder, read last month's files and run on a schedule.
• Seller Central: Download fee, returns, shipment, damaged and lost, and sales reports here.
• Seller Central revenue calculator: Amazon's own calculator gives the current referral fee, pick and pack and storage for your size and weight.
• A spreadsheet: Lets you save the sum and test price changes quickly.
• Any good chat AI: It only needs to solve one equation and compare the answer with the market.
• Google Sheets: Put the waterfall in a sheet so you can change CAC and see the price move.
• Seller Central: Where you create the shipment, print box labels, track receiving and read current fee tables.
• Your carrier's pickup booking: A printed label does not book a pickup. You must book the collection with your tracking number.
• Seller Central reports: Where the shipment, fee, returns, damaged and lost, and storage reports come from. Check which are available to you.
• A spreadsheet: Keeps the claim log with dates, amounts and results.
• Helium 10: Its keyword finder and reverse ASIN lookup export the volume, competing products and keyword sales columns the filters use. It has a free tier, so check current limits.
• Any good chat AI: Reads a long export and marks each phrase use or drop.
• Seller Central: Where you paste the listing, pick the category and set the offer start date. Its category style guides show current title limits.
• Any good chat AI: Writes and trims the copy from your facts and keyword tiers.
• Amazon Advertising console: Where you build the campaigns, read the live suggested bids and pull the advertising reports.
• Helium 10: Exports for keywords and competitor ASINs. It has a free tier, so check current limits.

Functions and deliverables

• Amazon margins, stock and claim review: Review Amazon reports for margins, restock needs and possible claims. Get a ranked action list using current fees and supporting records.
  • Profit per unit and the most each product can pay for ads per sale, against last month
  • One path per product, from margin fix, listing refresh, ad rebuild or hold
  • Restock sizes and send-by dates
  • Refund claims with the proof for each
• 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
• Minimum viable price calculator: Share costs, sales targets and acquisition spend. Calculate the lowest viable price or identify a product that cannot pay.
  • The lowest viable price
  • A bottom-to-top price table at low, mid and high CAC
  • A keep, reprice, reposition or cut call, with the reason
  • A list of checks it could not finish
• Amazon inbound stock planner: Give it sales, lead times and case sizes. Get how much to send, when, and a shipment checklist.
  • Units to order and to send now, with a re-order date
  • A shipment set-up checklist with label checks
  • A tracking and discrepancy sheet
• Amazon reimbursement claim finder: Find Amazon reimbursement claims you can file. Give it 90 days of shipment and fee reports. You get a readiness score and a list of claims with proof.
  • A claim-readiness score out of 100, with each part shown
  • A list of claims to file, with the proof for each and the amount at stake
  • A monthly check routine and a claim log
• Amazon keyword picker: Give it your product and a keyword export. Get the phrases for your title, bullets and backend.
  • A tiered list with main phrase, secondary phrases, phrases for bullets, backend-only phrases, each with its volume
  • Phrases dropped as too broad, too generic, brand names or untrue
  • An ad-ready list for manual campaigns
• Amazon listing writer: Write an Amazon listing from your product facts: a title with the main phrase first, five benefit bullets and backend keywords, ready to paste.
  • A title with the main phrase first
  • Five benefit-first bullets, the last one a plain money-back note
  • A short description, a backend keyword list, and notes on category, price and launch date
• Amazon Sponsored Products ad planner: Share product profit, keywords and budget. Get three Amazon ad campaign plans with bids, excluded search terms and stop rules.
  • A plan with campaign and ad group names, match types and starting bids
  • A negative keyword list and where each applies
  • Review rules and a stop rule
• 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

Tasks you can use it for

• You sell on Amazon and want the same checks every month.
• A product's sales or margin slipped and you don't know why.
• You've never checked your shipment, fee and returns reports for money owed.

Limits to check before starting

• You have one product and only a few sales a month: run the Amazon fee and margin checker alone.
• You want it to read your live Seller Central account or live ad reports: it only works from reports you give it.
• You resell with no margin to check: ask your accountant or use a simple spreadsheet instead.

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.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to run this month's check.
• Add the seven skills it runs, or let it read each one from the site: amazon-fee-and-margin-checker, waterfall-price-setter, amazon-inbound-stock-planner, amazon-reimbursement-claim-finder, amazon-keyword-picker, amazon-listing-writer and amazon-ppc-launch-builder. Reading them from the site needs web access in your AI. If yours has none, add each skill by hand first. Without them it can only do part of the check.
• The first time, give it your product facts. It saves them and reuses them.
• Each month, download the fee, returns, shipment and sales reports for the same dates and put them in the folder.
• Read the list. Make the changes you agree with in Seller Central yourself, and file claims with the proof it names.
• Run it again on the 3rd of next month. It compares against last month's files.

Read it as data

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