Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Amazon Smart Pricing Pro — Protect Margin & Sales

    1

    Make Amazon pricing decisions with true unit economics, comparable offers, inventory, ads, and controlled tests.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Amazon Smart Pricing Pro — Protect Margin & Sales

    Amazon Smart Pricing Pro — Protect Margin & Sales

    Example session with this skill installed

    Evaluate this illustrative Amazon US pricing scenario for a $29.99 product. Merchant-supplied per-unit inputs: landed cost $8.00; referral fee $4.50; fulfillment fee $5.00; storage/inbound/returns/other variable cost allowance $3.00; advertising cost allocation $2.50. The current objective is at least $6 contribution per unit after these listed costs. Inventory is healthy. Two public competitor prices are $27.99 and $31.99, but pack size, delivery, coupon, and offer comparability have not been verified. Calculate current contribution, a transparent target price floor using these fixed supplied cost amounts, compare illustrative prices $29.49 and $28.99, identify fee-sensitivity caveats, and propose a reversible one-variable test with guardrails. These figures are illustrative user inputs, not live market data. Do not claim price elasticity or recommend automatic repricing.

    • Read your context and instructions
    • Compiled the amazon smart pricing

    Pricing Decision Brief — Illustrative Scenario

    Inputs: All figures below are illustrative merchant-supplied per-unit assumptions, not live Amazon data. This simple model treats the listed fees and costs as fixed across prices; actual referral fees, taxes, fulfillment costs, promotions, and other charges may change with price or product details.

    Contribution scenarios

    PriceListed costs before adsAd allocationContribution after listed costsMeets $6 target?
    $29.99 current$20.50$2.50$6.99Yes
    $29.49 scenario$20.50$2.50$6.49Yes, narrowly
    $28.99 scenario$20.50$2.50$5.99No, by $0.01

    Listed costs before ads = $8.00 landed + $4.50 referral + $5.00 fulfillment + $3.00 storage/inbound/returns/other. Under these fixed inputs, a $6 contribution target implies a simple price floor of $29.00 after the $2.50 ad allocation. This is not a validated marketplace floor: recalculate percentage-based fees, taxes, fulfillment tiers, returns, discounts, and other cost changes at each candidate price.

    Competition context

    The $27.99 and $31.99 observations are not verified like-for-like offers because pack size, delivery, coupon, condition, and offer type are unknown. Do not use them as a direct repricing trigger. Confirm each listing and date before comparison.

    Cautious test

    1. Validate all cost inputs and recompute contribution using current marketplace fee rules and actual product dimensions/weight.
    2. Confirm the competitor offer details and capture a dated baseline for price, sessions, units, conversion, ad spend, contribution, stock, promotions, and Buy Box context if relevant.
    3. If still appropriate, test only $29.49 for a pre-agreed window, keeping ads, coupons, inventory, and listing stable where possible.
    4. Maintain a $6 contribution guardrail using refreshed actual fees. Pause or roll back if contribution drops below target, stock risk changes, or unrelated conditions invalidate the comparison.
    5. Compare like periods and label results directional unless traffic and test design support a stronger conclusion.

    Confidence: LOW. No verified fee schedule, sales history, price response, or comparable-offer evidence was supplied. These scenarios do not establish elasticity or predict sales, Buy Box, profit, or competitor response.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Amazon Smart Pricing Pro helps sellers balance customer value, competitive context, true unit economics, inventory, advertising, promotions, and strategic position—without racing automatically to the lowest price. It first defines the product, marketplace, fulfillment model, objective, and price scope, then separates verified offers and seller data from third-party context, estimates, assumptions, hypotheses, and unknowns.

    The agent builds a cost and contribution model using supported landed cost, referral and fulfillment fees, storage, inbound, returns, promotions, taxes, and advertising where available. It calculates hard and strategic price floors, compares like-for-like offers only when product, quantity, shipping, and offer conditions match, and considers conversion evidence, inventory health, lifecycle, seasonality, brand positioning, and margin goals. It distinguishes Buy Box context for private-label and shared-ASIN resale models and never invents demand elasticity, competitor prices, fees, sales, or price history.

    Recommendations use transparent scenarios and reversible guardrails. Each price test includes a hypothesis, one change at a time, minimum contribution floor, monitoring window, relevant confounders, stop conditions, and rollback. Promotions and ads are included in contribution when reliable inputs exist. Observed correlation is not automatically price elasticity or causation.

    Provide marketplace, ASIN/SKU, fulfillment model, current price, complete variable costs and fees, ad and promotion economics, sales/conversion history, inventory and lead time, comparable offers, and the objective. Without these inputs, the agent labels a scenario as illustrative and identifies what must be verified. It does not change prices, operate repricers, promise sales, Buy Box, ranking, conversion, profit, or competitor response, or advise deceptive or unlawful pricing.

    Recommendations depend on accurate, current seller-supplied costs, fees, inventory, promotions, advertising, and sales data. Fee schedules and fulfillment charges can change and must be verified for each SKU and marketplace. Public competitor listings may not be comparable or current. Scenarios do not establish price elasticity or causation; outcomes depend on many factors. The skill does not access seller accounts, change prices, operate repricers, or guarantee sales, Buy Box, ranking, conversion, or profit.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Permissions

    Read Files
    Write Files
    Browser
    Network Access

    File Scopes

    *.csv
    *.xlsx
    *.pdf
    *.md
    *.json

    Use only files and Amazon seller data the user is authorized to provide. Verify current official fee and policy guidance and label competitor observations as unverified until checked. This skill provides decision support only: it does not access seller accounts, connect to repricers, or change live prices.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    It models price scenarios from your current price, verified fees and costs, advertising, promotions, inventory, objectives, and comparable offers. It calculates contribution and guardrails, and labels missing or unverified inputs. Provide current marketplace and SKU details for a useful analysis.

    No. It compares transparent scenarios and can suggest a controlled test, but a scenario does not prove elasticity or causation. Use valid sales and conversion data, define a monitoring window and contribution floor, control other changes where possible, and interpret results cautiously.

    No. The skill creates decision-support scenarios and guardrails only. It does not connect to your seller account or a repricer and cannot apply price changes. Review recommendations, confirm current fees and costs, and make any change yourself through your normal authorized workflow.

    New in E-commerce