datadoe-ai-skills

Build a self-contained, interactive Amazon Reconciliation Dashboard powered by the DataDoe MCP tools. Use when the user asks to create, generate, scaffold, or build an Amazon reconciliation dashboard, settlements dashboard, orders-vs-settlements report, or any "reconcile my Amazon orders" deliverable using DataDoe.

Build a single-page Orders Manager application powered by the DataDoe REST API. Use when the user asks to create, scaffold, or build an orders manager, orders dashboard, orders table, or order management app using DataDoe.

Recompute Sponsored Products keyword bids toward a target ACoS and apply them through DataDoe Actions - always a dryRun preview first, and a real change only on your explicit approval. The write follow-through to the wasted-spend watchdog. Live from DataDoe, runs in chat. Use for "optimize bids", "fix ACoS", "lower my bids", "raise bids on winners", "adjust keyword bids", or "bid optimization".

Audit an Amazon seller's organic and sponsored search visibility by combining DataDoe search-term data, live Amazon search results, owned-ASIN matching, screenshots, and a reusable dashboard report. Use when asked to run an Amazon ASIN/search visibility audit for a specific DataDoe seller.

Run a daily Amazon account-health check: Account Health Rating (AHR), order-defect rate, late-shipment rate, valid-tracking rate, cancellation rate and policy violations - each scored against Amazon's own target and rolled up to a single red / amber / green verdict with the exact issues to fix first. Live from DataDoe, in chat, no dashboard. Use when the user asks about "account health", "is my account ok", "AHR", "account health rating", "am I at risk of suspension", "order defect rate", "late shipment rate", "policy violations", or a "daily account check".

Generate a weekly Amazon BUSINESS review - profit, margin, ad efficiency (TACoS) and inventory - comparing this week to your trailing 4-week normal, explaining any margin/fee anomaly, and ending in concrete actions. Use for "weekly business review", "weekly profit review", "weekly P&L", "how is the business doing", "what changed and why", "is my margin or TACoS ok", "profit this week". For a quick sales-only snapshot, use the Weekly Sales Briefing instead.

Generate a structured weekly Amazon sales briefing as an interactive HTML card. Use this skill whenever the user asks for a weekly sales report, weekly briefing, weekly summary, sales overview, or any request combining "week" with sales/revenue/performance. Also trigger when the user says things like "how did we do this week", "give me the weekly numbers", "show me this week's sales", or "weekly recap". The skill fetches live data from DataDoe (production) for pointed seller and renders a polished interactive HTML card with KPIs, top SKUs, biggest drops, and AI-generated insights.

Track your money keywords week over week - organic rank and, more importantly, your share of the query (impressions, clicks, purchases) - and flag the terms slipping, lost, rising or emerging before the sales drop shows up. Watches only the keywords you convert on, so the alert list is short. Degrades to a baseline on young accounts with little history. Live from DataDoe weekly Search Query Performance, read-only. Use for "keyword rank", "am I ranking", "search visibility", "rank tracker", "did my rank drop", "SQP", "search query performance", "losing rank", or "keyword trends".

Find the SKUs bleeding the most margin to returns, why they come back (the real return reasons, bucketed into product / listing / sizing / delivery), and the fix for each - ranked by money lost, not by return rate, and filtered so you chase the actionable returns, not the noise. Live from DataDoe, read-only. Use for "returns", "refunds", "return rate", "why are people returning", "return reasons", "which products get returned", "returns costing me money", or "reduce returns".

Scan the whole catalog for the SKUs that moved the most this period - up and down - and decompose each move into its cause: traffic, conversion, price, or buy-box. Ranked by the size of the swing in money, with a data-completeness guard so a lagging recent week doesn't read as a fake collapse. Live from DataDoe, read-only. Use for "what changed", "biggest movers", "why did sales drop", "what's up this week", "sales down", "which products dropped", "what moved", or "week over week".

Scan the whole catalog for listings that are silently not selling - suppressed, inactive, stranded (stock on hand but not buyable), or carrying an error/quality issue that blocks or limits them - and rank them by the revenue at risk so you fix the costly ones first. A listing can look fine and still be invisible to shoppers; this finds those. Live from DataDoe, read-only. Use for "suppressed listings", "inactive listings", "why isn't my product showing", "listing errors", "stranded inventory", "is my listing live", "listing health", or "why did this stop selling".

Optimize an Amazon listing from your own live data, tuned for 2026 Amazon (the 75-character title cap, the COSMO intent layer and the Rufus / Alexa for Shopping assistant). It benchmarks your search funnel against the market to find whether you leak at impressions, clicks, cart-adds or purchases, separates an exposure problem from a copy problem, finds the converting themes your title forgot to say, audits intent coverage and listing health, and returns a rewritten, policy-safe, upload-ready title, bullets, backend terms and attribute fills. Live from DataDoe. Use for "optimize my listing", "listing optimization", "fix my title", "improve my bullets", "keyword gaps", "why isn't my listing ranking", "why isn't it converting", "backend keywords", "listing audit", or "is my listing Rufus ready".

Find the Amazon SKUs losing the Buy Box (Featured Offer) and the most likely reason - price vs the featured offer, out of stock, or fulfilment - so you can win it back. Live from DataDoe. Use for "buy box", "featured offer", "lost the buy box", "buy box percentage", "why did sales drop but traffic did not", or "someone else has my listing".

Break down your true Amazon net profit by SKU for any period - after Amazon fees, FBA, COGS and ad spend, not just top-line sales - ranking the real winners and surfacing the SKUs quietly losing money. Live from DataDoe. Use for "net profit", "profit by SKU", "am I making money", "which products are profitable", "profit report", "true margin", or "where am I losing money".

Find the exact Sponsored Products search terms burning budget with no sales, then add them as negative keywords through DataDoe Actions - always a dryRun preview first, and a real change only on your explicit approval. The write follow-through to the wasted-spend watchdog. Live from DataDoe, runs in chat. Use for "wasted ad spend", "add negative keywords", "negate search terms", "search terms with no sales", "stop paying for these clicks", or "clean up my PPC".

Find the exact Amazon Sponsored Products search terms wasting your ad budget - dead spend (clicks but no orders) and bleeders (converting but ACoS above your break-even) - quantify the money to reclaim, and route them to the negative-keyword and bid-optimizer skills. Live from DataDoe. Use for "wasted ad spend", "high ACoS", "which keywords lose money", "PPC audit", "where is my ad budget going", or "negative keyword candidates".

Rank the Amazon FBA SKUs about to stock out by urgency - days of supply vs sales velocity, inbound-aware - with how many units to ship and by when, straight from DataDoe's FBA Inventory Health. Live from DataDoe. Use for "restock", "what's about to stock out", "days of supply", "reorder", "low inventory", "how much to ship in", or "stockout risk".