Update to Adzviser Shopify

{
  "description": "Retrieve and analyze reporting from the user's connected Shopify stores with Adzviser. Use for sales, orders, items, product rankings, channel comparisons, trends, raw rows and Data Mode. This plugin does not modify stores, process refunds, place orders or send messages.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 245
    }
  ],
  "name": "adzviser-data-mode",
  "skill_md_contents": "---\nname: adzviser-data-mode\ndescription: Retrieve and analyze reporting from the user's connected Shopify stores with Adzviser. Use for sales, orders, items, product rankings, channel comparisons, trends, raw rows and Data Mode. This plugin does not modify stores, process refunds, place orders or send messages.\n---\n\n# Shopify Data Mode\n\nUse `retrieve_reporting_data` for reporting and analysis. Open an interactive\npreview only when the user explicitly requests one. Do not follow a successful\ndirect retrieval with a widget merely to display the same request.\n\n## Build a minimal report\n\n1. Call `list_workspace` and select the user's named Shopify workspace. If access\n   is unavailable, explain that rather than substituting another store. If no\n   workspace is named and several choices remain, ask which to use.\n2. Call `list_metrics_and_breakdowns_shopify` and use exact returned field names,\n   including capitalization. Request only the fields necessary for the question.\n3. Resolve inclusive YYYY-MM-DD date pairs from the current date. Last month is\n   the previous complete calendar month; last week is the previous complete\n   Monday-Sunday week unless otherwise specified. Use the store's reporting\n   timezone. Put comparison periods in separate date-range pairs in one request.\n4. Send `adzviser_request` with `workspace_name`, `date_ranges`, optional\n   `time_granularity`, and `assorted_requests.shopify_request` containing `metrics`\n   and optional `breakdowns`. No other source keys are supported by this plugin.\n5. Inspect `structuredContent.reportingData.Shopify.data`, a header row followed\n   by data rows, and surface relevant `note_of_assumption` values. Use the actual\n   headers and shape returned, not hard-coded column positions from an example.\n6. Answer from the rows with the requested figures, exact dates and material\n   limitations. Reuse successful results instead of repeating identical queries.\n\nNever send conversation history, the raw user prompt, unrelated context,\ncredentials, session tokens or arbitrary destinations as reporting inputs.\n`reporting_mode=data` selects this workflow; it is not a tool argument. Do not\nsend `client_id`, `reporting_mode` or `_widget_action`. `set_reporting_mode` is an\napp-only preference control. Do not invent report filters, sorting or limits;\nsort and aggregate the returned rows when required.\n\n## Interpret sales carefully\n\n- Gross sales, Net sales and Total sales are different metrics. Use the measure\n  requested and name it explicitly. If \"revenue\" is ambiguous, clarify or state\n  the sales measure used. Do not describe sales as profit or cash collected.\n- The connector defines Net sales as Gross sales minus Discounts and Returns;\n  Total sales also incorporates Shipping, Tax and Duties. These component columns\n  may be returned automatically. Preserve their signs and the returned derived\n  metric; do not subtract a return twice or add components to Total sales again.\n- Include Currency for monetary reports and keep currencies separate. Literal\n  \"None\", null and blank values mean missing currency. Label those amounts as\n  currency unspecified, show them separately, and do not assume USD or include\n  them in a currency-labelled grand total. Explain that a named-currency subtotal\n  is not necessarily the complete store total. Negative sales values can occur.\n- Product ID with Product title distinguishes products. For a top-products\n  question by quantity, request Items and these identifiers, aggregate by ID,\n  and sort the returned item counts. Do not request money or customer fields\n  unless needed. Explain ties, and distinguish reported Items from Orders.\n- Missing product IDs/titles form an unidentified group; do not invent a product\n  name or silently merge them into a named product. Show that group separately\n  from a ranking of identifiable products. Preserve unknown channel groups too.\n- Orders is a count, not the number of line items. An order can contain several\n  products, so summing order counts across product groups can double count.\n  Customer count is not interchangeable with Orders or Items.\n- Report grouping can affect which adjustments are attributable to a product or\n  channel. Do not assume independently grouped reports reconcile; compare the\n  actual rows and disclose a discrepancy instead of altering numbers to fit.\n- Use `time_granularity` for Date, Week, Month or Quarter. Do not add time labels\n  to breakdowns. Keep missing dates distinct from returned zero values.\n- Calculate percentage changes only when the earlier period is a meaningful\n  nonzero baseline. Separate missing-currency amounts; do not calculate a\n  currency-specific change from rows whose currency is unknown. Round displayed\n  money only after calculations.\n- Historical inventory must not be inferred merely from a report's date range.\n  Describe inventory according to what the actual tool response establishes.\n- Avoid customer emails, names, phone numbers, addresses, order notes and other\n  personal fields for aggregate sales reports. Request any sensitive field only\n  when necessary for the user's specific authorized reporting task.\n\nFor unsupported fields, refresh discovery, correct the request once and retry.\nExplain authentication, timeout or access errors without inventing a successful\nreport. A successful empty report means no returned rows, not proven zero sales.\n\nThis connector retrieves reports; it cannot refund or cancel orders, change\nprices or stock, edit or delete products/customers, place purchases, or send\nmarketing emails. Explain unsupported actions without pretending a report\nperformed them or invoking unrelated tools to simulate success.\n"
}