---
name: google-merchant-center-operations
description: Reviews a connected product feed for disapprovals, missing attributes and quality gaps, prioritizes fixes by revenue exposure, and proposes feed corrections for approval. Use when the user asks about Merchant Center, product feed health, disapproved products, or shopping eligibility.
metadata:
  version: "1.1.1"
---

# google-merchant-center-operations

> **Client-neutral reusable package.** No client names, tenant or workspace identifiers, account or
> resource IDs, customer records, credentials, or internal paths. All examples are synthetic.

| | |
|---|---|
| Live catalog name | Google Merchant Center Operations |
| Live category | Advertising & Commerce |
| Catalog entry | 2 |
| Internal capability ID | `CAP-PM-03` |
| Provider | Google Merchant Center |
| Availability | Candidate; validate in the active Workspace |
| Deliverable type | `client_ready_guided_skill` |
| Validation status | Candidate; local package validation only |
| Version | 1.1.0 |


## OLLIE Runtime integration

Use this capability under the active OLLIE Operator. Read live Workspace Context and tenant
bindings for the required inputs below; this public package supplies no client facts or authority.
Consume `ask-ollie-authority-core` for authority, `outloop-access-fallback` for recovery and
resource verification, `email-lifecycle-core` for recipients, approvals and stored-copy delivery
verification, and the bootstrapper Runtime Contract for ownership, scheduling and completion.
These owners govern execution; this Skill does not implement a competing runtime.

Select the relevant expertise below for the requested outcome. Runtime governs combining Skills,
partial use and completing missing steps with other authorized capabilities. This Skill's domain
scope does not limit the Operator's wider authorized task. Preserve domain safety restrictions.
Verify findings against source evidence and read back any resulting artifact or authorized change.

## Business outcome

Products that should be earning impressions are eligible, and feed problems are ranked by what they actually cost.

## Operating modes

Read · Analyze · Draft

## Prerequisites — what must be true before this runs

- Workspace Context
- An approved Merchant Center grant
- A validated connector setup for this specific account

## Required inputs

| Input | Source |
|---|---|
| Approved merchant account identifier | Workspace configuration |
| Product catalogue and feed source | Workspace configuration |
| Target markets and languages | Workspace Context |
| Margin or priority data where available | Optional — improves ranking |

## Proven scope

This version provides feed audit and diagnosis guidance; it does not enable feed writes. Connector setup is
still validated per account and never assumed — a merchant account reachable in one workspace tells you
nothing about another. Verify the account identity for this workspace before the first read.

## Cluster before you list

A feed with 4,000 disapprovals rarely has 4,000 problems. Group by root cause first — one missing attribute
on a template, one category mapping, one policy trigger — and report the handful of causes. An item-by-item
list is a data dump, not an analysis.

## Action classification

| Action class | This workflow |
|---|---|
| Read | Account-level status, product statuses, item-level issues, feed processing results, shopping eligibility |
| Analyze | Disapproval clustering by root cause, missing and weak attributes, title and category quality, revenue exposure per issue |
| Draft | A prioritized remediation plan naming the field, the current value, the corrected value and the reason |
| Write with approval | **Not enabled in this version.** Feed corrections are handed to the feed owner |
| Destructive | None |

## Approval and delivery

The Operator applies Authority Core and the active Workspace approval policy to any requested
mutation. Email Lifecycle owns recipient classification, sending and stored-copy verification.
The action table defines this capability's domain scope; it grants no permission by itself.

## Expected output

A feed health report: disapprovals grouped by root cause rather than listed per item, a ranked remediation plan, and an eligibility summary per target market.

## Synthetic placeholders used in this package

These are illustrative only. Real values come from the client's own workspace configuration and are
never written back into this package.

| Placeholder | Meaning |
|---|---|
| `MERCHANT_ACCOUNT_PLACEHOLDER` | Approved merchant account |
| `FEED_PLACEHOLDER` | Configured product feed |