- Home
- Skills
- E-commerce
- Merchant Center Issue-to-Feed Repair Map
Merchant Center Issue-to-Feed Repair Map
Join affected-item issue exports to a local product feed and build an auditable manual repair queue.
$7
Works with the AI Agents you already use
Merchant Center Issue-to-Feed Repair Map
Example session with this skill installed
Using the included synthetic issues.csv, feed.csv and mapping.json, run Merchant Center Issue-to-Feed Repair Map locally. Give me the review queue with source row references and explain which findings require a person to inspect Merchant Center before changing a feed.
- Read your context and instructions
- Compiled the merchant center issue-to-feed
- Generated the data export
Synthetic demonstration using the sample files included in the download. The local analyzer's checked human-readable sample report is reproduced in full below; this is not a live account check or a platform-runtime test.
Merchant Center issue-to-feed review
This is a local join of user-supplied exports, not a Google policy decision or reapproval guarantee.
Issues: 3; feed products: 2; ID mode: exact.
Classifications
- FEED_FIELD_EMPTY_CANDIDATE: 1
- FEED_FIELD_PRESENT_REVIEW_OTHER_CAUSE: 1
- FEED_ID_NOT_FOUND: 1
Next checks
- Confirm issue export and feed represent the same product-data snapshot and target country
- Inspect source rows and fix only after checking Google issue details and landing pages
- Resubmit through the normal Merchant Center data-source workflow
- Recheck Needs attention after Google processes the update
Read repair-queue.csv for item and source row references. It does not copy feed field values.
Evidence in this sample
The complete sample repair queue has three records: sku-a, issue row 2 and feed row 2, FEED_FIELD_EMPTY_CANDIDATE for availability; sku-b, issue row 3 and feed row 3, FEED_FIELD_PRESENT_REVIEW_OTHER_CAUSE for price; and sku-z, issue row 4 with no matching feed row, FEED_ID_NOT_FOUND. The included repair-map.json records these classifications and input hashes; repair-queue.csv preserves the row references but does not copy the feed field values.
Next actions
Confirm that the issue export and feed refer to the same product snapshot and country. Inspect source rows, supplemental data, landing pages and current Google issue details before making a manual correction; recheck the account after its normal processing cycle.
repair-queue.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Use your downloaded Merchant Center issue CSV, local feed CSV or TSV and an explicit column mapping to find likely feed-field candidates. The local CLI produces a repair map, review queue and hash receipt. The download contains readable Python source, a companion Skill, a local stdio MCP adapter, setup instructions and synthetic samples. Python 3.11 or newer is required; MCP use requires the separately installed optional mcp==2.2.0 package. The tool never connects to Google, edits the feed or resubmits products. A present field can still be affected by supplemental feeds, transformations, landing pages or policy. Confirm the relevant source and recheck your account after a justified manual correction.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for E-commerce.
Requires local Python 3.11+ installation and buyer-supplied supported issue CSV, feed CSV/TSV and explicit mapping. Candidate fields are not Google policy decisions; supplemental feeds, landing pages, and current account details require human review. No live Google connection or automatic edits.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
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
- Software
PythonMerchant Issue Map MCP
Permissions
Reads the buyer-selected local issue export, feed, and mapping; writes a local review packet. No Google account connection, browser, network access, or automatic feed editing.