Amazon Listing Doctor

Problem it solves

Amazon listings often fail because of overly long titles, malformed highlights, duplicated keywords, weak bullets, missing attributes, incomplete images, or dirty backend search terms. When traffic drops, it is hard to tell whether the issue is indexability, intent coverage, or failure to answer AI shopping assistant questions. Amazon Listing Doctor turns this judgment into structured diagnostic dimensions instead of generic optimization advice.

How it works

It normalizes title, highlights, bullets, description, images, category, and backend search terms into a listing JSON, then checks four diagnostic dimensions:
- CDQ content quality: covers title, attributes, variations, images, bullets, and A+ content.
- A9 indexability: checks core keyword placement, backend search term hygiene, attribute completeness, and indexable information.
- COSMO intent coverage: uses use_case, audience, goal, and constraint to judge whether the listing expresses buyer intent.
- Alexa discoverability: simulates buyer questions to AI shopping assistants and checks whether the listing can be answered or recommended.

Key steps include detecting merged title-and-highlight strings from scrapers or APIs, extracting COSMO and Alexa semantic signals, running compliance, scoring, indexability, intent, Q&A, and keyword-layer checks, then producing a diagnostic report with data-coverage notes. Missing fields are marked with score=null and an explanation instead of forcing a zero score.

Boundaries

The skill does not scrape Amazon. It is meant for data exported from Seller Central, third-party tools, or APIs. It identifies what should be changed but does not rewrite the listing directly. The COSMO dimension is a community diagnostic inspired by published research, not an official score. Non-US marketplaces, niche categories, and missing backend fields should be reviewed manually.