Amazon Listing Doctor skill

A skill that audits an Amazon listing across CDQ, A9, COSMO and Alexa and returns a JSON report without rewriting the copy

  • 98 ★ on the repository
  • Last commit
Skill

Minimal access

Why this level

  • Runs local Python scripts over a listing file and makes no network calls
All reasons and checks

buluslan/amazon-listing-doctor

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/amazon-listing-doctor

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Minimal accessThe tool runs nothing and makes no network calls.

  • Runs local Python scripts over a listing file and makes no network calls

This is third-party code. Review the repository files before installing.

What it does

Amazon Listing Doctor scores a product listing with pure-Python scripts that need no dependencies or API keys. The user saves listing data into `listing.json` (title, bullets, description, backend terms, attributes, A+ flag), `compliance_report.py` runs all checks and prints structured JSON, and the agent renders it into a readable report from a template. The checks cover six areas: the CDQ quality score (attributes 30%, title 25%, variations 20%, images 15%, bullets and A+ 5% each), A9 indexability, COSMO intent coverage, Alexa and Rufus discoverability, compliance and title triage by phrase. Individual scripts such as `cdq_score.py` or `title_triage.py` run on their own. The skill only diagnoses: it says what to fix and does not rewrite the copy. It has no browser scraping, so listing data is pasted in or taken from tools like Sorftime and SellerSprite.

Who it is for. Amazon sellers and listing specialists who want a quick score and a fix list from Claude Code, Cursor or OpenCode.

Good fit when

  • A new listing needs a CDQ score and a list of weak spots before launch
  • Traffic is flat and you want to see whether title and backend keywords get indexed
  • You want to know whether Rufus can answer buyer questions from the listing text
  • The title is overloaded and you must decide what to keep, move to bullets or drop

Not a fit when

  • You need rewritten listing copy: the skill rewrites nothing
  • You need data collected from the site automatically: there is no built-in scraping
  • You need Amazon's official COSMO score: it has no public weights and the skill gives a diagnosis based on the public paper

Example request

Check the listing in listing.json with amazon-listing-doctor and show the CDQ score and fixes for the title and bullets

Limitations

  • The skill diagnoses and does not rewrite copy; the user makes the edits.
  • Listing data must be prepared by hand as JSON, with no collection from the Amazon page.
  • The COSMO score rests on a public paper and the ontology in `references/cosmo_ontology.json`. The author states that COSMO has no official weights.
  • Compliance checks follow the July 2026 rules and should be compared with Amazon's current policy.
  • Python 3.10 or newer is required.

How to disable. Delete the `amazon-listing-doctor` folder from the agent's skills directory. The skill leaves nothing else behind: it runs local scripts without installing packages.

FAQ

How do I audit an Amazon listing with an AI agent?

Save the listing data into `listing.json` and run `python scripts/compliance_report.py --file listing.json`. The script returns JSON with CDQ, A9, COSMO and Alexa scores and a violations list, and the agent formats it with `assets/report-template.md`.

What is CDQ and how is it computed here?

CDQ is Amazon's internal ASIN quality score. The skill computes it over six weighted dimensions: attributes 30%, title 25%, variations 20%, images 15%, bullets 5%, A+ 5%, giving 0-100 and a grade.

Do I need API keys or paid services?

No. The scripts use only the Python standard library. Listing data can be exported from Sorftime or SellerSprite or pasted by hand.

Does the skill work for markets other than the US?

The `market` field in `listing.json` takes the market and listing language, and checks are skipped when fields are missing. The README gives no list of supported markets.

Will the skill rewrite my title?

No, it splits the title into phrases and advises what to keep, move to bullets or drop. Rewriting is a separate task for the user or the agent.

Discussion

No questions or reviews yet.

Skills

A skill builds an Amazon listing from a brand and competitor ASINs into Excel with title, bullets and search terms.

SkillExtended access65Repository stars

E-commerce Visual Copywriting

ecommerce-visual-copywriting

A skill that turns product data into a plan for main images, the product page and A+ content, with on-image copy, generation prompts and a claims check

SkillMinimal access1.1KRepository stars

Six Codex skills that take an Amazon seller from product photos and competitor research to finished main images and A+ content.

SkillExtended access85Repository stars

A library of 26 e-commerce visual skills: flat-lay to on-model shots, detail pages, main-image video and compliance checks.

PluginExtended access67Repository stars

Seven workflows for a Shopee and Mercado Livre seller: category research, pricing, listing, images, video, ads and review analysis

SkillExtended access1.2KRepository stars

A skill that audits accounts and viral posts on Xiaohongshu, Douyin, Kuaishou, WeChat Channels and Bilibili, then drafts a copy.

SkillExtended access369Repository stars

Comparison with similar tools

Cards that share the main search query, and how they differ.

ToolOfficialRepository starsMain difference
Amazon Listing Doctor (this card)no98
Amazon Skillsno864an Amazon seller skill set covering keywords, listings, FBA and PPC, while this one diagnoses a listing with four engines
Amazon Sorftime MCP Skillsno1,122analyzes listings, competitors and reviews on Sorftime data, while this one scores CDQ, A9 and COSMO with no external services

README in short

The README states the purpose (a listing audit through four engines), a section on what it does not do, a quick start with commands, a minimal `listing.json` example and how CDQ, A9, COSMO, Alexa and title triage work. It ends with the repository layout: 13 scripts, references and a report template.

README badge

Report a problem