# Amazon Listing Audit - Listing Score, Reviews & Competitor Gaps (`centorprat/amazon-listing-audit`) Actor

Audit Amazon listings by ASIN: listing-content score with prioritised fixes (title, bullets, images, video, A+), review health (4-star cliff, 1-star share, polarized-rating pattern), buy box, stock, BSR and demand, plus a benchmark vs the competitors you list.

- **URL**: https://apify.com/centorprat/amazon-listing-audit.md
- **Developed by:** [Centor Prat](https://apify.com/centorprat) (community)
- **Categories:** E-commerce, Marketing
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $34.00 / 1,000 listing auditeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Amazon Listing Audit — Listing Score, Review Health & Competitor Gaps

Audit Amazon listings the way a marketplace agency does. Give ASINs (and optionally your competitors') and get back for each product:

- a **listing-content score** with **prioritised fixes** (title, bullets, images, video, A+ / brand story, attributes)
- a **review-health read**: the 4-star conversion cliff, 1-star share, and the **polarized-rating pattern**
- a **commercial read**: price and discount, buy-box seller, stock, Best Sellers Rank, monthly demand, Amazon's Choice
- a **benchmark against your competitors**, with concrete gaps

It runs Apify's Amazon Product Scraper under the hood, so you only pass ASINs. Agent-callable.

Built for Amazon sellers, brand owners and marketplace agencies (listing optimisation, account audits, competitor tear-downs).

### What it checks

| Area | Checks |
|---|---|
| **Title** | length vs the 80–200 sweet spot / 200-char policy, brand present, ALL-CAPS, repeated words (keyword stuffing), promotional claims that break title policy |
| **Bullets** | count (all 5 used?), thin or wall-of-text bullets |
| **Media** | image count (7+), product video |
| **A+ / brand story** | present or missing (and how many competitors use it) |
| **Attributes** | item-specifics completeness (they feed filters and AI shopping answers) |
| **Review health** | rating vs the 4.0 cliff, 1-star share, ratings volume, **polarized ratings** (lots of 5★ + lots of 1★, little in between = incentivised reviews or inconsistent quality) |
| **Commercial** | price / list price / discount, in-stock + low-stock units, buy-box seller, Best Sellers Rank (+ sub-category), "bought in past month" demand, Amazon's Choice, Amazon's own AI review summary |
| **vs competitors** | price, rating, ratings count, images, bullets, video, A+, BSR, monthly demand: who's ahead and by how much |

Each audit gets `listingContentScore`, `reviewHealthScore`, `listingScore`, a **grade (A–F)**, a verdict and a **sorted fix list** (high → low priority).

**Verdicts:** `strong-listing` · `solid-with-fixes` · `needs-content-optimization` · `review-pattern-check` · `at-risk-listing` · `not-found`.

### Why not just ask an AI agent?

An agent can't load Amazon product pages reliably: Amazon serves captchas and stripped pages to automated requests. Even with the data in hand, it would still have to:

- apply the listing-policy and conversion heuristics an agency uses,
- read the star distribution for manipulation patterns,
- benchmark against a competitor set,
- return the same structured scores for every ASIN.

This actor does all of that in one call.

### Input

| Field | Type | Required | Description |
|---|---|---|---|
| `products` | array of strings | ✅\* | ASINs or Amazon product URLs. |
| `competitors` | array of strings | | Up to 10 competitor ASINs/URLs to benchmark against. |
| `marketplace` | string | | Amazon domain for plain ASINs (default `com`). |
| `datasetId` | dataset | ✅\* | …or read products from an Amazon search dataset. |
| `maxProducts` | integer | | Cap per run (default 20). |
| `webhookUrl` | string | | POST the audits here as JSON. |

\* provide `products` or `datasetId`.

**Example input**

```json
{ "products": ["B07ZPKN6YR"], "competitors": ["B0D1XD1ZV3"], "marketplace": "com" }
```

### Output

One audit per product (+ a reference row per competitor). **Example** (real data, trimmed):

```json
{
  "asin": "B07ZPKN6YR",
  "brand": "Apple",
  "price": 179.99,
  "stars": 4.2,
  "reviewsCount": 60159,
  "oneStarPct": 11,
  "bestsellerRank": 22,
  "bestsellerCategory": "Amazon Renewed",
  "monthlyBought": 1000,
  "seller": "Woot",
  "images": 4, "videos": 0, "bullets": 3, "hasAPlus": true,
  "listingContentScore": 63, "reviewHealthScore": 63, "listingScore": 63, "grade": "C",
  "signal": "solid-with-fixes",
  "fixes": [
    {"priority": "high", "area": "title", "fix": "Title is 49 chars - expand toward 80-200 with the main search terms, key attributes (size/color/count) and use case."},
    {"priority": "high", "area": "images", "fix": "4 image(s) - use 7+: lifestyle, infographic (dimensions/features), in-use and comparison shots."},
    {"priority": "medium", "area": "bullets", "fix": "3 bullet point(s) - use all 5 (benefit first, then spec)."},
    {"priority": "medium", "area": "video", "fix": "No product video - video lifts conversion on most categories."}
  ],
  "findings": [
    {"severity": "medium", "code": "one-star-share", "detail": "11% of ratings are 1-star - read recent 1-star reviews for a recurring defect / listing mismatch."}
  ],
  "benchmark": {"competitorsCompared": 1, "gaps": [{"metric": "images", "you": 4, "competitorMedian": 7}]}
}
```

### Use cases

- **Listing optimisation:** a prioritised fix list per ASIN.
- **Agency account audits / pitches:** grade a prospect's catalogue in one run.
- **Competitor tear-downs:** see exactly where a rival's listing beats yours.
- **Review-risk monitoring:** catch a slide toward 4.0 or a rising 1-star share (schedule it).
- **AI agents:** a structured listing verdict + `summary` per ASIN.

### For AI agents / MCP

```
https://mcp.apify.com/?tools=actors,docs,centorprat/amazon-listing-audit
```

Loads as `centorprat--amazon-listing-audit`. Claude Code:

```
claude mcp add apify -- npx -y @apify/actors-mcp-server --actors centorprat/amazon-listing-audit
```

### FAQ

**Where does the data come from?** Public Amazon product pages, via Apify's Amazon Product Scraper run under the hood with residential proxies in the marketplace's country.

**Does it read individual reviews?** Amazon now puts the full review list behind a login, so the audit uses the public rating distribution, rating count and Amazon's own AI review summary. It doesn't read individual review pages.

**What does "polarized ratings" mean?** A star distribution with lots of 5★, a large 1★ share, and almost nothing in between. That's typical of incentivised reviews *or* inconsistent product quality. It's a prompt to check review recency and verified-purchase share, not a verdict.

**Which marketplaces?** amazon.com, .co.uk, .de, .fr, .it, .es, .ca, .com.au, .co.jp, .in, .com.mx, .nl, .se, .pl.

**Cost?** Pay-per-event: one event per product audited, plus a small event per competitor benchmarked. The underlying scraper (about half a cent per product) is billed to your run.

### Data & attribution

Public Amazon product data via Apify's Amazon Product Scraper. These are listing and review signals for sellers and agencies, not guarantees of ranking or sales.

### Related actors

- [Shopify Store Leads & App Audit](https://apify.com/centorprat/shopify-store-leads-app-audit)
- [Shopify App Detector](https://apify.com/centorprat/shopify-app-detector)

# Actor input Schema

## `products` (type: `array`):

ASINs (e.g. "B0D1XD1ZV3") or Amazon product URLs. One audit per product.

## `competitors` (type: `array`):

Up to 10 competitor ASINs/URLs. Every product is benchmarked against them (price, rating, ratings count, images, bullets, video, A+, BSR, monthly demand) with concrete gaps.

## `marketplace` (type: `string`):

Amazon domain for plain ASINs.

## `datasetId` (type: `string`):

Read products from another dataset (e.g. an Amazon search run) - uses the 'asin' / 'url' field.

## `maxProducts` (type: `integer`):

Cap how many of your products to audit this run.

## `webhookUrl` (type: `string`):

If set, the finished audits are POSTed here as JSON when the run completes.

## Actor input object example

```json
{
  "products": [
    "B0D1XD1ZV3"
  ],
  "marketplace": "com",
  "maxProducts": 20
}
```

# Actor output Schema

## `listings` (type: `string`):

One audit per product: listing-content score, review-health score, overall listing score + grade, prioritised fixes, findings (rating cliff, 1-star share, polarized ratings, stock), commercial data (price, discount, buy-box seller, BSR, monthly demand, Amazon's Choice), Amazon's AI review summary and a benchmark vs competitors. Competitor reference rows are included.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "products": [
        "B0D1XD1ZV3"
    ],
    "maxProducts": 20
};

// Run the Actor and wait for it to finish
const run = await client.actor("centorprat/amazon-listing-audit").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "products": ["B0D1XD1ZV3"],
    "maxProducts": 20,
}

# Run the Actor and wait for it to finish
run = client.actor("centorprat/amazon-listing-audit").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "products": [
    "B0D1XD1ZV3"
  ],
  "maxProducts": 20
}' |
apify call centorprat/amazon-listing-audit --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,centorprat/amazon-listing-audit"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/uNb8LuKiI8UIV5Hrr/builds/6IrN23tPCCtuO9UYA/openapi.json