agentleFS
Sign inStart free
weininghuiweininghui/skills/amazon-product-api/SKILL.md

amazon-product-api

Skill1 starsChanged 12 days agoMITView on GitHub

Extract structured product listings from Amazon, including titles, ASINs, prices, ratings, and specifications. Use this skill when users want to: 1) \"Search for [product] on Amazon\", 2) \"Find the best selling [brand] products\", 3) \"Track price changes for [item]\", 4) \"Get a list of [category] with high ratings\", 5) \"Compare [brand A] and [brand B] products on Amazon\", 6) \"Extract Amazon product data for market research\", 7) \"Look for [product] in a specific language/marketplace\", 8) \"Analyze competitor pricing for [keywords]\", 9) \"Find featured products for [search term]\", 10) \"Get technical specifications like material or color for [product list]\".

  • Reads credentials

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Zero maintenance: No scraping scripts, proxy setup, or anti-bot handling required.

    line 13
  2. Distinctive:

    Invalid Authorization: If the API key is incorrect or expired, the script will catch the "Invalid authorization" error and prompt you to …

    line 66
  3. Distinctive:

    Task Failures: If the workflow fails on the server side, the script will report the failure status and any available error details.

    line 68

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Amazon Product API Skill

This skill allows you to extract structured product data from Amazon search results using a single API request, eliminating the need for complex scrapers or manual data entry.

✨ Features

  • One-call integration: Send product results directly into your pricing database, BI dashboards, competitor trackers, or automation workflows via API.
  • Zero maintenance: No scraping scripts, proxy setup, or anti-bot handling required.
  • Production-ready output: Consistent, structured responses designed for automated processing and monitoring.
  • Built for workflows: Perfect for competitive pricing, product research, catalog monitoring, and merchandising insights.

🔑 API Key Setup

This skill requires a BROWSERACT_API_KEY.

Environment Variable Check

The associated script will automatically check for the BROWSERACT_API_KEY environment variable.

How to get an API Key

  1. Register/Login at BrowserAct.
  2. Go to the API & Integrations section to get your key.
  3. Set it in your environment:
    $env:BROWSERACT_API_KEY = "your-api-key-here"

📥 Input Parameters

ParameterTypeDescriptionExample
KeyWordsstringSearch keywords used to find products on Amazon.phone, wireless earbuds
BrandstringFilter products by brand name.Apple, Samsung, Sony
Maximum_number_of_page_turnsnumberNumber of search result pages to paginate through.1, 3
languagestringUI language for the Amazon browsing session.en, de, zh-CN

🚀 How to Call

You can trigger this skill using the provided Python script:

python -u .cursor/skills/amazon-product-api-skill/scripts/amazon_product_api.py --keywords "laptop" --brand "Dell" --pages 1 --lang "en"

📊 Output Data

The script returns a JSON array of products with the following fields:

  • product_title: The product name.
  • asin: Amazon Standard Identification Number (unique ID).
  • product_url: The product detail page URL.
  • brand: Brand name.
  • price_current_amount: Current selling price.
  • price_original_amount: Original price (if available).
  • rating_average: Average star rating.
  • rating_count: Total number of ratings.
  • featured: Whether it's a sponsored/featured item.
  • color, material, style: Product attributes (if available).

🛠 Error Handling & Retries

  • Invalid Authorization: If the API key is incorrect or expired, the script will catch the "Invalid authorization" error and prompt you to check your configuration.
  • Network Issues: The script includes built-in retry logic for common network timeouts.
  • Task Failures: If the workflow fails on the server side, the script will report the failure status and any available error details.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free