Skip to content
TakoAPI
Back to skills

amazon-product-search-api-skill

by phheng

Browser & Automation
1.6kDownloads reported by clawskills.sh
1Stars
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

This skill is designed to help users automatically extract product data from Amazon search results.

Description

What This Skill Does

Extracts structured product data from Amazon search results via BrowserAct's API template. Input keywords, an optional brand filter, a quantity limit, and a UI language to retrieve titles, prices, ratings, review counts, monthly sales estimates, and availability across paginated results.

Bypasses CAPTCHAs and regional IP restrictions automatically, which makes it more reliable and cheaper than running general-purpose AI browser automation against Amazon.

When to Use It

  • Tracking competitor prices and discounts on Amazon by brand
  • Identifying best-selling products in a specific category
  • Building a product catalog with titles and URLs from search results
  • Checking stock availability for specific brand items
  • Estimating market demand using monthly sales data

Example Workflow

INPUT

User asks: Find Sony wireless earbuds on Amazon with prices and ratings

AGENT
  1. 1

    Verify BROWSERACT_API_KEY is set in environment, prompt user to obtain one if missing

  2. 2

    Run amazon_product_search_api.py with keywords 'wireless earbuds', brand 'Sony', quantity 50, language 'en'

  3. 3

    Monitor terminal status logs until script completes or timeout is detected

  4. 4

    Parse returned records for product_title, rating_score, review_count, current_price, list_price, and is_best_seller

OUTPUT

Structured list of Sony wireless earbuds entries with titles, detail URLs, star ratings, review counts, current and list prices, and best seller flags

Requirements

  • BROWSERACT_API_KEY environment variable (obtain from browseract.com/reception/integrations)

Installation

clawhub install phheng/amazon-product-search-api-skill

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links