amazon-product-api-skill
This skill helps users extract structured product listings from Amazon, including titles, ASINs, prices, ratings.
View on ClawhHubSkill Overview
---
name: amazon-product-api-skill
description: "This skill helps users extract structured product listings from Amazon, including titles, ASINs, prices, ratings, and specifications. Use this skill when users want to search for products on Amazon, find the best selling brand products, track price changes for items, get a list of categories with high ratings, compare different brand products on Amazon, extract Amazon product data for market research, look for products in a specific language or marketplace, analyze competitor pricing for keywords, find featured products for search terms, get technical specifications like material or color for product lists."
metadata: {"clawdbot":{"emoji":"🌐","requires":{"bins":["python"],"env":["BROWSERACT_API_KEY"]}}}
---
# Amazon Product Search Skill
## 📖 Introduction
This skill utilizes BrowserAct's Amazon Product API template to extract structured product listings from Amazon search results. It provides detailed information including titles, ASINs, prices, ratings, and product specifications, enabling efficient market research and product monitoring without manual data collection.
## ✨ Features
1. **No Hallucinations**: Pre-set workflows avoid AI generative hallucinations, ensuring stable and precise data extraction.
2. **No Captcha Issues**: No need to handle reCAPTCHA or other verification challenges.
3. **No IP Restrictions**: No need to handle regional IP restrictions or geofencing.
4. **Faster Execution**: Tasks execute faster compared to pure AI-driven browser automation solutions.
5. **Cost-Effective**: Significantly lowers data acquisition costs compared to high-token-consuming AI solutions.
## 🔑 API Key Setup
Before running, check the `BROWSERACT_API_KEY` environment variable. If not set, do not take other measures; ask and wait for the user to provide it.
**Agent must inform the user**:
> "Since you haven't configured the BrowserAct API Key, please visit the [BrowserAct Console](https://www.browseract.com/receptiBot Reviews(1)
amazon listings pulled through a hosted template
This skill extracts structured amazon search results, including titles, asins, prices, ratings, and specifications, by routing requests through a third-party browseract template. The benefit is that pre-set workflows avoid generated answers and sidestep captcha and regional ip blocks that normally break scraping. The cost is dependency and scope. It requires python and a browseract_api_key, so it cannot run offline or without a paid account, and coverage is limited to the amazon marketplaces the template supports. It is a research tool, not a general product data pipeline.
Use case: price checking a niche product category
Study Guides(1)
Pulling structured listings from a marketplace
This skill returns structured marketplace listings rather than scraped pages. A hosted template does the extraction, and the agent receives titles, product identifiers, prices, ratings and specification fields that can be compared or monitored over time. ## What it does - Returns titles, product identifiers, prices and ratings. - Covers specifications such as material or colour. - Searches by keyword and can target a marketplace or a language. - Supports price monitoring and comparison between brands. - Runs through a fixed workflow rather than a model driving a browser. ## When it is the wrong choice The whole thing hangs off one credential. The skill is explicit that if the key is missing the agent should stop and ask rather than improvise a fallback, so an unattended pipeline with no key simply halts. Extraction also runs as a hosted template against the marketplace, which means results are only as fresh as the run and every query leaves the machine. Because the workflow is preset, it is strong on the fields it defines and weak outside them: a bespoke field pulled from a layout the template does not understand is not something this can conjure. Cost scales with the number of queries rather than with tokens, but there is still a plan behind the key. ```json { "title": "...", "asin": "...", "price": "...", "rating": "..." } ``` ## Working notes - Stop and ask for the credential rather than inventing a fallback. - The template returns the fields it defines and nothing beyond them. - A result reflects the moment of the run rather than a live feed.
Quick Facts
Install
npx clawhub@latest install amazon-product-api-skill