Amazon Product Search
SkillSearchSearch Amazon products - find items, compare prices, read reviews
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Amazon Product Search skill
What this skill tells your AI
The instructions your AI receives, as published by criptogus/agent-evolve-network in .claude/skills/amazon-search/SKILL.md and read by ahel’s review.
Setup
Read your credentials from ~/.gooseworks/credentials.json:
export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")
If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login
All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"
Search for products on Amazon. Find items by keyword, category, or criteria.
When to Use
- User wants to find a product on Amazon
- User asks "find me a [product] on Amazon"
- User wants to compare prices
- User needs product recommendations
How It Works
Uses the SearchAPI Amazon Search engine to query Amazon's catalog.
Usage
Basic Product Search
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
-H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"api":"searchapi","path":"/api/v1/search","query":{"engine":"amazon_search","q":"wireless earbuds"}}'
curl -X POST "https://api.orth.sh/v1/run" \
-H "Content-Type: application/json" \
-d '{"api":"searchapi","path":"/api/v1/search","query":{"engine":"amazon_search","q":"wireless earbuds"}}'
Search with Category
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
-H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"api":"searchapi","path":"/api/v1/search","query":{"engine":"amazon_search","q":"laptop","category_id":"electronics"}}'
Parameters
- engine (required) - Must be
amazon_search - q (required) - Search query
- category_id - Amazon category (electronics, books, etc.)
- page - Page number for pagination
Response
Top-level keys: search_metadata, search_parameters, search_information, organic_results, filters, pagination.
Each item in organic_results array:
- position (integer) - Result rank
- asin (string) - Amazon product ID
- title (string) - Product name
- link (string) - Product page URL
- image (string) - Product thumbnail URL
- price (string) - Display price (e.g., "$69.99")
- extracted_price (number) - Numeric price for comparison
- original_price / extracted_original_price - Pre-discount price (if on sale)
- currency (string) - Currency code (e.g., "USD")
- rating (number) - Star rating (0-5)
- reviews (integer) - Number of reviews
- is_prime (boolean) - Prime eligible
- is_best_seller / is_amazon_choice (boolean) - Badge flags
- delivery (string) - Delivery estimate text
Pagination: Use page=2, page=3, etc. for more results.
Examples
User: "Find wireless earbuds on Amazon"
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
-H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"api":"searchapi","path":"/api/v1/search","query":{"engine":"amazon_search","q":"wireless earbuds"}}'
User: "Search for laptops under $500"
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
-H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"api":"searchapi","path":"/api/v1/search","query":{"engine":"amazon_search","q":"laptop under 500"}}'
User: "Find highly rated coffee makers"
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
-H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"api":"searchapi","path":"/api/v1/search","query":{"engine":"amazon_search","q":"coffee maker best rated"}}'
Error Handling
- 400 - Invalid engine name or missing
qparameter - 401 - Invalid API key
- 429 - Rate limit — wait and retry
- Empty
organic_resultsarray means no products matched the query — try broader search terms - Use separate
-qflags if&in query string causes issues:-q 'engine=amazon_search' -q 'q=wireless earbuds'
Signals
- GitHub stars
- 308
- Forks
- 1
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
amazon-search- Source
- github.com/criptogus/agent-evolve-network