Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Search Amazon products - find items, compare prices, read reviews
.claude/skills/gooseworks-ai-amazon-search/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 34% | 0% |
Read your credentials from ~/.gooseworks/credentials.json:
bashexport 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.
Uses the SearchAPI Amazon Search engine to query Amazon's catalog.
bashcurl -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"}}'
<details> <summary>curl equivalent</summary>
bashcurl -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"}}'
</details>
bashcurl -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"}}'
amazon_searchTop-level keys: search_metadata, search_parameters, search_information, organic_results, filters, pagination.
Each item in organic_results array:
Pagination: Use page=2, page=3, etc. for more results.
User: "Find wireless earbuds on Amazon"
bashcurl -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"
bashcurl -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"
bashcurl -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"}}'
q parameterorganic_results array means no products matched the query — try broader search terms-q flags if & in query string causes issues: -q 'engine=amazon_search' -q 'q=wireless earbuds'Other measured skills in the registry, with their headline benchmark lift.