Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyze images with AI - extract text, describe content, detect objects
.claude/skills/gooseworks-ai-image-analyzer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 46% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 40% | 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"
Analyze images to extract text, describe content, and detect objects using AI.
Fetch image content:
bashcurl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \ -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \ -H "Content-Type: application/json" \ -d '{"api":"linkup","path":"/fetch","body":{"url":"https://example.com/image.jpg"}}'
Use AI to extract text from images:
bashcurl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \ -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \ -H "Content-Type: application/json" \ -d '{"api":"scrapegraph","path":"/v1/smartscraper"}' "website_url": "https://example.com/screenshot.png", "user_prompt": "Extract all visible text from this image" }'
Get specific data from images:
bashcurl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \ -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \ -H "Content-Type: application/json" \ -d '{"api":"riveter","path":"/v1/run"}' "input": { "urls": ["https://example.com/receipt.jpg"] }, "output": { "store_name": {"prompt": "Store name", "contexts": ["urls"]}, "date": {"prompt": "Date", "contexts": ["urls"]}, "items": {"prompt": "Items with names and prices", "contexts": ["urls"]}, "total": {"prompt": "Total amount", "contexts": ["urls"]} } }'
Get screenshots of web pages:
bashcurl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \ -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \ -H "Content-Type: application/json" \ -d '{"api":"brand-dev","path":"/v1/brand/screenshot","query":{"domain":"stripe.com"}}'
bash# Extract receipt data curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \ -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \ -H "Content-Type: application/json" \ -d '{"api":"scrapegraph","path":"/v1/smartscraper"}' "website_url": "https://example.com/receipt.jpg", "user_prompt": "Extract store name, date, all items with prices, and total amount" }' # Get website screenshot curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \ -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \ -H "Content-Type: application/json" \ -d '{"api":"brand-dev","path":"/v1/brand/screenshot","query":{"domain":"openai.com"}}'
List all endpoints, or add a path for parameter details:
bashcurl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/search \ -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \ -H "Content-Type: application/json" \ -d '{"prompt":"brand-dev API endpoints"}' api show linkup curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/search \ -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \ -H "Content-Type: application/json" \ -d '{"prompt":"riveter API endpoints"}' api show scrapegraph
Example: curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/details \ -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \ -H "Content-Type: application/json" \ -d '{"api":"olostep","path":"/v1/scrapes"}' for endpoint parameters.
Other measured skills in the registry, with their headline benchmark lift.