Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →microsoft/azure-ai-vision-imageanalysis-py
Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping.
Passed 19 of 22 test cases with the skill, and 15 of 22 without it.
and 9 more in the full report
7 fixed12 passed either way0 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
When processing dense captions from an Azure AI Vision result object in Python, someone wrote `for cap in result.dense_captions.values:`. Write the snippet that correctly accesses the dense caption items and bounding boxes.
| Checked | Without skill | With skill |
|---|---|---|
| The code accesses result.dense_captions.list to iterate over region captions. | Missed | Passed |
| The code reads bounding_box from each dense caption item. | Passed | Passed |
The instructions your model reads when the skill loads.
Client library for Azure AI Vision 4.0 image analysis including captions, tags, objects, OCR, and more.
pip install azure-ai-vision-imageanalysis
VISION_ENDPOINT=https://<resource>.cognitiveservices.azure.com # Required for all auth methods
AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production
VISION_KEY=<your-api-key> # Only required for the legacy API-key auth path below
🔑 Two rules apply to every code sample below:
- Prefer
DefaultAzureCredential. It works locally (Azure CLI / VS Code / Developer CLI) and in Azure (managed identity, workload identity) with no code change. Avoid connection strings, account/API keys — they bypass Entra audit and rotation.
- Local dev:
DefaultAzureCredentialworks as-is.- Production: set
AZURE_TOKEN_CREDENTIALS=prod(orAZURE_TOKEN_CREDENTIALS=<specific_credential>) to constrain the credential chain to production-safe credentials.- Wrap every client in a context manager so HTTP transports, sockets, and token caches are released deterministically:
- Sync:
with <Client>(...) as client:- Async:
async with <Client>(...) as client:andasync with DefaultAzureCredential() as credential:(fromazure.identity.aio)Snippets may abbreviate this setup, but production code should always follow both rules.
import os
from azure.identity import DefaultAzureCredential, ManagedIdentityCredential
from azure.ai.vision.imageanalysis import ImageAnalysisClient
from azure.ai.vision.imageanalysis.models import VisualFeatures
# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
credential = DefaultAzureCredential(require_envvar=True)
# Or use a specific credential directly in production:
test cases passed, vs 15 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.