azure-ai-vision-imageanalysis-py
Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping. Use for computer vision and image understanding tasks.
Install with Tessl CLI
npx tessl i github:sickn33/antigravity-awesome-skills --skill azure-ai-vision-imageanalysis-py87
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 97%
↑ 1.56xAgent success when using this skill
Validation for skill structure
Evaluation results
100%
12%Product Image Catalog Enrichment
OCR and tag extraction with error handling
Correct package import
100%
100%
VisualFeatures import
100%
100%
READ feature for OCR
100%
100%
TAGS feature for tagging
100%
100%
Only needed features selected
100%
100%
Correct OCR result traversal
100%
100%
Word-level confidence access
100%
100%
Tags result traversal
50%
100%
HttpResponseError handling
100%
100%
Error attributes accessed
50%
100%
Env var credentials
50%
100%
AzureKeyCredential usage
100%
100%
Without context: $0.3182 · 4m 7s · 21 turns · 28 in / 4,109 out tokens
With context: $0.6146 · 5m 32s · 31 turns · 367 in / 7,819 out tokens
96%
68%Automated Thumbnail Crop Advisor for a Publishing Platform
Smart crop thumbnail generation
Correct package install
0%
33%
SMART_CROPS feature
0%
100%
smart_crops_aspect_ratios parameter
0%
100%
Aspect ratios match requirements
100%
100%
Only needed features
100%
100%
Smart crops result traversal
0%
100%
Bounding box access
0%
100%
Aspect ratio attribute
0%
100%
Env var credentials
50%
100%
HttpResponseError handling
0%
100%
Structured output produced
100%
100%
Without context: $0.7506 · 7m 9s · 32 turns · 36 in / 12,950 out tokens
With context: $0.5472 · 4m 52s · 29 turns · 332 in / 5,562 out tokens
97%
25%Concurrent Accessibility Image Analyzer
Async batch people detection and dense captions
Async client import
0%
100%
Async context manager
0%
100%
PEOPLE feature
100%
100%
DENSE_CAPTIONS feature
100%
100%
gender_neutral_caption parameter
100%
100%
People result traversal
100%
100%
Dense captions traversal
100%
100%
Concurrent execution
70%
100%
Async credentials
37%
62%
Only needed features
100%
100%
Structured output saved
100%
100%
Without context: $0.2899 · 4m 48s · 23 turns · 26 in / 4,588 out tokens
With context: $0.5658 · 4m 13s · 27 turns · 297 in / 7,240 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Unknown
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.