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
Discovery
85%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description that clearly identifies the specific SDK and lists concrete capabilities. The explicit 'Use for' clause addresses when to use it, though the trigger terms could better match natural user language. The Azure-specific naming provides excellent distinctiveness.
Suggestions
Add more natural user trigger terms like 'analyze image', 'read text from picture', 'detect objects in photo', or common file extensions (.jpg, .png, .gif)
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'captions, tags, objects, OCR, people detection, and smart cropping' - these are distinct, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('captions, tags, objects, OCR, people detection, smart cropping') and when ('Use for computer vision and image understanding tasks') with an explicit 'Use for' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'computer vision', 'image understanding', 'OCR', but misses common user phrases like 'analyze image', 'read text from image', 'detect faces', 'describe picture', or file extensions like '.jpg', '.png'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with 'Azure AI Vision Image Analysis SDK' clearly identifying the specific tool, and the enumerated capabilities (OCR, people detection, smart cropping) create a clear niche unlikely to conflict with generic image skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality SDK reference skill with excellent actionability and conciseness. All code examples are executable and well-structured. The main weaknesses are the monolithic structure (could benefit from splitting detailed feature examples into separate files) and lack of explicit workflow guidance for common multi-step scenarios like batch processing or error recovery loops.
Suggestions
Consider splitting detailed feature examples (OCR, Object Detection, etc.) into a separate FEATURES.md file, keeping SKILL.md as a quick-start overview
Add a workflow example showing a common multi-step pattern, such as: load image -> analyze -> handle errors -> retry with different features if needed
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, presenting code examples without unnecessary explanation of what Azure Vision is or how APIs work. Every section provides direct, actionable code. | 3 / 3 |
Actionability | All code examples are fully executable and copy-paste ready with proper imports, client initialization, and result handling. The examples cover all major features with complete, working code. | 3 / 3 |
Workflow Clarity | While individual operations are clear, there's no explicit workflow for multi-step processes. Error handling is shown but not integrated into a validate-fix-retry pattern. For a reference-style SDK skill, this is acceptable but could include guidance on chaining operations. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear section headers, but it's a long monolithic file (~200 lines). The Visual Features table and Best Practices could be separate reference files, with SKILL.md focusing on quick start and linking to detailed feature documentation. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Reviewed
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.