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.
76
71%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/azure-ai-vision-imageanalysis-py/SKILL.mdQuality
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 solid description that clearly identifies the specific SDK (Azure AI Vision) and enumerates six concrete capabilities. The 'Use for...' clause provides trigger guidance, though it could be more detailed with natural user language variations. The description is concise and distinctive but could benefit from more natural trigger terms users might actually say.
Suggestions
Expand trigger terms with natural user phrases like 'read text from image', 'describe a photo', 'detect objects in picture', or mention common image file types (.jpg, .png, .bmp).
Enrich the 'Use for...' clause with more specific scenarios, e.g., 'Use when the user wants to analyze images, extract text from photos, detect objects or people, generate image captions, or perform smart cropping using Azure AI Vision.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: captions, tags, objects, OCR, people detection, and smart cropping. These are clearly defined capabilities within the Azure AI Vision domain. | 3 / 3 |
Completeness | Clearly answers 'what' (Azure AI Vision SDK for captions, tags, objects, OCR, people detection, smart cropping) and 'when' ('Use for computer vision and image understanding tasks'). The 'Use for...' clause serves as an explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some good terms like 'OCR', 'image analysis', 'computer vision', 'image understanding', but misses common user variations like 'read text from image', 'detect objects in photo', 'describe image', 'extract text from picture', or file extensions like '.jpg', '.png'. | 2 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Azure AI Vision SDK specifically, which distinguishes it from generic image processing skills or other cloud vision APIs. The mention of the specific SDK and its concrete capabilities (smart cropping, people detection) creates a distinct niche. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides highly actionable, executable code examples covering all Azure AI Vision features, which is its primary strength. However, it suffers from being a lengthy monolithic reference document with repetitive patterns across feature sections, generic boilerplate at the end, and no progressive disclosure structure. It would be significantly improved by condensing into a quick-start overview with a separate detailed reference file.
Suggestions
Split into a concise SKILL.md with authentication + one combined analyze example, and move per-feature details to a REFERENCE.md file
Remove the generic 'When to Use' and 'Limitations' boilerplate sections that add no skill-specific value
Remove the Visual Features table since the same information is already demonstrated in the code examples
Consolidate repetitive analyze_from_url calls—show one full example with multiple features and then just show result-parsing snippets for each feature
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code examples, but it's quite long with repetitive patterns (each feature section follows the same analyze_from_url + print pattern). The Visual Features table duplicates information already shown in code examples. The 'When to Use' and 'Limitations' sections are generic boilerplate that add no value. | 2 / 3 |
Actionability | Every section provides fully executable, copy-paste ready Python code with proper imports, authentication setup, and result handling. The examples cover all visual features with concrete output parsing including bounding boxes, confidence scores, and nested structures. | 3 / 3 |
Workflow Clarity | The skill is essentially an API reference rather than a multi-step workflow, so sequencing is less critical. However, there's no validation checkpoint guidance—e.g., no mention of checking result properties before accessing them beyond simple 'if result.caption' checks, and no guidance on verifying the endpoint/key are valid before making calls. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of code examples (~200+ lines) with no references to external files. The content would benefit greatly from a concise quick-start section with detailed feature examples split into a separate reference file. All features are presented inline at the same level of detail. | 1 / 3 |
Total | 8 / 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 | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
76cbde3
- 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.