CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

85

1.56x
Quality

79%

Does it follow best practices?

Impact

97%

1.56x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/azure-ai-vision-imageanalysis-py/SKILL.md

The canonical home for this skill is azure-ai-vision-imageanalysis-py in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, actionable reference with executable code across the SDK's full feature surface and clean organization. Weaknesses are minor redundancy across per-feature sections and a vestigial 'When to Use' section that adds no value.

Suggestions

Tighten redundancy: the Visual Features table partially duplicates the per-feature code sections; consider keeping one canonical reference per feature.

Replace or expand the empty 'When to Use' section with concrete trigger guidance that mirrors the description, or remove it to save tokens.

DimensionReasoningScore

Conciseness

Largely lean code examples with minimal concept re-explanation, but per-feature sections repeat the analyze_from_url boilerplate and the Visual Features table re-states what the code already shows; matches anchor 4 and not 5 due to that redundancy.

4 / 5

Actionability

Provides extensive copy-paste-ready, executable code spanning auth, URL/file analysis, every visual feature, async usage, and error handling, covering the common cases fully; matches anchor 5.

5 / 5

Workflow Clarity

Actions are unambiguous and a Best Practices list adds ordering guidance, but these are independent read-only recipes without an explicit multi-step sequence or validation checkpoints; the destructive/batch cap does not apply, so anchor 4 fits and not 3.

4 / 5

Progressive Disclosure

Well-organized single-file layout with clear section headers and no nested references; minor gaps (the near-empty 'When to Use' section and per-feature examples that could be split out) keep it at anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

76%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinctive, clearly communicating the SDK's capabilities and use domain. Its main weakness is the trigger/when clause, which is generic and lacks the concrete natural-language terms and synonyms that would maximize activation quality.

Suggestions

Expand the 'when' clause with concrete trigger phrases, e.g. 'Use when the user mentions image captions, OCR/text extraction, object detection, tagging, or cropping thumbnails.'

Add natural synonyms and file extensions users say (image analysis, image recognition, OCR, JPEG/PNG) to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Lists six concrete capabilities ('captions, tags, objects, OCR, people detection, and smart cropping'), matching the comprehensive-coverage anchor; not 4 because coverage has no notable gaps.

5 / 5

Completeness

Clearly answers 'what' (SDK for the listed visual features) and includes a 'when' clause, but the 'when' is generic rather than concrete trigger phrases; matches anchor 4 and not 5 for that reason.

4 / 5

Trigger Term Quality

Trigger phrase 'Use for computer vision and image understanding tasks' offers some relevant keywords but misses common variations like 'image analysis', 'image recognition', 'OCR', or image file formats; not 4 because several natural terms are absent.

3 / 5

Distinctiveness Conflict Risk

'Azure AI Vision Image Analysis SDK' names a clear niche with distinct triggers and minimal overlap with other skills, matching the anchor-5 example.

5 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.