Name: azure-ai-vision
Rating: 55.2 (1 reviews)
Author: membranedev

azure-ai-vision

Azure AI Vision integration. Manage data, records, and automate workflows. Use when the user wants to interact with Azure AI Vision data.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/azure-ai-vision/SKILL.md

Quality

Content

67%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 well-structured, highly actionable guide to driving Azure AI Vision through the Membrane CLI, with a clear sequenced workflow and validation for connection state. Its chief weakness is a padded marketing-style intro and a Popular actions table with empty descriptions.

Suggestions

Trim the opening 'Azure AI Vision is a cloud-based API...' paragraph to a single line or remove it, since Claude already knows the product.

Fill the blank Description column in the Popular actions table so the overview is self-contained.

Resolve the dangling 'Step 2' references and relabel '1b' consistently so the connection workflow reads as a coherent numbered sequence.

Dimension	Reasoning	Score
Conciseness	Mostly efficient CLI commands, but the opening paragraph explaining what Azure AI Vision is and its industry uses is concept padding Claude already knows, and the Best practices section re-explains rationale that could be trimmed.	3 / 5
Actionability	Provides copy-paste ready commands for the full lifecycle (install, login, connection ensure, action list/run, request proxy) covering common cases, with minor gaps such as the Popular actions table having blank descriptions.	4 / 5
Workflow Clarity	Clear install-to-run sequence with an explicit connection-state polling checkpoint (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), though references to a nonexistent 'Step 2' and an unexplained '1b' label introduce minor confusion.	4 / 5
Progressive Disclosure	Well-organized sections structure the content clearly with no bundle files present; minor gaps include the inlined Popular actions table (with empty descriptions) and proxy flag reference that could live in a separate file.	4 / 5
	Total	15 / 20 Passed

Description

57%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 correctly identifies the Azure AI Vision niche and includes an explicit 'Use when' trigger, satisfying the completeness floor. Its main weakness is generic boilerplate actions that fail to convey the skill's concrete vision capabilities.

Suggestions

Replace 'Manage data, records, and automate workflows' with concrete capabilities such as 'Analyze images, detect objects and faces, extract text via OCR, and generate image captions'.

Expand trigger terms to include natural user phrasings like 'image analysis', 'OCR', 'computer vision', and 'image recognition'.

Tie the 'Use when' clause to specific scenarios, e.g. 'Use when the user wants to analyze images, read text from images, or detect objects/faces in Azure AI Vision'.

Dimension	Reasoning	Score
Specificity	Names the domain ('Azure AI Vision integration') but the actions ('Manage data, records, and automate workflows') are generic boilerplate rather than concrete vision-specific capabilities like image analysis or OCR.	2 / 5
Completeness	Explicitly answers both what ('Azure AI Vision integration. Manage data, records, and automate workflows.') and when ('Use when the user wants to interact with Azure AI Vision data.'), though the 'when' could name concrete trigger phrases.	4 / 5
Trigger Term Quality	Includes the natural term 'Azure AI Vision' but misses common synonyms and variations users would say such as 'image analysis', 'OCR', 'computer vision', or 'image recognition'.	3 / 5
Distinctiveness Conflict Risk	The 'Azure AI Vision' trigger names a distinct product niche with low conflict risk, though the generic 'manage data, records, and automate workflows' phrasing could overlap with other integration skills.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/azure-ai-vision/SKILL.md
Commit: f484c82

Reviewed: 7 minutes ago

Table of Contents

Discovery Implementation Validation

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.