azure-ai-anomalydetector-java

Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java. Use when implementing univariate/multivariate anomaly detection, time-series analysis, or AI-powered monitoring.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

A highly actionable, code-complete skill body with executable Java for every core pattern. It is held back by monolithic structure with no progressive disclosure and by missing validation/polling checkpoints for the long-running batch operations.

Suggestions

Add explicit validation/polling checkpoints to the multivariate workflow: after trainMultivariateModel, poll getModelInfo().getStatus() until READY/failed before proceeding, and similarly poll getBatchDetectionResult(resultId) until DONE.

Move the large per-pattern API reference (multivariate training/inference, model management) into a separate reference file and link to it from a concise overview, improving progressive disclosure.

Trim the generic 'When to Use'/'Limitations' boilerplate and the 'Trigger Phrases' list (which duplicates the description) to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and code-driven, but the boilerplate 'When to Use'/'Limitations' sections restate what Claude already knows and 'Trigger Phrases' duplicates the description, adding tokens that earn little.	2 / 3
Actionability	Provides complete, copy-paste-ready Java across every pattern (client creation, batch/streaming/change-point detection, training, inference, model management, error handling) with real SDK method calls and imports.	3 / 3
Workflow Clarity	The multivariate flow names a Train -> Inference -> Results sequence, but long-running train and batch-inference operations lack explicit validation/polling checkpoints; per the guidelines, missing feedback loops for batch operations caps this at 2.	2 / 3
Progressive Disclosure	Sections are clearly organized, but the body is a monolithic wall of inline API reference with no external references; at this length, detailed reference material would be better split into separate files.	2 / 3
	Total	9 / 12 Passed

Description

100%

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

A strong, well-scoped description that names concrete capabilities, includes an explicit 'Use when' trigger, and uses natural user terminology. It uses third-person imperative voice with no over-claims or padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Build anomaly detection applications', 'implementing univariate/multivariate anomaly detection, time-series analysis, or AI-powered monitoring' — rather than vague language.	3 / 3
Completeness	Clearly answers both what ('Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java') and when via an explicit 'Use when implementing...' trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms a user would say ('anomaly detection', 'time-series analysis', 'univariate/multivariate') alongside the product name, with good variation.	3 / 3
Distinctiveness Conflict Risk	Scoped to a specific named SDK and language ('Azure AI Anomaly Detector SDK for Java'), giving it a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 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: boisenoise/skills-collections
Commit: f36337d

Reviewed: 2 days 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.