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.
Install with Tessl CLI
npx tessl i github:boisenoise/skills-collections --skill azure-ai-anomalydetector-java89
Quality
84%
Does it follow best practices?
Impact
98%
2.33xAverage score across 3 eval scenarios
Discovery
89%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 well-crafted skill description that clearly identifies its niche (Azure AI Anomaly Detector SDK for Java) and provides explicit 'Use when' guidance. The main weakness is that the capabilities could be more specific about concrete actions beyond the general categories of anomaly detection types.
Suggestions
Add more specific concrete actions like 'detect data spikes', 'identify seasonal patterns', 'train detection models', or 'configure sensitivity thresholds' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Azure AI Anomaly Detector SDK for Java) and mentions some actions (univariate/multivariate anomaly detection, time-series analysis), but doesn't list comprehensive concrete actions like 'detect spikes', 'identify trends', or 'configure detection models'. | 2 / 3 |
Completeness | Clearly answers both what ('Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java') and when ('Use when implementing univariate/multivariate anomaly detection, time-series analysis, or AI-powered monitoring') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms: 'anomaly detection', 'univariate/multivariate', 'time-series analysis', 'AI-powered monitoring', 'Azure AI', 'Java', 'SDK'. These are terms users working in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific technology stack (Azure AI Anomaly Detector SDK for Java) and clear niche (anomaly detection). Unlikely to conflict with other skills due to the specific platform, language, and use case combination. | 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 well-crafted SDK reference skill with excellent actionability and conciseness. The code examples are complete and executable, covering both univariate and multivariate detection patterns. The main weaknesses are the lack of explicit validation/error recovery workflows for long-running operations and the monolithic structure that could benefit from progressive disclosure to separate files.
Suggestions
Add explicit validation checkpoints for multivariate model training, including polling for completion status and handling failed training states before proceeding to inference
Consider splitting detailed patterns (univariate vs multivariate) into separate reference files with SKILL.md providing a quick-start overview and navigation
Add a feedback loop example showing how to handle and retry failed batch detection operations
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, jumping directly into installation, client creation, and code examples without explaining what anomaly detection is or how Azure services work. Every section provides actionable information. | 3 / 3 |
Actionability | All code examples are complete, executable Java code with proper imports. Examples cover the full workflow from client creation through detection and model management, ready for copy-paste use. | 3 / 3 |
Workflow Clarity | The multivariate workflow (Train → Inference → Results) is mentioned but lacks explicit validation checkpoints. The training status check is shown but there's no feedback loop for handling failed training or validation of results before proceeding. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but it's a monolithic document (~200 lines) that could benefit from splitting detailed patterns into separate reference files. No external file references are provided for advanced topics. | 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.