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.
78
73%
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/antigravity-azure-ai-anomalydetector-java/SKILL.mdQuality
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 solid skill description that clearly identifies its niche (Azure AI Anomaly Detector SDK for Java) and provides explicit trigger guidance. The main weakness is that the 'what' portion could be more specific about concrete actions beyond 'build applications'. The trigger terms and distinctiveness are strong due to the specific technology stack.
Suggestions
Add more concrete actions to the capability description, e.g., 'detect point anomalies, identify changepoints, train multivariate models, analyze time-series data' instead of the general 'build anomaly detection applications'.
| 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 multiple concrete actions like 'detect anomalies in streaming data, train multivariate models, configure detection sensitivity'. | 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 an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'anomaly detection', 'Azure AI', 'Anomaly Detector SDK', 'Java', 'univariate', 'multivariate', 'time-series analysis', 'monitoring'. Good coverage of terms a developer working in this space would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific combination of Azure AI Anomaly Detector + SDK + Java. Unlikely to conflict with other skills unless there are multiple Azure anomaly detection skills for different languages. | 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.
The skill excels at actionability with comprehensive, executable Java code examples covering the full Azure Anomaly Detector API surface. However, it suffers from being a monolithic reference document that should be split into focused sub-files, and it includes unnecessary conceptual explanations and boilerplate sections. The multivariate workflow would benefit from explicit validation checkpoints and polling loops.
Suggestions
Split the content into a concise SKILL.md overview with quick-start examples, and move detailed patterns into separate files (e.g., UNIVARIATE.md, MULTIVARIATE.md, MODEL_MANAGEMENT.md) with clear navigation links.
Add explicit polling/validation loops for the multivariate training workflow (e.g., poll until status is READY, handle FAILED status) and batch inference (poll until complete with timeout).
Remove the 'Key Concepts', 'Trigger Phrases', 'When to Use', and 'Limitations' boilerplate sections — these either belong in frontmatter or are things Claude already knows.
Remove or condense the 'Best Practices' section into inline comments within the relevant code examples to reduce redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with executable code examples, but includes some unnecessary sections like 'Key Concepts' explaining what univariate/multivariate detection is (Claude already knows this), 'Trigger Phrases' which belong in frontmatter, and boilerplate 'When to Use' / 'Limitations' sections that add no value. The code examples themselves are well-structured but the overall document could be tightened. | 2 / 3 |
Actionability | The skill provides fully executable Java code examples covering all major use cases: client creation, univariate batch/streaming detection, change point detection, multivariate training/inference, model management, and error handling. Code is copy-paste ready with proper imports and realistic usage patterns. | 3 / 3 |
Workflow Clarity | The multivariate workflow (train → inference → results) is presented but lacks explicit validation checkpoints. For example, after training a model, the code checks status but doesn't include a polling loop or explicit 'wait until ready before proceeding' step. The batch inference similarly shows polling but without a proper feedback loop for handling failures or retrying. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with all API patterns inlined in a single file. At ~200 lines of code examples covering univariate, multivariate, model management, and error handling, this would benefit significantly from splitting into separate reference files (e.g., UNIVARIATE.md, MULTIVARIATE.md) with a concise overview in the main skill file. | 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
- boisenoise/skills-collections
- Commit
431bfad
- 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.