azure-kusto
Query and analyze data in Azure Data Explorer (Kusto/ADX) using KQL for log analytics, telemetry, and time series analysis. USE FOR: KQL queries, Kusto database queries, Azure Data Explorer, ADX clusters, log analytics, time series data, IoT telemetry, anomaly detection DO NOT USE FOR: SQL databases, NoSQL queries (use azure-storage), Elasticsearch, AWS analytics tools
88
Quality
82%
Does it follow best practices?
Impact
97%
1.07xAverage score across 3 eval scenarios
Discovery
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.
This is an excellent skill description that hits all the key criteria. It provides specific capabilities, comprehensive trigger terms covering multiple naming conventions (KQL/Kusto/ADX/Azure Data Explorer), explicit 'USE FOR' and 'DO NOT USE FOR' guidance, and clear boundaries to prevent conflicts with similar data analytics skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Query and analyze data', 'log analytics', 'telemetry', 'time series analysis', 'anomaly detection'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what' (query and analyze data in ADX using KQL) and 'when' via explicit 'USE FOR' and 'DO NOT USE FOR' clauses that provide clear trigger guidance and boundary conditions. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'KQL queries', 'Kusto', 'Azure Data Explorer', 'ADX', 'log analytics', 'time series data', 'IoT telemetry'. Includes both acronyms and full names. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit 'DO NOT USE FOR' clause that differentiates from SQL databases, NoSQL/azure-storage, Elasticsearch, and AWS analytics. Clear niche around Azure Data Explorer/KQL specifically. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides strong actionable guidance with executable KQL examples and clear tool references, making it practically useful. However, it suffers from verbosity in explaining concepts Claude already knows (what ADX is, activation triggers) and lacks validation checkpoints in workflows. The content would benefit from trimming explanatory sections and adding explicit error-handling feedback loops.
Suggestions
Remove or significantly trim the 'Skill Activation Triggers', 'Key Indicators', and 'Overview' sections - Claude doesn't need explicit trigger lists or explanations of what Azure Data Explorer is
Add validation checkpoints to the Core Workflow, such as 'Verify query returns expected schema before proceeding with aggregations' or 'Check row count before large joins'
Split advanced content (time series analytics, join patterns, CLI fallbacks) into separate reference files and link from the main skill
Add a feedback loop for query errors: 'If query times out: 1) Add stricter time filter 2) Reduce columns with project 3) Re-run and verify'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary sections like 'Skill Activation Triggers' and 'Key Indicators' that Claude doesn't need explicitly listed. The Overview section explains what Azure Data Explorer is, which Claude already knows. However, the KQL examples and tool references are appropriately concise. | 2 / 3 |
Actionability | Provides fully executable KQL code examples for multiple query patterns, specific tool names with required parameters, and concrete CLI fallback commands. The examples are copy-paste ready and cover common use cases. | 3 / 3 |
Workflow Clarity | The Core Workflow section lists steps but lacks validation checkpoints. For query operations that could timeout or return errors, there's no explicit feedback loop for error recovery. The fallback strategy is good but the main workflow doesn't include verification steps. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but it's a monolithic document with no references to external files for detailed content like advanced KQL patterns or comprehensive troubleshooting. The 200+ line document could benefit from splitting advanced topics into separate files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.