azure-kusto
**ANALYSIS SKILL** — Query and analyze data in Azure Data Explorer (Kusto/ADX) using KQL. WHEN: "KQL queries", "Kusto database queries", "Azure Data Explorer", "ADX clusters", "time series data", "IoT telemetry", "anomaly detection". DO NOT USE FOR: App Insights / Log Analytics troubleshooting (azure-diagnostics), cost analysis (azure-cost-optimization).
68
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
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 strong skill description with excellent trigger term coverage, clear completeness (both what and when), and outstanding distinctiveness through explicit exclusion clauses. The main weakness is that the specificity of capabilities could be improved by listing more concrete actions beyond the general 'query and analyze data'. Overall, it would perform well in a multi-skill selection scenario.
Suggestions
Expand the capability description with more specific actions, e.g., 'Write and optimize KQL queries, build time series analyses, detect anomalies, aggregate and visualize telemetry data in Azure Data Explorer (Kusto/ADX).'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Azure Data Explorer/Kusto/ADX) and the general action ('Query and analyze data'), but doesn't list multiple specific concrete actions like writing KQL queries, building time series analyses, creating dashboards, or detecting anomalies. The action is somewhat generic. | 2 / 3 |
Completeness | Clearly answers both 'what' (query and analyze data in Azure Data Explorer using KQL) and 'when' (explicit WHEN clause with trigger terms). Additionally includes a 'DO NOT USE FOR' clause that helps with disambiguation, which goes beyond the minimum requirements. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'KQL queries', 'Kusto database queries', 'Azure Data Explorer', 'ADX clusters', 'time series data', 'IoT telemetry', 'anomaly detection'. These are terms users would naturally use when needing this skill, covering both acronyms and full names. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (Azure Data Explorer/KQL specifically). The explicit 'DO NOT USE FOR' clause proactively prevents conflicts with related Azure skills like azure-diagnostics and azure-cost-optimization, making it very unlikely to trigger incorrectly. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%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-organized, concise skill that effectively serves as an overview document with good progressive disclosure to reference files. Its main weakness is the lack of inline executable examples—at least one concrete KQL query and one MCP tool invocation would significantly improve actionability. The workflow could also benefit from explicit validation/error-handling steps, particularly around query timeouts and fallback scenarios.
Suggestions
Add at least one concrete, executable KQL query example inline (e.g., a basic time-filtered query using kusto_query) so the skill is immediately actionable without loading references.
Add a validation/error-handling step to the workflow, such as: 'If kusto_query times out or returns an auth error, follow fallback-strategy.md' to create a feedback loop.
Include a minimal MCP tool invocation example showing required parameters filled in with realistic placeholder values (e.g., a kusto_query call with subscription, cluster, database, and a sample KQL expression).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what KQL, Azure Data Explorer, or time-series data are—concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary elaboration. | 3 / 3 |
Actionability | The skill provides concrete tool names, parameter lists, and clear rules, but lacks executable code/command examples. There are no copy-paste-ready KQL queries or CLI commands inline—those are deferred to reference files. The quick reference table describes patterns but doesn't show them. | 2 / 3 |
Workflow Clarity | The four-step workflow (discover → explore → query → analyse) provides a clear sequence, but lacks validation checkpoints or error-handling feedback loops. For a data querying skill involving potentially large datasets and MCP tool interactions, there's no guidance on what to do if queries time out, return unexpected results, or if schema discovery reveals issues. | 2 / 3 |
Progressive Disclosure | The skill is well-structured as an overview with clear, one-level-deep references to query-patterns.md and fallback-strategy.md. The Reference Index table explicitly signals when to load each file. Content is appropriately split between the overview and detailed references. | 3 / 3 |
Total | 10 / 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.
- Repository
- jonathan-vella/azure-agentic-infraops
- Commit
05d7617
- 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.