azure-kusto
Query and analyze data in Azure Data Explorer (Kusto/ADX) using KQL for log analytics, telemetry, and time series analysis. WHEN: KQL queries, Kusto database queries, Azure Data Explorer, ADX clusters, log analytics, time series data, IoT telemetry, anomaly detection.
67
58%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/plugins/azure-skills/skills/azure-kusto/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 with excellent trigger term coverage and a clear 'WHEN' clause that makes it easy for Claude to select appropriately. The main weakness is that the 'what' portion could be more specific about concrete actions beyond 'query and analyze data'. Overall it performs well for skill selection purposes.
Suggestions
Expand the capability description with more specific actions, e.g., 'Write and optimize KQL queries, build summarize/join operations, create time series visualizations, detect anomalies' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Azure Data Explorer/Kusto/KQL) and some actions ('query and analyze data'), but doesn't list multiple specific concrete actions like creating queries, joining tables, rendering charts, or specific KQL operations. | 2 / 3 |
Completeness | Clearly answers both 'what' (query and analyze data in Azure Data Explorer using KQL for log analytics, telemetry, and time series analysis) and 'when' (explicit WHEN clause listing trigger scenarios like KQL queries, Kusto database queries, ADX clusters, etc.). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'KQL queries', 'Kusto database', 'Azure Data Explorer', 'ADX clusters', 'log analytics', 'time series data', 'IoT telemetry', 'anomaly detection' — these cover the major variations a user might use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — Azure Data Explorer, KQL, Kusto, and ADX are very specific technologies unlikely to conflict with other skills. The trigger terms are niche and clearly scoped. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill contains useful KQL examples and a solid MCP tools reference, but is severely bloated with content Claude already knows (what ADX is, activation triggers, use cases, generic field descriptions). There is significant redundancy (two best practices sections) and the entire document is monolithic with no progressive disclosure. Cutting the explanatory padding and splitting reference material into linked files would dramatically improve this skill.
Suggestions
Remove the 'Skill Activation Triggers', 'Overview', 'Key Data Fields', 'Result Format', and 'Use Cases' sections entirely — these describe concepts Claude already knows and waste tokens.
Merge the two 'Best Practices' sections and move the combined KQL reference (functions, patterns, best practices) to a separate KQL_REFERENCE.md file linked from the main skill.
Move the CLI fallback commands and troubleshooting to a separate TROUBLESHOOTING.md file, keeping only a brief mention and link in the main skill.
Add a concrete end-to-end example showing actual MCP tool calls with specific parameters (e.g., kusto_query with subscription, cluster, database, and query arguments) rather than just listing parameter names in a table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with significant redundancy. The 'Skill Activation Triggers' section is unnecessary (Claude can infer when to use the skill from the description). 'Overview' explains what Azure Data Explorer is (Claude already knows). 'Key Data Fields' and 'Result Format' sections describe generic concepts. 'Best Practices' appears twice with overlapping content. 'Use Cases' at the end is pure padding. The skill could be cut by 60%+ without losing actionable content. | 1 / 3 |
Actionability | The KQL examples are concrete and executable, and the MCP tools table with parameters is useful. However, much of the content is descriptive rather than instructive (e.g., 'Use for: Quick data inspection'). The CLI fallback section provides executable commands. But the skill lacks a complete end-to-end example showing actual MCP tool invocation with parameters, which would be more actionable. | 2 / 3 |
Workflow Clarity | The 'Core Workflow' provides a 4-step sequence but lacks validation checkpoints. There's no guidance on verifying query results, handling errors mid-workflow, or feedback loops. The fallback strategy section is good but disconnected from the main workflow. For a skill involving queries on production data, there should be explicit validation steps (e.g., check row count before proceeding with large operations). | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. At ~200 lines, the KQL patterns, best practices, CLI fallback, and troubleshooting sections could easily be split into separate reference files. Everything is inline with no navigation structure beyond flat headings. | 1 / 3 |
Total | 6 / 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
- microsoft/azure-skills
- Commit
9d594ab
- 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.