CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

65

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, actionable skill body with strong executable KQL and CLI examples, a clear tool inventory, and useful troubleshooting. Its main weaknesses are redundancy and overview padding that hurt conciseness, plus a monolithic single-file structure with no progressive disclosure to supporting references.

Suggestions

Merge the duplicate 'KQL Best Practices' and 'Best Practices' sections and trim the marketing-style Overview to tighten conciseness.

Add explicit validation/checkpoint steps to the Core Workflow (e.g., verify schema before querying, confirm row counts after execution) to lift workflow clarity.

Move the CLI fallback reference, common issues, and use cases into separate reference files linked from SKILL.md to enable proper progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly efficient operational content, but includes padding such as the marketing-style Overview ("sub-second query performance on billions of records") and two overlapping best-practices sections ("KQL Best Practices" and "Best Practices"), so it could be tightened; it is not level 1 because it avoids explaining basic KQL/library concepts from scratch, and not level 3 due to the redundancy and overview fluff.

2 / 3

Actionability

It provides five complete, copy-paste-ready KQL examples, a concrete MCP tools table with required/optional parameters, and executable Azure CLI fallback commands, matching the 'fully executable code/commands; copy-paste ready' anchor.

3 / 3

Workflow Clarity

The Core Workflow lists four sequenced steps and a fallback strategy with troubleshooting, but lacks explicit validation checkpoints or feedback loops in the core sequence; it is above level 1 because steps are present and ordered, but below level 3 because checkpoints are implicit rather than enforced.

2 / 3

Progressive Disclosure

The skill is a single ~220-line file with no bundle references, and content that could be split out (CLI fallback reference, common issues, use cases) is inline; sections are well-organized so it clears level 1, but with no signaled one-level-deep references it does not reach level 3.

2 / 3

Total

9

/

12

Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that pairs a concrete capability statement with an explicit WHEN trigger clause and a rich set of natural keywords. Its only weakness is a somewhat narrow action verb set (query/analyze) rather than enumerating more distinct operations.

DimensionReasoningScore

Specificity

Names the domain and a couple of concrete actions ("Query and analyze data ... using KQL"), but the verb set is limited to query/analyze rather than a comprehensive list of distinct actions, matching the 'names domain and some actions, but not comprehensive' anchor.

2 / 3

Completeness

It explicitly answers both 'what' ("Query and analyze data ... using KQL for log analytics, telemetry, and time series analysis") and 'when' via an explicit "WHEN:" trigger clause, satisfying the highest anchor; it is not 2 because trigger guidance is explicit rather than implied.

3 / 3

Trigger Term Quality

The WHEN clause lists natural terms users would actually say — "KQL queries, Kusto database queries, Azure Data Explorer, ADX clusters, log analytics, time series data, IoT telemetry, anomaly detection" — giving good coverage, so it is not the level below which only has some relevant keywords.

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche around Azure Data Explorer / Kusto / KQL with distinct triggers unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor rather than the overlapping level 2.

3 / 3

Total

11

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
microsoft/azure-skills
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.