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.

Quality

77%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.github/plugins/azure-skills/skills/azure-kusto/SKILL.md

Quality

Content

65%

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

The body is highly actionable with concrete executable KQL and CLI examples, but it is padded with redundant trigger/marketing text and presents everything in a single long file with no progressive disclosure to reference materials. Workflow sequencing is present but lacks embedded validation checkpoints.

Suggestions

Remove the Overview marketing line and the redundant Skill Activation Triggers / Key Indicators sections, since the description already carries the WHEN triggers.

Add inline validation checkpoints to the Core Workflow (e.g., verify the table/schema exists before querying, confirm results are non-empty before analyzing).

Split the CLI command reference and KQL query patterns into reference files under references/ and link to them one level deep to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The Overview restates the description and adds marketing language ("sub-second query performance on billions of records"), and the Skill Activation Triggers / Key Indicators sections duplicate the description's WHEN triggers; it is mostly efficient but carries padding Claude does not need.	2 / 3
Actionability	It provides four executable KQL examples, exact az kusto and az rest CLI fallback commands, and an MCP tool table with concrete required/optional parameters, all copy-paste ready.	3 / 3
Workflow Clarity	The Core Workflow gives a clear four-step sequence but embeds no validation checkpoints; error handling lives only in a separate Common Issues / When to Fallback section rather than as inline feedback loops, fitting the level-2 anchor.	2 / 3
Progressive Disclosure	The skill is a ~230-line monolithic SKILL.md with no bundle or reference files, and content that could be split (CLI reference, query patterns) is inline; the under-50-line simple-skill exemption does not apply, so it lands at level 2.	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 description that clearly states both capability and trigger conditions with natural, distinctive terms. The only mild weakness is that the capability list relies on two general verbs plus domains rather than a richer set of specific actions.

Dimension	Reasoning	Score
Specificity	It names two concrete actions ("Query and analyze data") plus several domains, but does not list a comprehensive set of specific actions like the level-3 anchor; it leans more on use-case domains than on distinct concrete operations.	2 / 3
Completeness	It explicitly states what it does ("Query and analyze data in Azure Data Explorer (Kusto/ADX) using KQL...") and provides an explicit WHEN trigger clause, satisfying both halves required for level 3.	3 / 3
Trigger Term Quality	The WHEN clause covers the natural terms users say ("KQL queries", "Kusto database queries", "Azure Data Explorer", "ADX clusters") with both full and abbreviated product names, matching the level-3 coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Kusto/ADX/KQL is a clear, well-defined niche with distinct product-specific triggers that are unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/azure-skills
Commit: 39464cb

Reviewed: about 6 hours ago

Table of Contents

Discovery Implementation Validation

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.