CtrlK
BlogDocsLog inGet started
Tessl Logo

analyze-skill-issues

Query the integration-test storage account to find why a specific skill's tests are failing. Reads blob-stored test result files and surfaces error details. TRIGGERS: why is skill failing, skill test failures, debug skill tests, skill failing tests, analyze skill failures, why are tests failing for skill, skill test errors, investigate skill issues. DO NOT USE FOR: analyzing a GitHub Actions run report or comparing test runs across runs (use analyze-test-run).

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

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

The body is well-structured and actionable with a clear phased workflow and clean progressive disclosure via a single reference file. Its main weakness is conciseness: the Referenced Files requirement and tool-responsibility note are stated redundantly.

Suggestions

State the Referenced Files / $env:TEMP requirement once in Output Requirements and reference it from later phases instead of repeating the full callout four times.

Consolidate the repeated 'mcp_azure_mcp_storage_blob_get for discovery, az storage blob download for content' tool-responsibility note into a single MANDATORY block to remove triplication.

Tighten Phase 1 step 2 by giving the date filter as a concrete inline example (e.g. a date regex) rather than prose, reducing ambiguity for Claude.

DimensionReasoningScore

Conciseness

Mostly efficient with tables and code blocks, but the Referenced Files / echo $env:TEMP requirement is repeated 4+ times and the tool-responsibility note repeats 3 times — more than minor padding.

3 / 5

Actionability

Provides concrete, executable tool calls (mcp_azure_mcp_storage_blob_get({...}) and an az storage blob download PowerShell command with real parameters) plus specific JSON keys and XML elements to look for, with only minor gaps (placeholders, filter logic left to Claude).

4 / 5

Workflow Clarity

A clear 4-phase sequence with explicit scope limits ('3 most recent dates', 'Stop as soon as failures are found') and skip/retry guidance for unreadable blobs; not a 5 because there is no true validate->fix->retry loop, though the operation is read-only so the destructive cap does not apply.

4 / 5

Progressive Disclosure

Well-organized sections with clearly signaled, one-level-deep anchored references to references/blob-structure.md (#blob-path-layout, #skill-name-mapping) — both anchors verified present — and the bulk detail appropriately split out of the overview.

5 / 5

Total

16

/

20

Passed

Description

95%Weight 40%Scale 1-5

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

The description is specific, trigger-rich, and clearly bounded, explicitly stating both what the skill does and when to use it. It distinguishes itself from sibling skills via an explicit DO NOT USE FOR clause.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Query the integration-test storage account', 'Reads blob-stored test result files', 'surfaces error details'), with only minor coverage gaps versus the comprehensive 5-anchor list.

4 / 5

Completeness

Explicitly answers both what ('Query…Reads blob-stored…surfaces error details') and when (a TRIGGERS list plus a DO NOT USE FOR clause), matching the 5-anchor example structure.

5 / 5

Trigger Term Quality

Nine natural trigger phrases plus synonyms ('why is skill failing', 'debug skill tests', 'skill test errors', 'investigate skill issues') and an explicit DO NOT USE FOR boundary give comprehensive coverage of terms a user would actually say.

5 / 5

Distinctiveness Conflict Risk

A narrow niche (integration-test storage for a specific skill) with a DO NOT USE FOR redirect to a sibling skill yields a clear niche with minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
microsoft/GitHub-Copilot-for-Azure
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.