CtrlK
BlogDocsLog inGet started
Tessl Logo

author-test

Generate a test given sample. Parameters: <cs_root> C# SDK repository root; <package_name> Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; <sample_name> the sample to use as a starting point for the test.

53

Quality

58%

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

Fix and improve this skill with Tessl

tessl review fix ./sdk/ai/.github/skills/azure-ai-projects-author-tests/SKILL.md
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 content is a compact, well-structured single-purpose skill with a clear workflow and a build/iterate feedback loop. Its main weakness is the test template, which is placeholder-like and contains a syntax error, reducing copy-paste actionability.

Suggestions

Fix the assertion syntax in the template (e.g. use NUnit's `Assert.That(result.Value, Is.EqualTo("Expected feature value"))` instead of the invalid `Is.Equal.To`).

Replace placeholder names like CallFeatureAsync and TestFeatureName with concrete guidance on how to derive them from the sample, or label them explicitly as placeholders to fill from the sample.

Collapse the duplicate powershell/bash build blocks into one `dotnet build` snippet unless the shell distinction is meaningful.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, with only minor padding such as duplicating the identical `dotnet build` command in both powershell and bash blocks, fitting the 'efficient; minor instances that could be trimmed' anchor.

4 / 5

Actionability

Provides a concrete test template and build commands, but the template is placeholder/pseudocode (CallFeatureAsync, 'Test cases if any') and contains invalid NUnit syntax (Is.Equal.To), so it is not copy-paste executable, matching the 'some concrete guidance but incomplete; pseudocode' anchor.

3 / 5

Workflow Clarity

The sequence (examine sample -> generate test -> build -> iterate on errors) is clear and includes an explicit validation/feedback loop, with only minor gaps, fitting the 'clear sequence with most checkpoints present' anchor.

4 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references, and is organized with clear section headers (# Basic information, # Task), qualifying for the simple-skill exception that allows a 5 with well-organized sections.

5 / 5

Total

16

/

20

Passed

Description

46%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 clearly states what the skill does and constrains it to a specific SDK niche, but it omits any trigger guidance and lacks natural user keywords, relying on parameter jargon instead. Adding a 'Use when...' clause with natural phrasing would substantially improve it.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill, e.g. 'Use when generating C# tests from SDK samples in the Azure AI packages.'

Replace parameter-only phrasing with natural trigger terms a user would say, such as 'write a test', 'generate a unit test', or 'create a recorded test from a sample'.

Lead with the action in third person and keep the parameter list as supporting detail rather than the bulk of the description.

DimensionReasoningScore

Specificity

Names the domain and one concrete action ("Generate a test given sample") plus a concrete enumeration of three valid package names, but action coverage is narrow with only a single verb, fitting the '1-2 concrete actions, not comprehensive' anchor.

3 / 5

Completeness

Provides a clear 'what' (generate a test from a sample) but no 'when'/trigger guidance whatsoever; per the rubric, a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Contains only generic technical phrasing ("Generate a test given sample") and parameter jargon with no natural keywords a user would actually say and no synonyms, matching the 'one or two generic keywords; missing the natural phrases' anchor.

2 / 5

Distinctiveness Conflict Risk

Tied to specific Azure SDK package names, giving it a clear niche with only minor overlap risk against other test-generation skills, though the total absence of trigger phrases slightly weakens distinguishability.

4 / 5

Total

12

/

20

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
Azure/azure-sdk-for-net
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.