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.

49

Quality

53%

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

57%

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

The content is concise and reasonably actionable with concrete code and build commands, and it is well-structured for a simple skill, but the workflow lacks explicit numbered checkpoints and the code template has a syntax error and placeholders that keep it from being fully copy-paste ready.

Suggestions

Number the workflow steps explicitly (1. Locate the sample, 2. Generate the test, 3. Build: 'dotnet build', 4. If build fails, fix and rebuild) to make the sequence and validation checkpoint unambiguous.

Fix the assertion syntax error ('Is.Equal.To' -> 'Is.EqualTo') and replace placeholder names like TestFeatureName/CallFeatureAsync with concrete guidance on deriving them from the sample.

Remove the redundant re-statement of the <cs_root>/<package_name>/<sample_name> parameters in the 'Basic information' section since they already appear in the frontmatter description.

DimensionReasoningScore

Conciseness

The body is fairly lean and mostly instruction, but the 'Basic information' section restates the <cs_root>/<package_name>/<sample_name> parameters already in the frontmatter and includes some explanatory padding, so it is 'mostly efficient but could be tightened' rather than every token earning its place.

2 / 3

Actionability

It provides a concrete C# test template and executable 'dotnet build' commands, which is more than pseudocode, but the template uses placeholder names (TestFeatureName, CallFeatureAsync) and contains a syntax error ('Is.Equal.To' rather than 'Is.EqualTo'), so it is not fully copy-paste ready as the score-3 anchor requires.

2 / 3

Workflow Clarity

The sequence (look at sample -> generate test -> build -> iterate on error) is present and even includes a feedback loop, but the steps are not explicitly numbered and the validation checkpoint ('If the project does not build, iterate') is implicit rather than a clear 'validate -> fix -> retry' checkpoint, matching the score-2 anchor of 'sequence present but checkpoints missing or implicit'.

2 / 3

Progressive Disclosure

This is a simple, single-purpose skill under 50 lines organized into clearly headed sections (Basic information, Task) with no external references needed; per the scoring note for simple skills, well-organized concise content can score 3 without external file references.

3 / 3

Total

9

/

12

Passed

Description

50%

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 conveys the task and its concrete parameters but lacks an explicit 'Use when' trigger clause, which caps completeness and limits trigger-term quality and distinctiveness.

Suggestions

Add a 'Use when...' clause stating the natural situations in which to invoke this skill (e.g. 'Use when the user asks to write or generate a unit test for an Azure AI C# sample').

Soften the jargon by pairing technical identifiers like 'C# SDK repository root' with natural terms such as 'unit test', 'test file', or 'sample' that users would actually say.

Expand the single 'Generate a test' action with a couple of concrete capabilities (e.g. locating the sample, scaffolding the test in the right file, and building it) to better hit the 'multiple specific concrete actions' anchor.

DimensionReasoningScore

Specificity

It names the concrete domain (generating a C# test from a sample) and lists specific parameters (<cs_root>, <package_name>, <sample_name>) with enumerated package values, but it describes only one core action rather than 'multiple specific concrete actions' as the score-3 anchor requires.

2 / 3

Completeness

It clearly answers 'what does this do', but there is no 'Use when...' clause or any explicit 'when should Claude use it' trigger, which the judging guidelines state must cap completeness at 2.

2 / 3

Trigger Term Quality

'Generate a test given sample' uses natural keywords a user might say, but the description leans on technical jargon ('C# SDK repository root', 'Azure.AI.Projects.Agents') and omits common natural variations like 'unit test' or 'write a test'.

2 / 3

Distinctiveness Conflict Risk

The narrow Azure AI C# package list gives it a clear niche, but without explicit trigger guidance it could still overlap with general test-generation skills, so it does not reach the 'distinct triggers, unlikely to conflict' score-3 anchor.

2 / 3

Total

8

/

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
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.