CtrlK
BlogDocsLog inGet started
Tessl Logo

translate-a-sample

Translate the Azure SDK sample from python to C# and generate markdownn file for the sample. Parameters: <cs_root> C# SDK repository root; <python_root> python SDK repository root; <package_name> Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; <sample_name> The name of sample file in Python SDK repository.

54

Quality

60%

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-sample-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The body gives concrete, executable examples and a clear validate-and-iterate workflow, but loses points to redundant code blocks, an incorrect bash validation snippet, and a monolithic structure with no progressive disclosure to the bundled script.

Suggestions

Fix the bash validation block: replace the backslash Windows path and .ps1 invocation with the correct PowerShell command (or remove the bash block), and align the <package> placeholder with <package_name>.

Collapse the duplicate async/sync example into one annotated block highlighting only the await/Async differences to reduce token cost.

Reference the bundled scripts/Program.cs (and any convention doc) explicitly from the body so the example structure is discoverable, or extract the region-snippet convention into a references/ file.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes Claude's competence, but the near-identical Asynchronous and Synchronous code blocks repeat a large snippet that differs only in await/Async suffixes, which could be tightened by showing one block and noting the difference.

2 / 3

Actionability

Concrete, largely executable C# examples and a real region-marking convention are provided, but the bash validation block incorrectly runs a Windows .ps1 script with backslash paths under bash, and placeholder names are inconsistent (<package> vs <package_name>).

2 / 3

Workflow Clarity

The process is sequenced (analyze sample → generate C# + .md → split into region blocks → run Update-Snippets.ps1) with an explicit validation feedback loop: "If there are errors, please iterate over it until the script will complete without errors."

3 / 3

Progressive Disclosure

Sections are present and the skill is self-contained, but at ~78 lines all content is inline with no signaled references; the bundled scripts/Program.cs is not referenced from the body, and the example conventions could live in a separate reference file.

2 / 3

Total

9

/

12

Passed

Description

57%

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 conveys a clear, distinctive purpose and concrete actions but is weakened by a missing "Use when..." trigger clause, jargon-heavy terms, and minor typos ("markdownn"). It answers "what" well but only implies "when."

Suggestions

Add an explicit trigger clause, e.g. "Use when translating an Azure AI SDK Python sample to C# and generating its markdown documentation."

Lead with the natural user-facing phrasing ("translate a Python sample to C#") before the parameter list, and surface common variations like "port", "convert", or "C# sample".

Fix the "markdownn" typo and move the long parameter enumeration into the body, keeping the description concise.

DimensionReasoningScore

Specificity

Names the domain (Azure SDK sample translation) and two concrete actions — "Translate the Azure SDK sample from python to C#" and "generate markdownn file" — but the rest of the description is parameter listing rather than additional actions, so it is not comprehensive.

2 / 3

Completeness

It clearly states what the skill does, but there is no "Use when..." clause or equivalent explicit guidance for when Claude should invoke it, which per the rubric caps completeness at 2.

2 / 3

Trigger Term Quality

Some relevant natural terms appear ("translate", "python to C#", "Azure SDK sample"), but the trigger space is dominated by technical jargon (Azure.AI.Projects, Azure.AI.Extensions.OpenAI) with no common variations or explicit trigger guidance.

2 / 3

Distinctiveness Conflict Risk

The niche is narrow and specific — translating Azure SDK samples from Python to C# for a fixed set of package names — making it unlikely to trigger for the wrong skill.

3 / 3

Total

9

/

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.