CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-ai-openai-dotnet

Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants.

87

1.43x
Quality

83%

Does it follow best practices?

Impact

92%

1.43x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is azure-ai-openai-dotnet in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A highly actionable, well-organized SDK reference packed with executable examples and useful error-handling guidance. Its weaknesses are length/time-sensitivity (a pinned version and a throwaway closing line) and total absence of progressive disclosure — everything is inlined into one file.

Suggestions

Move the pinned "Current Version: 2.1.0" out of the body or into a clearly marked version/compatibility note, and drop the vague "When to Use" boilerplate closing line.

Split the Key Types Reference table and the longer worked examples (structured outputs, RAG, function calling) into a references/ file linked from a short overview, so SKILL.md loads fewer tokens by default.

DimensionReasoningScore

Conciseness

The body is mostly lean executable code with little concept padding, but it is long (~450 lines), includes time-sensitive info not in a deprecated section ("Current Version: 2.1.0 (stable)"), and ends with a vague boilerplate "When to Use" line, so it sits at anchor 4 with minor trim opportunities rather than 5.

4 / 5

Actionability

Dozens of copy-paste-ready C# snippets cover the common cases (basic/async/streaming chat, embeddings, DALL-E, Whisper/TTS, function calling, structured outputs, RAG, error handling), matching the anchor 5 example of fully executable guidance across common cases.

5 / 5

Workflow Clarity

As a reference skill it has no destructive/batch multi-step workflow, but the Client Hierarchy diagram makes client selection unambiguous and the Error Handling section provides a 429 retry feedback loop; this is clear organization with a basic recovery loop, fitting anchor 4 rather than 5's full validate-fix-retry checklist.

4 / 5

Progressive Disclosure

All ~450 lines live in a single SKILL.md with no bundle files and no links to separate reference files; it has clear section headers (so above anchor 2's "no structure" wall of text) but content like the Key Types table and extensive API examples is inlined where a separate reference file would be appropriate, matching anchor 3.

3 / 5

Total

16

/

20

Passed

Description

88%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.

A strong description: it concisely states the platform-specific library and gives an explicit "Use for" trigger clause listing five concrete capabilities. The main gap is missing common synonyms (GPT, DALL-E, Whisper, TTS) that users naturally say.

Suggestions

Add natural synonyms/model names to the trigger list (e.g., "GPT chat completions, DALL-E image generation, Whisper audio transcription/TTS") so it matches how users phrase requests.

Clarify the Azure-vs-OpenAI boundary to reduce overlap with a non-Azure OpenAI skill, e.g. "Use for Azure OpenAI (and OpenAI-compatible) workloads in .NET".

DimensionReasoningScore

Specificity

Names the domain ("Azure OpenAI SDK for .NET") and lists multiple concrete capabilities — "chat completions, embeddings, image generation, audio transcription, and assistants" — giving comprehensive coverage, matching the anchor 5 example of several specific concrete actions.

5 / 5

Completeness

It explicitly answers both what ("Client library for Azure OpenAI and OpenAI services") and when ("Use for chat completions, embeddings, image generation, audio transcription, and assistants") with concrete trigger phrases, matching the anchor 5 example closely.

5 / 5

Trigger Term Quality

"chat completions, embeddings, image generation, audio transcription, and assistants" are natural developer terms, but common synonyms a user might say (GPT, DALL-E, Whisper, text-to-speech/TTS) are absent, so it falls just below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Azure OpenAI SDK for .NET" is a clear, distinct niche, but the "and OpenAI services" compatibility clause and generic trigger list create minor overlap risk with a hypothetical plain-OpenAI skill, placing it at anchor 4 rather than 5.

4 / 5

Total

18

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.