azure-ai-projects-dotnet

Azure AI Projects SDK for .NET. High-level client for Azure AI Foundry projects including agents, connections, datasets, deployments, evaluations, and indexes.

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/azure-ai-projects-dotnet/SKILL.md

Quality

Content

57%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 a dense, actionable SDK reference with eight executable workflows, but it inlines reference material and time-sensitive version info that belong in separate files or a versioned section, and its destructive workflows lack validation checkpoints. Splitting reference tables into bundle files and adding pre-delete verification would lift the weaker dimensions.

Suggestions

Add explicit validation/verification checkpoints before destructive calls (e.g. confirm a dataset exists and prompt before `Datasets.Delete(...)`), to lift workflow_clarity above the destructive-operation cap of 3.

Move the Key Types Reference, Available Agent Tools, and Related SDKs tables into separate bundle files under references/ and link to them one level deep, so SKILL.md stays a lean overview.

Relocate time-sensitive version numbers ("GA v1.1.0, Preview v1.2.0-beta.5") into a dedicated versions/deprecation section rather than inline prose, and remove the redundant install commands repeated in the Related SDKs table.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient, code-first reference that assumes Claude's competence, but inlines time-sensitive version numbers ("GA v1.1.0, Preview v1.2.0-beta.5") outside any deprecated/old-patterns section and includes redundant cross-reference tables ("Related SDKs" repeats install commands), which could be tightened.	3 / 5
Actionability	Eight numbered workflows provide concrete, executable C# with real class and method names plus env vars and install commands, with only minor gaps (some examples reference implicitly-bound variables and mix sync/async calls).	4 / 5
Workflow Clarity	Workflows are clearly sequenced and the agent flow includes a poll-until-complete checkpoint, but destructive operations (deleting datasets, indexes, and agent versions) lack pre-deletion validation/verification, which per the rubric caps workflow clarity at 3.	3 / 5
Progressive Disclosure	No bundle files exist and all reference material (Key Types, Available Agent Tools, Related SDKs, Reference Links) is inlined into a single SKILL.md with no one-level-deep bundle references; section headers provide decent organization, but content that should be split into separate files is inline.	3 / 5
	Total	13 / 20 Passed

Description

58%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 identifies the product and enumerates its capability areas but omits any explicit "when to use" trigger guidance, which caps its completeness. It is specific and mostly distinct, yet lacks the natural task-level keywords that would maximize trigger quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when working with Azure AI Foundry projects in .NET — creating agents, managing connections, datasets, deployments, evaluations, or indexes."

Add natural task-level keywords users would say, such as "create an Azure AI agent", "deploy a model", or "run an evaluation".

Express capabilities as concrete verb-actions (e.g. "create, list, and delete agents") rather than a bare noun list to lift specificity toward 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas ("agents, connections, datasets, deployments, evaluations, and indexes") for the named domain, though capabilities are stated as nouns rather than verb-actions, leaving minor coverage gaps.	4 / 5
Completeness	Has a clear "what" but no "Use when..." or equivalent trigger clause; per the rubric a missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant product terms a user would say ("Azure AI Projects SDK for .NET", "Azure AI Foundry projects") but misses common task-level variations and synonyms like "create Azure AI agent" or "deploy a model".	3 / 5
Distinctiveness Conflict Risk	The specific product name "Azure AI Projects SDK for .NET" / "Azure AI Foundry projects" makes it mostly distinct, with only minor overlap risk against closely related Azure AI SDKs.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/azure-ai-projects-dotnet/SKILL.md
Commit: 1f67c44

Reviewed: about 15 hours ago

Table of Contents

Discovery Implementation Validation

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.