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

68%

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/antigravity-azure-ai-projects-dotnet/SKILL.md

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.

A strongly actionable SDK reference: complete, executable code for all major workflows, clear section organization, and a useful client-hierarchy map. Its weaknesses are structural rather than instructional — everything is inlined in one long file with no progressive disclosure, and it carries boilerplate padding ('When to Use', duplicated install commands, bare version numbers) that could be trimmed or moved to reference files.

Suggestions

Move the 'Available Agent Tools', 'Key Types Reference', and 'Related SDKs' tables into a references/ file (e.g. references/types-and-tools.md) and link to them from the body, keeping SKILL.md as a lean overview.

Handle terminal failure in the polling loop — check run.Status == RunStatus.Failed and surface run.LastError before reading messages — and note verification before destructive deletes.

Cut the generic 'When to Use' filler and the 'Related SDKs' install-command duplication; keep version numbers in a dedicated, clearly-dated section or remove them.

Dimension	Reasoning	Score
Conciseness	The body is code-heavy with almost no explanation of concepts Claude already knows, but it contains padding and redundancy: the 'Related SDKs' table repeats install commands from 'Installation', the 'When to Use' section is generic filler ('This skill is applicable to execute the workflow or actions described in the overview'), and time-sensitive version info ('Current Versions: GA v1.1.0, Preview v1.2.0-beta.5') sits outside any old-patterns section. This matches 'mostly efficient but could be tightened' rather than the minor-trim anchor.	3 / 5
Actionability	Eight fully executable, copy-paste-ready C# workflows (auth, agent create/run/poll/messages, connections, deployments, datasets, indexes, evaluations, chat client) plus a concrete RequestFailedException error-handling block cover the common cases, matching the 'fully executable, copy-paste ready' anchor.	5 / 5
Workflow Clarity	Workflows are clearly sequenced with an explicit polling checkpoint ('do { await Task.Delay(500); ... } while (run.Status == RunStatus.Queued \|\| run.Status == RunStatus.InProgress)') and a dedicated error-handling section, but there are minor validation gaps: the poll loop never branches on RunStatus.Failed, and destructive cleanup (DeleteThreadAsync, DeleteAgentAsync, Datasets.Delete, Indexes.Delete) has no verification steps.	4 / 5
Progressive Disclosure	No bundle files exist (no references/, scripts/, or assets/), and everything — including the 'Available Agent Tools' table, 'Key Types Reference', 'Related SDKs', and 'Reference Links' sections — is inlined in a single ~350-line SKILL.md. Sections are clearly headed and organized, but reference material that belongs in separate one-level-deep files is inline, matching the anchor-3 example.	3 / 5
	Total	15 / 20 Passed

Description

66%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 specific, well-scoped description that clearly identifies the niche and enumerates the SDK's capability areas, but it is one-sided: it answers 'what' thoroughly while omitting any 'when to use' trigger guidance. Adding a 'Use when...' clause with natural user phrases would raise both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when working with Azure AI Foundry projects, AI agents, or Azure.AI.Projects in .NET/C# applications.'

Include natural synonyms users would say — 'C#', 'AI Foundry', 'persistent agents', 'Azure AI agents' — to improve trigger-term coverage.

Phrase capabilities as actions ('create and poll AI agents', 'upload datasets', 'run evaluations') rather than listing bare domain nouns.

Dimension	Reasoning	Score
Specificity	Names the domain ('Azure AI Projects SDK for .NET') and lists six concrete capability areas ('agents, connections, datasets, deployments, evaluations, and indexes'), but these are domain nouns rather than action verbs, so coverage is comprehensive in scope yet not action-phrased like the anchor-5 examples.	4 / 5
Completeness	Has a clear 'what' ('High-level client for Azure AI Foundry projects including agents, connections, datasets, deployments, evaluations, and indexes') but no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes natural terms users of this stack would say — 'Azure AI Projects', '.NET', 'Azure AI Foundry', 'agents', 'deployments', 'evaluations' — but misses common variations such as 'C#', 'AI Foundry agents', or 'persistent agents', so it falls short of the comprehensive-synonym anchor.	4 / 5
Distinctiveness Conflict Risk	'Azure AI Projects SDK for .NET' is a clear niche with minimal conflict risk against generic skills, but it overlaps with closely related Azure OpenAI / Azure AI .NET SDK skills (the body itself covers obtaining an Azure OpenAI chat client) and offers no trigger phrasing to disambiguate, so it is mostly distinct rather than fully.	4 / 5
	Total	15 / 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: boisenoise/skills-collections
Path: skills/antigravity-azure-ai-projects-dotnet/SKILL.md
Commit: 7390864

Reviewed: 5 days 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.