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.
57
66%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-azure-ai-projects-dotnet/SKILL.mdQuality
Discovery
67%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 is strong on specificity and distinctiveness, clearly identifying the SDK, platform, and concrete capabilities. However, it lacks an explicit 'Use when...' clause, which is critical for Claude to know when to select this skill. Adding natural trigger terms and user-facing language would improve selection accuracy.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user needs to work with Azure AI Foundry projects in .NET, including creating agents, managing deployments, or running evaluations.'
Include common user-facing trigger terms like 'C#', 'Azure.AI.Projects NuGet package', or 'AI Foundry SDK' to capture natural variations of how users might reference this technology.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete capabilities: agents, connections, datasets, deployments, evaluations, and indexes. Also specifies the SDK name, platform (.NET), and that it's a high-level client for Azure AI Foundry projects. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (high-level client for Azure AI Foundry projects with specific sub-capabilities), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Azure AI', '.NET', 'agents', 'deployments', 'evaluations', but misses common user variations like 'C#', 'NuGet', 'Azure.AI.Projects', or mentioning specific use cases users might describe naturally. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche: Azure AI Projects SDK for .NET. The combination of Azure AI Foundry, .NET, and the specific feature list (agents, connections, datasets, etc.) makes it clearly distinguishable from other skills and unlikely to conflict. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid SDK reference skill with excellent actionability — nearly every section has complete, executable C# code examples covering the full breadth of the Azure.AI.Projects SDK. However, it's overly long for a single SKILL.md file, includes some boilerplate sections that don't add value, and lacks integrated validation/error recovery in most workflows beyond the basic agent example.
Suggestions
Integrate error handling and validation checkpoints directly into multi-step workflows (e.g., evaluation creation should show polling for completion status, dataset upload should verify success).
Remove boilerplate sections ('When to Use', 'Limitations') and trim Best Practices to only non-obvious guidance that Claude wouldn't already know.
Consider splitting detailed workflow examples (agents, evaluations, datasets) into separate referenced files to keep SKILL.md as a concise overview with quick-start examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary sections like 'When to Use' and 'Limitations' which are boilerplate filler. The Best Practices section contains some advice Claude already knows (e.g., use async for I/O, handle pagination). The client hierarchy diagram and reference tables are efficient, but overall the document is quite long (~300 lines) and could be tightened. | 2 / 3 |
Actionability | All code examples are fully executable C# with proper using statements, concrete method calls, and complete workflows including setup, execution, and cleanup. Each workflow section provides copy-paste ready code covering agents, connections, deployments, datasets, indexes, evaluations, and chat clients. | 3 / 3 |
Workflow Clarity | The agent workflow includes polling and cleanup steps which is good, but most other workflows (datasets, indexes, evaluations) lack validation checkpoints or error recovery steps. The error handling section is separate and generic rather than integrated into workflows. The evaluation workflow doesn't show how to poll for completion status, which is a gap for an async operation. | 2 / 3 |
Progressive Disclosure | The content is a monolithic single file with no bundle files to reference. While it has clear section headers and tables, the document is very long and would benefit from splitting detailed API examples into separate files. The Reference Links section points to external resources but there's no internal progressive disclosure structure. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- boisenoise/skills-collections
- Commit
8ac11ab
- 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.