azure-ai-agents-persistent-dotnet
Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools.
57
48%
Does it follow best practices?
Impact
Pending
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-agents-persistent-dotnet/SKILL.mdQuality
Discovery
32%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 identifies a specific technology domain (Azure AI Agents Persistent SDK for .NET) and lists key SDK concepts, which provides some useful context. However, it lacks a 'Use when...' clause, reads more like a product tagline than an actionable skill description, and doesn't enumerate concrete actions Claude would perform with this skill.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about creating or managing Azure AI agents using the .NET Persistent Agents SDK, or mentions PersistentAgentsClient, AgentThread, or ThreadRun.'
List concrete actions instead of abstract concepts, e.g., 'Creates AI agents, manages conversation threads, sends and retrieves messages, executes agent runs, and configures tools like code interpreter and file search.'
Include common user-facing trigger terms and variations such as 'C#', 'Azure OpenAI agents', 'assistant API', 'PersistentAgentsClient', and '.NET agent SDK'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Azure AI Agents SDK for .NET) and lists some concepts (threads, messages, runs, tools), but these are more like SDK abstractions than concrete user-facing actions. It doesn't describe specific actions like 'create agents', 'manage conversation threads', or 'configure tool integrations'. | 2 / 3 |
Completeness | Describes what the skill covers (Azure AI Agents SDK concepts) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' portion is also only moderately clear, warranting a score of 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Azure', 'AI Agents', '.NET', 'SDK', 'threads', 'messages', 'runs', and 'tools' which users might mention. However, it misses common variations like 'C#', 'Azure OpenAI', 'assistant API', 'agent orchestration', or 'PersistentAgentsClient'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Azure AI Agents Persistent SDK for .NET' is fairly specific and distinguishes it from generic coding skills. However, it could overlap with other Azure SDK skills, general AI agent skills, or .NET development skills without clearer scoping of when to use it versus those alternatives. | 2 / 3 |
Total | 7 / 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, highly actionable SDK reference skill with excellent executable code examples covering the full range of Azure AI Agents Persistent functionality. Its main weaknesses are its length (could benefit from progressive disclosure by splitting advanced tool examples into separate files) and the lack of explicit validation/error recovery steps within the core workflow beyond a brief best practices mention. The boilerplate 'When to Use' and 'Limitations' sections at the end add no meaningful value.
Suggestions
Add explicit validation checkpoints in the polling workflow—e.g., handle RunStatus.Failed and RunStatus.Cancelled with error messages and recovery guidance, not just a best-practice bullet point.
Split advanced tool examples (function calling, file search, Bing grounding, Azure AI Search) into a separate TOOLS.md file and reference it from the main skill to reduce the monolithic length.
Remove the generic 'When to Use' and 'Limitations' boilerplate sections at the end, which add no skill-specific value and waste tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary sections like the boilerplate 'When to Use' and 'Limitations' sections that add no value. The reference tables and best practices are useful but the overall document is quite long (~300 lines) and could be tightened—e.g., the 'Related SDKs' and 'Reference Links' tables could be condensed. However, it mostly avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready C# code examples for every major workflow: agent creation, threading, polling, streaming, function calling, file search, Bing grounding, Azure AI Search, cleanup, and error handling. Code is complete with proper imports and realistic parameters. | 3 / 3 |
Workflow Clarity | The core workflow is clearly numbered (steps 1-9) with a logical sequence. However, there are no explicit validation checkpoints—for example, after creating a run, there's no guidance on handling the Failed or Cancelled statuses within the polling loop beyond a best practice bullet point. The function calling section handles RequiresAction but doesn't show error recovery for failed runs. | 2 / 3 |
Progressive Disclosure | The document is largely monolithic—all content is inline in a single file with no references to separate detailed files. The reference tables at the bottom and the external links help, but the 300+ line document could benefit from splitting advanced topics (function calling, file search, Bing grounding) into separate referenced files while keeping the core workflow concise in the main skill. | 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
431bfad
- 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.