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.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

82%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 highly actionable, well-structured reference with comprehensive executable C# examples and a clear numbered workflow, held back only by minor verbosity in boilerplate sections and inline reference tables that could live in separate files.

Suggestions

Move the Available Tools, Streaming Update Types, and Key Types Reference tables into a separate reference file (e.g. references/types.md) and link to it from the body to improve progressive disclosure.

Tighten or remove the generic 'When to Use' and 'Limitations' sections, which restate scope already implied by the frontmatter description.

Add an explicit validation/checkpoint note in the Core Workflow (e.g. verify run.Status terminal states before retrieving messages) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely executable code, tables, and a compact client hierarchy diagram with minimal prose, avoiding concept over-explanation; the generic 'When to Use' and 'Limitations' boilerplate and some inline reference tables could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready C# covering the common cases end-to-end — client auth, agent/thread/message/run creation, polling, streaming, function calling, file/vector-store search, Bing/AI Search grounding, cleanup, and error handling — all fully executable.	5 / 5
Workflow Clarity	A numbered 1–9 Core Workflow sequences the lifecycle clearly with polling-status feedback loops and a cleanup step, but explicit validation checkpoints between operations are only implied rather than stated.	4 / 5
Progressive Disclosure	Well-organized with clear section headers and flat (one-level) external reference links, no nested references; however bulk reference material (Available Tools, Streaming Update Types, Key Types) is inlined rather than split into bundle files.	4 / 5
	Total	17 / 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 is specific and well-differentiated, naming concrete SDK components and a clear low-level niche, but it omits any explicit 'Use when' trigger guidance and leans on technical jargon over natural user phrasing.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building .NET applications that need low-level control over Azure AI agents, threads, runs, or tool invocations.'

Soften SDK-internal jargon ('threads, messages, runs') with natural synonyms a user might actually say (e.g. 'conversations', 'agent runs', 'tool calls').

Add concrete verbs beyond 'creating and managing' (e.g. 'create, poll, stream, and clean up agent runs') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete components — 'creating and managing AI agents with threads, messages, runs, and tools' — but the verbs are limited to create/manage, leaving minor coverage gaps rather than comprehensive action enumeration.	4 / 5
Completeness	The 'what' is clearly stated ('Low-level SDK for creating and managing AI agents...') but there is no 'Use when...' or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Relevant terms like 'Azure AI Agents', '.NET', and 'AI agents' are present, but 'Persistent SDK', 'threads, messages, runs' are SDK-internal jargon and common synonyms/variations a user might say are missing.	3 / 5
Distinctiveness Conflict Risk	The 'Azure AI Agents Persistent SDK for .NET' / 'Low-level SDK' framing carves a clear niche distinct from the high-level Azure.AI.Projects SDK, with only minor overlap risk against closely related Azure AI skills.	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-agents-persistent-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.