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.
Install with Tessl CLI
npx tessl i github:boisenoise/skills-collections --skill azure-ai-projects-dotnet73
Quality
60%
Does it follow best practices?
Impact
100%
1.81xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-azure-ai-projects-dotnet/SKILL.mdEvaluation results
100%
38%Code Review Assistant Agent
Persistent agent run lifecycle
Azure.AI.Projects package
100%
100%
Azure.Identity package
100%
100%
Persistent agents package
0%
100%
DefaultAzureCredential auth
100%
100%
PROJECT_ENDPOINT env var
0%
100%
GetPersistentAgentsClient call
0%
100%
Async I/O methods
100%
100%
500ms poll delay
0%
100%
Correct poll status check
100%
100%
MessageTextContent cast
100%
100%
Thread cleanup
100%
100%
Agent cleanup
100%
100%
Without context: $0.3778 · 4m 36s · 25 turns · 30 in / 5,462 out tokens
With context: $0.4284 · 3m 54s · 22 turns · 442 in / 3,812 out tokens
100%
87%Real-Time Market Research Assistant
Versioned agents with OpenAI preview
Azure.AI.Projects package
100%
100%
OpenAI preview package
0%
100%
DefaultAzureCredential
100%
100%
PROJECT_ENDPOINT env var
0%
100%
PromptAgentDefinition used
0%
100%
CreateAgentVersionAsync call
0%
100%
GetProjectResponsesClientForAgent call
0%
100%
GetOutputText() used
0%
100%
DeleteAgentVersion cleanup
0%
100%
Without context: $0.3778 · 4m 35s · 19 turns · 23 in / 6,808 out tokens
With context: $0.4181 · 4m 31s · 24 turns · 319 in / 4,247 out tokens
100%
9%Azure AI Foundry Resource Inventory Tool
Connections and deployments discovery
Azure.AI.Projects package
100%
100%
DefaultAzureCredential
100%
100%
PROJECT_ENDPOINT env var
100%
100%
GetConnections listing
100%
100%
includeCredentials false for listing
100%
100%
includeCredentials true for specific connection
100%
100%
GetDeployments listing
100%
100%
Publisher filter on deployments
100%
100%
ModelDeployment cast
100%
100%
RequestFailedException handling
50%
100%
Without context: $1.7976 · 13m 20s · 66 turns · 62 in / 19,713 out tokens
With context: $0.5520 · 4m 42s · 27 turns · 189 in / 5,566 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
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.