azure-ai-projects-py
Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects). Use when working with Foundry project clients, creating versioned agents with PromptAgentDefinition, running evalua...
Install with Tessl CLI
npx tessl i github:sickn33/antigravity-awesome-skills --skill azure-ai-projects-py96
Does it follow best practices?
Evaluation — 84%
↑ 1.82xAgent success when using this skill
Validation for skill structure
Evaluation results
100%
55%Production Customer Service Agent Deployment
Versioned agent production deployment
Correct top-level import
100%
100%
Azure identity import
100%
100%
Endpoint env var
0%
100%
Model env var
0%
100%
PromptAgentDefinition import
100%
100%
create_version call
100%
100%
version_label parameter
0%
100%
Thread creation
0%
100%
create_and_process run
0%
100%
Status check
0%
100%
Agent cleanup
30%
100%
Correct SDK package
100%
100%
Without context: $1.1027 · 9m 9s · 49 turns · 50 in / 12,158 out tokens
With context: $0.4249 · 4m 5s · 22 turns · 182 in / 4,656 out tokens
88%
38%Async Coding Tutor Agent
Async client with tool-enabled agent
Async import path
100%
100%
Async context manager
100%
100%
Tools package
0%
0%
Await on agent operations
50%
100%
Endpoint env var
0%
100%
Model env var
0%
100%
DefaultAzureCredential
100%
100%
Thread creation
0%
100%
create_and_process
25%
100%
Message content access
75%
100%
Agent cleanup
30%
100%
Status check before messages
100%
100%
Without context: $0.6813 · 8m 35s · 35 turns · 42 in / 8,273 out tokens
With context: $0.3714 · 4m 13s · 22 turns · 26 in / 4,232 out tokens
66%
21%Persistent Memory Support Agent
Memory stores and OpenAI-compatible client
get_openai_client usage
100%
100%
No direct openai import
100%
100%
create_memory_store call
0%
0%
MemorySearchTool in tools
0%
40%
tool_resources memory structure
0%
0%
Connections usage
100%
100%
Endpoint env var
0%
100%
Model env var
0%
100%
DefaultAzureCredential
100%
100%
AIProjectClient import
100%
100%
Agent cleanup
0%
42%
Without context: $1.0016 · 8m 43s · 48 turns · 2,094 in / 10,667 out tokens
With context: $1.8483 · 13m 31s · 78 turns · 70 in / 17,986 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Unknown
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.