foundry-evals

Official

Score hosted agents with two-phase evals.

Authoraiappsgbb
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps you reliably evaluate Azure Foundry hosted agents by separating response invocation from scoring, avoiding common endpoint routing and cold-start pitfalls.

Core Features & Use Cases

  • Two-phase invoke+score pattern: Invoke the hosted agent first, then score outputs using Foundry built-in evaluators.
  • Hosted-agent cold-start handling: Warm up with retry/backoff logic, enforce sequential invocation, and add pacing to prevent empty responses.
  • Production-grade eval operations: Supports dataset creation, evaluator configuration (including tool evaluators), judge model deployment requirements, and RBAC troubleshooting.

Quick Start

Use the foundry-evals skill to evaluate an already-deployed hosted agent against a set of test scenarios and generate Foundry eval scores.

Dependency Matrix

Required Modules

azure-ai-projectsazure-identitypython-dotenvaiohttphttpx

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: foundry-evals
Download link: https://github.com/aiappsgbb/awesome-gbb/archive/main.zip#foundry-evals

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.