workflow-metrics

Name: workflow-metrics
Availability: InStock
Author: samelhousseini

Track and analyze multi-agent AI workflows with Azure Foundry metrics.

Updated Jan 15, 2026

Search Tags:#workflow #analytics #logging #metrics #Foundry #AI-evaluation

Ready to run

npx skills add https://github.com/samelhousseini/microhacks --skill workflow-metrics

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: workflow-metrics
Source: https://github.com/samelhousseini/microhacks/tree/main/.github/skills/workflow-metrics
Command: npx skills add https://github.com/samelhousseini/microhacks --skill workflow-metrics

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires azure-ai-projects, azure-identity, python-dotenv, openai, azure-ai-evaluation, and includes scripts (resource) components.

What problem does it solve?

This Skill enables teams to log, measure, and analyze multi-agent AI workflows by capturing agent trajectories, tool usage, and evaluation results in a structured, Foundry-compatible format.

Core Features & Use Cases

Trajectory logging and Foundry-compatible formats for multi-step agent workflows.
14 evaluation metrics (13 cloud-based via Azure Foundry + 1 local) and decorator-based automatic tracking.
Tool definition generation (from functions or JSON) and integration with Azure OpenAI tools for cloud evaluations.
Real-world use case: track a complex workflow, compute cloud metrics via Foundry, and surface actionable insights in dashboards.

Quick Start

Record a workflow trajectory using a unique ID, configure tool definitions, log a plan and tool steps, and finalize to generate local and cloud metrics.

Frequently Asked Questions about workflow-metrics

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I track multi-agent AI workflows and log trajectories?▼

To track multi-agent AI workflows, you log agent trajectories and tool usage in a structured format using a unique ID. This Skill captures multi-step agent workflows and applies decorator-based automatic tracking to record the full execution path.

Can I evaluate multi-agent workflows using Azure Foundry?▼

Yes, you can evaluate multi-agent workflows using Azure Foundry. The Skill computes 13 cloud-based evaluation metrics via Azure Foundry and 1 local metric, requiring the AZURE_AI_PROJECT_ENDPOINT to enable cloud evaluations.

How do I compute plan adherence and evaluation metrics for AI agents?▼

You compute plan adherence and evaluation metrics by logging a plan, recording tool steps, and finalizing the workflow trajectory. This triggers local and cloud metric computation, generating 14 evaluation metrics for multi-agent AI workflows.

Do I need Azure OpenAI to generate tool definitions for AI evaluation?▼

Azure OpenAI is optional for generating tool definitions. You need AZURE_AI_PROJECT_ENDPOINT for cloud evaluations, while AZURE_OPENAI_JUDGE is optional. Tool definitions can be generated from functions or JSON for Azure OpenAI integration.

What Python dependencies are required to analyze AI workflow metrics?▼

To analyze AI workflow metrics, you need the azure-ai-projects, azure-identity, python-dotenv, openai, and azure-ai-evaluation Python dependencies. These enable trajectory logging, cloud evaluations, and tool-definition generation.

Does this Skill support local evaluators alongside cloud-based metrics?▼

Yes, this Skill supports local evaluators alongside cloud-based metrics. It provides 13 cloud-based evaluation metrics via Azure Foundry and 1 local evaluator, allowing combined local and cloud metric computation for multi-agent workflows.