analyze-mlflow-trace

Analyze MLflow traces to inspect spans, attributes, and assessments.

69|21|Updated Jan 14, 2026
One-click install
npx skills add https://github.com/mlflow/skills --skill analyze-mlflow-trace-mlflow
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: analyze-mlflow-trace
Source: https://github.com/mlflow/skills/tree/main/analyze-mlflow-trace
Command: npx skills add https://github.com/mlflow/skills --skill analyze-mlflow-trace-mlflow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mlflow, opentelemetry, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows users to analyze and debug MLflow traces, providing insights into the performance and correctness of AI/ML applications.

Core Features & Use Cases

  • Trace Analysis: Inspect MLflow trace data for debugging and performance insights.
  • Span Details: Explore individual spans and their associated attributes.
  • Assessment Interpretation: Understand the rationale behind assessment values and feedback.
  • Quick Health Check: Execute a quick summary command to assess the trace's health.
  • Use Case: If a trace fails, use this Skill to examine the span data and identify the root cause of the issue.

Quick Start

Analyze the MLflow trace with the ID 'trace123' by running the command: 'analyze-mlflow-trace trace123'.

Frequently Asked Questions about analyze-mlflow-trace

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

FAQPage Schema
How do I debug MLflow traces to find the root cause of an application failure?

Debugging MLflow traces involves analyzing span data and attributes to pinpoint exact failure sources. This Skill inspects individual spans and assessment values to identify the root cause of issues in AI/ML applications.

How do I analyze MLflow trace spans for performance evaluation?

Analyzing MLflow trace spans for performance evaluation requires parsing the trace data to inspect individual spans and their associated attributes. This Skill provides detailed insights into spans to help evaluate AI/ML application performance.

Do I need OpenTelemetry to analyze MLflow traces?

Yes, you need both MLflow and OpenTelemetry to analyze traces with this Skill. These dependencies provide the necessary trace data framework and instrumentation to support detailed span analysis and JSON parsing.

Can I run a quick health check on an MLflow trace?

Yes, you can run a quick health check on an MLflow trace by executing a summary command. For example, running 'analyze-mlflow-trace trace123' assesses the health of trace 'trace123' to quickly evaluate its status.

What is the best way to interpret assessment values in MLflow traces?

Interpreting assessment values in MLflow traces is done by examining the rationale behind feedback within the trace data. This Skill helps you understand assessment values to ensure the correctness of your AI/ML applications.

Why does my MLflow trace analysis fail to parse span attributes?

MLflow trace analysis may fail to parse span attributes if the trace data lacks proper JSON formatting or if MLflow and OpenTelemetry dependencies are not correctly configured. This Skill supports JSON parsing for detailed span analysis.