skills.rest
alessandro9110
alessandro9110COMMUNITY
Explore all skills by this author →
GitHub

querying-mlflow-metrics

Fetch aggregated trace metrics from MLflow tracking servers.

4|2|Updated Feb 16, 2026
Search Tags:#performance#monitoring#llm#metrics#token usage#mlflow
One-click install
npx skills add https://github.com/alessandro9110/Speech-To-Text-With-Databricks --skill querying-mlflow-metrics-alessandro9110
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: querying-mlflow-metrics
Source: https://github.com/alessandro9110/Speech-To-Text-With-Databricks/tree/main/.claude/skills/querying-mlflow-metrics
Command: npx skills add https://github.com/alessandro9110/Speech-To-Text-With-Databricks --skill querying-mlflow-metrics-alessandro9110

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps users efficiently query and aggregate key performance metrics from MLflow tracking servers, enabling better understanding of model performance and resource utilization.

Core Features & Use Cases

  • Metric Aggregation: Fetch and aggregate metrics like token usage, latency, and trace counts.
  • Quality Evaluation: Analyze assessment scores from model evaluations.
  • Trend Analysis: Visualize usage trends over time (e.g., hourly token consumption).
  • Use Case: A machine learning engineer needs to understand the token usage and latency of their deployed models over the last week to identify cost-saving opportunities and performance bottlenecks.

Quick Start

Fetch the sum and average of total tokens for experiment IDs 1 and 2 from the MLflow server at http://localhost:5000.

Frequently Asked Questions about querying-mlflow-metrics

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

FAQPage Schema
How do I aggregate MLflow metrics like token usage and latency for deployed models?▼

You can query MLflow tracking servers to fetch aggregated trace metrics like token usage and latency using functions such as SUM, AVG, and percentiles. This enables analysis of model performance and resource utilization to identify bottlenecks.

Can I group MLflow trace metrics by status or trace name?▼

Yes, you can group MLflow trace metrics by dimensions like trace name or status. This allows for granular analysis of SPANS and ASSESSMENTS metrics, helping you isolate performance variations across different operational contexts.

What is the best way to analyze LLM token consumption trends over time in MLflow?▼

The best way to analyze LLM token consumption trends is by querying MLflow with flexible time-based bucketing. This visualizes usage trends over specific periods, such as hourly token consumption, to identify cost-saving opportunities.

How do I extract quality evaluation scores from MLflow tracking servers?▼

You extract quality evaluation scores by querying ASSESSMENTS metrics from the MLflow tracking server. This fetches model evaluation data, enabling you to analyze assessment scores alongside performance metrics like latency and trace counts.

Does querying MLflow metrics require any external dependencies or libraries?▼

No, querying MLflow metrics requires no external dependencies. The Skill operates independently using internal scripts and references to fetch aggregated trace metrics directly from your MLflow tracking server environment.

Related Skills

Explore More Software Engineering Skills→
BlackkadderBlackkadder

querying-mlflow-metrics

Fetch aggregated trace metrics from MLflow tracking servers.

Community
Intermediate
ice-droid-99ice-droid-99

querying-mlflow-metrics

Fetch aggregated MLflow trace metrics for token usage, latency, and quality scores.

Community
Intermediate
christhz666christhz666

evaluation

Evaluate AI agent performance using multi-dimensional rubrics and automated or human assessment.

Community
Advanced
chiptoe-svgchiptoe-svg

add-dashboard

Add a local monitoring dashboard for NanoClaw deployments.

Community
Intermediate