English
Official publisherSkillNewly listed 2026-10-18

MLflow Agent Skills

by mlflow · mlflow/skills

Instrument, debug, and evaluate GenAI applications using MLflow’s tracing and evaluation skills.

GitHub stars81 · collected 2026-10-18Repository pushedGuide checked2026-10-18

Install from the author’s instructions

Before connecting

Author README · agent skill installation

npx skills add mlflow/skills

Sources: Author README · Checked 2026-10-18.

The installer adds instructions. SDK dependencies and access to trace data remain prerequisites for the selected workflow.

Sources: Author README · Checked 2026-10-18.

Tools and capabilities

CapabilityWhat it does
Trace analysisInstrument applications and analyze spans, sessions, and failure causes.
EvaluationBuild datasets and scorers and inspect evaluation results.
MetricsQuery token usage, latency, and error trends through MLflow workflows.

Sources: Author README · Checked 2026-10-18.

Workflow examples

Suggested prompts for your own client. These are examples, not recorded tool executions.

Prompt 1

Review my agent’s MLflow traces and classify recurring failure modes, separating observations from hypotheses.

Prompt 2

Design a small evaluation dataset and scorer suite for my support agent, with reproducible comparisons before and after changes.

Sources and verification

Publisher-owned documentation and public GitHub metadata reviewed on 2026-10-18. Author installation examples are retained as documented. Prompts are illustrative; no third-party package or MCP was installed or executed, and no account was connected.

Recent activity refers to the repository push timestamp. It does not establish the product’s original release date. Stars are a dated snapshot of the entire repository.

  1. GitHub repository metadataVerified 2026-10-18
  2. Author READMEVerified 2026-10-18

Continue exploring

Related tools and workflows

Choose another guide for your workflow, or explore a collection.

Same collection group

Weights & Biases Agent Skills

Use W&B and Weave skills for experiment analysis, model training workflows, agent tracing, and evaluations.

Skill

Same collection group

LangSmith Skills

Inspect LLM application traces, build evaluation datasets, create evaluators, and work with LangSmith custom apps using publisher-authored skills.

Skill

Same collection group

PostHog Skills

Add PostHog’s official integration and feature-flag skills to your coding assistant for analytics, error tracking, and LLM analytics workflows.

Skill

Same topic collection

SigNoz Agent Skills

Use SigNoz’s agent skills for documentation search, ClickHouse queries, telemetry analysis, and observability workflows.

Skill

Browse all topic collections → · See 29 new official additions →