mcpField
M
mlflow-agent

mlflow-agent

github.com/mlflowAgent workflows82808 installsUpdated 2d ago
Repository

About mlflow-agent

mlflow-agent is a dispatcher skill for MLflow requests. It routes users to focused sub-skills for setup, tracing, evaluation, debugging, metrics, and documentation, rather than carrying out the work itself.

Key features

  1. 01Intent-based skill selection
  2. 02Dispatch to specialized MLflow skills
  3. 03One clarifying question maximum
  4. 04Ordered handling for multi-skill requests

Use cases

  1. 01Route a trace-debugging request
  2. 02Handle evaluation and tracing in sequence
  3. 03Direct an MLflow documentation question

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/mlflow/skills --skill mlflow-agent

After installing, type/mlflow-agentin Claude Code to confirm it loaded.

Details

From the project README

MLflow Agent

Master dispatcher for MLflow workflows. Reads user intent and invokes the right sub-skill.

Step 1: Identify the workflow

Use the user's request to choose the relevant skill. Ask at most one clarifying question if the intent is unclear.

Step 2: Dispatch

  • Tracing / instrumentation → instrumenting-with-mlflow-tracing
  • Debug or explain an agent failure → debug-agent
  • Fix or change an agent's behavior → fix-agent-issue
  • Evaluation / scoring → agent-evaluation
  • Debug a trace → analyze-mlflow-trace
  • Debug a chat session → analyze-mlflow-chat-session
  • Search traces → retrieving-mlflow-traces
  • Metrics / costs → querying-mlflow-metrics
  • Getting started → mlflow-onboarding
  • Docs / API questions → searching-mlflow-docs

Invoke the matched skill using the Skill tool.

Key Rules

  • Never do the work yourself — always dispatch to the appropriate sub-skill
  • One clarifying question maximum before dispatching
  • If the user says "evaluate AND trace", dispatch tracing first, then evaluation
  • Do not route an already-instrumented debugging request back to tracing setup
  • If the user's request spans multiple skills, handle them in logical order (setup → instrument → evaluate)

Comments

Markdown supported