mlflow

Skills for tracing, evaluating, and improving AI agents with MLflow. Supports the full agent improvement loop: instrument → trace → evaluate → iterate → validate.

Install

If the official marketplace isn’t added yet, run

Category: Monitoring
Author: MLflow Team
GitHub: mlflow/skills
Website: mlflow.org

Good for

Instrument Python and TypeScript code with MLflow Tracing (OpenAI, Anthropic, LangChain and more)
Analyze a failed trace to find the root cause and suggest fixes
Set up datasets and scorers and evaluate your agent's accuracy
Query metrics such as token usage trends

Getting started

Run /plugin install mlflow@claude-plugins-official in Claude Code
Ask directly, e.g. "Add tracing to my LangChain app"
Then ask Claude to evaluate and improve, e.g. "Improve my agent and verify your work"

Summarized by AI from the project docs; check the official docs before relying on it.

Similar tools

dash0Official plugin · Monitoring
OpenTelemetry observability for Claude Code sessions. Captures tool calls, LLM invocations, token usage, and errors as OTel traces. Send telemetry to Dash0 or any OpenTelemetry-compatible backend.
datadogOfficial plugin · Monitoring
Use Datadog directly in Claude Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation. This plugin is in preview.
DynatraceOfficial plugin · Monitoring
Dynatrace observability skills: DQL query patterns, application and infrastructure monitoring, log analysis, problem investigation, and incident response workflows, with the Dynatrace MCP server for live platform access.
fullstoryOfficial plugin · Monitoring
Connect Claude to Fullstory to query behavioral analytics, session replays, and customer experience insights.
grafana-assistantOfficial plugin · Monitoring
Skills and rules for developing and using the Grafana Assistant app and CLI.