instrumenting-with-mlflow-tracing
Add or repair MLflow tracing in Python or TypeScript applications, including tracing required for evaluation. Covers framework autologging, custom spans, backend setup, and persisted trace verification.
Install
With your agent
Install OMGSkills skill "mlflow/skills:instrumenting-with-mlflow-tracing" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/mlflow/skills /tmp/skills && ln -s /tmp/skills/instrumenting-with-mlflow-tracing ~/.claude/skills/instrumenting-with-mlflow-tracingFrom README
Instrument MLflow tracing Reuse working tracing for investigation or evaluation. Prerequisites Check entry point, language/framework, SDK version, tracking URI, experiment, and deployment identity. Preserve destinations and providers. Explicit application destinations override inherited environment values; assistant telemetry may use another experiment. Read Python or TypeScript for the runtime. Step 1: Check the destination (Databricks only) For OSS or SageMaker, keep the configured backend and proceed to Step 2. Read UC before editing; validate auth/workspace. Reuse the explicit destination; otherwise resolve schema choice before provisioning. Discover an accessible warehouse automatically. Default to UC; legacy storage requires an explicit request. Step 2: Enable framework tracing Enable the matching integration before execution. LangGraph uses mlflow.langchain.autolog(), not mlflow.langgraph.autolog(). Do not wrap automatically traced nodes, tools, or models again.
More from this repo
agent-evaluation
Use this when you need to EVALUATE OR IMPROVE or OPTIMIZE an existing LLM agent's output quality - including improving...
analyzing-mlflow-session
Analyzes an MLflow session — a sequence of traces from a multi-turn chat conversation or interaction.
analyzing-mlflow-trace
Analyzes a single MLflow trace to answer a user query about it.