Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Adding or repairing MLflow tracing in an app v1.0.0

Use this resource to add or repair MLflow tracing in a Python or TypeScript application

New

  • 517 downloads
  • 125 likes
  • 133 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install mlflow-tracing-instrumentation

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent checks the entry point, the framework and the trace destination, enables the framework's autologging, adds custom spans, then runs one request to confirm the trace is persisted. It keeps existing destinations and covers the tracing needed for evaluation.

Mostly picked by

Updated November 2, 2026

Card for the “Adding or repairing MLflow tracing in an app” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: destination check, enabling tracing and running one request
  • references/: Python, TypeScript, Databricks, distributed tracing and production guides

Good fit for

  • Your LangChain app sends no traces
  • You want to trace a custom business step

Not for

    Tags

    • mlflow
    • tracing
    • instrumentation
    • autologging
    • python

    About

    You say

    “Instrument my Python app that calls OpenAI so every request produces an MLflow trace.”

    Card for the “Adding or repairing MLflow tracing in an app” skill

    Skill published by mlflow under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to add or repair MLflow tracing in a Python or TypeScript application
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/advanced-patterns.md4.2 KB
    • references/databricks.md6.6 KB
    • references/distributed-tracing.md1.9 KB
    • references/feedback-collection.md2 KB
    • references/production.md1.8 KB
    • references/python.md3.8 KB
    • references/root-span-previews.md1.5 KB
    • references/typescript.md3.3 KB
    • SKILL.md5.6 KB

    Origin and licence

    Listed unmodified

    Author
    mlflow
    Source
    github.com/mlflow/skills/tree/6a505d8f30b7fbf93533cdf4e7d88fc30d66ba8b/mlflow-trace-instrumentation
    Licence
    Apache-2.0

    Notice

    « mlflow-trace-instrumentation » (mlflow, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.