autopilot-lab

What problem does it solve?

This Skill prevents machine learning experiments from becoming disposable one-off runs by organizing setup, evaluation, tracking, and reporting into a repeatable lifecycle.

Core Features & Use Cases

• Experiment Setup: Creates experiment specifications, scaffolds training and evaluation files, and guides reproducible setup from references or parent experiments.
• Evaluation and Reporting: Helps analyze checkpoints, record metrics, generate summaries, and maintain experiment lineage through structured artifacts.
• Use Case: A researcher testing model variants can use this Skill to prepare a controlled experiment, evaluate results after training, and preserve the findings for future iterations.

Quick Start

Ask the autopilot-lab skill to set up a new machine learning experiment for comparing a model change and tracking the results.