auto_experiment

Automate end-to-end ML experiment workflows from setup to reporting.

2|Updated Mar 20, 2026

Search Tags:#automation #workflow #planning #monitoring #logging #reproducibility #experiment

Ready to run

npx skills add https://github.com/Gonglitian/agent-skills --skill auto-experiment

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: auto_experiment
Source: https://github.com/Gonglitian/agent-skills/tree/main/skills/auto_experiment
Command: npx skills add https://github.com/Gonglitian/agent-skills --skill auto-experiment

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automated end-to-end ML experiment workflows by coordinating setup, planning, execution, evaluation, and reporting.

Core Features & Use Cases

End-to-end workflow orchestration: workspace setup, planning, running experiments, live monitoring, and final reporting.
Context-rich documentation: automatic sketch updates, per-round exp logs, and findings to improve reproducibility.
Safe data management: data is symlinked and outputs are kept separate from source data to prevent accidental modification.

For example, researchers can run multiple rounds with different hyperparameters, automatically generate baselines, and produce a comprehensive final report.

Quick Start

Provide code path, data path, and workspace, plus an instruction, and the skill will run the full experiment cycle.

Frequently Asked Questions about auto_experiment

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate end-to-end ML experiment workflows?▼

You can automate end-to-end ML experiment workflows by providing a code path, data path, workspace, and instruction to orchestrate setup, planning, execution, evaluation, and reporting automatically.

How does reproducibility work for iterative ML experiments?▼

Reproducibility for iterative ML experiments is maintained through strict data-symlink handling, branch-based rounds, per-round logging, and automatic sketch updates to ensure full context documentation.

Do I need a specific code repository structure to run automated experiments?▼

You need a code repository, data path, and workspace to run automated experiments. The workflow uses branch-based rounds and symlinks to keep outputs separate from source data.

What is the best way to compare baselines across multiple research cycles?▼

The best way to compare baselines across research cycles is using automated per-round logging and evaluation to track different hyperparameters and generate comprehensive final reports.

Will automating my ML workflow modify my original source data?▼

No, automating your ML workflow will not modify source data because the system uses strict data-symlink handling and keeps all outputs separate from source data to prevent accidental modification.