ship-analysis

Package completed analyses with environment freezing and reproducibility validation.

Updated Mar 25, 2026

Search Tags:#analysis #packaging #artifacts #environment #summary #ship #reproducibility

Ready to run

npx skills add https://github.com/tim-krausz/mlstack --skill ship-analysis

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ship-analysis
Source: https://github.com/tim-krausz/mlstack/tree/main/ship-analysis
Command: npx skills add https://github.com/tim-krausz/mlstack --skill ship-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill streamlines shipping a completed analysis into a reproducible, shareable package, ensuring results can be reproduced, environments frozen, and artifacts archived.

Core Features & Use Cases

Pre-flight artifact discovery and validation
Environment capture and dependency freezing
Reproducibility checks across notebooks and scripts
Executive summary generation and artifact packaging
Git-based commit and push for collaboration

Quick Start

Run the /ship-analysis workflow to validate reproducibility, freeze the environment, and package a deliverable.

Frequently Asked Questions about ship-analysis

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

FAQPage Schema

How do I package a completed data analysis into a reproducible deliverable?▼

To package a completed data analysis into a reproducible deliverable, the workflow automates pre-flight artifact discovery, environment capture, reproducibility validation, and final archival into a shareable package.

What is included in an analysis environment freeze for notebooks and model outputs?▼

An analysis environment freeze captures dependencies and validates artifacts across notebooks, data outputs, and scripts. This process ensures reproducibility checks pass before generating an executive summary and packaging the deliverable.

Can I use this workflow to run pre-flight checks and generate an executive summary for my data science project?▼

Yes, you can use this workflow to run pre-flight checks and generate an executive summary for your data science project. It validates discovered artifacts, verifies reproducibility, and packages the summary alongside the frozen environment.

Does the packaging process include a git commit and push step for collaboration?▼

Yes, the packaging process includes a git commit and push step for collaboration. After verifying reproducibility and freezing the environment, the workflow commits the final artifacts and summary to your repository.

What's the best way to archive data science artifacts and ensure reproducibility before sharing?▼

The best way to archive data science artifacts and ensure reproducibility is applying a structured workflow that validates outputs, freezes the environment, and runs reproducibility checks before final archival.