trainee-review

Review trainee Jupyter notebooks and analysis scripts into educational REVIEW.md artifacts.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/vitalwarley/hyprdots --skill trainee-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trainee-review
Source: https://github.com/vitalwarley/hyprdots/tree/main/claude-global/skills/trainee-review
Command: npx skills add https://github.com/vitalwarley/hyprdots --skill trainee-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a repeatable, educational review workflow for trainee and junior ML engineers by turning PR-contained notebooks and analysis scripts into a co-located REVIEW.md with actionable feedback, scoring, and artifacts for learning.

Core Features & Use Cases

  • PR and issue context gathering: fetches PR metadata, related issues, file lists, and author info to ground the review.
  • Notebook conversion and artifacts: converts notebooks to script form, extracts chart images, and co-locates original notebooks plus a pyproject for reproducibility.
  • Structured, educational reviews: produces a REVIEW.md with an executive summary, scoring matrix, detailed findings, prioritized fixes, and trainee-level educational notes, and posts a PT-BR PR comment linking the artifact.
  • Use Case: A tech lead reviewing a junior's Jupyter analysis PR can generate an evidence-based review, request changes, and push the review artifacts alongside the code.

Quick Start

Run the trainee-review skill against a pull request reference to generate a REVIEW.md, extracted charts, converted scripts, and a PT-BR PR comment.

Frequently Asked Questions about trainee-review

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

FAQPage Schema
How do I review Jupyter notebooks in a pull request for trainee ML engineers?

To review Jupyter notebooks in a pull request, this skill fetches PR metadata, converts notebooks to scripts, extracts chart images, and generates an educational REVIEW.md with a scoring matrix and prioritized fixes for trainees.

What is the best way to provide structured code review feedback on ML analysis scripts?

Structured code review feedback on ML analysis scripts is best delivered via a REVIEW.md artifact containing an executive summary, scoring matrix, detailed findings, and prioritized fixes tailored for trainee-level educational guidance.

Can I convert Jupyter notebooks to scripts and extract chart images during a PR review?

Yes, you can convert Jupyter notebooks to scripts and extract chart images during a PR review. The process performs notebook-to-script conversion, extracts visualizations, and co-locates original notebooks with a pyproject file for reproducibility.

Does this notebook review skill post PR comments and support git commits?

Yes, this notebook review skill posts PT-BR PR comments linking the REVIEW.md artifact and supports git commits to push review artifacts alongside the code. It also supports posting issue comments for additional context.

What scoring criteria are used when reviewing trainee machine learning notebooks?

Scoring criteria for reviewing trainee machine learning notebooks evaluate scientific method, statistical rigor, code quality, and visualizations. These dimensions are composed into a scoring matrix with actionable fixes within the generated REVIEW.md artifact.

When should I use an automated notebook review workflow instead of manual code review?

You should use an automated notebook review workflow instead of manual code review when you need a repeatable, educational process for trainee ML engineers. It turns PR-contained notebooks into co-located artifacts with consistent scoring and educational feedback.