pr-review-learnings

Analyze AI and human code review discrepancies to identify missed patterns.

1|Updated Dec 1, 2016
One-click install
npx skills add https://github.com/aaron-vaz/dotfiles --skill pr-review-learnings
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pr-review-learnings
Source: https://github.com/aaron-vaz/dotfiles/tree/main/opencode/.opencode/skills/pr-review-learnings
Command: npx skills add https://github.com/aaron-vaz/dotfiles --skill pr-review-learnings

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps improve the quality and accuracy of AI-generated code reviews by analyzing discrepancies between AI suggestions and human feedback.

Core Features & Use Cases

  • Gap Analysis: Compares AI review comments with human feedback on the same Pull Request (PR) to identify areas where the AI missed crucial points.
  • Pattern Identification: Surfaces recurring patterns in missed findings to pinpoint systematic weaknesses in AI reviews.
  • Skill Improvement: Generates actionable suggestions for improving the AI's review capabilities or refining the REVIEW.md guidelines.
  • Use Case: After an AI reviews a PR, human developers provide feedback. This Skill analyzes that feedback to find out what the AI missed, helping to train the AI to be more effective in future reviews.

Quick Start

Analyze the unlearned PR entries in your review log to identify patterns and suggest improvements.

Frequently Asked Questions about pr-review-learnings

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

FAQPage Schema
How do I improve AI code reviews using human feedback?

Improve AI code reviews by analyzing discrepancies between AI suggestions and human feedback on GitHub pull requests. This identifies missed patterns and generates actionable suggestions to refine automated code quality assurance guidelines.

How does gap analysis work for AI generated code review comments?

Gap analysis compares AI review comments with human feedback on the same pull request to identify areas where the AI missed crucial points. It surfaces recurring patterns in missed findings to pinpoint systematic weaknesses in automated reviews.

What is the best way to identify missed patterns in AI pull request reviews?

Identify missed patterns in AI pull request reviews by processing JSON logs fetched via the GitHub API. Analyzing these logs surfaces recurring systematic weaknesses and generates suggestions for improving the AI's review capabilities.

Do I need GitHub API access to analyze AI code review discrepancies?

Yes, you need GitHub API access to fetch PR review data required for analyzing AI code review discrepancies. The Skill processes JSON logs from this data to identify learning opportunities and suggest improvements for your review guidelines.

Can I use this to refine REVIEW.md guidelines for automated code quality assurance?

Yes, you can use this to refine REVIEW.md guidelines for automated code quality assurance. The Skill generates actionable suggestions for improving the AI's review capabilities by analyzing discrepancies between AI and human feedback.

What are the limitations of analyzing AI code review feedback with JSON logs?

Processing JSON logs to analyze AI code review feedback requires existing human feedback on pull requests to compare against. Without human developer feedback on the same PR, the Skill cannot identify discrepancies or suggest improvements.