pr-learning

Extract actionable learnings from merged PR lifecycles with evidence.

2|1|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/harshitsinghbhandari/domain-expansion --skill pr-learning-harshitsinghbhandari
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pr-learning
Source: https://github.com/harshitsinghbhandari/domain-expansion/tree/main/skills/pr-learning
Command: npx skills add https://github.com/harshitsinghbhandari/domain-expansion --skill pr-learning-harshitsinghbhandari

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract actionable learnings from merged PRs by analyzing the full lifecycle: initial submission → review feedback → final merge.

Core Features & Use Cases

  • Extracts learnings from PR lifecycles to feed a knowledge base for projects and organizations.
  • Deduplicates learnings across PRs, links to evidence from review comments, and maintains both project-specific and general learnings.
  • Supports single-PR and batch processing modes and outputs to maintain learning documents.

Quick Start

Run the pr-learning command on a merged PR to generate initial learnings and attach evidence.

Frequently Asked Questions about pr-learning

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

FAQPage Schema
How do I extract learnings from merged pull requests?

Process multiple recent pull requests in batch mode to deduplicate learnings across entries, classify them by category and scope, and maintain both project-specific and general knowledge base documents.

What is a post-merge PR retrospective?

Run the pr-learning command on a merged pull request to automatically generate initial learnings, link supporting evidence from review comments, and output categorized insights for your repository or global documentation.

How do I build a code review knowledge base from past pull requests?

This skill supports both single-PR and batch processing modes, allowing you to extract deduplicated learnings from multiple recent merged pull requests and classify them by category and scope to build a knowledge base.

Can I process multiple merged PRs at once to generate project learnings?

Batch processing deduplicates learnings across multiple merged pull requests, links evidence from review comments, and classifies insights by category and scope to maintain project-specific and global learning documents.

How do I generate per-PR learnings with evidence from review comments?

The skill extracts actionable learnings from the pull request lifecycle and links them to supporting evidence from review comments, maintaining categorized learning documents at both repository and global levels.