PR Review

Review open GitHub pull requests with severity-tagged, line-precise findings.

6|2|Updated May 21, 2026
One-click install
npx skills add https://github.com/anajuliabit/aeon --skill pr-review-anajuliabit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: PR Review
Source: https://github.com/anajuliabit/aeon/tree/main/skills/pr-review
Command: npx skills add https://github.com/anajuliabit/aeon --skill pr-review-anajuliabit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automated pull request review often generates noisy, vague, non-actionable feedback that lacks severity, line precision, and a clear rationale, slowing down merges and increasing human review load.

Core Features & Use Cases

  • Severity-tagged, line-specific findings: Emits up to 5 capped findings per PR using exactly one tag each ([CRITICAL], [ISSUE], [NIT]) with per-line path/to/file:LINE precision and a one-sentence “why it matters”.
  • Noise-reduction via skip rules: Skips drafts, WIP/Draft titles, blocked/no-review labels, bot/aeon authors, duplicate head SHA reviews within the last 2 days, and bot-reviewed-recently cases to avoid piling on.
  • Diff-aware review strategy: Reviews full diffs when feasible, otherwise reviews top delta files or falls back to per-file patches, and can early-exit for docs-only/test-only/lockfile-only changes.
  • Actionable verdict + consolidated summary: Produces an approval-ready verdict or flags blockers for critical issues, and posts both inline comments and a consolidated review body for downstream parsing.

Quick Start

Ask PR Review to review open pull requests for your configured repositories by running it without setting var, after ensuring memory/watched-repos.md lists the targets.

Frequently Asked Questions about PR Review

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

FAQPage Schema
How do I automate GitHub pull request review to reduce noise and accelerate merges?

Automated GitHub pull request review reduces noise by posting up to five severity-tagged, line-precise findings with a clear verdict. It skips drafts, bots, and duplicate SHAs to ensure feedback is actionable and safe merges are accelerated.

What is severity tagging in automated code review and how does it work?

Severity tagging in code review classifies findings into [CRITICAL], [ISSUE], or [NIT] tags. It works by analyzing diff content and emitting per-line path precision with a one-sentence rationale to highlight why the issue matters.

How do I skip draft pull requests and WIP branches during autonomous PR monitoring?

To skip draft pull requests and WIP branches during autonomous PR monitoring, configure skip rules for draft states, WIP titles, blocked labels, and bot authors. This prevents piling on unnecessary review comments for work-in-progress changes.

Can I review large diffs on GitHub without hitting context limits?

You can review large GitHub diffs without hitting context limits by using a diff-aware strategy that fetches top delta files or per-file patches. For extremely large changes, it can early-exit on docs-only, test-only, or lockfile-only modifications.

How do I post inline PR review comments and a consolidated summary on GitHub?

Posting inline PR review comments and a consolidated summary on GitHub involves generating line-specific findings and an overall verdict. The system posts both inline annotations and a consolidated review body for downstream parsing.

What are the limitations of autonomous GitHub PR monitoring for recurring workflows?

Limitations of autonomous GitHub PR monitoring include capping findings at five per PR and skipping reviews for duplicate head SHAs within two days. It requires reading watched repositories and memory logs to list PRs via GitHub CLI.