review-loop

Automate iterative AI-based code reviews on PRs or local diffs until issues resolve.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires gh, jq, git, and includes scripts (resource) components.

What problem does it solve?

This Skill streamlines the code review process by automatically looping AI reviews on pull requests or local diffs until all critical and warning issues are resolved, reducing manual review effort and improving code quality.

Core Features & Use Cases

  • Automated Review Looping: Continuously performs AI-driven code reviews across multiple viewpoints until no critical or warning issues remain.
  • Deep Iterative Analysis: Repeats review cycles, handles PR and local diffs, and consolidates feedback for developers.
  • Use Case: Ideal for teams aiming for high-quality releases by ensuring issues are auto-identified and resolved through dedicated looping until code is clean.

Quick Start

Invoke the review-loop skill on your current branch or pull request to automatically review and improve your code until issues are resolved.

Frequently Asked Questions about review-loop

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

FAQPage Schema
How do I automate AI code reviews to run repeatedly until issues are resolved?

Automated iterative code review works by looping AI analysis on pull requests or local diffs until no critical or warning issues remain. It coordinates multiple viewpoints like coding standards, architecture, security, and performance.

Can I run AI PR reviews on local git diffs before creating a pull request?

Yes, you can run AI PR reviews on local git diffs. The review loop processes both local diffs and pull requests, applying iterative analysis to identify and resolve issues before submission.

What's the best way to ensure code quality across security and architecture standards?

The best way to ensure code quality is using iterative AI reviews that coordinate multiple viewpoints including coding standards, architecture, security, and performance. Review cycles repeat until all issues are auto-identified and resolved.

Does automated AI code review require gh and jq dependencies?

Yes, automated AI code review requires gh, jq, and git dependencies. These tools enable the review loop to interact with pull requests, parse JSON data, and manage local diffs.

When should I stop the iterative code review loop?

The iterative code review loop stops automatically when no critical or warning issues are detected. It also stops when user intervention is required to resolve remaining issues.

Why does AI code review need to loop multiple times?

AI code review needs to loop multiple times to perform deep iterative analysis. Repeating review cycles ensures newly introduced changes are re-evaluated, consolidating feedback until the code is completely clean.