dev-review-loop

Orchestrate development, review, and fix loops with specialized subagents.

2|Updated Jun 1, 2015

Search Tags:#code quality #automation #code review #multi-agent #iterative development #development loop

Ready to run

npx skills add https://github.com/TimoFreiberg/dotfiles --skill dev-review-loop

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: dev-review-loop
Source: https://github.com/TimoFreiberg/dotfiles/tree/main/agents/skills/dev-review-loop
Command: npx skills add https://github.com/TimoFreiberg/dotfiles --skill dev-review-loop

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the software development process by automating the iterative cycle of code development, review, and fixing, reducing manual oversight and accelerating feedback loops.

Core Features & Use Cases

Orchestrates Multi-Agent Development: Manages a sequence of specialized agents (dev, review, fix) to build and refine code.
Automated Code Review: Integrates with defined review guidelines to identify issues in code changes.
Iterative Bug Fixing: Automatically addresses identified bugs and allows for rejection of frivolous findings.
Use Case: When asked to implement a new feature, this Skill will spawn a developer agent, commit the code, have it reviewed, and then have a fixer agent address any issues until the code passes review or all findings are rejected.

Quick Start

Use the dev-review-loop skill to build the new user authentication feature.

Frequently Asked Questions about dev-review-loop

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

FAQPage Schema

How do I automate code review cycles for iterative development?▼

Automated code review cycles are orchestrated by managing a sequence of specialized subagents for development, review, and fixing. This process applies review guidelines to code diffs and iteratively addresses identified issues until the code passes review.

What is a multi-agent code review loop and how does it work?▼

A multi-agent code review loop is a process that spawns specialized agents to handle distinct tasks: one agent writes and commits code, another reviews the generated diff against guidelines, and a third agent fixes identified bugs until quality assurance passes.

Do I need Git to run automated code review and fixing loops?▼

You need a Version Control System (VCS) like Git or JJ to run automated review and fixing loops. The system requires VCS detection to perform the commit and diff operations necessary for generating iterative code improvements.

How do I handle frivolous findings during an automated code review?▼

Frivolous findings during an automated code review can be rejected by the iterative fixing agent. The process allows the system to automatically address valid bugs while discarding frivolous findings, ensuring the loop progresses efficiently until code passes review.

Can I use this automated review loop for building new features?▼

You can use this automated review loop to build new features by spawning a developer agent to implement the code, committing it, and having a fixer agent address review findings. This accelerates feedback loops and reduces manual oversight.

What are the limitations of automating iterative code improvement?▼

A limitation of automating iterative code improvement is its strict dependency on detecting a compatible Version Control System like Git or JJ. Without proper VCS integration, the system cannot perform the required commit and diff operations to manage code changes.