skills.rest
nxZhai
nxZhaiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

auto-review-loop

Automate multi-round code review and remediation via Claude Code and claude-review MCP.

Updated Aug 23, 2026
Search Tags:#automation#MCP#claude-code#code-review#autonomous#state-persistence#multi-round
One-click install
npx skills add https://github.com/nxZhai/Nicy-Extension-Skills --skill auto-review-loop-nxzhai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: auto-review-loop
Source: https://github.com/nxZhai/Nicy-Extension-Skills/tree/main/skills-codex-claude-review/auto-review-loop
Command: npx skills add https://github.com/nxZhai/Nicy-Extension-Skills --skill auto-review-loop-nxzhai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Solves the time-consuming, repetitive cycle of editing, rerunning reviews, and implementing fixes during research or code review by automating multi-round feedback and revision.

Core Features & Use Cases

  • Autonomous multi-round review using Claude Code via claude-review MCP, with automatic fixes and re-evaluation until a positive readiness verdict or max rounds reached.
  • Stateful workflow with auto-logging to AUTO_REVIEW.md and persistent REVIEW_STATE.json for recovery.
  • Designed for research/code projects requiring rigorous iterative critique and improvement, especially when human review is constrained.

Quick Start

Trigger the loop by saying auto review loop to start autonomous iterative improvement.

Frequently Asked Questions about auto-review-loop

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

FAQPage Schema
How do I automate multi-round code review and remediation using Claude Code?▼

You can automate multi-round code review by triggering the loop to start autonomous iterative improvement, applying fixes and re-evaluating until a positive readiness verdict or maximum rounds are reached.

What is autonomous multi-round code review and how does it work?▼

Autonomous multi-round code review applies iterative critique, fixes, and re-evaluation to research-code projects using Claude Code via the claude-review MCP bridge.

Does the automated code review loop support state persistence and recovery?▼

Yes, the automated code review loop supports state persistence by auto-logging to AUTO_REVIEW.md and saving durable REVIEW_STATE.json files for workflow recovery.

Can I use this automated review loop for research-code projects requiring rigorous critique?▼

Yes, this automated review loop is specifically designed for research-code projects requiring rigorous iterative critique and improvement when human review is constrained.

What are the limitations of autonomous code review loops?▼

The autonomous code review loop stops when it reaches a positive readiness verdict or the maximum configured rounds, limiting endless iterations and requiring eventual human verification.

Related Skills

Explore More Software Engineering Skills→
IgorGanapolskyIgorGanapolsky
25

setup

Validate Codex bridge plugin readiness inside Claude Code.

Community
Basic
kitcafkitcaf
1

auto-review-loop-llm

Automate multi-round research review with OpenAI-compatible LLMs and persistent logs.

Community
Advanced
tqLi99tqLi99
1

auto-review-loop-minimax

Automate multi-round external review loops using the MiniMax API.

Community
Advanced
icartshicartsh
4

code-analyze

Analyze .NET solutions for code quality, security, and dependency issues.

Community
Advanced