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

auto-review-loop-llm

Automate iterative review loops with OpenAI-compatible LLM APIs.

Updated Aug 23, 2026
Search Tags:#documentation#llm#code-review#autonomous#review-loop#research-improvement#ml-reviewer
One-click install
npx skills add https://github.com/nxZhai/Nicy-Extension-Skills --skill auto-review-loop-llm-nxzhai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: auto-review-loop-llm
Source: https://github.com/nxZhai/Nicy-Extension-Skills/tree/main/skills-codex/auto-review-loop-llm
Command: npx skills add https://github.com/nxZhai/Nicy-Extension-Skills --skill auto-review-loop-llm-nxzhai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates an autonomous review loop for research and code projects, enabling iterative critique, fixes, and re-review until a reviewer approves or the maximum rounds are reached.

Core Features & Use Cases

  • Autonomous iteration: review → implement fixes → re-review in multiple rounds.
  • Configurable rounds and thresholds: MAX_ROUNDS, POSITIVE_THRESHOLD govern the loop and termination.
  • LLM integration: uses any OpenAI-compatible API via MCP server or environment variables, with state persistence via REVIEW_DOC and REVIEW_STATE.json.
  • Use Case: For a research project, run continuous automated reviews to surface weaknesses and guide incremental improvements until ready for submission.

Quick Start

Trigger the loop by running the trigger phrase "auto review loop llm" in your project workspace after configuring an LLM provider to enable MCP-based or environment-based communication.

Frequently Asked Questions about auto-review-loop-llm

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

FAQPage Schema
How do I automate an autonomous code review loop for my research project?▼

To automate an autonomous code review loop, configure an OpenAI-compatible LLM API and trigger the process in your workspace to enable iterative critique, fixes, and re-evaluation across multiple rounds.

What is an autonomous iterative review loop and when do I need it for software or research codebases?▼

An autonomous iterative review loop is an automated process that continuously critiques, fixes, and re-evaluates code until a reviewer approves or maximum rounds are reached. It is needed for incremental project improvement before submission.

Can I use any OpenAI-compatible LLM API for autonomous code review?▼

Yes, you can use any OpenAI-compatible LLM API for autonomous code review by configuring it via an MCP server or environment variables to enable communication and state persistence.

How do I configure maximum rounds and positive thresholds for an automated review loop?▼

You configure maximum rounds and positive thresholds using the MAX_ROUNDS and POSITIVE_THRESHOLD variables, which govern the automated review loop's iteration count and termination conditions.

How does state persistence work during an automated iterative review loop?▼

State persistence during an automated iterative review loop works by saving progress and documentation via AUTO_REVIEW.md and REVIEW_STATE.json files, ensuring round-based state tracking across sessions.

Does the autonomous review loop require an MCP server configuration?▼

An MCP server configuration is required for the autonomous review loop to enable MCP-based LLM communication, although environment-based configuration is also supported as an alternative.

Related Skills

Explore More Education & Research Skills→
TabithaFannyTabithaFanny

auto-review-loop-llm

Automate iterative research paper reviews using OpenAI-compatible LLM APIs.

Community
Advanced
jandan138jandan138

auto-review-loop-llm

Automates an end-to-end ML research review loop with cross-model critique and iterative fixes.

Community
Advanced
GoosLabGoosLab

moai-workflow-loop

Automate the Ralph Engine workflow loop with LSP diagnostics and AST-grep scanning.

Community
Advanced
prof-danielcprof-danielc

speckit.checker

Run static analysis tools and aggregate results into a prioritized issue report.

Community
Advanced