skills.rest
satsuki-64
satsuki-64COMMUNITY
Explore all skills by this author →
GitHub

auto-review-loop

Automate iterative Codex MCP-based reviews with state persistence and round logs.

2|Updated Mar 29, 2026
Search Tags:#automation#codex#quality-assurance#state-persistence#review-loop
One-click install
npx skills add https://github.com/satsuki-64/MiniAgentWorkflow --skill auto-review-loop-satsuki-64
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: auto-review-loop
Source: https://github.com/satsuki-64/MiniAgentWorkflow/tree/main/.skills/auto-review-loop
Command: npx skills add https://github.com/satsuki-64/MiniAgentWorkflow --skill auto-review-loop-satsuki-64

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Autonomous iterative reviews and fixes for research projects, automatically looping until a positive assessment or max rounds.

Core Features & Use Cases

  • Multi-round review cycle using Codex MCP to identify weaknesses, propose fixes, and re-review.
  • Automatic persistence of state across rounds and logging for traceability.
  • Use cases: teams needing autonomous quality improvement for research artifacts without constant manual prompting.

Quick Start

Activate the loop by instructing your agent to start the auto-review-loop and then let it iteratively review, fix, and re-review until completion.

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 iterative reviews for research projects?▼

Automating iterative reviews involves looping through evaluation and fix cycles using Codex MCP until acceptance or max rounds. State persistence and round logs maintain traceability across cycles.

What is an autonomous review loop?▼

An autonomous review loop is a self-improving cycle that evaluates research artifacts, applies fixes, and re-reviews without manual prompting. It persists state across rounds to ensure traceability throughout the process.

How do I start the auto-review-loop?▼

Activate the loop by instructing your agent to start the auto-review-loop. The agent then iteratively reviews, fixes, and re-reviews research artifacts until completion.

Does Codex MCP support state persistence for multi-round reviews?▼

Yes, Codex MCP supports multi-round reviews with automatic state persistence across rounds. It keeps detailed round logs to ensure traceability for research artifact evaluation and fixes.

Can I use automated review loops for complex research tasks?▼

Yes, automated review loops apply to complex research tasks requiring repeated evaluation, fixes, and re-review. They support autonomous quality improvement for research artifacts.

What are the limitations of autonomous multi-round reviews?▼

Autonomous multi-round reviews are bounded by a maximum rounds limit. If acceptance criteria are not met within max rounds, the loop terminates, requiring manual intervention for remaining weaknesses.

Related Skills

Explore More Software Engineering Skills→
tqLi99tqLi99
1

auto-review-loop-llm

Automate iterative review and improvement cycles for research projects via OpenAI-compatible LLM APIs.

Community
Advanced
WhampWhamp
1

web-research

Conduct multi-round web research prioritizing GitHub and StackOverflow for code solutions.

Community
Advanced
jkfeejkfee

auto-review-loop-minimax

Automate multi-round ML research review workflows using the MiniMax API.

Community
Advanced
CAPHTECHCAPHTECH
1

eld-ground-evaluate

Evaluate generated code outputs for Law compliance and quality.

Official
Advanced