skills.rest
HeXiao-55
HeXiao-55COMMUNITY
Explore all skills by this author →
WebsiteGitHub

auto-review-loop

Automate multi-round research reviews with iterative critique and fixes via Codex MCP.

1|Updated Mar 25, 2026
Search Tags:#workflow#research#logging#review#autonomous#state-persistence
One-click install
npx skills add https://github.com/HeXiao-55/Auto-SurveyMind --skill auto-review-loop-hexiao-55
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: auto-review-loop
Source: https://github.com/HeXiao-55/Auto-SurveyMind/tree/main/skills/auto-review-loop
Command: npx skills add https://github.com/HeXiao-55/Auto-SurveyMind --skill auto-review-loop-hexiao-55

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Autonomous, multi-round review loops help researchers improve work without manual, repeated iterations, ensuring quality before submission.

Core Features & Use Cases

  • Self-run review cycles using Codex MCP to score, critique, and propose fixes.
  • Automatic logging to AUTO_REVIEW.md and state persistence in REVIEW_STATE.json for recovery.
  • Recovery and compact recovery options to continue sessions after interruptions, and support for max rounds.

Quick Start

Run the command /auto-review-loop "topic" to start an autonomous, multi-round review cycle with optional flags as needed.

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 critique and fixes for research paper workflows?▼

You can start an autonomous multi-round review loop by running the command with your target topic and optional flags. This initiates self-run review cycles using Codex MCP to automatically score, critique, and propose fixes for your research.

How does state persistence work for autonomous research review loops?▼

State persistence for autonomous review loops saves session progress in REVIEW_STATE.json, enabling recovery after interruptions. This ensures your iterative critique cycles can resume from their last checkpoint without losing the refinement history.

Can I configure the maximum number of rounds for an autonomous research review?▼

Yes, autonomous research reviews support configurable max rounds to control how many iterative critique and fix cycles are executed. This prevents endless loops while ensuring sufficient passes for your research workflows.

Does the autonomous review loop support recovery and logging for research workflows?▼

The autonomous review loop supports compact recovery options and automatic logging to AUTO_REVIEW.md for research workflows. These features track iterative critique history and allow you to continue sessions after interruptions.

What is the best way to run a self-correcting research review cycle using Codex MCP?▼

The best way to run a self-correcting research review cycle is to automate multi-round scoring and critique using Codex MCP. This approach handles iterative re-analysis and re-review automatically, refining initial results until a positive assessment is achieved.

Related Skills

Explore More Education & Research Skills→
lightrain-alightrain-a

research-review

Critically review ML/AI research artifacts and validate results-to-claims.

Community
Advanced
KYRIE66nbKYRIE66nb

auto-review-loop

Orchestrate iterative review cycles with a secondary Codex agent until positive assessment.

Community
Advanced
ovachieverovachiever
52

serving-llms-vllm

Deploy OpenAI-compatible LLM APIs with vLLM for high-throughput inference.

Community
Advanced
Wenwen555Wenwen555

auto-review-loop-minimax

Automate multi-round research review loops with MiniMax API feedback.

Community
Advanced