skills.rest
wanshuiyin
wanshuiyinCOMMUNITY
Explore all skills by this author →
GitHub

auto-review-loop

Automate multi-round research review and improvement cycles with an external LLM reviewer.

14.4k|1.3k|Updated Mar 10, 2026
Search Tags:#automation#research#llm#iteration#review#ml
One-click install
npx skills add https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep --skill auto-review-loop
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: auto-review-loop
Source: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/main/skills/auto-review-loop
Command: npx skills add https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep --skill auto-review-loop

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the tedious and time-consuming process of iteratively reviewing and improving research work, ensuring it meets high standards before submission.

Core Features & Use Cases

  • Autonomous Multi-Round Review: Repeatedly reviews research artifacts using an external LLM (Codex MCP), identifies weaknesses, and implements fixes.
  • Iterative Improvement: Continues the review-fix cycle until a positive assessment is achieved or a maximum number of rounds is reached.
  • Use Case: A researcher can initiate this Skill on a draft paper or experiment results, and the Skill will autonomously refine it by addressing reviewer feedback until it's ready for submission.

Quick Start

Use the auto review loop skill to iteratively improve the current research topic until it passes review.

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 review and improvement for research drafts?▼

Automating iterative research review involves using an LLM to repeatedly assess artifacts, implement fixes, and re-evaluate until passing. This Skill automates that exact review-fix cycle autonomously until a positive assessment is met.

Can I set a maximum number of review rounds for automated LLM feedback?▼

Configuring maximum review rounds is supported. The Skill continues the review-fix cycle until a positive assessment is achieved or the configured maximum number of rounds is exhausted, preventing infinite loops.

Does automated research review support human checkpoints during the process?▼

Human checkpoints are supported during automated research review. You can configure these checkpoints to pause the LLM iteration loop, allowing manual intervention before continuing the review-fix cycle.

How does state persistence work for long-running LLM research review processes?▼

State persistence saves progress for long-running research review processes. This ensures the iterative LLM assessment and fix implementation cycle can resume accurately if interrupted during extensive artifact refinement.

What is the best way to continuously refine experiment results using an external LLM?▼

The best way to refine experiment results is an autonomous multi-round review loop. An external LLM reviewer identifies weaknesses in the research artifacts and implements fixes until the work is ready for submission.

Related Skills

Explore More Education & Research Skills→
OnlyaguestOnlyaguest
18

autoresearch

Scaffold a skill-improvement workspace with checklist, baseline, and changelog via Python CLI.

Community
Intermediate
kitcafkitcaf
1

auto-review-loop

Automate multi-round review loops with fixes and re-reviews until positive assessment.

Community
Advanced
chenghaoYangchenghaoYang
2

auto-review-loop-minimax

Run iterative manuscript review loops using MiniMax with state persistence.

Community
Advanced
satsuki-64satsuki-64
2

auto-review-loop-llm

Automates iterative multi-round review of research outputs using OpenAI-compatible LLM APIs with scoring and logging.

Community
Advanced