skills.rest
zhuyingqin
zhuyingqinCOMMUNITY
Explore all skills by this author →
GitHub

auto-review-loop-llm

Automate iterative research review and fix loops until an external reviewer approves.

1|1|Updated May 19, 2026
Search Tags:#llm evaluation#state persistence#prompt-driven workflow#research iteration#ml peer review#autonomous review
One-click install
npx skills add https://github.com/zhuyingqin/ARIS-WEB --skill auto-review-loop-llm-zhuyingqin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: auto-review-loop-llm
Source: https://github.com/zhuyingqin/ARIS-WEB/tree/main/crates/runtime/assets/skills/auto-review-loop-llm
Command: npx skills add https://github.com/zhuyingqin/ARIS-WEB --skill auto-review-loop-llm-zhuyingqin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

It prevents research work from stalling at “almost there” by running an autonomous review-and-fix loop until an external LLM reviewer deems the work submission-ready.

Core Features & Use Cases

  • Autonomous review iterations: Runs repeated cycles of review → identify weaknesses → implement minimum fixes → re-review for up to a configured maximum rounds.
  • Provider-agnostic external reviewing: Uses any OpenAI-compatible LLM API via an llm-chat MCP server (with a curl-based fallback).
  • Round-by-round audit trail: Appends a cumulative, detailed log of each round and persists compact recovery state so runs can be resumed after interruption.

Quick Start

Start the loop by asking your agent to run the command: auto review loop llm for this research topic.

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 iterative peer review for an ML manuscript?▼

Automating iterative peer review for an ML manuscript requires an autonomous review-and-fix loop that repeatedly identifies weaknesses, applies minimum fixes, and re-reviews until submission-ready. This Skill runs cycles up to a configured maximum using an external LLM reviewer.

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

Yes, you can use any OpenAI-compatible LLM API for autonomous research review via an llm-chat MCP server. A curl-based fallback is also supported for provider-agnostic external reviewing across your workflow.

How does state persistence work for an interrupted LLM evaluation loop?▼

State persistence for an interrupted LLM evaluation loop saves compact recovery data to REVIEW_STATE.json. This allows autonomous review runs to be resumed after an interruption without losing the audit trail.

What is the best way to fix research weaknesses before NeurIPS or ICML submission?▼

The best way to fix research weaknesses before NeurIPS or ICML submission is a prompt-driven workflow that applies minimum fixes and re-reviews iteratively. It remediates weaknesses across multiple rounds until an external reviewer returns a ready verdict.

Does the autonomous review loop log cumulative changes for audit trails?▼

Yes, the autonomous review loop logs cumulative changes for audit trails by appending detailed logs of each round. These cumulative round logs are written directly to review-stage/AUTO_REVIEW.md.

Related Skills

Explore More Education & Research Skills→
Wenwen555Wenwen555

auto-review-loop-llm

Automate iterative review, fixes, and re-checks of ML research artifacts via llm-chat.

Community
Advanced
zhuyingqinzhuyingqin
1

auto-review-loop-minimax

Run iterative MiniMax review loops to fix and re-review research work.

Community
Advanced
goupup-aigoupup-ai
2

auto-review-loop-llm

Automate iterative research paper review, fix, and re-review cycles using an OpenAI-compatible LLM API.

Community
Advanced
LingrongyeLingrongye
1

auto-review-loop-llm

Automate iterative ML research review loops with configurable LLM providers.

Community
Advanced