auto-review-loop-minimax

Automate multi-round research review and iterative fixes via MiniMax API.

Updated May 29, 2026
One-click install
npx skills add https://github.com/Mang30/myskills --skill auto-review-loop-minimax-mang30
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: auto-review-loop-minimax
Source: https://github.com/Mang30/myskills/tree/main/skills/auto-review-loop-minimax
Command: npx skills add https://github.com/Mang30/myskills --skill auto-review-loop-minimax-mang30

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It reduces the risk of publishing weak research by running an autonomous multi-round loop that sends your work for external review, applies the reviewer’s fixes, and re-submits for re-evaluation until quality criteria are met.

Core Features & Use Cases

  • Autonomous multi-round review loop: review → implement fixes → re-review until a positive assessment or MAX_ROUNDS is reached.
  • MiniMax-based external reviewer integration: uses an MCP tool when available or a curl-based API fallback when it is not.
  • State persistence for recovery: writes and overwrites review-stage/REVIEW_STATE.json to resume safely after context compaction or interrupted runs.

Use case: You have a research project that needs ICML/NeurIPS/ICLR-level critique; run the loop to collect a ranked list of weaknesses, implement the minimum fixes, and document each round in review-stage/AUTO_REVIEW.md.

Quick Start

Trigger an autonomous review loop for your current research topic by asking: auto review loop minimax <topic-or-scope>.

Frequently Asked Questions about auto-review-loop-minimax

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

FAQPage Schema
How do I automate paper revision for conference standards using an external reviewer?

Automating conference-level paper revision involves an autonomous loop that sends your work to an external reviewer, implements the minimum necessary fixes, and re-submits for re-evaluation until quality criteria are met or a maximum round limit is reached.

Can I use MiniMax API for automated research review and experiment automation?

Yes, automating research review with the MiniMax API uses an MCP tool for reviewer calls with a curl fallback. It drives experiment automation by repeatedly assessing claims, methods, and results, then applying fixes within an iterative loop.

What is state recovery in an autonomous review loop?

State recovery in an autonomous review loop persists the current review stage as a JSON file. This allows the automated paper revision process to safely resume after context compaction or interrupted runs without losing the iterative critique progress.

How do I run an iterative critique loop for ICML or NeurIPS level papers?

To run an iterative critique loop for ICML or NeurIPS level papers, trigger the autonomous review process with your topic. The loop collects a ranked list of weaknesses, implements minimum fixes, and documents each round in an auto review markdown file.

Does the automated paper revision loop work without MCP?

Yes, the automated paper revision loop works without MCP by falling back to a curl-based API call for the MiniMax reviewer. This ensures the autonomous multi-round review and experiment automation process remains functional across different environments.