skills.rest
KwongFuk
KwongFukCOMMUNITY
Explore all skills by this author →
GitHub

auto-review-loop-minimax

Automate multi-round research reviews via the MiniMax API.

Updated Apr 10, 2026
Search Tags:#minimax#state-persistence#research-automation#external-review#round-based#autonomous-review
One-click install
npx skills add https://github.com/KwongFuk/codex-skills --skill auto-review-loop-minimax-kwongfuk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: auto-review-loop-minimax
Source: https://github.com/KwongFuk/codex-skills/tree/main/global/auto-review-loop-minimax
Command: npx skills add https://github.com/KwongFuk/codex-skills --skill auto-review-loop-minimax-kwongfuk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Autonomous, iterative external-review workflow management for research projects by orchestrating multi-round feedback with MiniMax.

Core Features & Use Cases

  • Automated review loops: orchestrates review → fixes → re-review until a positive assessment or max rounds.
  • Flexible API access: uses MCP tool when available and curl as a fallback to the MiniMax API.
  • State persistence & logging: persists progress in REVIEW_STATE.json and logs in AUTO_REVIEW.md for traceability.
  • Documentation-driven: reads project materials and prior rounds to maintain context across rounds.

Quick Start

Run the skill on a project containing a SKILL.md to start the autonomous review loop.

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 iterative external reviews for research projects?▼

You can automate iterative external reviews by running this Skill on a project containing a SKILL.md file. It orchestrates review, fixes, and re-evaluation cycles via the MiniMax API until a positive assessment or max rounds.

How does state persistence work across multi-round research review loops?▼

State persistence works by saving progress in a REVIEW_STATE.json file and logging details in AUTO_REVIEW.md. This ensures context is maintained across rounds by reading prior project materials for full traceability.

Can I use curl to interact with the MiniMax API for autonomous review workflows?▼

Yes, you can use curl for autonomous review workflows. The system uses the MCP tool by default for MiniMax API interaction but automatically falls back to curl-based requests with safe defaults when MCP is unavailable.

What are the limitations of autonomous round-based review loops?▼

Autonomous round-based review loops are limited by a maximum round threshold to prevent infinite cycles. The loop terminates only when a positive assessment is reached or the configured maximum number of review rounds is exceeded.

Do I need MCP to run multi-round research review automation?▼

You do not need MCP to run multi-round research review automation. The workflow uses MCP when available but fully supports curl as a fallback for MiniMax API interaction, ensuring functionality without strict MCP dependencies.

Related Skills

Explore More Education & Research Skills→
fcastrillofcastrillo

rai-discover-start

Detect project type, languages, and key directories into work/discovery/context.yaml.

Community
Intermediate
KwongFukKwongFuk

auto-review-loop

Automate iterative research review rounds with scoring and fix implementation.

Community
Advanced
wanshuiyinwanshuiyin
14.4k

auto-review-loop-minimax

Automate multi-round research review loops using the MiniMax API.

Community
Advanced
KYRIE66nbKYRIE66nb

auto-review-loop-minimax

Coordinate multi-round external review with MiniMax and persist state to JSON.

Community
Advanced