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

auto-review-loop-llm

Automate multi-round research review cycles with an OpenAI-compatible LLM.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates iterative autonomous review cycles of research work using an OpenAI-compatible LLM to critique and improve submissions.

Core Features & Use Cases

  • Automates multi-round review with scoring, verdicts, and action items
  • Supports configurable MAX_ROUNDS, thresholds, and recovery from failures
  • Pluggable LLM providers via MCP or direct API access for flexibility
  • Persists state in REVIEW_STATE.json and logs in AUTO_REVIEW.md for auditability
  • Useful for academic manuscripts, technical reports, and research proposals

Quick Start

Trigger the loop on your project topic by invoking the skill and following the prompts to begin rounds.

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 peer review for academic manuscripts using an LLM?▼

Yes, multi-round research critique cycles can be configured by setting MAX_ROUNDS and scoring thresholds, allowing the LLM to iteratively evaluate, generate verdicts, and track action items until acceptance criteria are met.

Can I use MCP-based LLM chat servers for autonomous research review?▼

MCP-based LLM chat servers are supported for autonomous research review, alongside direct OpenAI-compatible API calls, providing flexible provider integration to execute critique and improvement workflows.

How does state persistence work during iterative LLM review workflows?▼

State persistence during iterative LLM review workflows operates by saving progress and audit logs to REVIEW_STATE.json and AUTO_REVIEW.md, ensuring traceability and enabling recovery from mid-process failures.

What is the best way to generate explicit verdicts and action items for technical reports?▼

Generating explicit verdicts and action items for technical reports is best handled by autonomous review loops that leverage configurable scoring thresholds and LLM critiques to systematically evaluate and improve the document.

Does this autonomous review loop work with any OpenAI-compatible LLM provider?▼

Yes, the autonomous review loop works with any OpenAI-compatible LLM provider through direct API access, while also supporting pluggable MCP-based chat servers for flexible integration across various platforms.

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
WhampWhamp
1

web-research

Conduct multi-round web research prioritizing GitHub and StackOverflow for code solutions.

Community
Advanced
ovachieverovachiever
52

serving-llms-vllm

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

Community
Advanced
KwongFukKwongFuk

auto-review-loop-llm

Automate iterative research review loops with OpenAI-compatible LLMs.

Community
Advanced