auto-review-loop-llm
CommunityIterative LLM-powered research review.
AuthorMACJONSW
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill automates the process of improving research papers by iteratively reviewing them with an LLM, implementing suggested fixes, and re-reviewing until a satisfactory assessment is achieved.
Core Features & Use Cases
- Autonomous Review Cycles: Runs multiple rounds of LLM-based critique and improvement.
- Configurable LLM Integration: Supports any OpenAI-compatible API via MCP server or direct
curlcalls. - State Persistence: Saves progress to
REVIEW_STATE.jsonfor recovery. - Use Case: A researcher can use this skill to get continuous feedback on a paper draft, automatically incorporating suggestions and re-submitting for review until it meets submission standards for top venues.
Quick Start
Initiate an autonomous review loop for the current research topic using the default LLM configuration.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: auto-review-loop-llm Download link: https://github.com/MACJONSW/AutoResearchIDEA/archive/main.zip#auto-review-loop-llm Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.