skills.rest
KYRIE66nb
KYRIE66nbCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

auto-review-loop-llm

Automate iterative ML research reviews using OpenAI-compatible LLM APIs.

Updated Apr 8, 2026
Search Tags:#llm#ai-assistant#workflow-automation#mcp-server#review-loop#ml-research#autonomous-review
One-click install
npx skills add https://github.com/KYRIE66nb/codex-omx-public-config --skill auto-review-loop-llm-kyrie66nb
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: auto-review-loop-llm
Source: https://github.com/KYRIE66nb/codex-omx-public-config/tree/main/home/.codex/skills/auto-review-loop-llm
Command: npx skills add https://github.com/KYRIE66nb/codex-omx-public-config --skill auto-review-loop-llm-kyrie66nb

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Autonomous ML research reviews often require cycling through evaluation, critique, and integration of fixes across multiple iterations. This skill automates that loop by orchestrating iterative assessments using an OpenAI-compatible LLM.

Core Features & Use Cases

  • End-to-end review loop: Initiates, scores, and iterates on research outputs across multiple rounds with persistent state.
  • MCP-enabled interfacing: Uses the llm-chat MCP server or a compatible API to query and receive expert-level feedback.
  • Audit trail: Logs full responses and round results for traceability and reproducibility.

Quick Start

Say 'auto review loop llm' to start an autonomous review cycle.

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 an iterative review loop for ML research artifacts?▼

Automate iterative ML research reviews by orchestrating evaluation, critique, and improvement cycles across multiple rounds with persistent state using an OpenAI-compatible LLM API.

Can I use an MCP server to generate autonomous critique rounds for research outputs?▼

Yes, an MCP-based LLM integration like the llm-chat MCP server queries and receives expert-level feedback to score and critique research artifacts autonomously.

When do I need persistent state for autonomous LLM research evaluations?▼

Persistent state is needed when conducting multi-round ML research evaluations to track iterative scores, retain critique context, and integrate fixes continuously across cycles.

How do I log LLM review responses to ensure reproducibility in ML workflows?▼

Log LLM review responses by recording full outputs and round results into a cumulative document, creating an audit trail for traceability and reproducibility in ML workflows.

Does autonomous workflow automation require an OpenAI-compatible API for iterative scoring?▼

Yes, autonomous workflow automation for iterative scoring requires an OpenAI-compatible LLM API or an equivalent MCP-based integration to generate research artifact critiques.

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-llm

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

Community
Advanced
HeXiao-55HeXiao-55
1

auto-review-loop-llm

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

Community
Advanced
alo-expalo-exp
6

artifact-reviewer

Orchestrate two-pass artifact reviews with audit trails and state tracking.

Official
Advanced