skills.rest
Lingrongye
LingrongyeCOMMUNITY
Explore all skills by this author →
GitHub

auto-review-loop

Coordinate multi-round reviews of research artifacts with structured scoring and Codex MCP.

1|Updated Mar 26, 2026
Search Tags:#traceability#autonomous#review-loop#codex-mcp#research-improvement#iterative-feedback
One-click install
npx skills add https://github.com/Lingrongye/federated-learning --skill auto-review-loop-lingrongye
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: auto-review-loop
Source: https://github.com/Lingrongye/federated-learning/tree/main/Auto-claude-code-research-in-sleep/skills/auto-review-loop
Command: npx skills add https://github.com/Lingrongye/federated-learning --skill auto-review-loop-lingrongye

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Autonomous multi-round review of research artifacts to identify weaknesses, implement fixes, and re-evaluate until a positive assessment or a maximum number of rounds is reached.

Core Features & Use Cases

  • Automates an iterative critique and improvement process for research outputs via Codex MCP.
  • Maintains a structured, auditable log of each review round, decisions, and results.
  • Provides readiness checks for submission and traceable feedback to guide subsequent work.

Quick Start

Provide a topic or scope to begin an autonomous review loop and specify the maximum rounds if different from the default.

Frequently Asked Questions about auto-review-loop

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

FAQPage Schema
How do I automate an iterative review loop for research artifacts?▼

An iterative review loop automates multi-round critiques of research artifacts, driving repeated fixes until a positive assessment or maximum round limit is reached.

How do I ensure traceability during autonomous research improvement?▼

Traceability is maintained by persisting state and logging structured scoring, reviewer feedback, and decisions for each review round.

Does an autonomous review loop work with Codex MCP?▼

Yes, the autonomous review loop integrates with Codex MCP to generate automated replies and coordinate the critique process.

What is the best way to enforce structured scoring on multi-round research reviews?▼

The best way is enforcing structured scoring within the review loop, which applies traceable feedback to guide subsequent improvements.

When should I set a maximum round limit for an autonomous review loop?▼

A maximum round limit should be set to prevent endless iterations when a positive assessment is not reached.

Related Skills

Explore More Education & Research Skills→
WhampWhamp
1

web-research

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

Community
Advanced
bmsull560bmsull560

jr-architect-review

Validate architectural coherence across code, tests, and documentation before merge.

Community
Advanced
chenghaoYangchenghaoYang
2

research-review

Coordinate multi-round external research reviews using Codex MCP.

Community
Advanced
kitcafkitcaf
1

auto-review-loop

Automate multi-round review loops with fixes and re-reviews until positive assessment.

Community
Advanced