iterate-revision

Automate iterative writer-reviewer revision loops for research manuscript sections.

30|8|Updated May 10, 2026
One-click install
npx skills add https://github.com/youngeun1209/oh-my-claudecode-research --skill iterate-revision
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: iterate-revision
Source: https://github.com/youngeun1209/oh-my-claudecode-research/tree/main/skills/iterate-revision
Command: npx skills add https://github.com/youngeun1209/oh-my-claudecode-research --skill iterate-revision

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually revising research manuscript sections through repeated rounds of writing and peer feedback is time-consuming, inconsistent, and difficult to track. This skill automates the entire loop between the paper-writer and reviewer agents, eliminating manual coordination and ensuring every revision is logged and trackable.

Core Features & Use Cases

  • Automated Writer-Reviewer Loop: Coordinates the @paper-writer and @reviewer agents to revise a single manuscript section iteratively until it is approved, blocked by critical issues, or the iteration cap is reached.
  • Automatic State Tracking: Logs all review issues, iteration counts, and section status to reviews.json and paper.json, with support for safe re-runs and resuming interrupted or blocked runs.
  • Venue-Aware Reviewing: Adjusts reviewer strictness based on the target publication venue, and enforces guardrails like blocking runs with unresolved [TBD:] markers to prevent fabricated content.
  • Use Case: When finalizing the results section of a conference paper, use this skill to automatically iterate between writing and reviewing until the section meets venue standards, with all feedback and version history preserved for transparency.

Quick Start

Invoke the iterate-revision skill by providing the file path to the manuscript section you wish to revise to launch the automated writer-reviewer revision loop.

Frequently Asked Questions about iterate-revision

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

FAQPage Schema
How do I automate peer review and revision loops for academic manuscript sections?

Automating academic manuscript revision involves coordinating writer and reviewer agents to iteratively edit sections until approved or the iteration cap is reached. This skill orchestrates that loop automatically, logging all feedback to reviews.json for full trackability.

Can I adjust reviewer strictness based on my target publication venue?

Yes, you can configure venue-specific reviewer strictness for academic papers. The skill adjusts its automated peer review critique intensity based on the target publication venue, ensuring feedback meets appropriate academic standards.

What happens if my research writing has unresolved TBD markers?

Research writing with unresolved [TBD:] markers will be blocked from proceeding. The skill enforces safety guardrails that block revision runs containing TBD markers to prevent fabricated content from entering the manuscript.

How do I resume an interrupted manuscript revision run?

To resume an interrupted manuscript revision run, simply re-invoke the skill with the manuscript section file path. The tool uses atomic state writes to paper.json and reviews.json, enabling safe resume functionality for blocked or interrupted runs.

What is the best way to track iteration counts and review issues during paper editing?

Tracking iteration counts and review issues during paper editing is handled automatically through atomic state writes. The skill logs all review issues, iteration counts, and section status directly to reviews.json and paper.json files.

Do I need any specific dependencies to run the automated writer-reviewer loop?

No specific dependencies are required to run the automated writer-reviewer loop for paper editing. The skill operates independently, coordinating paper-writer and reviewer agents without needing external components or frameworks.