supervisor-drive

Coordinate multi-agent academic research workflows with safety gates and audit logging.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually coordinating multiple specialized research agents for academic paper development is time-consuming and error-prone, requiring constant state tracking, task prioritization, and safety checks to avoid unintended changes to research integrity.

Core Features & Use Cases

  • Hardcoded bottleneck ranker: Automatically prioritizes the highest-impact research task (drafting unwritten sections, filling missing citations, responding to reviewer feedback, refining figures) based on real-time project state.
  • Six mandatory safety gates: Requires explicit user confirmation for high-risk actions (hypothesis changes, new citations, budget overruns, structural rewrites) even in fully autonomous mode, preventing accidental modifications to core research content.
  • Three flexible operation modes: Supports interactive mode for step-by-step user approval, auto mode for hands-off autonomous execution, and plan-only mode to preview upcoming actions without making changes.
  • Use Case: A researcher finalizing a conference submission can run the skill in auto mode to automatically address all remaining reviewer feedback, fill pending citations, and refine incomplete figures without manually switching between tools or tracking progress.

Quick Start

Invoke the supervisor-drive skill with the /supervisor-drive slash command to start an automated, safety-guarded orchestration loop that coordinates all OMCR research agents to advance your academic paper project.

Frequently Asked Questions about supervisor-drive

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

FAQPage Schema
How do I automate multi-agent research workflows for academic paper development?

To automate multi-agent research workflows, this skill coordinates task prioritization, engine dispatch, and safety validation autonomously. It handles drafting, citation management, and reviewer rebuttals without manual intervention while maintaining full audit logging of all orchestration steps.

What is the best way to coordinate multiple research agents for paper writing?

The best way to coordinate multiple research agents is using a hardcoded bottleneck ranker that automatically prioritizes high-impact tasks like drafting unwritten sections or filling missing citations based on real-time project state.

Can I run autonomous research workflows without manually approving every action?

Yes, you can run autonomous research workflows in auto mode for hands-off execution. However, six mandatory safety gates still require explicit user confirmation for high-risk actions like hypothesis changes, new citations, budget overruns, and structural rewrites.

Does the OMCR orchestrator support step-by-step interactive mode for research tasks?

Yes, the OMCR orchestrator supports interactive mode for step-by-step user approval. It also offers auto mode for autonomous execution and plan-only mode to preview upcoming actions without making changes to your research project.

How does safety validation work during automated academic paper development?

Safety validation during automated academic paper development works through six mandatory safety gates that halt execution for high-risk actions. It includes budget tracking, halt-on-exception error handling, and full audit logging of all orchestration steps to prevent unintended changes.

What limitations exist when using autonomous workflow execution for research papers?

Limitations of autonomous workflow execution include mandatory user confirmation for high-risk actions like hypothesis changes and structural rewrites, even in auto mode. Additionally, halt-on-exception error handling stops execution entirely when errors occur during orchestration.