Research OS — Testing skill for Claude Code

Research-OS

**An agentic research engineering ecosystem for Claude Code**

Research-OS is an orchestration system built on top of Claude Code that combines rigorous research planning with spec- and test-driven engineering. It provides a structured workflow for transforming research ideas into fully implemented, production-ready code through spec- and test-driven development principles with sophisticated context engineering.

Overview

Research-OS separates the cognitive work of research planning from the execution work of engineering implementation through two specialized, marketplace-compatible plugins that can be used independently or together:

• Researcher Plugin: Focuses on hypothesis development, literature review, and experiment planning
• Engineer Plugin: Handles spec-driven development with implementation and verification workflows

This separation enables:

• Clear distinction between "what to build" (research) and "how to build it" (engineering)
• Reusable research artifacts that inform multiple implementations
• Professional development practices with automated verification
• Sophisticated context engineering through standards and templates

Key Features

🔬 Research-First Development

• Systematic hypothesis refinement and validation
• Comprehensive literature review and related work analysis
• Experiment roadmap with dependency tracking
• Mission-driven project planning

🏗️ Spec-Driven Implementation

• Requirements gathering with visual asset support
• Detailed specification generation
• Strategic task breakdown with agent assignments
• Automated verification and testing

🤖 Multi-Agent Orchestration

• 19 specialized agents across research and engineering domains
• Intelligent task delegation based on agent expertise
• Parallel execution for independent tasks
• Context passing between agents via file artifacts

📐 Standards & Quality

• Customizable coding standards and conventions
• Automatic code quality checks (via ruf