Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Plan and manage AI research projects: brainstorm ideas, discover related work, assess claims, and generate structured mission statements, experiment roadmaps, and project documentation.
npx claudepluginhub wielandbrendel/research-os --plugin researcherUse the @research-strategist agent to deeply investigate and reflect on the following aspect: $ARGUMENTS
You are helping to brainstorm and iteratively refine a research idea through critical assessment, related work analysis, and focused questioning. This command orchestrates a multi-phase workflow that:
You are helping to plan and document a research project with a mission, experiment roadmap, and technical requirements. This will include:
Use this agent when you need to critically evaluate and improve a research project assessment written in research-os/project/assessment.md. This agent should be called after an initial assessment has been completed and you want to ensure the critique is well-grounded, focused, and maximally helpful.
Develop a roadmap for the experiments that are necessary to support all claims of the research project
Turn a project vision into a compelling mission statement for a top-tier venue
Research a project idea and iterate towards a full vision together with the user
You are a research specialist. Your role is to discuss a project idea, perform extensive research about the related work, challenge the idea and work with the user towards an impactful project vision. Note that the project idea has been submitted by an external PhD student, so ultrathink and be as honest and constructive as you can.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
PhD-level research capabilities: literature review, multi-source investigation, critical analysis, hypothesis-driven exploration, quantitative/qualitative methods, and lateral thinking
AI-powered deep research with multi-agent source verification and structured outputs
Strategic research thinking agents — idea evaluation, project triage, and structured brainstorming inspired by Carlini's research methodology
Academic research agents — hypothesis generation, experiment design, paper drafting, peer review simulation, and more.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Scientific presentation agents and skills specializing in professional, insightful and engaging research presentations.
Comprehensive Software engineering agents specializing in professional spec- and test-driven development of artifacts.
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.
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:
This separation enables:
Research-OS is compatible with the Claude Code marketplace and plugin system. Add this marketplace to Claude Code:
/plugin marketplace add wielandbrendel/research-os
Then browse and install individual plugins (commands or agents):
/plugin
For more details on the Claude Code plugin system, see the official documentation
Start by brainstorming and refining your initial research idea:
Step 1: Create research-os/project/idea.md with your initial research concept:
# Initial Research Idea
[Your research idea, hypothesis, or problem statement]
Step 2: Run the brainstorm command:
/brainstorm
This iterative refinement command will:
idea.mdOutput is created in research-os/project/:
idea.md - Your refined research idea (updated after each iteration)assessment.md - Critical assessment with strengths, weaknesses, and recommendationsresearch-journal.md - Related work exploration and searchesIterate: Run /brainstorm multiple times to progressively refine your research concept. Each iteration deepens the analysis and sharpens the focus.
When satisfied with your refined idea, proceed to full research planning with /plan-research.
Develop your comprehensive research vision with the Researcher plugin:
/plan-research
This comprehensive command will:
Output is created in research-os/project/:
research-journal.md - Iterative refinement historyrelated-work.md - Literature review and analysismission.md - Project vision and goalsroadmap.md - Phased experiment plantech-stack.md - Technical requirementsUse the Engineer plugin to implement your research vision:
/new-artifact [feature-description]
/create-artifact
spec.mdtasks.md with agent assignments