denario
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
Security Assessment
Detected risks:
About denario
Denario is a multiagent AI system designed to streamline and automate the entire scientific research workflow, from the initial stages of data analysis to the final stages of publication-ready manuscripts. This skill addresses the complexities of scientific research by providing a structured approach that allows researchers to efficiently generate hypotheses, develop methodologies, execute experiments, and publish their findings. By leveraging advanced AI technologies, Denario simplifies the process of transforming raw data into actionable insights and well-crafted papers, significantly reducing the time and effort required for research activities.
FAQ
How do I install Denario?
You can install Denario using the command 'uv init' followed by 'uv add "denario[app]"' or with pip using 'uv pip install "denario[app]"'.
What API keys are required for Denario?
Denario requires API keys from supported LLM providers such as Google Vertex AI and OpenAI. Store these keys securely using environment variables or .env files.
Can I customize the research methodologies in Denario?
Yes, you can develop custom research methodologies by providing markdown files with your methodologies.
What type of output can I generate with Denario?
Denario can generate publication-ready LaTeX papers formatted for various journals, including the American Physical Society.
Is there a graphical user interface available for Denario?
Yes, you can launch a web-based graphical user interface by running the command 'denario run'.
Install denario
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
davila7/claude-code-templates