denario

Coordinate scientific research workflows from data description to publication.

1|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/m0at/claudemd --skill denario-m0at
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: denario
Source: https://github.com/m0at/claudemd/tree/main/skills/denario
Command: npx skills add https://github.com/m0at/claudemd --skill denario-m0at

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Denario automates end-to-end scientific research workflows, coordinating data understanding, idea generation, methodology development, computational execution, and publication-ready manuscript production to reduce manual coordination and accelerate outcomes.

Core Features & Use Cases

  • Multiagent orchestration using AG2 and LangGraph to coordinate specialized research tasks and tools.
  • Reproducible research pipelines with structured outputs, versioning, and LaTeX-ready papers.
  • End-to-end workflow from data description to publication, including optional literature search and modular components.
  • Flexible input: manual or automated at each stage, with Docker deployment for reproducible environments.

Quick Start

Create a new Denario project, describe your data with set_data_description, then generate an idea, develop a method, run results, and export a publication-ready paper.

Frequently Asked Questions about denario

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

FAQPage Schema
How do I automate an end-to-end scientific research workflow?

You can automate an end-to-end scientific research workflow by using multiagent orchestration to coordinate data description, idea generation, methodology, computational execution, and publication-ready manuscript production in a structured pipeline.

Can I generate a LaTeX publication-ready manuscript automatically from research data?

Yes, you can generate LaTeX-ready papers automatically. The workflow produces structured outputs and versioned results that compile directly into publication-ready manuscripts, reducing manual formatting and coordination.

How does multiagent orchestration work for research planning and hypothesis generation?

Multiagent orchestration works by using modular agents built with frameworks like LangGraph to coordinate specialized research tasks. These agents handle distinct stages like hypothesis generation, experimental design, and literature search.

Do I need Docker to run reproducible research pipelines?

Docker deployment is supported to ensure reproducible environments for your research pipelines, but it is not strictly required. You can run the modular components with structured outputs and versioning directly.

What is the best way to manage literature search and experimental design in an automated pipeline?

The best way to manage literature search and experimental design is through a modular workflow that allows manual or automated input at each stage, coordinating specialized agents to handle these distinct research tasks.

Are there limitations when using modular agents for computational execution?

The main limitation is that each stage requires valid structured inputs to function correctly. While modular agents coordinate computational execution, complex experimental designs may need manual intervention to ensure accurate methodology development.