denario

Coordinate multiple agents to transform data into publication-ready LaTeX manuscripts.

15|2|Updated Dec 17, 2025
One-click install
npx skills add https://github.com/rubensliv/k-dense-ai --skill denario-rubensliv
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: denario
Source: https://github.com/rubensliv/k-dense-ai/tree/main/scientific-skills/denario
Command: npx skills add https://github.com/rubensliv/k-dense-ai --skill denario-rubensliv

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Denario automates end-to-end scientific research workflows by coordinating multiple AI agents to handle hypothesis generation, methodology development, data analysis, literature search, and publication-quality paper writing. This reduces manual drudgery and accelerates insights from data to dissemination.

Core Features & Use Cases

  • Multiagent orchestration using AG2 and LangGraph to coordinate specialized agents for ideas, methods, execution, and writing.
  • End-to-end research pipeline from data description to publication-ready LaTeX manuscripts, with journal-formatting support.
  • Flexible, customizable workflows with GUI launching via denario run and containerized deployment in Docker.

Quick Start

Initialize a new Denario project, set your data context with set_data_description, then run the automated idea-to-paper pipeline.

Frequently Asked Questions about denario

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

FAQPage Schema
How do I automate end-to-end scientific research workflows from data to LaTeX publication?

You can automate scientific research workflows by using multiagent orchestration to coordinate hypothesis generation, methodology design, computational analysis, literature searches, and LaTeX paper production, transforming raw data into publication-ready manuscripts.

How does multiagent orchestration work for generating publication-ready manuscripts?

Multiagent orchestration coordinates specialized AI agents for ideas, methods, execution, and writing using frameworks like AG2 and LangGraph, systematically transforming data descriptions into formatted LaTeX manuscripts with reproducible outputs.

Do I need Docker to run reproducible computational analyses and literature searches?

Docker is not strictly required because the pipeline supports installation via uv, but containerized deployment in Docker is available to ensure reproducible computational analyses, literature searches, and consistent research pipeline execution.

What's the best way to start an automated research pipeline for hypothesis generation?

Initialize a new project, set your data context using the set_data_description command, then run the automated idea-to-paper pipeline via the denario run command or GUI to generate hypotheses, methodologies, and results.

Can I customize LangGraph workflows for specific journal-formatting LaTeX outputs?

Yes, workflows are flexible and customizable, allowing you to coordinate multiagent execution for specific journal-formatting requirements and produce publication-ready LaTeX manuscripts tailored to your target journal.

What are the limitations of automating methodology design and computational analyses with AI agents?

While multiagent orchestration accelerates methodology design and computational analyses, users must validate the generated hypotheses and reproducible outputs, as automated research pipelines require human oversight for scientific accuracy.