CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

83

2.77x
Quality

75%

Does it follow best practices?

Impact

100%

2.77x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/denario/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

100%

Automate a Particle Physics Research Pipeline

Automated research pipeline

Criteria
Without context
With context

Correct import statement

0%

100%

Journal import

0%

100%

project_dir parameter

0%

100%

Detailed data description

0%

100%

set_data_description called first

0%

100%

get_idea() called

0%

100%

get_method() called

0%

100%

get_results() called

0%

100%

Journal.APS used

0%

100%

Correct workflow order

0%

100%

100%

80%

Generate a Publication from Completed Neuroscience Research

Hybrid workflow with custom inputs

Criteria
Without context
With context

Correct import

0%

100%

Journal import

0%

100%

project_dir parameter

0%

100%

set_data_description called

0%

100%

set_idea() used

0%

100%

get_idea() NOT called

100%

100%

set_method() used

0%

100%

get_method() NOT called

100%

100%

get_results() called

0%

100%

Journal.APS in get_paper

0%

100%

100%

10%

Set Up Denario for a University Research Lab

Installation and API key configuration

Criteria
Without context
With context

uv install command

100%

100%

uv init step

100%

100%

Python 3.12 requirement

100%

100%

OPENAI_API_KEY env var

100%

100%

Google credentials env var

100%

100%

.env file approach

100%

100%

load_dotenv() usage

0%

100%

.gitignore for secrets

100%

100%

No hardcoded keys

100%

100%

LaTeX or Docker for paper generation

100%

100%

Repository
K-Dense-AI/claude-scientific-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.