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.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable skill body with executable code and clean progressive disclosure into verified reference files. Its main weaknesses are a duplicated end-to-end example that adds length, and the absence of validation checkpoints between research-pipeline stages.

Suggestions

Collapse the 'End-to-End Research Pipeline' common workflow into a pointer to the staged Core Research Workflow section, or trim it to only the parts it adds, to remove duplication and tighten conciseness.

Insert explicit validation/verification checkpoints between stages (e.g. 'Review the generated idea with the user before calling get_method(); regenerate if unsuitable') to lift workflow clarity above level 2.

Add a short note on expected output or how to inspect intermediate artifacts at each stage so the user can confirm progress before moving on.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with lean code blocks and no explanation of basic concepts, but the 'Common Workflows > End-to-End Research Pipeline' section largely duplicates the staged code already shown in 'Core Research Workflow', so it could be tightened — matching the level-2 anchor rather than the fully lean level-3.	2 / 3
Actionability	It provides real, executable, copy-paste-ready snippets throughout — 'from denario import Denario', 'den = Denario(project_dir=...)', 'den.get_idea()', 'den.get_paper(journal=Journal.APS)' — plus concrete install commands, matching the level-3 anchor for fully executable guidance.	3 / 3
Workflow Clarity	The pipeline is clearly sequenced into numbered stages (Data Description → Idea → Method → Results → Paper) and shows set_* alternatives, but there are no validation/verification checkpoints between stages (e.g. review the generated idea before building a method), which caps it at level-2 per the missing-checkpoint guideline.	2 / 3
Progressive Disclosure	SKILL.md is a clear overview that defers detail to real, one-level-deep files (references/installation.md, llm_configuration.md, research_pipeline.md, examples.md — all present), with a dedicated 'Detailed References' section and inline pointers, matching the level-3 anchor for well-signaled one-level references.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concisely states what the skill does and gives an explicit Use-when clause with concrete, natural trigger terms. The only mild blemish is light buzzword padding ('customizable agent orchestration', 'end-to-end research pipelines'), but it does not undermine clarity or specificity.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format' — matching the level-3 anchor of several specific concrete actions rather than the vague level-1 or partial level-2.	3 / 3
Completeness	It explicitly answers both what ('automates research workflows from data analysis to publication') and when via the explicit trigger clause 'This skill should be used when generating research ideas from datasets...', satisfying the level-3 anchor and avoiding the level-2 cap for a missing Use-when clause.	3 / 3
Trigger Term Quality	It surfaces natural terms a researcher would say — 'research ideas', 'research methodologies', 'literature searches', 'publication-ready papers', 'LaTeX' — giving good coverage of common variations rather than only jargon, matching the level-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The niche — scientific research automation culminating in LaTeX publication — is clearly demarcated with distinct triggers, making it unlikely to fire for unrelated skills as required by the level-3 anchor.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/coding/denario/SKILL.md
Commit: 52845c3

Reviewed: about 10 hours ago

Table of Contents

Discovery Implementation Validation

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.