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.

The body is highly actionable with clean executable code and well-structured progressive disclosure to verified reference files. Its main weaknesses are content redundancy (the end-to-end example duplicates the core workflow) and the absence of validation/feedback checkpoints in the pipeline.

Suggestions

Remove or condense the "Common Workflows / End-to-End Research Pipeline" block, since it duplicates the five-stage sequence already shown in "Core Research Workflow"; keep only the genuinely different workflows (hybrid, literature search).

Add explicit validation checkpoints between pipeline stages — e.g. verify the generated idea/method is sensible before proceeding, and check results before paper generation — with a fix-and-retry loop for failures.

Trim the Overview and "When to Use This Skill" sections so they do not restate the frontmatter description verbatim.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but redundant: the "Common Workflows / End-to-End Research Pipeline" block repeats the five-stage sequence already shown in "Core Research Workflow", and the Overview and "When to Use" sections restate the description. Not a 1 because it avoids explaining concepts Claude already knows, and not a 3 because the duplicated content does not earn its tokens.	2 / 3
Actionability	Provides fully executable, copy-paste-ready Python with real imports and method calls (e.g. `from denario import Denario, Journal`; `den.get_paper(journal=Journal.APS)`) plus real shell commands (`uv add "denario[app]"`, `denario run`), with placeholders marking genuine user-input slots rather than pseudocode.	3 / 3
Workflow Clarity	The pipeline is a clear numbered five-stage sequence, but there are no validation checkpoints or error-recovery feedback loops anywhere — relevant given the computational/batch experiment stage — so it matches the sequence-present-but-checkpoints-missing anchor rather than a 3.	2 / 3
Progressive Disclosure	The body is an overview that defers detail to four real, one-level-deep reference files (installation.md, llm_configuration.md, research_pipeline.md, examples.md — all verified present with no nested references), signaled both inline and in a "Detailed References" section.	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.

The description is strong: it states concrete capabilities, includes an explicit use-when trigger clause, uses natural trigger terms, and occupies a distinct niche. Voice is correctly third person with no first/second-person phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "generating research ideas", "developing research methodologies", "executing computational experiments", "performing literature searches", and "generating publication-ready papers in LaTeX format" — matching the score-3 anchor of multiple specific concrete actions rather than the domain-plus-some-actions of a 2.	3 / 3
Completeness	Clearly states what it does ("Multiagent AI system for scientific research assistance that automates research workflows") and provides an explicit "This skill should be used when..." trigger clause, satisfying both what and when.	3 / 3
Trigger Term Quality	Uses natural terms a researcher would actually say (research ideas, methodology, literature searches, LaTeX papers, datasets), giving good coverage rather than just a few relevant keywords.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (multiagent scientific research automation to LaTeX publication) with distinct triggers unlikely to collide with general-purpose skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/denario/SKILL.md
Commit: f627ab5

Reviewed: about 8 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.