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

76%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/coding/denario/SKILL.md

Quality

Content

61%Weight 40%Scale 1-5

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

The body is a well-organized, actionable overview that correctly delegates detail to real reference files. Its weaknesses are duplicated workflow examples that hurt conciseness and a lack of validation checkpoints in the pipeline sequence.

Suggestions

Remove or condense the "Common Workflows" end-to-end example since it duplicates the numbered "Core Research Workflow" steps, keeping only the genuinely distinct hybrid and literature-search variants.

Add explicit validation checkpoints between pipeline stages (e.g., verify get_idea() produced a usable hypothesis before calling get_method()).

Replace template placeholders like [specify domain] and [phenomenon] with brief concrete example values so snippets are copy-paste runnable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code and no concept-explaining filler, but the "Common Workflows" end-to-end example largely duplicates the numbered "Core Research Workflow" steps, and trailing explanatory sentences after each snippet could be trimmed, fitting the score-3 anchor.	3 / 5
Actionability	Provides concrete, executable guidance throughout (uv add commands, Denario API calls, full end-to-end script), with only minor gaps from template placeholders like [specify domain] and vague notes such as "Additional journals may be available", matching the score-4 anchor.	4 / 5
Workflow Clarity	The five-stage pipeline is clearly numbered with code per stage, but there are no validation or verification checkpoints between stages (e.g., confirming an idea/method was produced before proceeding), matching the score-3 anchor of steps listed but checkpoints missing.	3 / 5
Progressive Disclosure	Good structure with a dedicated "Detailed References" section plus inline pointers to four real one-level-deep files (installation.md, llm_configuration.md, research_pipeline.md, examples.md), with only minor organization gaps from the duplicated inline workflow examples, fitting the score-4 anchor.	4 / 5
	Total	14 / 20 Passed

Description

92%Weight 40%Scale 1-5

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: third-person voice, explicit what-and-when guidance, and a comprehensive list of concrete research-pipeline actions. The only minor gap is trigger-term synonyms for less formal phrasings.

Dimension	Reasoning	Score
Specificity	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" — giving comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	Explicitly states both what ("Multiagent AI system...automates research workflows from data analysis to publication") and when ("This skill should be used when generating research ideas...") with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Good coverage of relevant phrases ("research ideas", "methodologies", "computational experiments", "literature searches", "publication-ready papers", "LaTeX"), but misses common natural variations like "write a paper" or "hypothesis", fitting the score-4 anchor with a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (scientific research automation ending in LaTeX publication) with distinct triggers and minimal overlap risk with other skills, matching the score-5 anchor.	5 / 5
	Total	19 / 20 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: 3a6c3a9

Reviewed: 1 day 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.