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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

65%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 well-structured with good progressive disclosure into real, one-level-deep reference files and mostly executable guidance. It is let down by a duplicated end-to-end example, marketing filler, an internal 'four-stage vs five-stage' inconsistency, and the absence of validation checkpoints in the pipeline workflow.

Suggestions

Remove the duplicated 'End-to-End Research Pipeline' example (it repeats the five stages already shown) and trim the marketing-style bullets in 'Advanced Features'.

Add validation checkpoints between pipeline stages, e.g. 'Review den.get_idea() output and confirm or override with den.set_idea() before generating the methodology'.

Fix the 'four-stage research pipeline' header to match the five numbered stages that follow.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable snippets and no basic-concept padding, but the 'End-to-End Research Pipeline' section duplicates the five stages already documented, 'Advanced Features' is marketing-style filler ('Reproducible research', 'Flexible input'), and the header says 'four-stage' over five numbered stages.	3 / 5
Actionability	Provides real commands (`uv add "denario[app]"`, `denario run`) and concrete API calls (`den.get_idea()`, `den.get_paper(journal=Journal.APS)`); placeholders like `[phenomenon]` are justified user-content slots, but later snippets drop imports and return-value handling, so it is not fully copy-paste ready.	4 / 5
Workflow Clarity	The five pipeline stages are clearly numbered and sequenced with set_/get_ alternates, but there are no validation checkpoints between stages (e.g., review the generated idea before developing the method) and error handling is deferred to a generic Troubleshooting list.	3 / 5
Progressive Disclosure	Installation, LLM configuration, full API reference, and examples are appropriately split into four real reference files, signposted inline where relevant and summarized in a 'Detailed References' section; references are one level deep with no nesting.	5 / 5
	Total	15 / 20 Passed

Description

88%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.

A strong description: it clearly states what the skill does and when to use it, with multiple concrete trigger actions in third person. Keyword coverage is good but could add a few more natural synonyms (e.g., 'hypothesis', 'manuscript').

Dimension	Reasoning	Score
Specificity	Lists five concrete actions ('generating research ideas from datasets', 'developing research methodologies', 'executing computational experiments', 'performing literature searches', 'generating publication-ready papers in LaTeX format'), giving comprehensive coverage of the pipeline.	5 / 5
Completeness	Explicitly answers both 'what' ('automates research workflows from data analysis to publication') and 'when' ('This skill should be used when generating research ideas...') with concrete trigger phrases, in third-person voice.	5 / 5
Trigger Term Quality	Contains natural phrases users would say ('research ideas', 'literature searches', 'papers in LaTeX format'), but misses common variations such as 'hypothesis', 'draft/write a manuscript', or 'analyze data'.	4 / 5
Distinctiveness Conflict Risk	The end-to-end scientific-research-pipeline framing with LaTeX journal output is a distinct niche, but broad terms like 'data analysis' and 'literature searches' carry minor overlap risk with dedicated analysis or literature-review skills.	4 / 5
	Total	18 / 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: 4082a2e

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.