scientific-visualization

Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.

Quality

80%

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/visualization/scientific-visualization/SKILL.md

Quality

Content

67%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.

A thorough, actionable skill body with strong code examples and a sensible file split, weakened by substantial duplication and a few dangling external references. Tightening the repeated seaborn content and fixing import/reference paths would notably improve it.

Suggestions

De-duplicate the body: the seaborn Quick Start, boxplot-with-stripplot example, Okabe-Ito palette, and heatmap example each appear more than once — keep one canonical instance and point to references/matplotlib_examples.md for the rest.

Fix import paths to match the bundle: scripts use `from style_presets import ...` and `from figure_export import ...` but those files live under scripts/, and the `scientific-packages/seaborn/...` paths referenced near line 644 do not exist in this bundle.

Move the large seaborn subsection (axes-level vs figure-level, advanced techniques, issues) into a reference file and keep only the essentials inline, improving both conciseness and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The ~770-line body is noticeably verbose: the seaborn Quick Start and boxplot examples are each duplicated, the Okabe-Ito palette is listed three times, and several sections restate best-practice lists; some preamble explains concepts Claude already knows.	3 / 5
Actionability	Mostly executable copy-paste code backed by real bundle files (style_presets.py, figure_export.py, assets/color_palettes.py, .mplstyle files), though import paths omit the scripts/ directory and the referenced scientific-packages/seaborn/ paths do not exist in the bundle.	4 / 5
Workflow Clarity	A clear 6-step Workflow Summary (Plan→Configure→Create→Verify→Export→Review) with inline code and a verify checkpoint (check_figure_size), plus pitfalls and a final checklist; no destructive/batch operations require additional validation caps.	4 / 5
Progressive Disclosure	Good one-level-deep structure: the body is an overview and detail is pushed to references/, scripts/, and assets/ with a clear Resources listing; the large inlined seaborn section and broken scientific-packages/seaborn/ references prevent a top score.	4 / 5
	Total	15 / 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.

A strong, third-person description that clearly conveys both purpose and trigger conditions with concrete capabilities and a useful boundary clause. Minor synonym coverage could be expanded, but it answers what-and-when comprehensively.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell)' — and three named libraries, giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' ('Meta-skill for publication-ready figures', 'Orchestrates matplotlib/seaborn/plotly with publication styles') and 'when' ('Use when creating journal submission figures requiring…') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural terms ('publication-ready figures', 'journal submission figures', journal names, 'error bars', 'colorblind-safe palettes'), but a few common synonyms (e.g. 'plots', 'manuscript figures') are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (publication/journal figures) with distinct triggers and an explicit boundary clause ('For quick exploration use seaborn or plotly directly'), minimizing overlap with general plotting skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (779 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/visualization/scientific-visualization/SKILL.md
Commit: 1d182e9

Reviewed: 7 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.