scientific-visualization

Create and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use for figure design, multi-panel layouts, uncertainty and missing-data displays, color/contrast review, image metadata validation, and journal export planning.

Quality

89%

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

Quality

Content

86%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 an actionable, well-structured overview that defers detail to real bundle files and supplies executable code and CLIs. It is slightly verbose in its guardrail/encoding lists and lacks an explicit error-retry feedback loop.

Suggestions

Tighten the 'Non-negotiable guardrails' and 'Choose an honest encoding' bullet lists by merging near-duplicate items to reduce token load.

Add an explicit feedback loop in Step 6 (e.g., 'If metadata/contrast checks fail, fix the export and re-run inspection') to reach the top workflow-clarity anchor.

Note that some inline Seaborn/Plotly version details could move to references/matplotlib_examples.md to keep the overview leaner.

Dimension	Reasoning	Score
Conciseness	Dense and technical with no basic-concept padding (it does not explain what Matplotlib or a PDF is), but the guardrails list and the many sub-bullets in 'Choose an honest encoding' could be trimmed slightly to tighten token use.	4 / 5
Actionability	Provides copy-paste-ready code (object-oriented Matplotlib with style_context, TwoSlopeNorm, Seaborn errorbar API, Plotly export) and fully-specified CLI invocations with flags covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced 6-step workflow with explicit validation checkpoints (inspect metadata, audit contrast, compare to a dated snapshot, re-check the live journal page) and a final checklist, though an explicit 'on failure, fix and re-run' feedback loop is not stated.	4 / 5
Progressive Disclosure	The body is an overview that signals one-level-deep references ('Read references/publication_guidelines.md', 'See references/color_palettes.md') with a References section describing each file; verified referenced files (references/.md, scripts/, assets/*) all exist and content is appropriately split.	5 / 5
	Total	18 / 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 specific, complete, and distinct, cleanly pairing a concrete capability statement with an explicit 'Use for...' trigger list. Its only gap is synonym/extension coverage in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create and audit truthful, accessible, publication-ready scientific figures', plus 'figure design, multi-panel layouts, uncertainty and missing-data displays, color/contrast review, image metadata validation, and journal export planning' — giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both what ('Create and audit truthful, accessible, publication-ready scientific figures...') and when ('Use for figure design, multi-panel layouts...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural terms and library names ('scientific figures', 'Matplotlib, Seaborn, or Plotly', 'multi-panel layouts', 'color/contrast review', 'journal export planning') that users would say, but common synonyms ('plots', 'charts', 'graphs') and file extensions are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche — publication-ready scientific figures with named plotting libraries — with distinct triggers and minimal overlap risk against generic data or document skills.	5 / 5
	Total	19 / 20 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: K-Dense-AI/scientific-agent-skills
Path: skills/scientific-visualization/SKILL.md
Commit: 9e8b0cb

Reviewed: 2 days 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.