matplotlib

Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.

Quality

83%

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

78%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, highly actionable matplotlib skill with excellent progressive disclosure and executable examples. Its main weakness is conciseness, as it explains basic plotting concepts Claude already knows and re-states the description's triggers.

Suggestions

Trim conceptual explanations Claude already knows (e.g., the Figure/Axes/Artist hierarchy definitions and the 'what each plot type is for' glosses) to tighten conciseness.

Remove or condense the 'When to Use This Skill' bullet list since the frontmatter description already covers triggers.

Consolidate the per-plot-type examples in the body and rely more on references/plot_types.md to reduce inline duplication.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with dense, useful code, but it explains concepts Claude already knows (e.g., the Figure/Axes/Artist hierarchy, what heatmaps, contour, and violin plots are 'for') and the 'When to Use' bullet list duplicates the frontmatter description.	3 / 5
Actionability	Provides extensive copy-paste-ready, executable code covering the common cases — basic plots, subplots, plot types, styling, saving, and 3D — with specific parameters and runnable commands.	5 / 5
Workflow Clarity	Plot-creation workflows are clearly sequenced (create figure, plot data, customize, savefig), and there are no destructive or batch operations requiring validation caps, though checkpoints are implicit rather than emphasized.	4 / 5
Progressive Disclosure	SKILL.md is a well-organized overview with clearly signaled, one-level-deep references (plot_types.md, styling_guide.md, api_reference.md, common_issues.md) and helper scripts — all verified to exist — with bulk detail appropriately split out.	5 / 5
	Total	17 / 20 Passed

Description

87%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 states capabilities and triggers while distinguishing the skill from siblings via explicit routing. It is comprehensive on the 'what' and 'when' with only minor synonym gaps in trigger terms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'fine-grained control over every plot element', 'creating novel plot types', 'integrating with specific scientific workflows', 'Export to PNG/PDF/SVG' — but 'full customization' remains somewhat abstract, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' (low-level plotting library with fine-grained control and format export) and 'when' (Use when you need fine-grained control..., creating novel plot types, integrating scientific workflows) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('plot', 'scientific workflows', 'publication', 'PNG/PDF/SVG') plus sibling-skill routing (seaborn, plotly), but misses common synonyms like 'chart', 'figure', or 'visualization'.	4 / 5
Distinctiveness Conflict Risk	Establishes a clear niche (low-level customization) and explicitly routes overlapping cases to seaborn, plotly, and scientific-visualization, minimizing conflict risk.	5 / 5
	Total	18 / 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/matplotlib/SKILL.md
Commit: 1e5eeff

Reviewed: 4 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.