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

78%

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 ./skills/matplotlib/SKILL.md

Quality

Content

68%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 reference with excellent executable examples and well-signaled one-level-deep references. It is held back by length and concept re-explanation that could be trimmed or deferred to the existing reference files.

Suggestions

Trim the 'Core Concepts' hierarchy and 'Two Interfaces' explanations — Claude already knows Figure/Axes/pyplot — keeping only the OO recommendation.

Move the per-plot-type code catalog out of the body and into references/plot_types.md, retaining only 2-3 representative examples inline.

Reduce the styling section to key rcParams/style-sheet essentials and rely on references/styling_guide.md for the rest.

Dimension	Reasoning	Score
Conciseness	Predominantly concrete code but ~370 lines re-explain concepts Claude already knows (the Figure/Axes/Artist hierarchy, pyplot vs OO interface trade-offs, NumPy/Pandas integration), and the plot-types/styling sections duplicate material available in the reference files.	3 / 5
Actionability	Provides copy-paste-ready, executable code across the common cases — basic plots, subplot layouts (regular/mosaic/GridSpec), all major plot types, styling, saving, and 3D — matching the fully-executable top anchor.	5 / 5
Workflow Clarity	Workflows (create figure → plot → customize → save) are sequenced but lack explicit validation or verification checkpoints; while plotting is not destructive so the 3-cap for missing validation does not bind, the sequence-only-with-implicit-checkpoints fits the 3 anchor better than 4.	3 / 5
Progressive Disclosure	Good structure with a dedicated 'Detailed References' section pointing one level deep to four real reference files and two real scripts; minor gap is that substantial plot-type and styling content is inlined in the body rather than deferred to those references.	4 / 5
	Total	15 / 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, provides explicit 'Use when' triggers, and distinguishes itself from adjacent skills via routing guidance. Minor specificity could be added by naming common chart types.

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 for publication' — with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	Explicitly answers both 'what' (low-level plotting library for full customization, exports to PNG/PDF/SVG) and 'when' ('Use when you need fine-grained control... creating novel plot types, or integrating with specific scientific workflows') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural phrases a user would say are well covered ('fine-grained control', 'novel plot types', 'scientific workflows', 'publication', 'PNG/PDF/SVG', 'quick statistical plots', 'interactive plots', 'journal styling'), missing only common synonyms like explicit chart names (scatter, histogram).	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (low-level matplotlib for full customization) and explicitly routes competing needs to seaborn, plotly, and scientific-visualization, minimizing conflict risk as in the top anchor.	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: 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.