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.

Install with Tessl CLI

npx tessl i github:K-Dense-AI/claude-scientific-skills --skill matplotlib

What are skills?

Overall
score

72%

Review — 70%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 15 / 16 Passed

Validation for skill structure

SKILL.md

Review

Evals

Discovery

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong description that excels at completeness and distinctiveness by explicitly stating when to use it and when to use alternatives. The trigger terms are natural and comprehensive. The main weakness is that the specific capabilities could be more concrete - listing actual actions like 'customize axes, create subplots, add annotations' rather than abstract concepts like 'full customization'.

Suggestions

Replace abstract phrases like 'full customization' and 'fine-grained control over every plot element' with concrete actions such as 'customize axes, legends, colors, create subplots, add annotations'

Dimension	Reasoning	Score
Specificity	Names the domain (plotting) and mentions some actions like 'full customization', 'creating novel plot types', 'Export to PNG/PDF/SVG', but doesn't list multiple concrete specific actions like 'create scatter plots, customize axes, add annotations'.	2 / 3
Completeness	Clearly answers both what ('Low-level plotting library for full customization', 'Export to PNG/PDF/SVG') and when ('Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows') with explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes good natural keywords users would say: 'plotting', 'plot', 'customization', 'PNG/PDF/SVG', 'publication', 'scientific workflows', plus explicit mentions of alternative tools (seaborn, plotly) which helps with disambiguation.	3 / 3
Distinctiveness Conflict Risk	Excellent distinctiveness - explicitly differentiates from seaborn (quick statistical plots), plotly (interactive), and scientific-visualization (publication-ready multi-panel), carving out a clear niche for low-level customization needs.	3 / 3
	Total	11 / 12 Passed

Implementation

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides excellent actionable code examples that are immediately executable, but suffers from significant verbosity by explaining matplotlib fundamentals that Claude already knows. The structure references external files appropriately but fails to move enough content there, resulting in a bloated main document. The promotional K-Dense section at the end is inappropriate for a skill file.

Suggestions

Remove the 'Core Concepts' section explaining matplotlib hierarchy and the two interfaces comparison - Claude knows this. Keep only the recommendation to use OO interface.

Move the extensive 'Plot Types and Use Cases' section to the referenced plot_types.md file, keeping only a brief mention that plot types are documented there.

Remove the 'When to Use This Skill' section entirely - this duplicates the skill description and explains obvious use cases.

Remove the K-Dense promotional section at the end - it's not relevant to matplotlib usage and wastes tokens.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive explanations of concepts Claude already knows (matplotlib hierarchy, what figures/axes are, basic plot types). The 'When to Use This Skill' and 'Core Concepts' sections explain fundamentals that don't need explanation. The promotional K-Dense section at the end is irrelevant padding.	1 / 3
Actionability	Provides fully executable, copy-paste ready code examples throughout. All code snippets are complete with imports, and cover a comprehensive range of plot types with specific syntax and parameters.	3 / 3
Workflow Clarity	Steps are listed clearly for basic workflows, but lacks validation checkpoints. For example, the save workflow doesn't verify the file was created successfully, and there's no error handling guidance for common failure modes like missing fonts or memory issues.	2 / 3
Progressive Disclosure	References external files (references/plot_types.md, references/styling_guide.md, scripts/) appropriately, but the main document is bloated with content that should be in those reference files. The inline API explanations and extensive plot type examples belong in the referenced documents.	2 / 3
	Total	8 / 12 Passed

Validation

94%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Reviewed: about 1 month 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.