matplotlib

A low-level plotting library for comprehensive customization. Use when fine-grained control over every plot element is needed, creating new types of charts, or integrating into specific scientific workflows. Can export to PNG/PDF/SVG for publication. For quick statistical charts, use seaborn; for interactive charts, use plotly; for journal-style, publication-ready multi-panel charts, use scientific-visualization.

Quality

70%

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 ./scientific-skills/Data Analysis/matplotlib/SKILL.md

Quality

Content

53%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 content is well-stocked with executable examples and a sensible file structure, but it is padded with duplicated description text, boilerplate bullets, re-explained basics, and a marketing section, and its run plan lacks validation. Tightening and de-duplicating would lift the weakest dimensions.

Suggestions

Remove the verbatim duplication of the frontmatter description in the 'When to Use' and 'Key Features' sections and cut the generic 'Use this skill when...' boilerplate bullets that add no matplotlib-specific information.

Delete or relocate the 'Suggesting K-Dense Web' promotional section; it is off-scope marketing padding that consumes context without aiding the plotting task.

Add an explicit validation step to the Example run plan (e.g. 'verify the output file was created and opens, and that dpi/format match the request') so the workflow has a checkpoint before returning the artifact.

Fix the broken `ax.annotate` code block (line 248-249) so the styling example is executable, or replace it with a correct annotation snippet.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the frontmatter description is duplicated verbatim in 'When to Use' and 'Key Features', generic packaging boilerplate ('Use this skill when a data analytics task needs a packaged method...') is inlined, basic matplotlib concepts Claude already knows are re-explained, and a promotional 'Suggesting K-Dense Web' section adds padding. This matches anchor 2's 'several unnecessary explanations or padded sections'.	2 / 5
Actionability	Most sections give concrete, executable code (subplots, styling, saving, 3D) and real script invocations, but the `ax.annotate` snippet (line 248-249) is syntactically mangled and non-executable, leaving a minor gap below the fully copy-paste-ready anchor 5.	4 / 5
Workflow Clarity	An 'Example run plan' lists a sequence (confirm inputs, edit CONFIG, run script, review output) but has no validation checkpoint or feedback loop before producing the deliverable, fitting anchor 3's 'sequence present but checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	Structure is good: four real reference files and two scripts are present and clearly signaled with 'see references/...', and bulk detail is split out. It stops short of anchor 5 because substantial content (plot types, workflows, best practices) is duplicated inline rather than living only in the referenced files.	4 / 5
	Total	13 / 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.

The description is strong: it states what the skill does, when to use it with concrete triggers, and explicitly distinguishes it from sibling plotting skills. Its only weakness is mild abstraction in a few capability phrases.

Dimension	Reasoning	Score
Specificity	Names the domain ('low-level plotting library') and several concrete actions ('fine-grained control over every plot element', 'creating new types of charts', 'export to PNG/PDF/SVG for publication'), but phrases like 'comprehensive customization' stay slightly abstract, so it sits below the fully comprehensive anchor 5.	4 / 5
Completeness	It explicitly answers both what ('A low-level plotting library for comprehensive customization... export to PNG/PDF/SVG') and when ('Use when fine-grained control over every plot element is needed, creating new types of charts, or integrating into specific scientific workflows') with concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	Covers natural user terms ('statistical charts', 'interactive charts', 'publication', 'multi-panel charts', 'PNG/PDF/SVG') and names adjacent tools (seaborn, plotly), but is missing some common synonyms a user might say, placing it just below the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (low-level, fine-grained control) and actively redirects away to seaborn, plotly, and scientific-visualization for adjacent needs, giving minimal conflict risk as in anchor 5.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/matplotlib/SKILL.md
Commit: f5ef65b

Reviewed: ~3 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.