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

77%

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

The body is rich with executable, well-organized matplotlib guidance, but it is bloated with foundational concepts Claude already knows and—more seriously—points to four reference files and two scripts that do not exist, breaking its progressive-disclosure structure.

Suggestions

Create the referenced bundle files (references/plot_types.md, styling_guide.md, api_reference.md, common_issues.md and scripts/plot_template.py, style_configurator.py) or remove the dangling references so navigation is not broken.

Trim the Overview/Core Concepts explanation of the Figure/Axes/Artist hierarchy and the rcParams key list, moving that detail into a reference file and keeping only what Claude cannot infer.

Move the per-plot-type one-liners and color-specification catalog out of SKILL.md into references/plot_types.md and references/styling_guide.md to reduce the inline wall of text.

Dimension	Reasoning	Score
Conciseness	The body explains concepts Claude already knows — the Figure/Axes/Artist/Axis hierarchy, one-line plot-type definitions, color-specification methods, and a raw rcParams key list — so it is padded rather than lean; it stops short of fully verbose prose only because the embedded code is genuinely useful.	2 / 3
Actionability	Numerous complete, executable snippets (plt.subplots, subplot_mosaic, GridSpec, 3D surface, savefig with dpi/bbox_inches) are copy-paste ready, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Workflows are clearly sequenced (create figure → plot data → customize → save) and the single-action plotting task is unambiguous; no validation cap applies because plotting is not a destructive or batch operation.	3 / 3
Progressive Disclosure	References are clearly signaled ('see references/plot_types.md', scripts/plot_template.py) but none of the referenced files or directories actually exist in the bundle, and the 200+ lines of plot-type/styling/API material that should be offloaded sit inline — the 'content that should be separate is inline' anchor rather than the clean one-level-deep structure.	2 / 3
	Total	10 / 12 Passed

Description

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.

A strong, well-scoped description that states concrete capabilities and explicit use-triggers while differentiating from sibling visualization skills. The only blemish is second-person voice ('you need'), which costs it a specificity point.

Suggestions

Rewrite the trigger clause in third person to avoid the second-person penalty, e.g. 'Use when fine-grained control over every plot element is needed' instead of 'Use when you need...'.

Add a couple of the most common user-facing nouns ('figures', 'charts', 'subplots') to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'fine-grained control over every plot element', 'creating novel plot types', and 'Export to PNG/PDF/SVG for publication' list multiple concrete actions (a base of 3), but the second-person phrasing 'Use when you need...' triggers the rubric's −1 specificity penalty, lowering it to 2.	2 / 3
Completeness	Clearly answers both what ('Low-level plotting library for full customization... Export to PNG/PDF/SVG for publication') and when ('Use when you need fine-grained control...'), matching the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Phrases like 'fine-grained control', 'publication', 'PNG/PDF/SVG', 'novel plot types', and 'scientific workflows' are natural terms a user would say; not the vague-jargon level below.	3 / 3
Distinctiveness Conflict Risk	Explicitly routes quick statistics to seaborn, interactivity to plotly, and journal multi-panel figures to scientific-visualization, carving a clear low-level-customization niche unlikely to trigger the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/general/matplotlib/SKILL.md
Commit: df37802

Reviewed: about 1 hour 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.