creating-data-visualizations

Generate plots, charts, and graphs from data with automatic visualization type selection. Use when requesting "visualization", "plot", "chart", or "graph". Trigger with phrases like 'generate', 'create', or 'scaffold'.

Quality

37%

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 ./plugins/ai-ml/data-visualization-creator/skills/creating-data-visualizations/SKILL.md

Quality

Content

20%

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

The skill body is verbose and conceptual rather than instructional, with no executable code or references to the bundled scripts and assets that are present. It reads as a generic overview rather than actionable guidance.

Suggestions

Replace conceptual prose with concrete, executable examples: show how to invoke scripts/data_analyzer.py and generate a chart with a specific library (e.g. matplotlib) and sample code.

Link to the actual bundled resources — reference scripts/data_analyzer.py, the chart_templates/ and example_data/ directories — so Claude can navigate to them.

Cut filler sections (Overview, Integration, Resources) that restate what Claude already knows, and add validation checkpoints to the visualization workflow.

Dimension	Reasoning	Score
Conciseness	The body is padded with high-level conceptual explanation Claude already knows (e.g. 'empowers Claude to transform raw data into compelling visual representations', 'helps users understand complex data') and generic filler sections that add no actionable value.	1 / 3
Actionability	Despite a bundled data_analyzer.py script, the body gives no executable code, commands, or concrete library guidance — it only describes steps abstractly ('Claude generates the visualization using appropriate libraries').	1 / 3
Workflow Clarity	A sequence exists (analyze, select, generate) but there are no validation checkpoints or error-recovery feedback loops, and the listed steps are vague rather than concrete commands.	2 / 3
Progressive Disclosure	Sections are organized, but the body never references the actual bundled files (scripts/data_analyzer.py, chart templates, example data) that exist, so navigation to supporting materials is missing.	2 / 3
	Total	6 / 12 Passed

Description

55%

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 covers a clear domain and includes a use-when clause, but it relies on generic trigger verbs and lists only one broad action rather than multiple specific capabilities. It is solid but not exemplary.

Suggestions

Replace generic trigger verbs (generate, create, scaffold) with concrete situational triggers users would actually say, e.g. 'Use when the user asks to plot data, visualize a dataset, or chart relationships between variables'.

Enumerate multiple specific actions beyond 'generate', such as 'select chart type, render plots, and export figures'.

Tighten the description to remove the trailing blank line and redundant phrasing for a cleaner, more specific statement.

Dimension	Reasoning	Score
Specificity	Names the domain (plots, charts, graphs) and the single action of generation with automatic type selection, but does not list multiple distinct concrete actions like the score-3 anchor (e.g. fill, merge).	2 / 3
Completeness	It states what the skill does and includes a 'Use when...' clause, but the 'when' trigger guidance relies on generic verbs (generate/create/scaffold) rather than explicit situational conditions, leaving the when partly implied.	2 / 3
Trigger Term Quality	Includes natural terms (visualization, plot, chart, graph) but the listed triggers (generate, create, scaffold) are generic verbs rather than domain-specific variations users would say, missing common phrasings.	2 / 3
Distinctiveness Conflict Risk	The visualization domain is reasonably distinct, but generic trigger verbs (generate, create) could overlap with many other generation skills, so conflict risk remains moderate.	2 / 3
	Total	8 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/ai-ml/data-visualization-creator/skills/creating-data-visualizations/SKILL.md
Commit: 15940c5

Reviewed: 3 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.