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'.
40
41%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/ai-ml/data-visualization-creator/skills/creating-data-visualizations/SKILL.mdQuality
Discovery
82%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 reasonably well-structured with a clear 'Use when' clause and good visualization-specific trigger terms. However, the generic trigger words 'generate', 'create', and 'scaffold' introduce conflict risk with other skills, and the specificity could be improved by listing concrete capabilities like supported chart types or data input formats. The term 'scaffold' feels out of place for a visualization skill and may cause confusion.
Suggestions
Remove or replace the generic trigger term 'scaffold' which is more associated with code/project generation and could cause false matches with other skills.
Add more specific capabilities such as supported chart types (bar, line, scatter, histogram) or data input formats to improve specificity and distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (data visualization) and some actions ('generate plots, charts, and graphs', 'automatic visualization type selection'), but doesn't list comprehensive specific actions like supported chart types, data formats, or output formats. | 2 / 3 |
Completeness | Clearly answers both 'what' (generate plots, charts, and graphs from data with automatic visualization type selection) and 'when' (explicit 'Use when' clause with trigger terms and phrases). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'visualization', 'plot', 'chart', 'graph', 'generate', 'create', 'scaffold'. These cover common variations of how users would request this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | The trigger terms 'generate', 'create', and 'scaffold' are very generic and could conflict with many other skills (e.g., code generation, project scaffolding). The visualization-specific terms help, but 'scaffold' in particular seems misplaced and could cause false triggers. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is almost entirely boilerplate and filler content with no actionable guidance whatsoever. It lacks any executable code, specific library recommendations, concrete visualization selection logic, or real examples. It reads like a template that was never filled in with actual implementation details.
Suggestions
Replace the abstract descriptions with executable Python code using matplotlib/seaborn showing how to create common chart types (bar, line, scatter, histogram) with concrete data examples.
Add a concrete visualization selection decision tree or mapping (e.g., 'categorical comparison → bar chart, time series → line plot, distribution → histogram') instead of vaguely saying Claude will 'select the most appropriate type'.
Remove all generic boilerplate sections (Overview, How It Works, When to Use, Integration, Prerequisites, Instructions, Output, Error Handling, Resources) that provide no actionable information.
Add specific code patterns for common tasks like axis labeling, title formatting, saving to file, and handling different data input formats (CSV, JSON, pandas DataFrame).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations of things Claude already knows. The 'Overview', 'How It Works', 'When to Use', 'Integration', 'Prerequisites', 'Instructions', 'Output', 'Error Handling', and 'Resources' sections are all filler that explain obvious concepts or provide no actionable information. Phrases like 'This skill empowers Claude to transform raw data into compelling visual representations' are pure padding. | 1 / 3 |
Actionability | No executable code, no concrete commands, no specific library usage, no actual implementation guidance. The examples describe what 'the skill will' do in abstract terms rather than providing any code. There's no Python/matplotlib/seaborn code, no data format specifications, no concrete visualization selection logic. | 1 / 3 |
Workflow Clarity | The numbered steps are entirely abstract ('Analyze the data', 'Generate the visualization') with no concrete commands, validation checkpoints, or error recovery loops. The 'Instructions' section is generic boilerplate ('Invoke this skill when trigger conditions are met') that provides zero workflow guidance. | 1 / 3 |
Progressive Disclosure | No bundle files exist, yet the content is a monolithic wall of vague text with no meaningful structure. References to 'Project documentation' and 'Related skills and commands' point to nothing. The content that is present is all filler that should either be replaced with actionable content or removed entirely. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
6e9558f
- Reviewed
Table of Contents
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.