plotly
Interactive visualization library. Use when you need hover info, zoom, pan, or web-embeddable charts. Best for dashboards, exploratory analysis, and presentations. For static publication figures use matplotlib or scientific-visualization.
85
81%
Does it follow best practices?
Impact
91%
1.13xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%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 skill description that clearly communicates its niche (interactive visualization) and provides explicit guidance on when to use it versus alternatives. The inclusion of negative routing ('For static publication figures use matplotlib or scientific-visualization') is a notable strength. The main weakness is that the specific capabilities could be more concrete—listing actual chart types or actions rather than just interaction features.
Suggestions
Add specific concrete actions like 'create interactive scatter plots, build heatmaps, generate time series charts, construct bar charts' to improve specificity beyond just interaction features.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (interactive visualization) and some actions (hover info, zoom, pan, web-embeddable charts), but doesn't list specific concrete actions like 'create scatter plots, build heatmaps, generate time series charts'. The capabilities mentioned are more feature-level than action-level. | 2 / 3 |
Completeness | Clearly answers both 'what' (interactive visualization library with hover, zoom, pan, web-embeddable charts) and 'when' ('Use when you need hover info, zoom, pan, or web-embeddable charts. Best for dashboards, exploratory analysis, and presentations'). Also includes explicit negative guidance for when NOT to use it. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'hover', 'zoom', 'pan', 'web-embeddable charts', 'dashboards', 'exploratory analysis', 'presentations', 'interactive visualization'. Also provides contrast terms ('matplotlib', 'scientific-visualization') to help with routing. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive by explicitly differentiating from matplotlib/scientific-visualization for static figures. The focus on interactivity (hover, zoom, pan) and specific use cases (dashboards, exploratory analysis) creates a clear niche that is unlikely to conflict with other visualization skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid skill file with excellent progressive disclosure and highly actionable code examples. Its main weakness is verbosity — the extensive chart type catalog and multiple workflow sections could be trimmed or moved to reference files, as much of this is information Claude already knows. The workflow clarity is adequate for a visualization library but could benefit from explicit output verification steps.
Suggestions
Trim the 'Core Capabilities > Chart Types' section to just a brief mention and pointer to chart-types.md, since the full categorized list is redundant with the reference file.
Reduce the 'Common Workflows' section — most of these are straightforward px/go calls that Claude can construct from the Quick Start example and API knowledge; keep only the non-obvious patterns like the subplot specs syntax.
Remove the 'Additional Resources' section with external links, as Claude cannot browse these and they consume tokens without adding actionable value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but includes some unnecessary verbosity. The 'Core Capabilities' section listing all 40+ chart types by category is essentially a catalog that Claude already knows and could be more concisely handled by just pointing to the reference file. The 'Common Workflows' section repeats patterns already shown or easily inferred. The 'Additional Resources' section with external links adds little value. | 2 / 3 |
Actionability | All code examples are concrete, executable, and copy-paste ready. The skill provides specific import statements, complete function calls with real parameters, and covers installation commands. Examples span from basic scatter plots to complex multi-plot dashboards with full working code. | 3 / 3 |
Workflow Clarity | The skill presents clear decision guidance (when to use px vs go) and provides good examples for different use cases, but lacks explicit validation steps. For a visualization library, there's no mention of verifying output (e.g., checking file was written successfully, validating HTML output). The workflows are more like recipe collections than sequenced processes with checkpoints. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to five specific reference files (plotly-express.md, graph-objects.md, chart-types.md, layouts-styling.md, export-interactivity.md). References are consistently linked throughout the document at relevant points and collected in a summary section. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
b58ad7e
- 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.