data-artist

Create beautiful data visualizations with mathematical elegance, color theory, and narrative design - the "Data is Beautiful" aesthetic.

Quality

42%

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 ./bundled/skills/data-artist/SKILL.md

Quality

Content

35%

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

The body is a well-organized but verbose conceptual overview that re-teaches data-viz fundamentals Claude already knows, with abstract implementation guidance and no validation checkpoints in its execution workflow.

Suggestions

Cut the explanations of well-known concepts (encoding accuracy hierarchy, log/linear/sqrt scale basics, colorblind-accessibility primers) and keep only domain-specific guidance Claude would not infer.

Add executable code snippets or concrete build steps instead of abstract tool lists (e.g., a minimal D3/SVG example rather than 'D3.js for custom visualizations').

Insert explicit validation checkpoints into the execution workflow (verify data integrity, simulate colorblind rendering, confirm contrast ratio) before the final implementation step.

Move the long output brief template and palette references into separate bundle files referenced one level deep to reduce inline bulk.

Dimension	Reasoning	Score
Conciseness	The ~274-line body explains textbook concepts Claude already knows (encoding accuracy hierarchy, log/linear scale choice, colorblind accessibility, perceptually uniform scales) and repeats its principle lists multiple times, padding the context unnecessarily.	1 / 3
Actionability	It offers some concrete artifacts (hex-coded CSS palettes, a visualization-type table, a brief template), but the implementation guidance is abstract lists ("D3.js for custom visualizations", "Hover for details") with no executable examples.	2 / 3
Workflow Clarity	The Execution Strategy gives a clear parallel-then-sequential sequence, but there are no validation checkpoints or feedback loops (e.g., verify data, check contrast, confirm encodings do not mislead) in the workflow.	2 / 3
Progressive Disclosure	The skill is a single monolithic file with no bundle references, and content that could be split (the output template, palette reference, type table) is all inline, though it is well-sectioned with clear headers.	2 / 3
	Total	7 / 12 Passed

Description

50%

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 clearly conveys the skill's aesthetic mission but reads as branding more than trigger guidance, listing qualities rather than concrete actions and omitting any explicit 'when to use' clause.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., when the user asks for a chart, graph, data visualization, or dashboard).

Replace quality nouns with concrete actions the skill performs (e.g., 'Design encodings, build color palettes, and generate D3/SVG visualizations').

Include common keyword variations users actually say (charts, graphs, plots, dashboards) to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and several facets ("mathematical elegance, color theory, and narrative design"), but these are qualities/themes rather than concrete executable actions, so it does not reach the multi-action list anchor.	2 / 3
Completeness	It states what the skill does (create data visualizations) but has no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2.	2 / 3
Trigger Term Quality	It includes a relevant natural term ("data visualizations") but leans on aspirational phrasing ("Data is Beautiful" aesthetic) and omits common variations like charts, graphs, plots, or dashboards.	2 / 3
Distinctiveness Conflict Risk	Data visualization is a recognizable niche, but without distinct trigger phrasing it could still overlap with generic charting or data-analysis skills.	2 / 3
	Total	8 / 12 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/data-artist/SKILL.md
Commit: f627ab5

Reviewed: about 9 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.