data-viz-renderer

Generate self-contained HTML/SVG infographics from JSON data, including stat cards, bar charts, flow diagrams, and mixed dashboards. Offers 8 color palettes and built-in icons with no external dependencies. Triggered when users request data visualization, infographics, charts, or dashboards.

Quality

85%

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

82%Weight 40%Scale 1-5

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

A clean, example-driven SKILL.md that is highly actionable and keeps the heavy implementation in a referenced script. It is concise and well-structured; the main improvement room is trimming the redundant 'Design Highlights' recap and making the script reference slightly more explicit.

Suggestions

Trim the 'Design Highlights' bullet list, which largely restates fields and capabilities already documented in the tables and examples above.

Explicitly frame 'scripts/build_infographic.py' as the detailed reference for icon/palette internals rather than only as the invocation target, strengthening the one-level-deep navigation signal.

Add a brief note on how to validate a generated HTML (e.g., open in browser / check size_bytes) so the single-step workflow has a light verification checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is well-organized and largely avoids teaching concepts Claude already knows; it leans on tables and example JSON rather than prose. Minor padding like the 'Design Highlights' bullet list restates features already shown, but it is not severely verbose.	4 / 5
Actionability	Provides copy-paste-ready invocation commands ('python3 scripts/build_infographic.py config.json' and stdin form) plus complete, executable JSON configuration examples covering each of the four types and the documented output/error format.	5 / 5
Workflow Clarity	Usage is clearly sequenced (write config -> run script -> read JSON status + HTML output) with explicit error-status output shown. There is no validate/retry feedback loop, but the operation is non-destructive single-pass generation, so checkpoints are not critical here.	4 / 5
Progressive Disclosure	The SKILL.md acts as a clear overview with well-organized sections and points to a real referenced script (scripts/build_infographic.py, verified present) one level deep rather than inlining 27KB of Python. It could be marginally clearer by explicitly labeling the script as the detailed reference.	4 / 5
	Total	17 / 20 Passed

Description

88%Weight 40%Scale 1-5

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, third-person description that names concrete capabilities and provides an explicit activation trigger. It is specific and complete; the only minor gap is slightly thinner coverage of natural synonyms and file extensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('stat cards, bar charts, flow diagrams, and mixed dashboards') plus concrete features ('8 color palettes', 'built-in icons', 'no external dependencies'), giving comprehensive coverage of capabilities.	5 / 5
Completeness	Clearly answers 'what' (generates self-contained HTML/SVG infographics from JSON data) and 'when' with the concrete trigger clause 'Triggered when users request data visualization, infographics, charts, or dashboards.'	5 / 5
Trigger Term Quality	Includes natural user-facing terms ('data visualization', 'infographics', 'charts', 'dashboards') with the explicit trigger phrase 'Triggered when users request...', but omits common synonyms like 'graphs' or file extensions, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The narrow focus on generating HTML/SVG infographics from JSON via a dedicated renderer carves a distinct niche with minimal conflict risk, though broad data-viz adjacent skills could overlap on generic chart requests.	4 / 5
	Total	18 / 20 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: zebbern/claude-code-guide
Path: skills/data-viz-renderer/SKILL.md
Commit: 59c5fc4

Reviewed: 4 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.