blog-chart

Generate dark-mode-compatible inline SVG data visualization charts for blog posts. Supports horizontal bar, grouped bar, donut, line, lollipop, area, and radar charts with automatic platform detection (HTML vs JSX/MDX). Enforces chart type diversity, accessible markup (role=img, aria-labelledby), source attribution, and transparent backgrounds. Use when user says "blog chart", "generate chart", "data visualization", "svg chart", "blog graph", or "visualize data".

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

The body is a well-structured, highly actionable reference with concrete SVG shells, per-chart construction recipes, and a closing validation checklist. Its main weakness is redundancy across the shell and output-format sections, which slightly dents token efficiency and progressive disclosure.

Suggestions

Consolidate the repeated SVG shell: present the HTML and JSX/MDX shells once and have the 'Output Format' section reference them rather than re-emitting the full figure markup, reducing token redundancy.

Add a short error-recovery note for when the deterministic CLI fails or validation checklist items are unmet (e.g., re-run with --json to inspect, or fall back to manual construction), to lift workflow clarity toward a feedback loop.

Move the per-chart construction recipes' shared coordinate/sizing conventions into a single referenced block (or the bundled script's --help) so each chart section only states what is unique to it.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no concept over-explanation), but the SVG shell plus title/desc/source-text pattern repeats across the 'Standard SVG Shell', 'JSX/MDX Shell', and 'Output Format' sections — minor instances that could be trimmed. Not a 5 because not every token earns its place; not a 3 because it is mostly efficient rather than padded.	4 / 5
Actionability	Provides copy-paste-ready HTML and JSX/MDX SVG shells, a JSX attribute conversion table, concrete coordinates and formulas for each chart type, and points to a fully executable bundled CLI script (generate_chart_svg.py) covering all seven types — fully executable guidance for the common cases.	5 / 5
Workflow Clarity	A clear sequence runs from input format through type selection, styling, construction, and output format, ending with an explicit 'Quality Checklist (Verify Before Returning)' validation checkpoint. Not a 5 because there is no error-recovery feedback loop; not capped at 3 because chart generation is not a destructive or batch operation.	4 / 5
Progressive Disclosure	Sections are well-organized and the body points one level deep to a verified bundled script (scripts/generate_chart_svg.py); the visual-media.md reference sits outside this bundle. Most chart construction is inline, which is appropriate as core content. Not a 5 because some inline examples duplicate the shell that could live in the script reference.	4 / 5
	Total	17 / 20 Passed

Description

100%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.

The description is exemplary: it states concrete capabilities, lists natural trigger phrases, and explicitly covers both what the skill does and when to use it in third-person voice. No vague fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions across all seven chart types plus 'automatic platform detection (HTML vs JSX/MDX)', 'accessible markup (role=img, aria-labelledby)', 'source attribution, and transparent backgrounds' — comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers 'what' ('Generate dark-mode-compatible inline SVG data visualization charts...') and 'when' ('Use when user says...') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Six natural user phrases are listed ('blog chart', 'generate chart', 'data visualization', 'svg chart', 'blog graph', 'visualize data') including synonyms a user would naturally say, matching comprehensive coverage.	5 / 5
Distinctiveness Conflict Risk	A clear niche (blog SVG charts) with distinct, specific triggers and named chart types gives minimal conflict risk with other skills.	5 / 5
	Total	20 / 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: AgriciDaniel/claude-blog
Path: skills/blog-chart/SKILL.md
Commit: 84f7abf

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.