CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/wcag-color-contrast

Use for any question about color contrast or whether colors pass WCAG, including quick checks of a few hex values and hard-to-read text: WCAG 2.2 text, large-text and non-text contrast ratios (4.5:1, 3:1) at AA and AAA, the measurement formula, palette and component reviews, and bulk checks over CSS and design tokens.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

67%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, largely actionable reference with a genuinely useful failures/anti-patterns treatment and an executable bulk-check script. Its main weakness is token efficiency — it repeats ratio information and explains WCAG concepts Claude already knows. The dangling reference to a non-existent scripts/check-contrast.js file is a minor structural gap.

Suggestions

Remove duplication between the Overview table and the 'Contrast ratios' section (the 4.5:1/3:1 values appear in both), and trim material Claude already knows such as the large-text definition, exceptions list, luminance formula, and the computable 'Common ratios' table — keep only the non-obvious #767676 boundary pitfall.

Add an inline executable command for the headline 'quick check of a few hex values' use case (e.g., a one-liner using polished or a curl-able checker) so the most common invocation doesn't depend on external tools.

Either include the referenced scripts/check-contrast.js as an actual bundle file in a scripts/ directory or remove the path comment from the code block, since the file does not exist in the bundle.

DimensionReasoningScore

Conciseness

The 4.5:1/3:1 ratios are stated in the Overview table and repeated in 'Contrast ratios', and the SC definitions, large-text rule, exceptions, luminance formula, and the computable 'Common ratios' table (21:1 black/white, etc.) re-explain concepts Claude already knows. This is mostly efficient but padded with duplication and known material, fitting the score-3 anchor rather than the minor-trimming case at 4.

3 / 5

Actionability

The polished bulk-check script is executable and complete with error reporting, the tool table names specific checkers with URLs, and the failures table gives exact hex fixes. Minor gaps remain — the token JSON path is assumed, and the headline 'quick checks of a few hex values' use case has no inline command — so it fits the score-4 anchor rather than the fully copy-paste-ready coverage of 5.

4 / 5

Workflow Clarity

The bulk-check workflow is concrete and the script embeds validation (collects violations, exits 1 on failure), but no explicit step sequence or checkpoint prose is written out for any process. That places it at the score-4 anchor; it is not 5 because no articulated sequence with feedback loops exists, and not 3 because the check workflows are unambiguous and validation is present in code.

4 / 5

Progressive Disclosure

The body is well organized with clear section headers and the inline reference material is appropriate for a single-topic lookup skill. However, the code comment '// scripts/check-contrast.js' references a script that does not exist in the bundle (no scripts/ directory present), a minor organization gap that fits the score-4 anchor rather than the clean one-level-deep structure of 5.

4 / 5

Total

15

/

20

Passed

Description

92%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 description that explicitly states both capabilities and trigger conditions with concrete, natural language. Keyword coverage is good though it omits a few common synonyms like 'accessibility' or 'readability'. Conflict risk is minimal given the tightly scoped WCAG-contrast niche.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities — 'quick checks of a few hex values', 'large-text and non-text contrast ratios (4.5:1, 3:1) at AA and AAA', 'the measurement formula', 'palette and component reviews', and 'bulk checks over CSS and design tokens' — giving comprehensive coverage of the contrast domain with no minor gaps, matching the score-5 anchor.

5 / 5

Completeness

It explicitly answers both 'what' (the enumerated capability list including ratio thresholds, formula, palette/component reviews, and bulk token checks) and 'when' ('Use for any question about color contrast or whether colors pass WCAG') with concrete trigger phrases, matching the score-5 anchor; the 'when' clause is explicit rather than weakly implied so it is not a 4.

5 / 5

Trigger Term Quality

Good natural keyword coverage ('color contrast', 'whether colors pass WCAG', 'hard-to-read text', 'hex values', 'palette', 'design tokens', 'CSS'), but common variations users would say such as 'accessibility', 'a11y', or 'readability' are missing, fitting the score-4 anchor rather than the comprehensive synonym coverage of 5.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (WCAG 2.2 color contrast) with distinct triggers like 'color contrast' and 'colors pass WCAG', creating minimal conflict risk with general accessibility or design skills; this matches the score-5 anchor rather than the minor-overlap case at 4.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Reviewed

On this page