accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android).

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/accessibility/SKILL.md

Quality

Content

65%

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

The content is highly actionable with concrete WCAG values and executable cross-platform code, and is clearly sequenced around POUR. Its weaknesses are mild verbosity from re-explaining fundamentals Claude knows, missing validation/feedback checkpoints in the workflow, and a monolithic single-file structure with no progressive disclosure into bundle files.

Suggestions

Trim the intro and Core Concepts sections to remove restatements of POUR and the accessibility-tree definition that Claude already knows; keep only the skill-specific framing.

Add an explicit validation/verification step to the How-It-Works workflow — e.g., audit with axe-core or a screen reader, then fix and re-verify — to create a verify→fix→retry feedback loop appropriate for an auditing skill.

Move the three platform-specific code examples and the Cross-Platform Mapping table into a dedicated reference file (e.g., references/platform-mapping.md) and link to it one level deep, leaving SKILL.md as a leaner overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, but the intro and "Core Concepts" re-explain POUR ("Perceivable, Operable, Understandable, and Robust") and the accessibility tree — concepts Claude already knows; it is not a 3 because some explanatory padding remains, and not a 1 because the bulk is tight and value-dense.	2 / 3
Actionability	Provides concrete values (4.5:1/3:1 contrast, 24x24 CSS px per SC 2.5.8) and fully executable, copy-paste-ready code for Web, iOS, and Android plus an exact cross-platform API mapping table; it is not a 2 because the examples are complete and runnable rather than pseudocode with missing details.	3 / 3
Workflow Clarity	The 5-step POUR sequence is clearly ordered and a best-practices checklist exists, but there are no embedded validation checkpoints or a verify→fix→retry loop (e.g., test with a screen reader or axe-core) within the workflow; it is not a 1 because the sequence and checklist are present, and not a 3 because explicit validation/feedback steps are missing.	2 / 3
Progressive Disclosure	The file is well-sectioned with clear headers, but it is a monolithic ~140-line SKILL.md with no bundle references and content (3-platform examples, mapping table) that could be split into reference files kept inline; it is not a 1 because organization is clear, and not a 3 because there are no one-level-deep references and no content split across files.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 specific and distinct, with strong natural trigger terms and concrete multi-action verbs. Its main weakness is completeness: it uses a "Use this skill to [do X]" formulation instead of explicit "Use when [trigger situation]" guidance, leaving the invocation conditions implied rather than stated.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Design, implement, and audit inclusive digital products", "generate semantic ARIA", "accessibility traits" — matching the multiple-specific-actions anchor; it is not the level below because it goes well beyond naming a single domain with partial actions.	3 / 3
Completeness	The "what" is explicit ("Design, implement, and audit... using WCAG 2.2 Level AA standards"), but the "Use this skill to generate..." clause restates the capability rather than giving explicit trigger conditions; per the guideline a missing "Use when..."/equivalent trigger clause caps this at 2, and it is not a 1 because the what is clearly answered.	2 / 3
Trigger Term Quality	"WCAG 2.2", "semantic ARIA", "accessibility", and "iOS/Android" are natural terms users say when requesting accessibility work, giving good coverage; it is not a 2 because it supplies several genuinely natural keywords rather than only technical jargon with missing variations.	3 / 3
Distinctiveness Conflict Risk	The WCAG/ARIA/accessibility-traits niche with platform scoping is clearly distinct from the listed related skills (frontend-patterns, design-system, swiftui-patterns) and unlikely to trigger the wrong skill; it is not a 2 because the niche is sharply bounded rather than broadly overlapping.	3 / 3
	Total	11 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Commit: 754b8dd

Reviewed: 3 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.