accessibility

Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

Quality

81%

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

72%Weight 40%Scale 1-3

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

A highly actionable, well-structured reference: executable examples, real testing commands, and clean one-level-deep references whose anchors all resolve. The main gaps are conceptual padding and duplicated focus-visible CSS that hurt token efficiency, and an audit workflow that lacks an explicit re-verification checkpoint.

Suggestions

Trim conceptual padding Claude already knows (the POUR table, the conformance-levels table, and prose restatements of target-size exceptions) and de-duplicate the `:focus-visible` outline CSS that appears in both the 1.4.3/1.4.6 contrast section and the 2.4.7 focus-visible section.

Add an explicit validation/re-verification step to the audit workflow — e.g., after fixing issues, re-run `npx lighthouse` and `axe` to confirm the score improved and no regressions were introduced.

Frame the audit as a clearly sequenced process with checkpoints (automated scan → manual checklist → fix by impact tier → re-scan to verify) instead of leaving the workflow implicit across separate reference sections.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete code, but the POUR and conformance-levels tables and prose explanations of target-size exceptions restate concepts Claude already knows, and the `:focus-visible` outline CSS is duplicated across the contrast and focus-visible sections. This matches the 2-anchor ("Mostly efficient but includes some unnecessary explanation or could be tightened"); it is not a 1 because the bulk is actionable code, and not a 3 because of the conceptual padding and duplication.	2 / 3
Actionability	It provides extensive executable HTML/CSS/JS examples plus real CLI commands ("npx lighthouse … --only-categories=accessibility", "axe https://example.com"), copy-paste ready and criterion-referenced. This matches the 3-anchor for fully executable, specific guidance.	3 / 3
Workflow Clarity	An audit sequence is implied via the automated-testing commands, the manual-testing checklist, and the fix-priority tiers (Critical/Serious/Moderate), but there is no explicit validation or re-verification checkpoint (e.g., re-running the audit after fixes). This matches the 2-anchor ("sequence present but checkpoints missing or implicit"); it is not a 3 because the feedback loop is absent.	2 / 3
Progressive Disclosure	SKILL.md serves as an overview with detailed patterns offloaded to references/A11Y-PATTERNS.md and references/WCAG.md via well-signaled one-level-deep links; all eight referenced anchors (modal-focus-trap, skip-link, form-labels, error-handling, dragging-movements, aria-tabs, live-regions-and-notifications, screen-reader-commands) resolve to real headings in the bundle. This matches the 3-anchor for a clear overview with appropriately split, navigable references.	3 / 3
	Total	10 / 12 Passed

Description

90%Weight 40%Scale 1-3

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: it clearly states purpose and scope, uses natural third-person voice, and provides explicit, distinctive trigger terms. The only weakness is that the action verbs (audit, improve) are relatively high-level rather than a comprehensive set of concrete actions.

Dimension	Reasoning	Score
Specificity	"Audit and improve web accessibility following WCAG 2.2 guidelines" names the domain and two actions but the verbs are high-level rather than a comprehensive granular list, matching the 2-anchor ("Names domain and some actions, but not comprehensive"). It falls short of 3 because it lacks multiple distinct concrete actions like the anchor example.	2 / 3
Completeness	It explicitly states what the skill does ("Audit and improve web accessibility following WCAG 2.2 guidelines") and when to use it (an explicit "Use when…" trigger clause), satisfying the 3-anchor for both 'what' and 'when'.	3 / 3
Trigger Term Quality	The clause "Use when asked to 'improve accessibility', 'a11y audit', 'WCAG compliance', 'screen reader support', 'keyboard navigation', or 'make accessible'" gives broad coverage of natural phrasings a user would actually say, including the common 'a11y' abbreviation. It is not a 2 because no common variations are missing.	3 / 3
Distinctiveness Conflict Risk	The WCAG 2.2 / web-a11y niche with distinct triggers (a11y audit, screen reader support, keyboard navigation) is unlikely to fire for unrelated skills. Voice is third person, so no voice penalty applies.	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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: addyosmani/web-quality-skills
Path: skills/accessibility/SKILL.md
Commit: 95d6e25

Reviewed: 9 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.