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

85%

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

81%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 high-quality, actionable reference skill with executable patterns, a validated audit workflow, and well-organized external references. The main improvement is conciseness: several conceptual tables and explanatory sentences restate knowledge Claude already has and could be offloaded to the WCAG.md reference.

Suggestions

Move the POUR principles and A/AA/AAA conformance-level tables into references/WCAG.md and link to them, since they restate concepts Claude already knows.

Trim explanatory prose such as 'Users who rely on consistent placement shouldn't have to hunt for help on every page' to the bare rule, letting the WCAG criterion number carry the context.

Consider relocating some of the larger inline code blocks (e.g. the full session-warning modal JS) into references/A11Y-PATTERNS.md to shorten the overview further.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with extensive executable code, but the POUR and conformance-level tables and sentences like 'Users who rely on consistent placement shouldn't have to hunt for help on every page' restate concepts Claude already knows and could be trimmed or moved to references.	3 / 5
Actionability	Provides copy-paste-ready HTML/CSS/JS patterns, specific commands ('npx lighthouse ... --only-categories=accessibility', 'axe https://example.com'), and named MCP tools ('lighthouse_audit', 'take_snapshot') covering the common cases.	5 / 5
Workflow Clarity	The 'Evidence-led audit workflow' is a clear 4-step sequence that localizes via failed audit nodes and includes an explicit feedback loop ('Fix the source, then re-run the same audit and manual interaction'), matching the score-5 anchor.	5 / 5
Progressive Disclosure	Well-signaled one-level-deep references to real files with section anchors (e.g. references/A11Y-PATTERNS.md#modal-focus-trap, references/WCAG.md), but the body itself is long with substantial inline code that keeps it just shy of the score-5 'appropriately split' anchor.	4 / 5
	Total	17 / 20 Passed

Description

90%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: third-person voice, clear what/when structure, and rich natural trigger terms including synonyms. The only weakness is that 'audit and improve' are broad verbs rather than a comprehensive enumeration of concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('web accessibility', 'WCAG 2.2 guidelines') and two actions ('Audit and improve'), but the verbs are generic rather than a comprehensive list of concrete capabilities, matching the score-3 anchor of domain plus 1-2 actions.	3 / 5
Completeness	Explicitly states both what ('Audit and improve web accessibility following WCAG 2.2 guidelines') and when ('Use when asked to ...') with concrete trigger phrases, hitting the score-5 anchor.	5 / 5
Trigger Term Quality	Lists natural user phrases including synonyms and the spec name — 'improve accessibility', 'a11y audit', 'WCAG compliance', 'screen reader support', 'keyboard navigation', 'make accessible' — giving comprehensive coverage of what a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Targets a clear accessibility niche with distinctive triggers (a11y, WCAG, screen reader, keyboard navigation) that are unlikely to fire for unrelated skills, matching the score-5 anchor.	5 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: addyosmani/web-quality-skills
Path: skills/accessibility/SKILL.md
Commit: afa8da9

Reviewed: 5 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.