accessibility

Audit and improve web accessibility following WCAG 2.1 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible". Do NOT use for SEO (use seo), performance (use core-web-vitals), or comprehensive site audits covering multiple areas (use web-quality-audit).

Quality

84%

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

78%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 well-organized, highly actionable reference skill with strong code examples and real testing commands. Its main gaps are underused progressive disclosure (an existing WCAG.md bundle is never linked) and an implicit rather than explicit audit workflow.

Suggestions

Add a "## Workflow" section that sequences an audit (e.g., 1. Run automated audit 2. Run manual checks 3. Triage by impact 4. Apply fixes 5. Re-verify) with an explicit verify-after-fix loop.

Link the bundled references/WCAG.md from the body (e.g., under a "## References" or "## Full WCAG reference" heading) so the one-level-deep detail is clearly signaled rather than orphaned.

Consider trimming the POUR and conformance-levels tables, which restate foundational WCAG knowledge Claude already has, to recover token budget.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly executable examples/tables, but restates foundational WCAG knowledge Claude already has (POUR principles table, conformance-levels table, intro sentence) — efficient overall with minor trims available.	4 / 5
Actionability	Concrete copy-paste HTML/CSS/JS examples throughout (alt text, focus traps, skip links, ARIA tablist, live regions) plus executable test commands (`npx lighthouse`, `axe https://example.com`) and specific screen-reader commands cover the common cases.	5 / 5
Workflow Clarity	A testing checklist (Automated then Manual) and a Critical/Serious/Moderate triage section provide clear organization and most checkpoints, but an explicit sequenced audit workflow with a verify-after-fix loop is only implicit rather than spelled out.	4 / 5
Progressive Disclosure	The body is well-sectioned (## headings, tables, fenced code) but the bundled references/WCAG.md file is never referenced or signaled from the body, so a one-level-deep reference that should be split out and linked is missing.	3 / 5
	Total	16 / 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: clear what/when, comprehensive natural trigger terms, and explicit boundary guidance against sibling skills. The only weakness is specificity, which lists just two generic verbs (audit, improve) rather than several distinct concrete actions.

Dimension	Reasoning	Score
Specificity	"Audit and improve web accessibility following WCAG 2.1 guidelines" names the domain and two concrete actions, but does not enumerate several specific actions, fitting the 1-2-action anchor rather than the comprehensive 4-5 anchors.	3 / 5
Completeness	It explicitly answers what ("Audit and improve web accessibility following WCAG 2.1 guidelines") and when ("Use when asked to ...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Six natural user phrases ("improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", "make accessible") including the a11y synonym give comprehensive coverage matching the top anchor.	5 / 5
Distinctiveness Conflict Risk	Explicit "Do NOT use for SEO (use seo), performance (use core-web-vitals), or comprehensive site audits (use web-quality-audit)" disambiguation establishes a clear niche with minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (532 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: tech-leads-club/agent-skills
Path: packages/skills-catalog/skills/(quality)/web-accessibility/SKILL.md
Commit: fc886b7

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.