accessibility-review

Run a WCAG 2.1 AA accessibility audit on a design or page. Trigger with "audit accessibility", "check a11y", "is this accessible?", or when reviewing a design for color contrast, keyboard navigation, touch target size, or screen reader behavior before handoff.

Quality

86%

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

75%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-constructed, efficient audit skill: it assumes Claude's competence, provides a concrete WCAG quick reference with numeric thresholds, a sensible testing sequence, and a complete output template. Main gaps are the unnamed automated scanning tool, loosely defined severity tiers, and a long inline report template that could be offloaded to a reference file.

Suggestions

Name a specific automated scanner (e.g., axe DevTools, Lighthouse, pa11y) in the Testing Approach so the first step is executable rather than generic.

Define severity tiers (Critical/Major/Minor) explicitly — e.g., what makes a finding 'Critical' (blocks task completion) vs 'Major' vs 'Minor' — instead of relying on emoji alone.

Consider moving the full output template to a references/output-template.md file and keeping only the section skeleton in SKILL.md to reduce token load.

Dimension	Reasoning	Score
Conciseness	The body is a tight checklist with concrete thresholds (">= 4.5:1", ">= 44x44 CSS pixels") and no explanations of concepts Claude already knows. Minor trimming opportunities — the ~50-line output template, the "Audit for accessibility: @$1" line duplicating the Usage block, and tips like "Nice to have" — place it at anchor 4 rather than 5.	4 / 5
Actionability	Concrete guidance throughout: named WCAG criteria with numeric thresholds, a 5-step testing approach, and a copy-paste output template. It sits at anchor 4 rather than 5 because "Automated scan (catches ~30% of issues)" names no specific tool (e.g., axe, Lighthouse, pa11y) and severity tiers are defined only by emoji.	4 / 5
Workflow Clarity	"Testing Approach" gives an ordered sequence (automated scan → keyboard-only → screen reader → contrast → zoom) and the output template enforces a complete report; the read-only audit context means the destructive/batch validation cap does not apply. Anchor 4 rather than 5 because there is no explicit verify-before-reporting checkpoint or error-recovery guidance.	4 / 5
Progressive Disclosure	No bundle files exist; the ~120-line body is well organized with clear section headers and a single one-level reference ([CONNECTORS.md]). Good structure overall, but at this length the full output template is borderline content that could live in a reference file — anchor 4 (good structure; minor organization gaps) rather than 5, which expects well-split content with signaled references.	4 / 5
	Total	16 / 20 Passed

Description

95%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: it names the exact standard (WCAG 2.1 AA), the target artifacts (design or page), and gives explicit, natural trigger phrases including synonyms like 'a11y'. The only mild limitation is that capability coverage is conveyed through the trigger clause rather than a fuller list of audit actions.

Dimension	Reasoning	Score
Specificity	The description states a concrete action — "Run a WCAG 2.1 AA accessibility audit on a design or page" — and explicitly names audit dimensions ("color contrast, keyboard navigation, touch target size, or screen reader behavior") with a named standard. It falls at anchor 4: several specifics are covered but the action list is not comprehensive; it is above anchor 3 because coverage areas are explicitly stated rather than merely implied by the domain.	4 / 5
Completeness	Both 'what' ("Run a WCAG 2.1 AA accessibility audit on a design or page") and 'when' ("Trigger with 'audit accessibility', 'check a11y', 'is this accessible?', or when reviewing a design for... before handoff") are explicit and concrete, matching anchor 5; the 'when' is explicit trigger guidance, not merely implied.	5 / 5
Trigger Term Quality	Includes natural phrases users would say — "audit accessibility", "check a11y", "is this accessible?" — with synonyms (a11y/accessible) and topical keywords (color contrast, keyboard navigation, touch target, screen reader). Matches anchor 5; no common variation is obviously missing.	5 / 5
Distinctiveness Conflict Risk	Clear niche — WCAG 2.1 AA accessibility audits of designs/pages — with distinct trigger phrases and a pinned standard, so it is unlikely to fire for a general code review or design skill. Matches anchor 5 (clear niche with distinct triggers; minimal conflict risk).	5 / 5
	Total	19 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: anthropics/knowledge-work-plugins
Path: design/skills/accessibility-review/SKILL.md
Commit: 8444efc

Reviewed: 6 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.