accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support. 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 findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

67%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.

The body is a well-structured, actionable accessibility reference with concrete cross-platform code and a verification checklist. Its main weakness is conciseness, since the intro and Core Concepts re-explain accessibility fundamentals Claude already knows.

Suggestions

Trim the intro paragraph and 'Core Concepts' definitions of POUR / accessibility tree / focus management, which restate knowledge Claude already has; keep only the non-obvious framing.

Add an explicit validation/audit checkpoint in 'How It Works' (e.g. a concrete contrast-check command or a 'run an automated axe-core scan' step) rather than relying on the implicit final checklist.

Consider moving the detailed Cross-Platform Mapping table into a references/ file linked from the body, to shorten the inline SKILL.md and better leverage progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The intro and 'Core Concepts' section re-explain POUR principles, the accessibility tree, and focus management that Claude already knows, but the bulk (steps, mapping table, examples, checklist) is reasonably tight, matching the 'mostly efficient with some unnecessary explanation' anchor.	3 / 5
Actionability	Provides concrete executable code for Web/iOS/Android, a cross-platform API mapping table with specific calls, and a checklist with exact values (24x24px, 44x44pt, 4.5:1); minor gaps like the placeholder '<svg aria-hidden="true">...</svg>' keep it just below a 5.	4 / 5
Workflow Clarity	A clear 5-step 'How It Works' sequence (Identify role -> Perceivable -> Operable -> Understandable -> Robust) with a final 'Best Practices Checklist' serving as a verification checkpoint; this is an audit/design skill (not destructive/batch) so the missing-validation cap does not apply, though validation steps are otherwise implicit.	4 / 5
Progressive Disclosure	Well-organized with clear section headers and one-level-deep external URL references; no bundle files exist so all content is inline, and at >50 lines the cross-platform mapping table and examples could arguably be split into a reference file, placing it just below the clean anchor-5.	4 / 5
	Total	15 / 20 Passed

Description

78%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.

The description clearly communicates a distinct accessibility niche with concrete actions and explicit trigger guidance. It is marred by a YAML line-wrap artifact producing an orphaned 'standards.' fragment and by second-person phrasing ('Use this skill to generate') that triggers a specificity penalty.

Suggestions

Fix the line-wrap artifact so the description reads as one clean sentence (e.g. end the first sentence at 'screen-reader support.' and remove the stranded 'standards.' token).

Rephrase 'Use this skill to generate...' in third person (e.g. 'Generates semantic ARIA for Web and accessibility traits for iOS/Android') to avoid the second-person specificity penalty.

Consolidate the duplicate trigger clauses ('Use when...' and 'Use this skill...') into a single explicit 'Use when...' clause to remove redundancy.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Design, implement, and audit inclusive digital products', 'generate semantic ARIA', 'accessibility traits') with comprehensive Web/Native coverage, but the imperative 'Use this skill to generate' is second-person voice, invoking the -1 specificity penalty from a base of 5.	4 / 5
Completeness	Both 'what' (design/implement/audit, generate ARIA/traits) and 'when' ('Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support') are explicit, but a broken line-wrap leaves an orphaned 'standards.' fragment and a redundant second 'Use this skill' clause, keeping it below the clean anchor-5 example.	4 / 5
Trigger Term Quality	Strong natural keywords a user would say ('WCAG 2.2 Level AA', 'keyboard', 'contrast', 'screen-reader support', 'ARIA', 'iOS/Android'), with only minor synonyms (e.g. 'a11y', 'compliance') missing.	4 / 5
Distinctiveness Conflict Risk	A clear WCAG 2.2 Level AA / ARIA / screen-reader niche with distinct triggers and minimal overlap risk against the listed related skills (frontend-patterns, design-system, etc.).	5 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/accessibility/SKILL.md
Commit: 06c5e11

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.