design-accessibility

WCAG AA and ARIA best practices — screen readers, keyboard navigation, focus management. Use when building any user-facing interface or reviewing accessibility compliance.

Install with Tessl CLI

npx tessl i github:ravnhq/ai-toolkit --skill design-accessibility

What are skills?

0.98x

Quality

73%

Does it follow best practices?

Impact

95%

0.98x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/design/design-accessibility/SKILL.md

SKILL.md

Review

Evals

Quality

Discovery

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid skill description with excellent trigger terms and clear 'when to use' guidance. The main weakness is that it describes knowledge areas rather than concrete actions Claude can perform. Adding specific verbs like 'audit', 'implement', or 'fix' would strengthen the specificity dimension.

Suggestions

Add concrete action verbs to clarify capabilities, e.g., 'Audits interfaces for WCAG AA compliance, implements ARIA attributes, fixes keyboard navigation issues'

Dimension	Reasoning	Score
Specificity	Names the domain (accessibility/WCAG) and lists some specific areas (screen readers, keyboard navigation, focus management), but doesn't describe concrete actions like 'audit', 'fix', 'implement', or 'generate reports'.	2 / 3
Completeness	Clearly answers both what (WCAG AA and ARIA best practices for screen readers, keyboard navigation, focus management) and when (building user-facing interfaces or reviewing accessibility compliance) with explicit 'Use when' clause.	3 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'WCAG', 'AA', 'ARIA', 'screen readers', 'keyboard navigation', 'focus management', 'accessibility', 'user-facing interface'. Good coverage of accessibility-related terms.	3 / 3
Distinctiveness Conflict Risk	Clear accessibility niche with distinct triggers like 'WCAG', 'ARIA', 'screen readers', 'accessibility compliance'. Unlikely to conflict with general UI or coding skills due to specific accessibility focus.	3 / 3
	Total	11 / 12 Passed

Implementation

57%

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

The skill has a solid foundation with concise principles and good progressive disclosure to external rules. However, it's weakened by generic boilerplate sections (troubleshooting, examples) that don't add accessibility-specific value, and the workflow lacks concrete, executable guidance for performing actual accessibility audits.

Suggestions

Replace the generic troubleshooting section with accessibility-specific issues (e.g., 'Common ARIA mistakes', 'Focus trap detection patterns')

Add executable code examples for common tasks like auditing form labels, checking contrast programmatically, or testing keyboard navigation

Make the workflow actionable with specific steps: e.g., '1. Run axe-core audit: `npx axe <url>` 2. Check heading hierarchy with DOM inspection 3. Test keyboard navigation: Tab through all interactive elements'

Dimension	Reasoning	Score
Conciseness	The principles section is lean and efficient, but the boilerplate troubleshooting and examples sections add unnecessary bulk. The trigger examples and troubleshooting patterns are generic templates that don't add accessibility-specific value.	2 / 3
Actionability	The principles provide concrete guidance (4.5:1 contrast ratio, semantic HTML rules), but lack executable code examples. The workflow is abstract ('apply the skill rules') rather than showing specific audit commands or code patterns for accessibility testing.	2 / 3
Workflow Clarity	The 3-step workflow is present but vague—'apply the skill rules' and 'validate output quality' lack specificity. For accessibility audits involving potentially destructive changes or batch fixes, there are no explicit validation checkpoints or feedback loops.	2 / 3
Progressive Disclosure	Good structure with a clear reference to external rules via [rules/_sections.md]. The skill appropriately keeps the overview concise and points to detailed patterns in a separate file with one-level-deep navigation.	3 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	10 / 11 Passed

Reviewed: 4 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.