accessibility-react-native
Implement, audit, and fix accessibility (a11y) in React Native and Expo mobile apps.
60
70%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/accessibility-react-native/SKILL.mdQuality
Discovery
54%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 identifies a clear, distinctive niche (accessibility in React Native/Expo) with good trigger terms including the 'a11y' abbreviation. However, it lacks a 'Use when...' clause which is critical for Claude's skill selection, and the capability descriptions could be more specific about what concrete actions the skill performs.
Suggestions
Add a 'Use when...' clause such as 'Use when the user asks about screen reader support, VoiceOver, TalkBack, accessibility labels, focus management, or WCAG compliance in React Native or Expo projects.'
Expand the specific actions beyond 'implement, audit, fix' to include concrete examples like 'add accessible labels, configure focus order, test with screen readers, resolve accessibility warnings, ensure WCAG compliance.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (accessibility in React Native/Expo) and lists some actions (implement, audit, fix), but doesn't elaborate on specific concrete actions like 'add screen reader labels', 'fix focus order', or 'generate WCAG compliance reports'. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'what' is also only moderately detailed, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'accessibility', 'a11y', 'React Native', 'Expo', 'mobile apps'. The parenthetical 'a11y' abbreviation is a particularly good inclusion as it's a common shorthand developers use. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of accessibility + React Native/Expo creates a very clear niche that is unlikely to conflict with other skills. It's specific enough to distinguish from general React skills, general accessibility skills, or web accessibility skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable accessibility skill with clear workflows, explicit validation checkpoints, and good progressive disclosure to reference files. Its main weakness is moderate verbosity — the 'When This Skill Is Needed' bullet list and some of the 'Core Principles' could be trimmed since Claude already understands WCAG fundamentals. Overall it's a strong skill that would effectively guide Claude through a11y implementation and auditing.
Suggestions
Remove or significantly trim the 'When This Skill Is Needed' section — it largely restates the skill description and the workflow steps already make the scope clear.
Condense 'Core Principles' into a tighter format (e.g., a compact table or single-line rules) since Claude already knows WCAG basics — focus on the RN-specific implementation details rather than explaining why contrast matters.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary content like the 'When This Skill Is Needed' section which largely restates what the skill does, and the 'Core Principles' section explains concepts Claude already knows (WCAG basics, contrast ratios). The props table and checklist are useful but could be more concise given references exist. | 2 / 3 |
Actionability | Provides executable code examples (ESLint config, AccessibilityInfo usage, Dynamic Type), specific bash commands for auditing and installing dependencies, and concrete prop usage patterns. The audit checklist gives specific, actionable criteria with exact thresholds (44×44 pts, 4.5:1 ratio). | 3 / 3 |
Workflow Clarity | The 5-step implementation workflow is clearly sequenced (Audit → Fix → Verify contrast → Add testing → Reduce Motion), with explicit validation steps (run audit script, manual walkthrough with specific tools, contrast check script, ESLint rules). The audit checklist provides a comprehensive verification framework with clear pass/fail criteria. | 3 / 3 |
Progressive Disclosure | Excellent structure with a clear overview in SKILL.md and well-signaled one-level-deep references to props.md, components.md, contrast.md, and testing.md. The reference files table and scripts table provide clear navigation. Content is appropriately split between the main file (workflow, checklist, quick reference) and detailed references. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ucdavis/ai-skills-registry
- Commit
c0b2e4b
- Reviewed
Table of Contents
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.