web-accessibility
Implement web accessibility (a11y) standards following WCAG 2.1 guidelines. Use when building accessible UIs, fixing accessibility issues, or ensuring compliance with disability standards. Handles ARIA attributes, keyboard navigation, screen readers, semantic HTML, and accessibility testing.
89
88%
Does it follow best practices?
Impact
93%
1.09xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%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 well-crafted skill description that excels across all dimensions. It provides specific capabilities, includes natural trigger terms users would actually use (including the common abbreviation 'a11y'), explicitly states when to use it, and carves out a distinct niche in accessibility that won't conflict with general web development skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'ARIA attributes, keyboard navigation, screen readers, semantic HTML, and accessibility testing' - these are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Implement web accessibility standards', 'Handles ARIA attributes, keyboard navigation...') AND when ('Use when building accessible UIs, fixing accessibility issues, or ensuring compliance with disability standards'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'a11y', 'accessibility', 'WCAG', 'ARIA', 'keyboard navigation', 'screen readers', 'semantic HTML', 'accessible UIs', 'disability standards' - covers both technical and common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on web accessibility with distinct triggers like 'a11y', 'WCAG 2.1', 'ARIA', 'screen readers' - unlikely to conflict with general web development or other UI skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 excellent executable code examples covering common UI patterns (dropdowns, modals, forms, tabs). The workflow is clear with explicit testing/validation steps. However, the document is verbose for Claude's context window - it explains concepts Claude already knows and could benefit from splitting detailed examples into referenced files.
Suggestions
Remove explanatory text about what semantic HTML and ARIA are - Claude knows these concepts. Focus only on the specific patterns and code.
Split the detailed component examples (dropdown, modal, form, tabs) into a separate EXAMPLES.md file and reference it from the main skill.
Condense the 'Tasks' bullet points into the code examples themselves with inline comments rather than separate prose sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary explanations Claude would know (e.g., explaining what semantic HTML is, what ARIA attributes do). The content could be tightened by removing explanatory text and focusing purely on the actionable patterns. | 2 / 3 |
Actionability | Excellent executable code examples throughout - the React dropdown, modal, form, and tabs components are complete and copy-paste ready. Specific ARIA attributes, CSS patterns, and testing code are all concrete and immediately usable. | 3 / 3 |
Workflow Clarity | Clear 5-step process with explicit validation in Step 5 (testing). Each step has clear tasks, checklists, and decision criteria. The output format provides a comprehensive checklist for verification. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but it's a monolithic document (~400 lines) that could benefit from splitting detailed examples into separate files. References to external resources are present but internal progressive disclosure is lacking. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (632 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- supercent-io/skills-template
- Commit
c033769
- 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.