scanning-for-accessibility-issues
This skill enables Claude to perform comprehensive accessibility audits. It uses the accessibility-test-scanner plugin to identify WCAG 2.1/2.2 compliance issues, validate ARIA attributes, check keyboard navigation, and assess screen reader compatibility. Use this skill when the user requests an accessibility scan, audit, or compliance check, or when terms like "WCAG", "ARIA", "screen reader", "accessibility testing", or "a11y" are mentioned. It provides actionable insights for improving web application accessibility.
63
53%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./backups/skills-migration-20251108-070147/plugins/testing/accessibility-test-scanner/skills/accessibility-test-scanner/SKILL.mdQuality
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 strong skill description that excels across all dimensions. It provides specific concrete actions, comprehensive trigger terms covering both technical and colloquial variations, explicit 'Use when' guidance, and a clearly distinct niche in accessibility auditing. The description is well-structured and uses appropriate third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'identify WCAG 2.1/2.2 compliance issues, validate ARIA attributes, check keyboard navigation, and assess screen reader compatibility.' These are distinct, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (perform accessibility audits, identify WCAG issues, validate ARIA, check keyboard navigation, assess screen reader compatibility) and 'when' with an explicit 'Use this skill when...' clause listing specific trigger scenarios and terms. | 3 / 3 |
Trigger Term Quality | Includes excellent natural trigger terms that users would actually say: 'accessibility scan', 'audit', 'compliance check', 'WCAG', 'ARIA', 'screen reader', 'accessibility testing', 'a11y'. Good coverage of both formal and informal terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in accessibility testing. The specific mentions of WCAG 2.1/2.2, ARIA, a11y, and the accessibility-test-scanner plugin make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is largely a high-level description of what the accessibility scanner does rather than actionable instructions for how to use it. It lacks concrete command syntax, example outputs, specific flags/options, and validation steps. Most of the content restates things that belong in metadata or that Claude already knows, wasting token budget.
Suggestions
Add concrete, executable command syntax with flags and arguments (e.g., `a11y-scan --url <URL> --standard wcag2.1-aa --format json`) and show example output.
Remove the 'When to Use This Skill' and 'Overview' sections—this information belongs in frontmatter metadata, not the body.
Add a validation/feedback loop: show how to interpret scan results, fix issues, and re-scan to verify fixes, with specific examples of common error types and their remediation.
Replace the abstract examples with concrete ones showing actual input commands and expected output formats (e.g., a sample JSON report snippet).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is verbose and padded with unnecessary explanations. Sections like 'How It Works,' 'When to Use This Skill,' and 'Integration' restate information Claude already knows or that belongs in frontmatter metadata. The 'Overview' restates the description. Much of the content could be cut without losing actionable value. | 1 / 3 |
Actionability | The skill provides no concrete commands, code snippets, or executable examples. 'Execute the a11y-scan command' is vague—there's no syntax, flags, arguments, URL parameters, or output format shown. The examples describe what the skill will do abstractly rather than showing how to invoke it. | 1 / 3 |
Workflow Clarity | The workflow is described at a high level ('invoke command, audit runs, report generated') with no concrete steps, no validation checkpoints, and no error handling or feedback loops. There's no guidance on what to do if the scan fails, how to interpret results, or how to re-scan after fixes. | 1 / 3 |
Progressive Disclosure | The content is organized into sections with headers, which provides some structure. However, there are no references to external files, no bundle files to reference, and content that could be trimmed (like 'When to Use' which duplicates frontmatter triggers) is kept inline. The organization is adequate but not optimal. | 2 / 3 |
Total | 5 / 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.
- Commit
13d35b8
- 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.