Run a comprehensive WCAG accessibility audit covering perceivable, operable, understandable, and robust principles. Use this skill whenever the user wants to audit accessibility, review WCAG compliance, fix accessibility issues, prepare for accessibility certification, address an accessibility lawsuit risk, or systematically improve a site's accessibility. Triggers on accessibility audit, WCAG audit, a11y audit, accessibility compliance, ADA compliance, screen reader test, keyboard navigation, accessibility report, fix accessibility, axe scan. Also triggers when accessibility issues have been reported and need systematic remediation.
64
76%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/accessibility-audit/SKILL.mdQuality
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 strong skill description with excellent trigger term coverage and completeness, clearly answering both what the skill does and when to use it. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed beyond just 'run a comprehensive audit.' The trigger terms and explicit 'Use when' and 'Triggers on' clauses make it highly effective for skill selection.
Suggestions
Expand the capability description with more specific concrete actions, e.g., 'Scans pages with automated tools, evaluates color contrast, checks ARIA attributes, tests keyboard navigation paths, and generates prioritized remediation reports.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (WCAG accessibility audit) and mentions the four WCAG principles (perceivable, operable, understandable, robust), but the core action is essentially one thing: 'run a comprehensive WCAG accessibility audit.' It doesn't list multiple distinct concrete actions like 'scan pages with axe, generate remediation reports, fix ARIA labels, test keyboard navigation.' | 2 / 3 |
Completeness | Clearly answers both 'what' (run a comprehensive WCAG accessibility audit covering four principles) and 'when' (explicit 'Use this skill whenever...' clause with multiple trigger scenarios, plus a dedicated 'Triggers on' list). Both dimensions are well-addressed. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'accessibility audit', 'WCAG audit', 'a11y audit', 'accessibility compliance', 'ADA compliance', 'screen reader test', 'keyboard navigation', 'accessibility report', 'fix accessibility', 'axe scan'. These are terms users would naturally use and cover common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a very clear niche around WCAG/accessibility auditing with highly specific trigger terms like 'WCAG audit', 'a11y audit', 'ADA compliance', and 'axe scan' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%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 accessibility audit skill with a clear methodology and good prioritization framework. Its main weaknesses are verbosity (restating WCAG criteria Claude likely knows) and lack of executable commands/code examples for the tools it recommends. The workflow is strong but the content would benefit from being leaner in the principles section and more concrete in the tooling section.
Suggestions
Move the WCAG 4 principles detail into the referenced `wcag-quick-reference.md` file and keep only a brief summary in the main skill, reducing token usage significantly.
Add executable command examples for the recommended tools (e.g., `npx pa11y https://example.com --standard WCAG2AA`, `npx axe-cli https://example.com`) to increase actionability.
Provide the referenced bundle files (audit-report-template.md, wcag-quick-reference.md, aria-patterns.md) so the progressive disclosure structure actually works.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is well-organized but verbose in places. The WCAG 4 principles section essentially restates WCAG criteria that Claude already knows. The 'When to use / When NOT to use' and 'Required inputs' sections add some value but could be tighter. The failure patterns section, while useful, includes some obvious advice. | 2 / 3 |
Actionability | The skill provides clear checklists and tool names, which is good. However, it lacks executable code or commands—no actual axe CLI invocations, no Pa11y command examples, no contrast-checking scripts. The guidance is specific enough to follow but stays at the checklist/description level rather than providing copy-paste-ready commands or code snippets. | 2 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced with logical progression from automated scans through manual testing to report writing. The severity classification provides clear prioritization criteria. The methodology stages (1-5) each have explicit test items. The workflow includes validation through scoring against WCAG criteria before writing the report. | 3 / 3 |
Progressive Disclosure | The skill references three external files (audit-report-template.md, wcag-quick-reference.md, aria-patterns.md) which is good progressive disclosure design. However, no bundle files are provided, so these references are broken. The main file itself is quite long (~250 lines) and the WCAG principles section could arguably be in a reference file rather than inline, since it's reference material rather than workflow guidance. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
8e70d03
Table of Contents
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.