accessibility-general
Reviews UI for accessibility issues against WCAG 2.1/2.2 AA. Triggers on "is this accessible?", "check accessibility", or contrast/a11y review requests.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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' guidance. Its main weakness is the lack of specific concrete actions beyond the general 'reviews UI for accessibility issues' — listing specific checks (e.g., contrast ratios, alt text, keyboard navigation, ARIA labels) would strengthen it. Overall it performs well for skill selection purposes.
Suggestions
Add specific concrete actions to improve specificity, e.g., 'Checks color contrast ratios, alt text, keyboard navigation, ARIA labels, and focus management against WCAG 2.1/2.2 AA.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (UI accessibility) and references WCAG 2.1/2.2 AA standards, but only describes one general action ('reviews UI for accessibility issues') without listing specific concrete actions like checking color contrast ratios, evaluating alt text, auditing keyboard navigation, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (reviews UI for accessibility issues against WCAG 2.1/2.2 AA) and 'when' (triggers on specific phrases like 'is this accessible?', 'check accessibility', contrast/a11y review requests). The trigger guidance is explicit. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms that users would actually say: 'is this accessible?', 'check accessibility', 'contrast', 'a11y review'. These cover common variations of how users request accessibility reviews. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: WCAG accessibility auditing for UI. The specific triggers ('a11y', 'contrast', 'accessible') are unlikely to conflict with other skills, and the WCAG standard reference further narrows the scope. | 3 / 3 |
Total | 11 / 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-crafted accessibility review skill with an excellent stepped interaction workflow that prevents overwhelming users with all findings at once. The actionability is strong with specific templates, contrast ratios, and decision-handling protocols. The main weaknesses are moderate verbosity (explaining concepts Claude already knows like semantic HTML basics and general review etiquette) and the lack of actual bundle files to support the referenced wcag-checklist.md.
Suggestions
Move the 'Common Patterns to Check' section into the referenced `references/wcag-checklist.md` file to reduce SKILL.md length and improve progressive disclosure.
Remove or significantly trim the 'Review Guidelines' section — directives like 'Be Practical', 'Be Specific', and 'Be Constructive' are things Claude already understands and waste tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary explanation (e.g., 'When to Use This Skill' section largely restates the trigger conditions, and some guidelines like 'Be Practical' and 'Be Constructive' are things Claude already knows). The common patterns section, while useful, is somewhat verbose for concepts Claude understands well (like semantic HTML basics). | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific contrast ratios, exact issue presentation format with templates, clear response handling protocols for fix/ignore decisions, specific WCAG criteria, and concrete examples of critical vs warning issues. The stepped review process is particularly well-defined with exact interaction patterns. | 3 / 3 |
Workflow Clarity | The workflow is exceptionally clear with a well-sequenced 5-step process: identify target → conduct review → prioritize findings → stepped review (one at a time) → final summary. It includes explicit feedback loops (user decides fix/ignore, tracking decisions), validation through the summary step, and clear templates for each stage of the interaction. | 3 / 3 |
Progressive Disclosure | The skill references `references/wcag-checklist.md` appropriately for detailed WCAG criteria, but no bundle files are actually provided, making this reference unverifiable. The common patterns section is quite lengthy and could potentially be split into a reference file. The overall structure is reasonable but the inline content is heavy for a SKILL.md overview. | 2 / 3 |
Total | 10 / 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.