accessibility-review
Run a WCAG 2.1 AA accessibility audit on a design or page. Trigger with "audit accessibility", "check a11y", "is this accessible?", or when reviewing a design for color contrast, keyboard navigation, touch target size, or screen reader behavior before handoff.
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 ./design/skills/accessibility-review/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 clear completeness, explicitly stating both what the skill does and when to use it. The main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., generating reports, flagging violations, providing remediation suggestions) rather than just naming the audit type and the areas it covers.
Suggestions
Add specific output actions to improve specificity, e.g., 'Flags WCAG violations, rates severity, and suggests remediation steps' rather than just naming the audit type.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (WCAG 2.1 AA accessibility audit) and mentions specific aspects like color contrast, keyboard navigation, touch target size, and screen reader behavior, but doesn't list concrete output actions (e.g., 'generates a report', 'flags violations', 'suggests fixes'). The actions are more about what it checks than what it does. | 2 / 3 |
Completeness | Clearly answers both 'what' (run a WCAG 2.1 AA accessibility audit on a design or page) and 'when' (explicit trigger phrases and contextual triggers like reviewing a design for specific accessibility concerns before handoff). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'audit accessibility', 'check a11y', 'is this accessible?', plus specific concern areas like 'color contrast', 'keyboard navigation', 'touch target size', 'screen reader behavior', and the contextual trigger 'before handoff'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — WCAG 2.1 AA accessibility auditing with specific trigger terms like 'a11y', 'accessible', and domain-specific concerns. Unlikely to conflict with other skills unless there's another accessibility-focused skill. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a solid structure for accessibility auditing with good WCAG reference material and a comprehensive output template. However, it lacks concrete executable tooling (no actual commands or scripts for automated checks), the output template is overly verbose for inline inclusion, and the workflow could benefit from explicit validation checkpoints. The content would be stronger if it were more concise and included actionable tool commands rather than high-level descriptions.
Suggestions
Add concrete, executable commands or tool integrations for automated accessibility checks (e.g., axe-core CLI commands, contrast ratio calculation scripts) rather than just listing 'automated scan' as a step.
Move the large output template to a separate TEMPLATE.md file and reference it from the main skill to improve progressive disclosure and reduce token usage.
Add validation checkpoints to the testing approach workflow, such as 'If automated scan finds critical issues, address those before proceeding to manual keyboard testing.'
Trim the Tips section — Claude doesn't need to be told to prioritize by impact or that manual testing catches more issues; focus on non-obvious guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The WCAG quick reference and common issues list are useful reference material, but the output template is very lengthy and could be more concise. The tips section explains things Claude already knows (e.g., 'manual testing with VoiceOver/NVDA catches things I can't'). Some sections like the testing approach are somewhat obvious. | 2 / 3 |
Actionability | The skill provides a detailed output template and WCAG criteria references, which is helpful. However, there are no executable code/commands for automated scanning, contrast checking, or any concrete tooling. The testing approach is a high-level checklist rather than specific executable steps. The audit process itself relies on Claude's judgment rather than concrete procedures. | 2 / 3 |
Workflow Clarity | The testing approach provides a sequence (automated scan → keyboard → screen reader → contrast → zoom), but lacks validation checkpoints or feedback loops. There's no guidance on what to do if issues are found during the audit process itself, or how to verify fixes. The workflow is more of a checklist than a sequenced process with explicit validation. | 2 / 3 |
Progressive Disclosure | The skill references CONNECTORS.md appropriately, and content is organized into logical sections. However, the massive output template dominates the file and could be split into a separate template file. The WCAG quick reference could also be a separate reference document, keeping the main skill leaner. | 2 / 3 |
Total | 8 / 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 | |
- Repository
- anthropics/knowledge-work-plugins
- Commit
3bf5929
- 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.