accessibility-specialist
Skill dedicada a acessibilidade digital. Use quando precisar revisar WCAG, teclado, screen reader, contraste, semantica, motion reduction e acessibilidade de formularios, componentes e fluxos. Trigger em: "acessibilidade", "accessibility", "a11y", "WCAG", "screen reader", "navegacao por teclado", "contraste de cor", "ARIA", "semantica HTML", "motion reduction", "leitor de tela", "audit de acessibilidade".
52
56%
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 ./skills/22-accessibility-specialist/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 solid skill description with excellent trigger term coverage in both Portuguese and English, clear 'when to use' guidance, and a distinct niche. Its main weakness is that the 'what it does' portion lists topic areas rather than concrete actions—it says 'revisar' (review) but doesn't enumerate specific outputs or operations like auditing, fixing, or generating recommendations.
Suggestions
Replace topic-area listing with specific concrete actions, e.g., 'Audita conformidade WCAG, verifica contraste de cores, gera atributos ARIA, corrige navegação por teclado, e recomenda melhorias de semântica HTML' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (digital accessibility) and lists several areas it covers (WCAG, keyboard, screen reader, contrast, semantics, motion reduction, form/component/flow accessibility), but these read more as topic areas than concrete actions. It lacks specific verbs describing what it does (e.g., 'audit contrast ratios', 'generate ARIA attributes', 'fix keyboard navigation issues'). | 2 / 3 |
Completeness | The description answers both 'what' (reviews WCAG, keyboard, screen reader, contrast, semantics, motion reduction, and accessibility of forms/components/flows) and 'when' with an explicit 'Use quando precisar...' clause and a detailed 'Trigger em:' list specifying exact trigger terms. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms in both Portuguese and English: 'acessibilidade', 'accessibility', 'a11y', 'WCAG', 'screen reader', 'leitor de tela', 'navegacao por teclado', 'contraste de cor', 'ARIA', 'semantica HTML', 'motion reduction', 'audit de acessibilidade'. These are terms users would naturally use when seeking accessibility help. | 3 / 3 |
Distinctiveness Conflict Risk | Digital accessibility is a clear, well-defined niche. The trigger terms are highly specific to accessibility concerns (WCAG, ARIA, screen reader, a11y, contrast) and are unlikely to conflict with other skills like general code review or design skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as a high-level process description or role definition rather than an actionable skill. It lacks concrete WCAG criteria (e.g., specific success criteria like 2.1.1, 1.4.3), testing tools/commands (axe-core, Lighthouse, screen reader testing steps), code examples for common fixes, and any sequenced audit workflow. The checklist is too abstract to guide Claude through an actual accessibility review.
Suggestions
Add specific WCAG success criteria references (e.g., '1.4.3 Contrast Minimum: 4.5:1 for normal text, 3:1 for large text') and concrete testing commands (e.g., 'npx axe-core url' or Lighthouse CLI commands).
Provide a sequenced audit workflow with explicit steps: 1) automated scan, 2) keyboard navigation test, 3) screen reader walkthrough, 4) manual contrast check — each with validation criteria and tools.
Include executable code examples for common accessibility patterns (e.g., proper ARIA usage, focus management, skip navigation, reduced motion media queries) rather than abstract checklist items.
Either provide the referenced bundle files (templates/accessibility-check.md, policies/handoffs.md) or inline the critical content so the skill is self-contained and actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively brief but includes some unnecessary sections like 'Quando Não Usar' with obvious statements, and the 'Governança Global' section listing policy files adds little actionable value. Some sections like 'Entradas Esperadas' and 'Saídas Esperadas' describe process rather than instruct. | 2 / 3 |
Actionability | The skill provides no concrete code, commands, tools, WCAG criteria numbers, testing procedures, or executable guidance. The checklist is a vague list of abstract goals ('navegação por teclado completa', 'contraste adequado') without specific thresholds, testing commands (e.g., axe-core, Lighthouse), or code examples for implementing fixes. | 1 / 3 |
Workflow Clarity | There is no sequenced workflow for performing an accessibility audit. The checklist items are unordered goals without steps, validation checkpoints, or feedback loops. There's no guidance on how to test each item, what tools to use, or how to verify findings. | 1 / 3 |
Progressive Disclosure | References to external files like `policies/handoffs.md` and `templates/accessibility-check.md` are mentioned, but no bundle files are provided to verify they exist. The SKILL.md itself is appropriately brief as an overview, but the referenced files that should contain the actual detailed guidance are absent, making the references unverifiable and potentially hollow. | 2 / 3 |
Total | 6 / 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
- felvieira/claude-skills-fv
- Commit
7577622
- 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.