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".

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A high-quality, actionable body that pairs concrete code, named tooling, and a WCAG 2.2 AA checklist with an evidence-of-completion gate and clear handoffs. It is lean and well-structured, with only minor room to tighten framing and to split the checklist/examples into reference files.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (references WCAG criterion numbers like 1.4.3 and 2.5.8 without explaining them) and is mostly lean checklists, examples, and anti-patterns; only minor motivational framing ("decidem se 15-20% dos usuarios conseguem usar o produto") could be trimmed, fitting the efficient-with-minor-over-explanation anchor.	4 / 5
Actionability	It provides copy-paste-ready HTML and CSS examples, a concrete runnable command ("node scripts/check-contrast.mjs <css>"), named tools with activation steps (axe-core via @axe-core/playwright, NVDA, VoiceOver Cmd+F5), and specific numeric thresholds (4.5:1, 3:1, 24x24 CSS px), fully covering the common cases as the anchor-5 example requires.	5 / 5
Workflow Clarity	The process is clearly sequenced (4 test categories -> WCAG checklist -> prioritized findings -> handoff) with an explicit "Evidencia de Conclusao" verification gate, but it is not a rigid numbered workflow with validate-fix-retry feedback loops, so it sits at clear-sequence-with-most-checkpoints rather than the full anchor-5 example.	4 / 5
Progressive Disclosure	The single SKILL.md is well-organized with clear section headers and signals external references inline (policies/*.md, scripts/check-contrast.mjs, templates/accessibility-check.md); with no bundle files provided the content is appropriately self-contained, leaving only minor organization gaps versus a fully split reference structure.	4 / 5
	Total	17 / 20 Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-structured description that clearly states what the skill does, when to use it, and surfaces a rich bilingual trigger-term list. Its weakest point is specificity, since it conveys one review action applied across many areas rather than a list of distinct concrete operations.

Suggestions

Strengthen specificity by listing distinct concrete actions beyond the single verb "revisar", e.g. "Audita contra WCAG 2.2 AA, define requisitos a11y para features novas, gera correcoes de ARIA/contraste e prioriza findings por impacto x esforco."

Consider adding one or two outcome-oriented trigger phrases users naturally say (e.g. "foco visivel", "tab order", "teclado trava", " Daltonismo") to push trigger coverage toward comprehensive.

Dimension	Reasoning	Score
Specificity	The description names the accessibility domain and many concrete review areas ("revisar WCAG, teclado, screen reader, contraste, semantica, motion reduction e acessibilidade de formularios, componentes e fluxos"), but the action is essentially singular ("revisar") rather than multiple distinct operations, matching the anchor that names a domain with 1-2 concrete actions but is not comprehensive in its action verbs.	3 / 5
Completeness	It explicitly answers both what ("Skill dedicada a acessibilidade digital" + review areas) and when ("Use quando precisar revisar...") with concrete trigger phrases, closely matching the anchor-5 example that pairs a capability statement with a "Use when..." clause and explicit triggers.	5 / 5
Trigger Term Quality	An explicit "Trigger em:" list gives natural terms users would say, including synonyms across two languages ("acessibilidade", "accessibility", "a11y", "screen reader", "leitor de tela", "WCAG", "ARIA"), which is good keyword coverage above the midpoint but short of the anchor-5 example that also names file extensions (not applicable to this domain).	4 / 5
Distinctiveness Conflict Risk	Accessibility is a clear niche with distinctive triggers (a11y, WCAG, screen reader, ARIA) and minimal conflict risk, but it borders on frontend/UI-UX review territory, so it is mostly distinct with minor overlap risk rather than a fully isolated niche.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: felvieira/claude-skills-fv
Path: skills/22-accessibility-specialist/SKILL.md
Commit: f3492ef

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.