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.

Quality

56%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/22-accessibility-specialist/SKILL.md

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 that clearly identifies its niche (digital accessibility) and provides explicit 'Use when' guidance with relevant trigger terms. Its main weakness is that it describes the domain areas to review rather than listing specific concrete actions it can perform (e.g., auditing, fixing, generating reports). The trigger term coverage is strong and the skill is highly distinctive.

Suggestions

Replace the general 'revisar' with specific concrete actions like 'auditar conformidade WCAG', 'gerar relatórios de acessibilidade', 'corrigir atributos ARIA', 'validar navegação por teclado' to improve specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain (digital accessibility) and lists several areas like WCAG, keyboard, screen reader, contrast, semantics, motion reduction, and form/component/flow accessibility, but it doesn't describe concrete actions (e.g., 'audit contrast ratios', 'generate ARIA attributes', 'fix keyboard navigation'). It says 'revisar' (review) but remains at a high level.	2 / 3
Completeness	The description explicitly answers both 'what' (digital accessibility review covering WCAG, keyboard, screen reader, contrast, semantics, motion reduction, forms, components, and flows) and 'when' with an explicit 'Use quando precisar revisar...' clause that lists trigger scenarios.	3 / 3
Trigger Term Quality	Includes strong natural trigger terms that users would actually say: 'WCAG', 'teclado' (keyboard), 'screen reader', 'contraste', 'semantica', 'motion reduction', 'acessibilidade', 'formularios', 'componentes'. These cover a good range of accessibility-related keywords users would naturally use.	3 / 3
Distinctiveness Conflict Risk	Digital accessibility is a clear, well-defined niche. The specific trigger terms like WCAG, screen reader, contrast, motion reduction, and semantic HTML make it highly unlikely to conflict with other skills. This would only trigger for accessibility-related requests.	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 more like a role description or job posting than an actionable skill file. It lacks concrete testing procedures, specific WCAG criteria, tool commands, code examples, or any executable guidance that would help Claude actually perform accessibility reviews. The checklist is too abstract to be useful without specific techniques, thresholds, or validation methods.

Suggestions

Add concrete, executable testing steps for each checklist item (e.g., specific axe-core commands, contrast ratio thresholds like 4.5:1 for AA, specific ARIA patterns to check for common components).

Include specific WCAG success criteria references (e.g., 1.4.3 for contrast, 2.1.1 for keyboard) with pass/fail criteria so Claude knows exactly what to verify.

Add a sequenced workflow with validation checkpoints, e.g.: 1) Run automated scan → 2) Manual keyboard test → 3) Screen reader audit → 4) Prioritize findings → 5) Generate report.

Provide at least one concrete example of an accessibility review output showing what a finding looks like with severity, WCAG criterion, description, and remediation guidance.

Dimension	Reasoning	Score
Conciseness	The skill is relatively brief but includes some unnecessary sections like 'Quando Não Usar' with obvious statements, and the governance references add tokens without actionable value in the body itself. The checklist items are lean but the overall structure has some padding.	2 / 3
Actionability	The skill provides no concrete code, commands, tools, WCAG criteria numbers, testing procedures, or executable guidance. It reads as a high-level role description with abstract checklists rather than actionable instructions Claude can follow to actually perform accessibility reviews.	1 / 3
Workflow Clarity	There is no clear sequenced workflow for performing an accessibility review. The checklist is a flat list of items to check without ordering, validation steps, or feedback loops. There's no guidance on how to actually test keyboard navigation, contrast ratios, or screen reader compatibility.	1 / 3
Progressive Disclosure	References to external files like policies and templates are present and one-level deep, which is good. However, the references are vague (e.g., 'templates/accessibility-check.md') without describing what they contain, and the main content itself lacks enough substance to serve as a useful overview.	2 / 3
	Total	6 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: felvieira/claude-skills-fv
Commit: d87ad31

Reviewed: 15 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.