CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

65

Quality

77%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/22-accessibility-specialist/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

64%

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

This is a solid, actionable accessibility skill with excellent concrete examples (before/after HTML, CSS snippets, specific WCAG criteria) and a comprehensive checklist. Its main weaknesses are the lack of a clearly sequenced workflow with explicit validation checkpoints, some unnecessary framing content, and references to external files that aren't provided in the bundle. The checklist and anti-patterns sections are particularly strong and immediately useful.

Suggestions

Add an explicit numbered workflow sequence (e.g., '1. Run axe-core → 2. Fix critical/serious → 3. Keyboard walkthrough → 4. Screen reader check → 5. Zoom/reflow → 6. Document findings') with validation gates between steps.

Trim the opening paragraph and 'Quando Nao Usar' section — Claude doesn't need motivation about why accessibility matters or warnings about legal compliance scope; focus on the actionable content.

DimensionReasoningScore

Conciseness

The skill is mostly efficient but includes some unnecessary framing (e.g., the opening paragraph explaining why accessibility matters, the 'Quando Nao Usar' section with caveats Claude doesn't need). The governance section references many external policies without adding actionable value. However, the checklists and code examples are tight.

2 / 3

Actionability

Provides fully executable HTML/CSS code snippets with clear before/after patterns, a concrete WCAG checklist with specific criterion numbers, specific tool names (axe-core, NVDA, VoiceOver), and exact contrast ratios. The guidance is copy-paste ready and leaves no ambiguity about what to do.

3 / 3

Workflow Clarity

The 4-category testing table provides a clear methodology, and the checklist is well-structured. However, there's no explicit sequenced workflow with validation checkpoints — the skill doesn't define a clear order of operations (e.g., run automated first, then keyboard, then screen reader) with feedback loops for when issues are found. The 'Evidencia de Conclusao' section lists verification criteria but doesn't integrate them into a step-by-step process.

2 / 3

Progressive Disclosure

The skill references multiple external files (GLOBAL.md, various policies, templates/accessibility-check.md) but none are provided in the bundle, making it impossible to verify their existence or usefulness. The content itself is well-sectioned but somewhat long (~150 lines) with the full checklist inline rather than split into a reference file. For a skill this detailed, a separate checklist reference file would improve organization.

2 / 3

Total

9

/

12

Passed

Description

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 and clear 'when to use' guidance. Its main weakness is that the 'what it does' portion lists topic areas rather than concrete actions—it says 'revisar WCAG, teclado, screen reader' but doesn't specify what concrete outputs or transformations it produces (e.g., generating audit reports, fixing ARIA attributes, suggesting semantic HTML replacements). The description also uses a mix of imperative/instructional voice rather than third person, though this is a minor issue.

Suggestions

Replace topic-area listings with concrete action verbs: e.g., 'Audits pages for WCAG compliance, identifies contrast ratio failures, suggests semantic HTML fixes, generates ARIA attribute recommendations, and reviews keyboard navigation flows.'

Use third person voice consistently (e.g., 'Reviews and audits digital accessibility...' instead of 'Skill dedicada a...').

DimensionReasoningScore

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 explicitly answers both 'what' (reviews WCAG, keyboard, screen reader, contrast, semantics, motion reduction, and accessibility of forms/components/flows) and 'when' (with a clear 'Use quando' clause and an explicit 'Trigger em' list). Both dimensions are well-covered.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms in both Portuguese and English, including common abbreviations like 'a11y', technical terms like 'WCAG' and 'ARIA', and user-friendly phrases like 'screen reader', 'leitor de tela', 'navegacao por teclado', and 'contraste de cor'. 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 and unlikely to conflict with other skills like general code review, CSS styling, or HTML editing. The explicit trigger list further reduces ambiguity.

3 / 3

Total

11

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
felvieira/claude-skills-fv
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.