CtrlK
BlogDocsLog inGet started
Tessl Logo

aria-roles

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Use valid ARIA role values. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

61

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/aria-roles/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

The body is a well-structured, token-efficient overview that correctly delegates implementation detail to a single verified reference file. Its weakest point is actionability: the in-body Check/Fix guidance lacks any concrete detection pattern or valid-vs-invalid role examples, so the reviewer must open the reference before they can act.

Suggestions

Inline one or two concrete detection aids in the Check section, e.g. a grep for role= attributes or the most common misspellings (btn, check-box, tooltip-item), so the check is executable without opening the reference.

Name a specific verification tool in the Code Review section (e.g. axe DevTools, WAVE, or a screen reader pass) instead of the generic "browser accessibility tooling or assistive tech".

Tighten or merge the meta-templated "Explain" section, which instructs Claude to explain rather than adding concrete guidance.

DimensionReasoningScore

Conciseness

The 35-line body is lean: terse bullets in Quick Reference and short Check/Fix sections that assume Claude's competence. Minor trimmable padding remains in the meta-templated "Explain" section and the opening motivation sentence, keeping it just below anchor 5.

4 / 5

Actionability

The Check step gives concrete direction ("Search for any role attributes that use non-standard or misspelled ARIA role values") and the Fix step names the right replacement strategy, but the body itself contains no executable specifics — no detection pattern or query, no inline examples of valid vs. misspelled roles (those all live in references/rule.md). This sits between anchors 2 and 4: guidance is present but incomplete within the body.

3 / 5

Workflow Clarity

A coherent Check → Fix → Explain → Code Review sequence covers detection, remediation, and communication, and the Code Review section includes a verification hint ("note how to verify the fix with browser accessibility tooling or assistive tech"). This is a non-destructive review task so the validation cap does not apply; it falls short of 5 only because no specific verification tool or loop is named.

4 / 5

Progressive Disclosure

The body is a concise overview with a single, clearly signaled, one-level-deep pointer — "For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`" — and that file exists as a real 54-line bundle containing the examples, exceptions, and standards detail. Content is appropriately split with easy navigation, matching the anchor-5 example.

5 / 5

Total

16

/

20

Passed

Description

75%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.

The description answers both what and when with mostly natural trigger terms and concrete review actions. Its main defect is an unedited template fragment ("related to Use valid ARIA role values") that garbles the core statement of purpose, plus omission of the most natural domain keywords like "accessibility" or "a11y".

Suggestions

Rewrite the templated clause into a plain statement of purpose, e.g. "Reviews HTML for invalid or misspelled ARIA role values and flags custom widgets that should use native semantic elements instead."

Add the natural trigger terms users actually say for this domain — "accessibility", "a11y", "screen reader", and "WCAG" — to the Use-when clause.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output") rather than vague language. Falls short of 5 because the templated fragment "related to Use valid ARIA role values" obscures the core deliverable, leaving a minor gap in what is actually produced.

4 / 5

Completeness

Explicitly answers when ("Use when reviewing rendered HTML, interactive components, or design-system patterns") and what (check native semantics, inspect keyboard behavior, focus flow, accessible names, screen-reader output). Falls between anchors 4 and 5: the unedited "related to Use valid ARIA role values" template phrase makes the what slightly less crisp than the anchor-5 example.

4 / 5

Trigger Term Quality

Natural terms like "rendered HTML", "interactive components", "design-system patterns", "keyboard behavior", and "screen-reader output" would plausibly appear in a user's request. Not 5 because the most common user phrasings for this domain — "accessibility", "a11y", or "WCAG" — are missing.

4 / 5

Distinctiveness Conflict Risk

Scoped to ARIA role validity review, which is a fairly distinct niche with low conflict risk against unrelated skills. Minor overlap risk remains with sibling accessibility-review skills that share the keyboard/focus/accessible-name triggers.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
thedaviddias/Front-End-Checklist
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.