CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

carousel-accessibility

Use when reviewing templates, rendered HTML, or shared components related to Make carousels accessible. Validate the final browser-facing markup, not just the source framework abstraction.

Quality

72%

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/carousel-accessibility/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 lean, well-structured overview that appropriately delegates implementation detail to references/rule.md. Its main weaknesses are redundant restatement of the same four requirements across four sections and 'proper ARIA roles' left unspecified, which weakens actionability despite the deferred reference.

Suggestions

Consolidate the four requirements into a single checklist (Quick Reference) and have Check, Fix, and Explain reference it rather than restating it nearly verbatim four times.

Replace 'proper ARIA roles' with the specific attributes to check — e.g. aria-roledescription='carousel', role='region', aria-live='polite' — either inline or as a one-line pointer into references/rule.md's code example.

Add a short verification step in the Fix section (re-run the Check list against the rendered markup after changes) to close the check-to-fix loop.

DimensionReasoningScore

Conciseness

The same four requirements (pause/play controls, keyboard/arrow navigation, aria-live/ARIA, prefers-reduced-motion) are restated nearly verbatim across the Quick Reference, Check, Fix, and Explain sections, and the intro sentence re-explains WCAG rationale Claude already knows ('trap users, cause disorientation, and violate WCAG requirements'). This is more than minor trimming, matching the 'mostly efficient but could be tightened' anchor rather than the 'minor instances' anchor at 4.

3 / 5

Actionability

Concrete items are named — 'pause/stop controls', 'arrow keys and tab', 'aria-live regions', 'prefers-reduced-motion' — but 'proper ARIA roles' never specifies which roles or attributes to check (e.g. aria-roledescription, region role, aria-live='polite'), and no inline code or selectors are given, deferring all specifics to the reference. This fits the 'concrete guidance but incomplete, missing key details' anchor.

3 / 5

Workflow Clarity

As a simple, single-purpose review skill it is clearly sectioned (Check, Fix, Explain, Code Review) giving an implicit check-then-fix flow, and the Code Review section names the deliverable ('Flag exact elements, attributes, and routes'). It falls short of 5 because the sequence between sections is implicit and there is no checkpoint for verifying that a fix satisfies the checks; it is not a destructive or batch operation, so no cap applies.

4 / 5

Progressive Disclosure

The body is a lean ~30-line overview with a clearly signaled one-level-deep pointer ('For full implementation details, code examples, and framework-specific guidance, see references/rule.md'), and that file exists (425 lines with a full HTML code example) with no further nested references. This matches the 'clear overview with well-signaled one-level-deep references' anchor.

5 / 5

Total

15

/

20

Passed

Description

70%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 solid description with an explicit 'Use when' trigger clause and a specific, unusual scope distinction (final browser-facing markup vs. source framework abstraction). Its weaknesses are limited action coverage in the 'what', a missing synonym or two (slider, slideshow), and awkward phrasing where the rule title is spliced into the sentence.

Suggestions

State the skill's output in the 'what' clause — e.g. 'Flag exact elements, attributes, and routes where the rendered markup violates carousel accessibility rules' — so the description covers both checking and reporting, not just validation.

Add natural synonyms such as 'slider' or 'slideshow' to broaden trigger coverage beyond just 'carousels'.

Rewrite the spliced phrase 'related to Make carousels accessible' into grammatical prose, e.g. 'related to carousel accessibility', to remove the template-fill artifact.

DimensionReasoningScore

Specificity

The description names two concrete actions — 'reviewing templates, rendered HTML, or shared components' and 'Validate the final browser-facing markup' — with precisely scoped targets, but coverage is not comprehensive (it never states what the skill does on violations, e.g. flag or fix). This fits the anchor for 1-2 concrete actions better than the 'several specific actions' anchor above it.

3 / 5

Completeness

Both parts are explicitly present: an explicit trigger clause ('Use when reviewing templates, rendered HTML, or shared components...') and a what-clause ('Validate the final browser-facing markup, not just the source framework abstraction'). The 'what' is somewhat narrow and awkwardly embedded in the phrase 'related to Make carousels accessible', so it does not reach the fully explicit what-and-when anchor of 5.

4 / 5

Trigger Term Quality

Good natural keyword coverage: 'carousels', 'templates', 'rendered HTML', 'shared components', 'browser-facing markup' are phrases users would naturally say. A few natural terms are missing — synonyms like 'slider', 'slideshow', or 'a11y' — so it falls between the good-coverage (4) and comprehensive-coverage (5) anchors, closer to 4.

4 / 5

Distinctiveness Conflict Risk

The carousel-accessibility niche is clear and distinctive, but the generic trigger phrase 'reviewing templates, rendered HTML, or shared components' would equally apply to many sibling HTML-review rule skills, creating minor overlap risk with closely related skills — matching the 'mostly distinct; minor overlap risk' anchor.

4 / 5

Total

15

/

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

Path

skills/carousel-accessibility/SKILL.md

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.