CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

decorative-elements

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Hide decorative elements from assistive technology. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant. If an image is clearly decorative, default to no finding unless the snippet shows an actual issue such as broken semantics, focusability, or visible layout instability.

Quality

81%

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

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.

A well-structured, appropriately short body with concrete attribute-level guidance and a correctly signaled one-level-deep reference file. The main cost is redundancy: the no-finding guardrail is stated three times and the intro/Explain sections pad with knowledge Claude already has.

Suggestions

Consolidate the 'do not report decorative images as failures unless there is a concrete problem' guidance into a single Quick Reference bullet — it currently appears twice there and a third time in the Check section.

Drop or heavily condense the intro sentence and the generic Explain section explaining that screen readers announce every image; Claude already knows this and the Quick Reference carries the operative rules.

Add a short good/bad markup pair to the Fix section (e.g., <img src="divider.png"> vs <img src="divider.png" alt="" aria-hidden="true">) so fixes are copy-paste ready without opening references/rule.md.

DimensionReasoningScore

Conciseness

The body is short but repeats the same "don't raise findings unless there's a concrete problem" guidance three times (two Quick Reference bullets, again in Check: "Do not report decorative images as accessibility or performance failures unless the code shows a concrete problem"), and the intro/Explain sections restate concepts Claude already knows ("Screen readers announce every image and icon—decorative elements clutter the experience"). This fits "mostly efficient but includes some unnecessary explanation or could be tightened" rather than the trimmed-to-essential anchor 4.

3 / 5

Actionability

Concrete, executable guidance throughout: "Use alt='' (empty) for decorative images", "Add aria-hidden='true' to decorative SVGs and icons", "Use CSS background-image", plus a worked example (`<img src="/divider.svg" alt="" aria-hidden="true">`). Not anchor 5 because the Fix section lacks an inline good/bad markup pair — the full code examples live only in references/rule.md, leaving minor gaps in copy-paste readiness.

4 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sections give a clear review sequence, and the Code Review section names a verification step ("note how to verify the fix with browser accessibility tooling or assistive tech"), so most checkpoints are present. It falls short of anchor 5 because the ordering between sections is implicit and no explicit validate-the-fix loop is described.

4 / 5

Progressive Disclosure

The SKILL.md is a concise overview that clearly signals one-level-deep detail — "For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`" — and that file exists with the promised code examples. Content is appropriately split and easy to navigate, matching the clear-overview anchor.

5 / 5

Total

16

/

20

Passed

Description

83%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 description with an explicit "Use when..." trigger clause and multiple concrete review actions, including a sensible default-no-finding rule that prevents over-reporting. Main weaknesses are the awkwardly embedded rule title and missing common synonyms like "alt text" and "aria-hidden".

DimensionReasoningScore

Specificity

The description lists several concrete review actions — "Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output" — plus a concrete default rule ("default to no finding unless the snippet shows an actual issue such as broken semantics, focusability, or visible layout instability"). It stops short of anchor 5 because it embeds the vague rule title "related to Hide decorative elements from assistive technology" and omits concrete fix vocabulary like alt='' or aria-hidden.

4 / 5

Completeness

Both what and when are explicitly and concretely answered: "Use when reviewing rendered HTML, interactive components, or design-system patterns..." (when) and "Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output... default to no finding unless..." (what). This matches the anchor-5 pattern of explicit trigger phrases plus concrete capability statements.

5 / 5

Trigger Term Quality

Good natural-term coverage: "rendered HTML", "interactive components", "design-system patterns", "decorative", "assistive technology", "screen-reader", "keyboard behavior", "focus", "accessible names". Not anchor 5 because common synonyms users would say — "alt text", "aria-hidden", "icons", "accessibility audit" — are absent.

4 / 5

Distinctiveness Conflict Risk

The decorative-elements/assistive-technology niche is clear, but phrases like "keyboard behavior, focus flow" and "design-system patterns" overlap with sibling accessibility review skills (focus order, keyboard navigation, alt-text rules), creating minor conflict risk. It is well above the generic overlap of anchor 3 but not the minimal-conflict niche of anchor 5.

4 / 5

Total

17

/

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/decorative-elements/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.