CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

landmark-regions

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

Quality

70%

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/landmark-regions/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.

The body is well-structured with an appropriately split one-level reference to references/rule.md, and the Check/Fix flow is clear for a simple single-purpose skill. Weaknesses are mild padding (an intro and Explain section that restate what Claude already knows) and actionability that stops short of an inline code example, leaving executable detail entirely in the reference file.

Suggestions

Cut the opening paragraph explaining what landmark regions do and fold the vague "Explain" section into "Fix" — Claude already knows why landmarks matter.

Inline one minimal snippet (a nav/main/footer skeleton with aria-label on a second nav) so the fix is executable without opening the reference; move the rest to rule.md as now.

Make the "Check" section concrete (e.g. "confirm exactly one <main>, and that sibling <nav> elements are distinguished via aria-label") instead of "verify that they are correctly structured".

DimensionReasoningScore

Conciseness

The opening paragraph ("Landmark regions allow screen reader users to quickly identify and jump to major sections of a page, significantly improving navigation efficiency") explains a concept Claude already knows, and the "Explain" section restates it as filler. The rest is lean, so it fits anchor 3 (mostly efficient, some unnecessary explanation); not 4 because two sections add no information Claude lacks.

3 / 5

Actionability

Concrete specifics are present (the landmark elements <header>, <nav>, <main>, <footer>; "labels for multiple landmarks of the same type using aria-label"; "Replace generic <div> containers with semantic landmark elements"), but the body contains no code example and "Check" stays abstract ("Verify that the page uses appropriate HTML5 landmark elements"). Fits anchor 3 (some concrete guidance, incomplete); not 4 because the executable example exists only in the reference file, not the body.

3 / 5

Workflow Clarity

As a simple single-purpose review skill, the Check → Fix → Code Review flow is unambiguous and verification is invoked ("note how to verify the fix with browser accessibility tooling or assistive tech"), with concrete validation steps (axe/Lighthouse, accessibility tree, keyboard test) correctly delegated to references/rule.md. Fits anchor 4 (clear sequence, minor validation gaps in-body); not 5 since the body itself has no explicit validation checkpoint.

4 / 5

Progressive Disclosure

The body is a concise, well-sectioned overview (Quick Reference / Check / Fix / Explain / Code Review) 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 and delivers exactly those details (code example, rationale, verification steps). Matches anchor 5 (clear overview, well-signaled one-level-deep references); anchor 4 would require organization gaps that are not present.

5 / 5

Total

15

/

20

Passed

Description

63%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 several concrete inspection actions, but the duplicated rule-title phrase ("related to Use landmark regions correctly") reads as a templating artifact and weakens naturalness. Trigger terms and distinctiveness are middling: common accessibility phrasing users actually say is missing, and the generic review framing could collide with other accessibility skills.

Suggestions

Remove the templating artifact "related to Use landmark regions correctly" and rewrite the when-clause with natural trigger phrases a user would say, e.g. "Use when the page uses (or should use) semantic landmarks like header, nav, main, footer, or when a screen-reader/a11y review flags page structure".

Add the natural keywords users actually say — "accessibility", "a11y", "semantic HTML", "ARIA", "screen reader" — so the description matches real requests instead of only technical framing.

Make the listed actions landmark-specific (e.g. "check for duplicate unlabeled nav/main landmarks") rather than generic accessibility-review steps, which would also reduce conflict risk with other a11y skills.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output") but they are generic accessibility-review actions rather than landmark-specific ones, and the embedded rule title "related to Use landmark regions correctly" blurs them. Fits anchor 4 (several specific actions, minor gaps) — above anchor 3's 1-2 actions, below anchor 5's comprehensive landmark-specific coverage.

4 / 5

Completeness

Both parts are present: the what ("Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output") and an explicit when ("Use when reviewing rendered HTML, interactive components, or design-system patterns"). Fits anchor 4 (both present, when could be more explicit); not 5 because the when-clause awkwardly embeds the rule title instead of concrete natural trigger phrases.

4 / 5

Trigger Term Quality

Relevant keywords exist ("rendered HTML", "interactive components", "keyboard", "screen-reader", "landmark regions"), but common natural terms users would say are missing ("accessibility", "a11y", "semantic HTML", "ARIA", "WCAG"), and "Use landmark regions correctly" is a rule title rather than a phrase a user would naturally say. Matches anchor 3 (some relevant keywords, missing common variations); not 4 because several natural synonyms are absent.

3 / 5

Distinctiveness Conflict Risk

"Landmark regions" names a specific niche, but the trigger surface ("reviewing rendered HTML, interactive components, or design-system patterns") and the inspection actions (keyboard behavior, focus flow, accessible names, screen-reader output) overlap heavily with generic accessibility/frontend-review skills. Matches anchor 3 (somewhat specific, still overlaps with similar skills); not 4 because the overlap with sibling a11y skills is more than minor.

3 / 5

Total

14

/

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/landmark-regions/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.