CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

landmark-one-main

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

Quality

76%

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-one-main/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.

A lean, well-structured single-purpose skill with a clean Check/Fix/Explain workflow and exemplary progressive disclosure through one clearly signaled reference file. Its weaknesses are modest: a redundant concept explanation Claude does not need, and a missing explicit re-verification step after the fix.

Suggestions

Drop the opening sentence and the 'Provides a clear starting point' bullet — Claude already knows what a main landmark does; keep only the rule statement.

Add an explicit verification loop after Fix, e.g. 'Re-count main elements to confirm exactly one remains' or 'Re-run the accessibility checker to confirm the violation is resolved'.

Include one concrete detection snippet in the Check section, such as document.querySelectorAll('main, [role=main]').length, instead of the prose-only instruction.

DimensionReasoningScore

Conciseness

The body opens by explaining what a main landmark does for screen reader users ("allows keyboard and screen reader users to jump directly to the primary content") and the Quick Reference bullet "Provides a clear starting point for the page's primary content" repeats it — both are concepts Claude already knows, and the Code Review section largely restates the frontmatter description in generic terms. This matches anchor 3 ("mostly efficient but includes some unnecessary explanation or could be tightened") better than anchor 4, where over-explanation would be only a minor instance rather than a full intro paragraph plus a redundant bullet.

3 / 5

Actionability

The Check and Fix sections give concrete, executable direction — "Count the number of <main> elements or elements with role='main' on the page" and "Combine multiple main content areas into a single <main> element or remove the 'role=main' attribute from extra containers" — and code examples are appropriately deferred to references/rule.md. It is not anchor 5 because no concrete command or selector is given inline (e.g. a querySelectorAll expression or axe rule id) and the Code Review section stays at the level of general instruction; it is well above anchor 3, whose guidance is incomplete or pseudocode.

4 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sequence is clearly laid out with unambiguous steps for this simple single-purpose skill. It falls short of anchor 5 because there is no explicit validation checkpoint after the fix — the workflow never says to re-count the main elements or re-run the checker to confirm exactly one remains, only a vague mention of noting "how to verify the fix with browser accessibility tooling" — matching anchor 4's "clear sequence with most checkpoints present; minor validation gaps".

4 / 5

Progressive Disclosure

The body is a concise overview and the single reference is clearly signaled and one level deep: "For full implementation details, code examples, and framework-specific guidance, see references/rule.md" — and references/rule.md exists and contains exactly that material (code examples, best practices, verification steps). No nesting, no buried references, no inline content that belongs in a separate file; this matches the anchor-5 example of a clear overview with well-signaled one-level-deep references.

5 / 5

Total

16

/

20

Passed

Description

71%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" clause and several concrete inspection actions, weakened slightly by templated phrasing that embeds the rule title instead of natural trigger synonyms, and by generic accessibility boilerplate that reduces distinctiveness within a family of similar rule skills. It sits comfortably above the midpoint on all four dimensions.

Suggestions

Replace the templated clause 'related to Use exactly one main landmark' with natural trigger phrases users would actually say, e.g. 'when a page has multiple <main> elements or duplicate role=main landmarks'.

Add missing synonyms and concrete tokens to broaden trigger matching: '<main> element', 'role=main', 'landmark navigation', 'skip to content'.

Differentiate from sibling accessibility rule skills by making the trigger specific to this rule (counting/deduplicating main landmarks) rather than generic accessibility-review boilerplate.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output" — which is actionable and multi-step. It falls short of anchor 5 because coverage has gaps (no mention of remediation or what artifact is produced) and the templated phrase "related to Use exactly one main landmark" blurs what the skill actually operates on; it is clearly above anchor 3, which expects only 1-2 concrete actions.

4 / 5

Completeness

Both halves are present: the "what" is "Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output" and the "when" is an explicit "Use when reviewing rendered HTML, interactive components, or design-system patterns". It is not anchor 5 because the trigger clause "related to Use exactly one main landmark" embeds the rule title verbatim rather than natural concrete trigger phrases a user would say, leaving the "when" slightly less explicit than the anchor-5 example.

4 / 5

Trigger Term Quality

Good natural-term coverage: "rendered HTML", "interactive components", "design-system patterns", "keyboard behavior", "focus flow", "accessible names", "screen-reader output", "main landmark" are phrases a user doing accessibility review would plausibly say. Not anchor 5 because common synonyms and concrete tokens are missing — e.g. "<main> element", "role=main", "landmark navigation", "skip to content" — which would catch more user phrasings.

4 / 5

Distinctiveness Conflict Risk

The rule name "Use exactly one main landmark" carves out a niche, but the surrounding trigger boilerplate ("reviewing rendered HTML, interactive components, or design-system patterns" plus "keyboard behavior, focus flow, accessible names, and screen-reader output") would appear verbatim in every sibling accessibility-rule skill, so it could still overlap with similar skills. Not anchor 4, which requires mostly distinct triggers with only minor overlap risk among closely related skills — here the shared template creates broader overlap across the whole rule family.

3 / 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/landmark-one-main/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.