CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

56

Quality

63%

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

60%

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 clean, well-structured overview that correctly pushes detail to references/rule.md, earning high progressive-disclosure marks. It is held back by an absence of executable verification steps in SKILL.md itself and some generic explanatory prose that assumes less of Claude than it should.

Suggestions

Add one concrete verification command or selector to the 'Check' section (e.g. `document.querySelectorAll('main, [role=main]').length === 1`) so the body is actionable without opening the reference.

Add an explicit validation checkpoint in 'Fix' confirming the page still exposes exactly one main landmark after the change.

Trim the opening sentence and the generic 'Code Review' paragraph, which restate concepts Claude already knows about landmark navigation.

DimensionReasoningScore

Conciseness

The body is short and lightly padded rather than verbose, but several lines are restatements Claude already knows (e.g. 'A single main landmark allows keyboard and screen reader users to jump directly to the primary content') and the 'Code Review' section largely re-describes the skill rather than adding load-bearing detail, so it is mostly efficient but could be tightened.

2 / 3

Actionability

The 'Check' step gives a concrete counting heuristic ('Count the number of <main> elements or elements with role=main') and 'Fix' gives a remediation, but there is no executable command, selector, or code snippet in the body itself — the only runnable examples live in references/rule.md — so guidance is concrete but incomplete in SKILL.md.

2 / 3

Workflow Clarity

The Check / Fix / Explain / Code Review sections provide a recognizable sequence, but there is no validation checkpoint confirming the fix actually yields exactly one <main> (a verification step exists only in the reference file), so checkpoints are implicit rather than explicit.

2 / 3

Progressive Disclosure

The body is a concise overview with a single clearly signaled one-level-deep reference ('see references/rule.md'), the referenced file exists, and content is appropriately split between the overview and the detail file rather than nested multiple levels, matching the well-organized reference anchor.

3 / 3

Total

9

/

12

Passed

Description

67%

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 has an explicit 'Use when...' trigger and enumerates concrete review dimensions, but the trigger language is generic and would overlap with sibling accessibility skills. Tightening the keywords to the rule-specific terms ('main landmark', 'exactly one main', 'skip-to-content') would lift specificity and distinctiveness.

Suggestions

Replace the generic 'rendered HTML, interactive components, or design-system patterns' phrasing with rule-specific trigger terms users would say, e.g. 'Use when auditing a page for landmark structure, checking for more than one <main>, or verifying skip-to-content behavior'.

State the concrete action the skill performs (e.g. 'Verify each page exposes exactly one <main> or role="main" element') so the 'what' is as specific as the 'when'.

Drop the self-referential 'related to Use exactly one main landmark' clause, which duplicates the title without adding user-facing vocabulary.

DimensionReasoningScore

Specificity

Quotes a concrete domain ('rendered HTML, interactive components, or design-system patterns') and lists several specific checks ('keyboard behavior, focus flow, accessible names, and screen-reader output'), but these are generic review activities rather than concrete actions tied to the single main-landmark rule, and the repeated phrase 'related to Use exactly one main landmark' reads as a label rather than a listed action.

2 / 3

Completeness

It explicitly answers 'when' via the 'Use when reviewing...' clause and 'what' via the enumerated inspection steps, satisfying both halves with an explicit trigger; not score 2 because the trigger clause is present rather than merely implied.

3 / 3

Trigger Term Quality

It opens with 'Use when reviewing rendered HTML, interactive components, or design-system patterns' which are reasonable natural phrases, but it omits the common variations a user would actually say ('main landmark', 'one main', 'screen reader jump to main', 'skip to content') and leans on the title-phrase rather than user vocabulary.

2 / 3

Distinctiveness Conflict Risk

The description is scoped to a specific accessibility rule, but the phrase 'reviewing rendered HTML, interactive components, or design-system patterns' is broad and would overlap with many other accessibility/design-system skills, so conflict risk remains moderate.

2 / 3

Total

9

/

12

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.

Validation15 / 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.