CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

focus-not-obscured

Use when reviewing sticky navigation, consent banners, chat widgets, skip links, or any fixed-position UI. Validate the actual tab order and viewport behavior at realistic zoom levels.

Quality

78%

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/focus-not-obscured/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 uses progressive disclosure correctly by deferring code and verification detail to a single clearly-signaled reference file. The body itself is directive rather than executable, and the workflow lacks an explicit post-fix validation checkpoint.

Suggestions

Inline one small executable snippet in the Fix section (e.g., a two-line scroll-padding-top/bottom CSS rule) so the most common remediation is actionable without opening the reference file.

Add an explicit validation step after Fix, such as 'Re-tab through the page with all sticky UI active and at 200% zoom; pass only if the focused element and its indicator stay visible' — the pass/fail criteria currently live only in references/rule.md.

Trim the introductory rationale sentence ('Keyboard users need to see the actual focused control... to continue the task') to a single clause, since it explains a concept Claude already knows.

DimensionReasoningScore

Conciseness

The ~35-line body is efficient with well-scoped Check/Fix/Explain/Code Review sections, but the intro sentence explaining that keyboard users 'need to see the actual focused control and the focus indicator at the same time in order to continue the task' briefly restates a concept Claude already knows. Matches the 4 anchor (efficient, minor trimmable instances) rather than the lean 5 anchor.

4 / 5

Actionability

Directives name concrete targets ('headers, footers, cookie banners, promo bars, and chat launchers') and techniques ('scroll-padding', 'reduce overlay height'), but the body contains no executable code, commands, or selectors — all implementation detail is deferred to references/rule.md. This sits between the vague-hints of 2 and the mostly-executable guidance of 4.

3 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sections imply a coherent sequence, but there is no explicit validation checkpoint (e.g., re-test tabbing after applying the fix); pass/fail criteria exist only in the reference file. This matches the 3 anchor (sequence present, checkpoints missing or implicit) rather than 4.

3 / 5

Progressive Disclosure

The body is a concise, well-sectioned overview that clearly signals a single one-level-deep reference ('For full implementation details, code examples, and framework-specific guidance, see references/rule.md'), which is a real, self-contained file with no nested references. This matches the 5 anchor exactly.

5 / 5

Total

15

/

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 and specific 'Use when...' trigger clause, natural terminology, and concrete validation actions. Its main weaknesses are modest synonym coverage and slight overlap risk with broader accessibility/keyboard-navigation skills.

DimensionReasoningScore

Specificity

Lists several specific actions — reviewing 'sticky navigation, consent banners, chat widgets, skip links, or any fixed-position UI' and validating 'the actual tab order and viewport behavior at realistic zoom levels' — with minor gaps such as no mention of remediation techniques (scroll-padding). It exceeds the 3 anchor (only 1-2 concrete actions) but is less comprehensive than the 5 anchor.

4 / 5

Completeness

Explicitly answers both parts: 'Use when reviewing sticky navigation, consent banners...' is a concrete when-clause, and 'Validate the actual tab order and viewport behavior at realistic zoom levels' states clearly what it does. This exceeds the 4 anchor, whose 'when' is only adequately explicit.

5 / 5

Trigger Term Quality

Natural phrases users would say include 'sticky navigation', 'consent banners', 'chat widgets', 'skip links', 'tab order', and 'zoom'. A few common synonyms are missing (e.g., 'sticky header', 'cookie banner', 'keyboard navigation', 'focus'), keeping it below the 5 anchor's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The fixed-position UI / focus-obscuring niche is distinct with specific triggers, but 'tab order' and 'consent banners' could also plausibly fire a general keyboard-navigation or accessibility-audit skill, giving minor overlap with closely related skills rather than the minimal conflict of the 5 anchor.

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/focus-not-obscured/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.