CtrlK
BlogDocsLog inGet started
Tessl Logo

focus-order

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

58

Quality

67%

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-order/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-organized, concise overview with excellent progressive disclosure pointing to a real one-level-deep reference. Its weaknesses are minor verbosity from explaining a known concept and deferring all code examples and verification steps to the reference rather than including a minimal executable/verification slice in the body.

Suggestions

Drop or trim the opening "When focus jumps unexpectedly…" sentence (Claude already knows why focus order matters) and de-duplicate the positive-tabindex guidance repeated in Quick Reference and Fix.

Inline at least one concrete code snippet — e.g., the positive-tabindex anti-pattern and tabindex 0/−1 usage — so the skill is actionable without opening references/rule.md.

Add an explicit verification checkpoint in the body (a brief Verify step: tab through the page, run axe/Lighthouse) and order sections as Check → Fix → Verify rather than leaving validation only in the reference.

DimensionReasoningScore

Conciseness

The body is mostly lean and well-sectioned, but the opening "When focus jumps unexpectedly, keyboard users get disoriented…" explains a concept Claude already knows, and the positive-tabindex guidance is repeated across the Quick Reference and Fix sections, so it could be tightened.

2 / 3

Actionability

Concrete, specific guidance is present (tabindex 0/−1 values, a tab-through review procedure, modal focus-trapping checks), but all code examples and full implementation details are deferred to references/rule.md, leaving the body an actionable overview rather than fully self-sufficient.

2 / 3

Workflow Clarity

A loose Check→Fix→Code Review sequence exists, but there is no explicit validation checkpoint in the body — verification lives only in the reference — and the interleaved "Explain" section disrupts a clean operational sequence, matching the score-2 anchor of steps present but checkpoints implicit.

2 / 3

Progressive Disclosure

The body is a concise overview that clearly signals a one-level-deep reference — "For full implementation details, code examples, and framework-specific guidance, see references/rule.md" — and that file exists, so content is appropriately split with easy navigation.

3 / 3

Total

9

/

12

Passed

Description

77%

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 is strong on specificity and completeness, with an explicit Use-when trigger and a concrete list of inspection actions. It is held back by trigger-term coverage that misses the most common natural phrasings (tab order, tabindex, keyboard navigation) and an action list broad enough to overlap with sibling accessibility skills.

Suggestions

Add the natural trigger terms users most often say for this topic — "tab order," "keyboard navigation," and "tabindex" — alongside "focus order" so the skill surfaces for those phrasings.

Replace the rule-title phrasing "related to Ensure logical focus order" with natural wording such as "related to keyboard focus order" to read as a trigger a user would actually say.

Narrow the action list from general accessibility (native semantics, accessible names, screen-reader output) to focus-order-specific checks to reduce overlap with sibling accessibility skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete inspection actions — "Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output" — matching the score-3 anchor that expects several specific concrete actions rather than a single domain mention.

3 / 3

Completeness

It explicitly answers both "what" (check native semantics, inspect keyboard behavior, focus flow, accessible names, screen-reader output) and "when" via an explicit "Use when reviewing rendered HTML, interactive components, or design-system patterns…" clause, matching the score-3 anchor for both what AND when with explicit triggers.

3 / 3

Trigger Term Quality

Relevant domain keywords are present ("rendered HTML, interactive components, keyboard behavior, focus flow, accessible names, screen-reader output"), but it omits the most common natural variations users say for this topic ("tab order," "keyboard navigation," "tabindex") and embeds the awkward rule-title phrase "Ensure logical focus order" as a trigger.

2 / 3

Distinctiveness Conflict Risk

The focus-order niche is fairly distinct, but the action list broadens into general accessibility territory (native semantics, accessible names, screen-reader output) that would overlap with sibling accessibility skills, so it is "somewhat specific but could still overlap."

2 / 3

Total

10

/

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.