CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

focus-management

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

Quality

75%

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-management/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 well-structured, token-efficient overview body that correctly pushes implementation detail to a single one-level-deep reference. Its weaknesses are in execution guidance: the Check step lacks any concrete method, and no explicit validation/verification step is built into the workflow.

Suggestions

Make the Check section instructive rather than descriptive: name the concrete method (e.g., keyboard-only pass: open/close each modal and confirm focus moves in and returns to the trigger; Tab through SPAs after route change), instead of "Verify that focus is properly managed".

Add an explicit validation checkpoint to the workflow, e.g., a final step "Re-test with keyboard only and confirm focus moves to new content and returns on close — using axe/Lighthouse or manual keyboard pass" — turning the advisory verify mention into a sequenced step.

Drop or merge the "Explain" section and the duplicated Check/Code Review prose; fold their unique content (flag exact elements/roles, note verification approach) into a single tighter review step to raise conciseness.

DimensionReasoningScore

Conciseness

The body is lean with no over-explanation of concepts Claude already knows, but the "Explain" section and the motivational opener ("Poor focus management leaves keyboard users stranded…") are tokens Claude doesn't need, and "Check" duplicates part of "Code Review". Not 5 for these redundancies; not 3 because nothing is noticeably verbose.

4 / 5

Actionability

Concrete specifics exist ("Use tabindex='-1' to make non-interactive elements focusable", "tabindex, focus(), and focus trapping for modal dialogs", "Move focus to modal when opened, return to trigger when closed"), but the Check section ("Verify that focus is properly managed…") describes rather than instructs and no executable example appears inline — key details are deferred to the reference. Matches "some concrete guidance but incomplete".

3 / 5

Workflow Clarity

Check → Fix → Explain gives a coherent sequence, but validation checkpoints are implicit: "note how to verify the fix with browser accessibility tooling" is advisory prose rather than a step, and there is no explicit re-test step. This is a review skill, so the destructive/batch cap does not apply. Not 4 because checkpoints are missing rather than mostly present.

3 / 5

Progressive Disclosure

The body is a concise overview and the single reference (references/rule.md, verified to exist) is one level deep and clearly signaled with its purpose stated ("For full implementation details, code examples, and framework-specific guidance"). The reference itself contains no nested references, and content is appropriately split between overview and detail.

5 / 5

Total

15

/

20

Passed

Description

75%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 five concrete inspection actions. Its weaknesses are a template-stuffed, hard-to-parse when-clause and a what-side that covers only checking, not the flagging/fixing/explaining the skill body actually does.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output"), but coverage is inspection-only — the flagging and fixing work the skill actually performs is not reflected, leaving minor gaps.

4 / 5

Completeness

Explicitly answers both what ("Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output") and when ("Use when reviewing rendered HTML, interactive components, or design-system patterns related to Manage focus during dynamic interactions"). Not 5 because the when-clause is convoluted template phrasing and the what undersells the fix/explain scope.

4 / 5

Trigger Term Quality

Good natural keyword coverage ("rendered HTML", "interactive components", "keyboard behavior", "focus flow", "screen-reader"), but common variations users would say are missing ("a11y", "keyboard navigation", "tab order", "modal/dialog"). Not 3 because coverage is solid rather than partial; not 5 because synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

Focus management during dynamic interactions is a distinct accessibility niche, but the broad opening trigger ("reviewing rendered HTML, interactive components, or design-system patterns") creates minor overlap risk with general frontend-review and other accessibility skills. Not 5 for that overlap; not 3 because the focus-management qualifier keeps it mostly distinct.

4 / 5

Total

16

/

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-management/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.