CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

orientation

Use when reviewing mobile-first layouts, tablet experiences, fullscreen flows, forms, dashboards, or media interfaces. Check rendered behavior in both portrait and landscape and separate genuine layout constraints from unnecessary orientation assumptions.

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

The body is a well-organized, appropriately concise overview that delegates code examples and deep detail to a verified one-level-deep reference file. The main improvement opportunities are removing duplication between the Check and Code Review sections and making the Fix guidance and validation checkpoints more explicitly executable inline.

Suggestions

Merge the overlapping flag lists in "Check" and "Code Review" into a single section to remove duplicated guidance about orientation locks, rotate-device overlays, and hidden functionality.

Add one brief inline example (e.g., the `screen.orientation.lock('portrait')` anti-pattern) so the flag/fix guidance is executable without opening the reference file.

State an explicit validation checkpoint in "Check" (e.g., "confirm the control is truly unreachable in the rendered layout before flagging it") to close the workflow's implicit-validation gap.

DimensionReasoningScore

Conciseness

The ~45-line body is lean with tight, non-padded sections, but "Check" and "Code Review" duplicate the same flag list ("orientation locks, rotate-device overlays… hide essential functionality") and the closing rule-page URL repeats the frontmatter metadata — minor instances that could be trimmed, so not the every-token-earns-its-place anchor.

4 / 5

Actionability

Concrete instruction-level guidance — "Rotate the page between portrait and landscape on mobile and tablet viewports", specific anti-patterns to flag, and named remediation techniques ("responsive CSS, wrapping layouts, and adaptive spacing") — with executable code examples verified one level deep in references/rule.md; not 5 because the Fix section stays at the technique level with no inline example.

4 / 5

Workflow Clarity

A clear phase structure (Quick Reference → Check → Fix → Explain → Code Review) for a simple single-task review skill, but validation checkpoints such as confirming content is truly unreachable before flagging are only implicit in the body (the numbered verification list lives in the reference file) — a minor gap, so not the explicit-validation anchor.

4 / 5

Progressive Disclosure

A concise overview body with a well-signaled, one-level-deep pointer — "For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`" — and that file exists and itself contains no nested references; the split of overview versus code/details is appropriate and navigation is easy.

5 / 5

Total

17

/

20

Passed

Description

78%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, well-structured "Use when" trigger clause and a clearly stated purpose anchored to the orientation-accessibility niche. Its main weakness is specificity — only two concrete actions are named — and it would benefit from natural synonyms like "device rotation" or "responsive" among the triggers.

Suggestions

Add one or two more concrete actions to the what-clause (e.g., "flag orientation-lock APIs and blocking rotate-device overlays") to lift specificity toward comprehensive coverage.

Include natural trigger synonyms such as "device rotation", "screen orientation", or "responsive layouts" so the description matches more user phrasings.

Narrow the broad trigger contexts ("forms, dashboards, or media interfaces") toward situations where orientation behavior is the actual concern, reducing overlap with general frontend-review skills.

DimensionReasoningScore

Specificity

Names the domain and exactly two concrete actions — "Check rendered behavior in both portrait and landscape" and "separate genuine layout constraints from unnecessary orientation assumptions" — matching the 1-2-concrete-actions anchor; it is not 4 because it does not list several specific actions with comprehensive coverage.

3 / 5

Completeness

Explicitly answers both parts: "Use when reviewing mobile-first layouts, tablet experiences, fullscreen flows, forms, dashboards, or media interfaces" gives a concrete when, and the two stated checking/separating actions give a clear what; the when is explicit and specific, so this fits the top anchor rather than the 4 anchor's "when could be more explicit".

5 / 5

Trigger Term Quality

"mobile-first layouts", "tablet experiences", "forms", "dashboards", and "portrait and landscape" are phrases users would naturally say, but common synonyms such as "device rotation", "responsive", or "screen orientation" are missing — good coverage with a few gaps, not comprehensive.

4 / 5

Distinctiveness Conflict Risk

"portrait and landscape" and "orientation" establish a distinct niche, but the broad triggers "forms, dashboards, or media interfaces" overlap with general frontend-review and accessibility skills — mostly distinct with minor overlap risk, not the minimal-conflict top anchor.

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/orientation/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.