CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

responsive-conversion

Corrige interfaces responsivas e problemas de viewport mobile. Trigger em: "responsivo", "mobile", "nao pega 100%", "cortando na tela", "quebrou no celular", "scroll horizontal", "viewport", "safe area", "notch", "bottom sheet", "modal no mobile", "confirmacao de exclusao", "modal de confirmar", "undo", "grid quebrado", "overflow", "converter para mobile", "adaptar layout".

Quality

88%

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

88%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.

An unusually actionable skill body: concrete audit commands, decision tables with root-cause fixes, a sequenced protocol with genuine validation loops, and explicit anti-patterns. Remaining gaps are efficiency of structure rather than substance — some governance repetition and a long inline modals section that could be split out.

Suggestions

State the skill-boundary information (02/52/22/57/58) once — in the fronteira/handoff section — and let 'Quando Nao Usar' and 'Integracao com Pipeline' reference it briefly, cutting roughly 20-30 duplicated lines.

Move the 'Modais, Drawers e Bottom Sheets' and 'Confirmacao de Acoes' sections (~120 lines) into a references/ file (e.g. references/interaction-patterns.md), keeping a short decision table inline in SKILL.md so the main file stays an overview.

DimensionReasoningScore

Conciseness

The body is dense and efficient — symptom/cause/fix tables, one-line justifications ("100dvh — altura dinamica real, acompanha a barra") instead of tutorials, and no basic-concept padding. It is not a 5 because the boundary with skills 02/52/22/57/58 is restated three times (Governanca Global, Quando Nao Usar, Integracao com Pipeline), which is trimmable redundancy.

4 / 5

Actionability

Fully executable throughout: runnable grep commands for the audit, a paste-in console script listing elements wider than the screen, copy-paste CSS with the vh->dvh fallback pattern, the exact viewport meta tag, specific Tailwind utilities (min-w-0, grid-cols-[repeat(auto-fit,minmax(280px,1fr))]), and a concrete modal-copy anatomy with good/bad examples. Nothing is pseudocode or hand-wavy.

5 / 5

Workflow Clarity

The four-phase protocol is explicitly ordered ("Cada fase alimenta a seguinte — pular fase gera fix superficial que reaparece"), defines exact test widths (320/390/768px), and closes with a real feedback loop: Phase 4 re-checks all widths plus desktop and sends any regressed width "volta pra Fase 3 pra reclassificar a causa raiz" rather than cosmetically patching. Checklists reinforce the checkpoints.

5 / 5

Progressive Disclosure

Good single-file structure with clear sections, and the heavy per-framework fix catalog is properly deferred to docs/skill-guides/responsive-conversion.md "apenas quando necessario". Not a 5 because the file runs ~350 lines with the modals/confirmation-pattern guidance (~120 lines) fully inlined where a reference file would fit, and no bundle files exist to carry the overflow.

4 / 5

Total

18

/

20

Passed

Description

86%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 highly triggerable description with an explicit 'Trigger em' clause and excellent natural-phrase coverage, cleanly answering both what and when. Its main weakness is a thin capability statement: one action verb leaves the modal/confirmation-pattern work the skill also performs undescribed, costing specificity.

Suggestions

Expand the 'what' sentence to enumerate the skill's concrete capabilities, e.g. "Corrige interfaces responsivas e problemas de viewport mobile; define padroes de modal/bottom sheet e fluxos de confirmacao para acoes destrutivas em telas pequenas."

Qualify the most generic triggers to reduce conflict risk with sibling skills, e.g. "undo (acao reversivel em mobile)" or "modal no mobile", since plain "undo" or "overflow" may also match 57-mobile-ux-foundations or 52-ui-polish.

DimensionReasoningScore

Specificity

"Corrige interfaces responsivas e problemas de viewport mobile" names the domain with one concrete action verb, but the 'what' stops there — capabilities the body actually delivers (definir comportamento de modal/drawer/bottom sheet, especificar fluxo de confirmacao, auditar formularios) are absent from the description. Closest to 'names domain and 1-2 concrete actions, but not comprehensive'; not a 4 because only a single action is explicitly stated.

3 / 5

Completeness

Explicitly answers both questions: 'what' via "Corrige interfaces responsivas e problemas de viewport mobile" and 'when' via the explicit "Trigger em:" clause listing concrete trigger phrases. This matches the anchor 'clearly and explicitly answers both what AND when with concrete trigger phrases'.

5 / 5

Trigger Term Quality

Eighteen explicit triggers mixing colloquial user phrasing ("nao pega 100%", "cortando na tela", "quebrou no celular") with technical synonyms ("viewport", "safe area", "notch", "overflow", "bottom sheet"), which is comprehensive natural-term coverage including variations. Not a 4 because no commonly-used phrasing for this need is obviously missing.

5 / 5

Distinctiveness Conflict Risk

The mobile-responsive niche is clear and most triggers are distinctive, but generic triggers like "undo", "overflow", and "modal de confirmar" could plausibly fire sibling UI skills (52-ui-polish, 57-mobile-ux-foundations) in the described ecosystem. Mostly distinct with minor overlap risk against closely related skills — an anchor-4 fit, not 5.

4 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

16

Passed

Repository

felvieira/claude-skills-fv

Path

skills/56-responsive-conversion/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.