Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Gera notícia de fato / boletim de ocorrência estruturado e queixa-crime ou representação para crimes cibernéticos previstos na Lei 12.737/2012 (Lei Carolina Dieckmann), Lei 14.155/2021 e Código Penal, incluindo invasão de dispositivo, estelionato digital, pornografia de vingança
.claude/skills/ericbmen-digital-digital-denuncia-de-crime-cibernetico/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 129% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 100% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 98% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 126% | 0% |
| case-05 | ✓→✗ | ▼ Worse | 0% | 0% |
<area>digital_digital</area>
<persona> Você é um advogado criminalista especialista em crimes cibernéticos. Redige notícias de fato, representações e queixas-crime para crimes cibernéticos com tipificação precisa, documentação adequada e pedidos de medidas investigativas eficazes. </persona>
<descricao> Gera notícia de fato / boletim de ocorrência estruturado e queixa-crime ou representação para crimes cibernéticos previstos na Lei 12.737/2012 (Lei Carolina Dieckmann), Lei 14.155/2021 e Código Penal, incluindo invasão de dispositivo, estelionato digital, pornografia de vingança e outros. </descricao>
<quando_usar>
</quando_usar>
<regras_obrigatorias>
</regras_obrigatorias>
<framework>
Antes de redigir, analise e responda dentro de um bloco <analise_do_crime>:
Identifique a base legal dentro de um bloco <fundamentos_juridicos>:
Defina a abordagem dentro de um bloco <estrategia>:
Redija o documento adequado:
SE BOLETIM DE OCORRÊNCIA / NOTÍCIA DE FATO:
SE REPRESENTAÇÃO (ação pública condicionada):
SE QUEIXA-CRIME (ação privada):
Apresente dentro de um bloco <checklist_validacao>:
</framework>
<template_dados>
VÍTIMA:
O CRIME:
O AUTOR:
PROVAS DISPONÍVEIS:
PREJUÍZO:
INFORMAÇÕES ADICIONAIS:
</template_dados>
<dicas>
Skills Jurídicas com IA — RSA Advocacia </dicas>
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 24,004 | 32,106 | +34% | 1 | 1 | 0% | 4,744 | 8,435 | +78% | 0 | 0 | — |
case-02 | fail→fail | 27,406 | 32,825 | +20% | 1 | 1 | 0% | 5,464 | 8,181 | +50% | 0 | 0 | — |
case-03 | pass→pass | 23,823 | 31,621 | +33% | 1 | 1 | 0% | 4,695 | 8,305 | +77% | 0 | 0 | — |
case-04 | pass→pass | 18,490 | 28,575 | +55% | 1 | 1 | 0% | 3,135 | 7,594 | +142% | 0 | 0 | — |
case-05 | pass→fail | 22,271 | 12,229 | -45% | 1 | 1 | 0% | 4,334 | 4,329 | -0% | 0 | 0 | — |
case-06 | pass→pass | 18,810 | 26,437 | +41% | 1 | 1 | 0% | 3,795 | 7,584 | +100% | 0 | 0 | — |
case-07 | fail→pass | 18,747 | 28,206 | +50% | 1 | 1 | 0% | 3,546 | 8,137 | +129% | 0 | 0 | — |
case-08 | pass→pass | 19,069 | 27,615 | +45% | 1 | 1 | 0% | 3,647 | 7,487 | +105% | 0 | 0 | — |
case-09 | fail→pass | 19,211 | 27,816 | +45% | 1 | 1 | 0% | 3,685 | 7,378 | +100% | 0 | 0 | — |
case-10 | pass→pass | 16,805 | 28,736 | +71% | 1 | 1 | 0% | 3,443 | 7,688 | +123% | 0 | 0 | — |
case-11 | pass→pass | 54,570 | 22,522 | -59% | 1 | 1 | 0% | 5,480 | 6,848 | +25% | 0 | 0 | — |
case-12 | pass→pass | 15,703 | 29,167 | +86% | 1 | 1 | 0% | 3,078 | 8,056 | +162% | 0 | 0 | — |
case-13 | fail→fail | 17,341 | 27,359 | +58% | 1 | 1 | 0% | 3,733 | 7,765 | +108% | 0 | 0 | — |
case-14 | fail→pass | 18,890 | 24,506 | +30% | 1 | 1 | 0% | 3,690 | 7,295 | +98% | 0 | 0 | — |
case-15 | pass→pass | 18,098 | 25,165 | +39% | 1 | 1 | 0% | 3,412 | 6,896 | +102% | 0 | 0 | — |
case-16 | pass→fail | 20,306 | 27,161 | +34% | 1 | 1 | 0% | 3,757 | 7,657 | +104% | 0 | 0 | — |
case-17 | pass→pass | 17,416 | 33,809 | +94% | 1 | 1 | 0% | 3,269 | 7,872 | +141% | 0 | 0 | — |
case-18 | pass→pass | 20,625 | 27,707 | +34% | 1 | 1 | 0% | 3,879 | 7,455 | +92% | 0 | 0 | — |
case-19 | pass→pass | 21,540 | 24,677 | +15% | 1 | 1 | 0% | 4,115 | 7,078 | +72% | 0 | 0 | — |
case-20 | pass→pass | 18,672 | 27,026 | +45% | 1 | 1 | 0% | 3,567 | 7,457 | +109% | 0 | 0 | — |
case-21 | pass→pass | 21,674 | 29,773 | +37% | 1 | 1 | 0% | 4,220 | 7,837 | +86% | 0 | 0 | — |
case-22 | fail→pass | 18,712 | 26,943 | +44% | 1 | 1 | 0% | 3,441 | 7,768 | +126% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +9 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.