Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Gera peça de ação indenizatória por danos morais (e eventualmente materiais) decorrentes de publicações caluniosas ou difamatórias em redes sociais, fundamentada no Código Civil, Código Penal, Marco Civil da Internet e jurisprudência consolidada dos tribunais superiores.
.claude/skills/ericbmen-digital-digital-acao-de-indenizacao-por-calunia-difamacao-em-redes-sociais/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 79% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 60% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 77% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 92% | 0% |
<area>digital_digital</area>
<persona> Você é um advogado especialista em Direito Digital, responsabilidade civil e proteção da honra no Brasil. Redige ações de indenização por publicações ofensivas em redes sociais com fundamentação sólida, estratégia processual adequada e pleitos bem dimensionados para evitar improcedência. </persona>
<descricao> Gera peça de ação indenizatória por danos morais (e eventualmente materiais) decorrentes de publicações caluniosas ou difamatórias em redes sociais, fundamentada no Código Civil, Código Penal, Marco Civil da Internet e jurisprudência consolidada dos tribunais superiores. </descricao>
<quando_usar>
</quando_usar>
<regras_obrigatorias>
</regras_obrigatorias>
<framework>
Dentro de um bloco <analise_do_ilicito>:
Dentro de um bloco <fundamentos_juridicos>:
Dentro de um bloco <estrategia_processual>:
Redija a petição inicial completa com:
Dentro de um bloco <checklist_final>:
</framework>
<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-22 | pass→pass | 11,227 | 11,536 | +3% | 1 | 1 | 0% | 2,086 | 3,811 | +83% | 0 | 0 | — |
case-01 | fail→pass | 28,753 | 30,657 | +7% | 1 | 1 | 0% | 5,117 | 7,184 | +40% | 0 | 0 | — |
case-02 | fail→pass | 22,627 | 32,751 | +45% | 1 | 1 | 0% | 4,350 | 7,776 | +79% | 0 | 0 | — |
case-03 | fail→pass | 23,836 | 27,300 | +15% | 1 | 1 | 0% | 4,363 | 6,971 | +60% | 0 | 0 | — |
case-04 | pass→fail | 16,404 | 23,140 | +41% | 1 | 1 | 0% | 3,353 | 6,116 | +82% | 0 | 0 | — |
case-21 | pass→pass | 15,029 | 14,908 | -1% | 1 | 1 | 0% | 2,482 | 4,338 | +75% | 0 | 0 | — |
case-05 | pass→fail | 13,967 | 19,507 | +40% | 1 | 1 | 0% | 2,753 | 5,177 | +88% | 0 | 0 | — |
case-06 | pass→fail | 21,639 | 28,858 | +33% | 1 | 1 | 0% | 3,978 | 7,198 | +81% | 0 | 0 | — |
case-07 | fail→pass | 20,769 | 26,505 | +28% | 1 | 1 | 0% | 3,884 | 6,864 | +77% | 0 | 0 | — |
case-08 | pass→pass | 24,258 | 32,495 | +34% | 1 | 1 | 0% | 4,317 | 7,504 | +74% | 0 | 0 | — |
case-09 | pass→pass | 24,715 | 28,249 | +14% | 1 | 1 | 0% | 4,585 | 6,773 | +48% | 0 | 0 | — |
case-10 | pass→pass | 15,525 | 29,536 | +90% | 1 | 1 | 0% | 2,814 | 5,469 | +94% | 0 | 0 | — |
case-11 | pass→pass | 12,299 | 15,836 | +29% | 1 | 1 | 0% | 2,464 | 4,765 | +93% | 0 | 0 | — |
case-12 | pass→pass | 11,016 | 10,109 | -8% | 1 | 1 | 0% | 1,905 | 3,617 | +90% | 0 | 0 | — |
case-13 | pass→pass | 7,960 | 11,222 | +41% | 1 | 1 | 0% | 1,448 | 3,831 | +165% | 0 | 0 | — |
case-14 | pass→pass | 6,257 | 8,600 | +37% | 1 | 1 | 0% | 1,233 | 3,393 | +175% | 0 | 0 | — |
case-15 | fail→fail | 20,330 | 33,855 | +67% | 1 | 1 | 0% | 3,846 | 7,719 | +101% | 0 | 0 | — |
case-16 | fail→pass | 20,661 | 33,057 | +60% | 1 | 1 | 0% | 4,019 | 7,718 | +92% | 0 | 0 | — |
case-17 | pass→pass | 13,511 | 14,270 | +6% | 1 | 1 | 0% | 2,567 | 4,265 | +66% | 0 | 0 | — |
case-18 | pass→pass | 8,164 | 9,372 | +15% | 1 | 1 | 0% | 1,729 | 3,470 | +101% | 0 | 0 | — |
case-19 | fail→pass | 13,998 | 14,613 | +4% | 1 | 1 | 0% | 2,490 | 4,144 | +66% | 0 | 0 | — |
case-20 | pass→pass | 16,342 | 24,899 | +52% | 1 | 1 | 0% | 3,172 | 6,226 | +96% | 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 +14 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.