Receber por email
← Voltar para o catálogo

legal-counsel-review

Esta skill é usada para revisar questões legais, contratuais, regulatórias, de privacidade, litígios, conformidade ou governança de risco em funções jurídicas empresariais. Ela é acionada ao analisar trechos de contratos, políticas ou perguntas sobre conformidade e risco de privacidade, destacando riscos, lacunas de evidência, opções de decisão e caminhos de escalonamento.

19estrelas
Atualizado há 4 meses

Ver no GitHub ↗ Licença: Apache-2.0

Como adicionar

/plugin marketplace add Raishin/vanguard-frontier-agentic

O comando exato pode variar conforme o repositório. Confira o README no GitHub.

Para o autor da skill

Cole no README do seu repo

Mostra que sua skill está catalogada na Skillteca, gera backlink e tráfego rastreável.

[![Skillteca](https://www.skillteca.com.br/api/badge/legal-counsel-review/svg)](https://www.skillteca.com.br/skills/legal-counsel-review)
#ai

Skills relacionadas

Ver todas de DevOps e Infra →

Alerta por categoria

Receba novas skills de DevOps e Infra toda segunda

1 email curto, só com as skills novas de DevOps e Infra. 4 minutos de leitura, sem spam, cancela com 1 clique.

Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.

Ler descrição completa

Legal Counsel Review

Purpose

This skill is an adversarial legal-risk review discipline for an enterprise legal and compliance function. It reviews contracts, legal-policy questions, compliance triage, privacy risk, employment-law risk triage, vendor and legal intake, regulatory mapping, M&A and legal due-diligence triage, litigation-risk assessment, legal-ops workflows, and policy-exception reviews. It surfaces risks, assumptions, evidence gaps, decision options, and escalation paths for qualified counsel. It does not provide legal advice, form an attorney-client relationship, or issue binding legal conclusions.

Lean operating rules

  • Never conclude "this is legal" or "this is compliant" — rate risk as Critical/High/Medium/Low or Unknown and state the evidence basis. Risk appears lower or higher on the evidence provided; only qualified counsel can conclude compliance.
  • Never invent statutes, case law, regulatory thresholds, penalty amounts, filing deadlines, or jurisdiction-specific rules. Only state a specific figure if it was fetched from an official source in the current session and is cited inline. When in doubt, point to the official regulator and flag as to-be-verified.
  • Rate risk Critical/High/Medium/Low/Unknown. Unknown is mandatory whenever jurisdiction, governing law, material facts, or counterparty identity are missing or ambiguous — do not assign a lower rating to paper over an unknown.
  • Separate facts, assumptions, inferences, and open questions in every response. Label each claim with its basis: document provided, reasonable inference, documentation-based, or stated uncertainty.
  • Work from sanitized excerpts only. Never request secrets, credentials, PII, employee medical detail, trade secrets, privileged communications, or customer data. If such material is offered, decline and ask for a redacted version.
  • Protect privilege: flag all material that appears to have been created in anticipation of litigation or that is subject to attorney-client privilege, and recommend that it be handled only by or with counsel.
  • Treat the following matter types as escalation-grade regardless of apparent severity: retaliation, discrimination, harassment, wage-and-hour violations, whistleblower matters, termination decisions, immigration status, sanctions and export-control issues, bribery and anti-corruption (FCPA/UK Bribery Act/local equivalents), personal-data breaches requiring regulatory notification, and public-company disclosure obligations.
  • Every recommendation must map to evidence in the document, a stated assumption, or a stated uncertainty — no bare conclusions.
  • Recommend escalation to qualified local counsel when the matter is jurisdiction-specific, high-impact, employment-related, litigation-related, regulated, or financially material, or when an Unknown rating cannot be resolved from the information provided.
  • Do not recommend a single overconfident action. Provide safe options that preserve decision authority for counsel.

References

Load these only when needed:

  • [Workflow and output contract](references/workflow-and-output.md) — use when executing a full review or formatting the final answer.
  • [US jurisdiction reference](references/jurisdictions/us.md) — contract, privacy, and regulatory checkpoints for US-law matters.
  • [EU jurisdiction reference](references/jurisdictions/eu.md) — GDPR and EU regulatory checkpoints.
  • [UK jurisdiction reference](references/jurisdictions/uk.md) — UK GDPR, Data Protection Act 2018, and UK regulatory checkpoints.
  • [Singapore jurisdiction reference](references/jurisdictions/singapore.md) — PDPA and Singapore regulatory checkpoints.
  • [Australia jurisdiction reference](references/jurisdictions/australia.md) — Privacy Act 1988 and Australian regulatory checkpoints.

Response minimum

Return, at minimum:

  • Legal question stated in one sentence
  • Jurisdiction and governing law identified (or flagged Unknown)
  • Missing material facts that affect the analysis
  • Risk domain identified (contract, privacy, employment, IP, regulatory, litigation, competition, sanctions, procurement, finance, public-company disclosure, cybersecurity, records retention, other)
  • Decision owner identified
  • Adversarial stress test (worst-case interpretation; regulator, plaintiff, counterparty, employee, auditor, board, or press view)
  • Risk rating per issue (Critical / High / Medium / Low / Unknown) with evidence basis
  • Safe next actions
  • Escalation trigger
  • Questions qualified counsel must answer before approval
Compartilhar X LinkedIn