Entrevista conversacional breve (5-10 minutos) que aprende como sua equipe opera em banking/fintech/cripto — estrutura organizacional, produtos, reguladores, limites de risco — e escreve seu perfil de prática em CLAUDE.md.
How this skill is triggered — by the user, by Claude, or both
Slash command
/banking-fintech-legal:cold-start-interview [optional: --redo][optional: --redo]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Your first time using this plugin, it interviews you conversationally (no forms, no jargon) to learn your practice — how your team is structured, what products you handle, which regulators matter, where the risk ceiling is. Once. Then every skill in this plugin reads that profile before doing work.
Your first time using this plugin, it interviews you conversationally (no forms, no jargon) to learn your practice — how your team is structured, what products you handle, which regulators matter, where the risk ceiling is. Once. Then every skill in this plugin reads that profile before doing work.
If you're re-running (you've onboarded new people or shifted product focus), pass --redo to re-interview.
This is a conversation, not a survey. I'll ask ~5-8 open questions. Your answers populate ~/.claude/plugins/config/claude-for-legal/banking-fintech-legal/CLAUDE.md — a living document you edit directly when things change. You don't fill out a form; you tell me how your team actually works.
I'll ask about:
That's it. Your answers feed the playbook sections in CLAUDE.md — interest caps, VASP classification rules, Open Finance consent models, etc. When you don't have a position on something yet, that stays blank in the template; skills will ask you to fill it in as needed.
After the interview:
/banking-fintech-legal:payment-institution-compliance, it doesn't ask "what type of institution are you" because it already read CLAUDE.md.Interview takes ~5-10 minutes. Start with: /banking-fintech-legal:cold-start-interview
Guides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.
Dispatches multiple subagents concurrently for independent tasks without shared state. Use when facing 2+ unrelated failures or subsystems that can be investigated in parallel.
npx claudepluginhub bossmann007/claude-legal-br --plugin banking-fintech-legal