From vanguard-frontier-agentic
Classifies and routes Legal or HR matters to the right specialist agent, handles cross-domain parallel review, and resolves agent conflicts with controlled handoffs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/vanguard-frontier-agentic:legal-hr-routing-protocolThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill defines how a Legal or HR matter is classified, routed to the right
This skill defines how a Legal or HR matter is classified, routed to the right specialist agent, and coordinated when it crosses both domains. It exists so agents never work in silos when risk crosses a domain boundary, and so every handoff is controlled and auditable rather than free-form. It does not give legal or HR advice; routing is a recommendation that a human owner confirms.
legal-hr-case-capsule. No free-form agent chatter.do_not_do_list.Fifteen recurring cross-domain scenarios and their agent sets are defined in
references/handoff-matrix.md. Each row names the
primary agent, the secondary agents, the escalation gate, and the mandatory
do_not_do items.
When Legal and HR agents disagree, follow this order and stop at the first step that is unmet:
unclassified rather than guessing a specialist.npx claudepluginhub raishin/vanguard-frontier-agentic --plugin vanguard-frontier-agenticTriages HR and employment-relations risk for enterprise People functions. Surfaces risks, evidence gaps, decision options, and escalation paths for HR actions and complaints.
Interactive setup for employment-law jurisdiction mapping. Reads handbooks and termination memos, builds an escalation table, and configures CLAUDE.md. Use on fresh install or with --redo.
Routes legal requests to specialists: legal counsel for IP/corporate, compliance-officer for GDPR/SOC2, contract-manager for NDAs/SLAs, paralegal for docs. Triggers on contract review, privacy policy, regulatory queries.