一键导入
cross-practice-coordination
Coordinate handoffs when work spans multiple practice areas (e.g., M&A diligence touching IP + employment + privacy).
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Coordinate handoffs when work spans multiple practice areas (e.g., M&A diligence touching IP + employment + privacy).
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer, distributor, authorized representative, product manufacturer) and risk tier (prohibited, high-risk, limited, minimal, GPAI, GPAI+systemic).
Run an AI impact assessment — structured intake, risk analysis, regulatory classification per regime in scope, policy consistency diff, and recommendation with conditions.
Run the cold-start interview — learns your AI governance practice and writes `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md` from your AI policy, a reference impact assessment, and key vendor AI agreements.
Guided customization of your AI governance practice profile — change one thing without re-running the whole cold-start interview.
Manage matter workspaces — new, list, switch, close, or detach (practice-level).
Keep the AI policy current with practice — weekly sweep of saved AIAs, triage results, and vendor reviews to find policy drift, or direct query for a proposed new AI practice.
| slug | cross-practice-coordination |
| name | Cross-Practice Coordination |
| description | Coordinate handoffs when work spans multiple practice areas (e.g., M&A diligence touching IP + employment + privacy). |
| version | 0.1.0 |
| metadata | {"sources":[{"mode":"port-original","author":"Jannes Stubbemann","added_in":"0.1.0"}]} |
Port-original skill. Hand-authored for this Agent Company; not from upstream
anthropics/claude-for-legal. Owned by the CEO role.
After intake-triage flagged the matter as multi-practice (2+ specialists from different practice areas). The CEO uses this skill to sequence handoffs so specialists don't block each other, duplicate work, or — worst — produce work product that contradicts another practice's position on the same matter.
intake-triage (primary agent, secondary agents, deadline, priority, jurisdiction, privilege posture).A coordination plan, recorded on the matter:
sequence:
- step: 1
agent: <agent-slug>
skill: <skill-slug>
inputs: <what they need to start>
outputs: <what they produce, by when>
privilege: <how privilege is preserved across this handoff>
- step: 2
agent: <agent-slug>
...
checkpoints:
- after_step: 1
review: <what the CEO checks before unblocking step 2>
deconflict_protocol: <rule for resolving disagreements between specialists>
final_deliverable_owner: <agent that owns the deliverable to the requester>
human_signoff_required_before: [<artifact>, ...]
corporate-legal produces the diligence memo + disclosure schedule.ip-legal produces the IP portfolio + clearance findings; employment-legal produces the workforce diligence (restrictive covenants, leave-tracker exposure, open investigations); privacy-legal produces the processing-activity inventory and DPA-stack review.Write the coordination plan to the matter as a comment / note. Enqueue step 1's specialist skill. After each checkpoint, the CEO re-reviews against the plan; only then does step N+1's specialist get unblocked.