Install
openclaw skills install employeeCreate and manage virtual AI employees with persistent memory, defined roles, and graduated autonomy. Hire, train, and delegate tasks to specialized workers.
openclaw skills install employeeEmployees live in ~/employee/ with per-employee folders. See employee-template.md for setup.
~/employee/
├── registry.json # Index of all employees + status
├── employees/
│ └── {name}/
│ ├── employee.json # Role, permissions, stats
│ ├── memory/
│ │ └── context.md # Persistent learnings
│ └── logs/ # Work history by date
└── shared/
└── protocols.md # Common instructions
| Topic | File |
|---|---|
| Setup templates | employee-template.md |
| Autonomy levels | autonomy.md |
| Task routing | routing.md |
| Lifecycle commands | lifecycle.md |
employee.json → role and permissionsmemory/context.md before every taskemployee.json| Level | Behavior |
|---|---|
| shadow | Watches, doesn't act (onboarding) |
| draft-only | Creates drafts, human sends |
| review | Acts, human approves before external effect |
| autonomous | Full delegation within permissions |
See autonomy.md for promotion criteria.
canSpawn and canMessage flagsWhen request arrives:
registry.json roles → suggestrouting.md for auto-delegation rulesEach employee provides:
| Command | Action |
|---|---|
| hire {name} as {role} | Create employee |
| train {name} on [docs] | Add to memory |
| evaluate {name} | Performance review |
| promote/demote {name} | Change autonomy |
| retire {name} | Archive |
See lifecycle.md for full command reference.
registry.json tracks all employees + status (active/paused/retired)