ae-automation

AE Automation

See command risks. Read the command contract before writing or executing an automation. Use ae-cli automation --help and leaf help to discover flags.

1. Resolve the host and space. A local user signs in with ae-cli auth login; a sandbox uses the current conversation user's injected CLI token, never a shared sandbox's user binding. Pass --agent-space-id when the user identifies a space. Without an explicit space, the CLI inherits the current AgentSpace from its runtime context, working directory or verified current conversation; only a local invocation without space context uses the personal default. Show the resolved space when it matters.
2. Discover the automation with automation list and inspect automation get. Use the returned IDs; names are not unique.
3. For creation, select an Agent or team through the corresponding discovery commands. Match configuration to the target type. Use --weekdays or --days-of-month JSON arrays for multiple days with one time; skip dates absent in a month. For the actual last day of every month use --days-of-month '["L"]', or combine it with dates, e.g. '[1,15,"L"]'; overlapping selections execute only once. Both Agent and Agent Team accept result notifications. Confirm the complete configuration before creation; save only the recurring task instructions as --message, never the automation-creation guide. Preview writes with --dry-run when useful; the CLI shows a redacted request and asks the server to validate authentication, space, permissions, target state, fields, and idempotency without applying the operation.
4. Execute the requested operation. Deleting an automation or stopping an execution requires confirmation; use --yes only when the user already authorized that action. In a non-interactive shell, these operations fail immediately unless global --yes is present.
5. Read the returned run ID, then automation runs result. Report acceptance separately from completion. Use --wait only when the user needs the final outcome now.

Results are read from the server and work outside the sandbox. This skill does not read complete conversations or continue a chat. Never infer an output from a different execution sharing the same conversation.