workflowescalate-to-human
Escalates a session issue to a human reviewer.
Installation
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
View source ↗GuidesSkill instructions
Workflow: Escalate to Human
1. Context
This skill records a human escalation request for a session issue, capturing severity, target, and related artifacts.
2. Inputs
- context (required): Bounded context name (safe path segment).
- session_id (required): Session identifier (safe path segment).
- reason (required): Escalation reason or trigger summary.
-
severity (optional): Escalation severity (
low,medium,high). - target (optional): Escalation target (default: human).
- requested_by (optional): Requester label.
- artifacts (optional): Semicolon-delimited artifact paths.
- notes (optional): Freeform notes.
- agent_model (optional): Agent model identifier.
- role_assignment (optional): RoleAssignment for U.Work logging (default: Strategist).
- decisions (optional): Semicolon-delimited DRR ids/paths.
- timestamp_start (optional): ISO-8601 timestamp for deterministic output.
3. Outputs
-
runtime/contexts/<context>/escalations/<session_id>.<n>.escalation.md
4. Procedure
- Validate inputs and compute the next escalation index.
- Write the escalation record with status open.
- Emit U.Work via
telemetry/log-workwhen available.
Examples
Read the usage examples in the source repository.
View source ↗Source history
- Indexed on
- 2026-01-20
- Index updated
- 2026-01-26
- Branch
- main
Index and sync dates describe this directory. View the source repository for code history.
GitHub ↗chat Comments (0)
Sign in to join the discussion and leave a comment.
No comments yet. Be the first to share your thoughts!