name: workflow/escalate-to-human description: Escalates a session issue to a human reviewer. version: 0.1.0 status: experimental family: workflow role: Strategist allowed_tools:
- list_dir
- write_to_file policies:
- E.16 RoC-Autonomy
- A.15.1 U.Work outputs:
- EscalationRecord
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.
chat Comments (0)
Sign in to join the discussion and leave a comment.
Skill Details
GitHub Stars
0
GitHub Forks
0
Created
Jan 2026
Last Updated
5 months ago
tools
tools security
Related Skills
Build your own?
Join 12,000+ developers contributing to the Claude ecosystem.
No comments yet. Be the first to share your thoughts!