escalation
SolidEscalate unresolvable or sensitive requests to a human agent by recording an escalation entry. Use when the user asks to speak to a human, the bot cannot answer confidently, the request involves financial, legal, or security concerns, a safety issue is detected, or the user is frustrated after repeated failures.
Install
Quality Score: 87/100
Skill Content
Details
- Author
- 0xranx
- Repository
- 0xranx/golembot
- Created
- 5 months ago
- Last Updated
- 2 days ago
- Language
- TypeScript
- License
- MIT
Similar Skills
Semantically similar based on skill content — not just same category
human-escalation
Recognize when to stop autonomous work and escalate decisions, ambiguity, or risk to a human.
escalation-governance
Assess whether to escalate models. Use when evaluating reasoning depth.
escalate
Escalate the task to a stronger subagent (opus; fable only on explicit user request) via the Agent tool when its stakes or difficulty exceed Sonnet's default — UI work, a stuck bug, hard reasoning, security-sensitive changes. Say 'escalate this' / 'eskaliere das'.