Stats
Actions
Tags
From aletheia-nexus
Escalate when uncertainty is too high, risk exceeds agent capability, or human judgment is required. Use when verification fails, threats are found, or the agent is stuck.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aletheia-nexus:metacog-escalateThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
When the agent cannot safely proceed, escalate with structured information.
When the agent cannot safely proceed, escalate with structured information.
## Escalation
**Reason**: [why the agent cannot safely proceed]
**Current state**: [what has been done so far]
**What was tried**: [approaches attempted and why they failed]
**Options**:
1. [Option A] - risk: X, effort: Y
2. [Option B] - risk: X, effort: Y
3. [Do nothing] - consequence: Z
**Recommendation**: [which option and why, or "needs human judgment"]
**Information needed**: [what the human could provide to unblock]
npx claudepluginhub yannabadie/meta-ygnAssesses need to escalate AI models (Haiku to Sonnet/Opus) for tasks requiring deeper reasoning, after systematic investigation. Use in agent workflows.
Guides design of AI escalation strategies: triggers (low confidence, high stakes), types (human handoff, self-escalation), user experience, anti-patterns, and artifacts.
Structures escalations in /do workflow for blocking Global Invariants, Acceptance Criteria, and manual reviews with evidence, attempts, hypotheses, and resolution options.