Email Triage

Zero-trust email triage — prioritize inbox by sender trust tier, not arrival order. Surfaces paying customers immediately, batches newsletters, and applies a...

This skill appears coherent and low-risk: it provides heuristics for prioritizing email and doesn't ask for credentials or install code. Before enabling it, confirm what your agent/runtime already exposes (email metadata, thread context, known contacts, calendar/meeting signals) because the skill relies on those signals — if the runtime has broad mailbox access, the agent will process your email data to apply these rules. If you have privacy concerns, test the skill on a limited or non-sensitive mailbox first, and consider restricting the agent's permissions or disabling autonomous invocation for this skill in your agent settings.

Type: OpenClaw Skill Name: zero-trust-email-triage Version: 0.1.2 The skill provides instructional logic for an AI agent to prioritize emails based on sender trust tiers rather than arrival order. It includes specific guidance on identifying high-priority contacts versus noise and explicitly warns against common social engineering tactics like self-claimed urgency or phishing-style notifications. There is no executable code, and the instructions are well-aligned with the stated purpose of email triage without requesting unauthorized access or data exfiltration (SKILL.md).