Nudge Coach

Accountability coaching behavior for nudge — psychology, messaging, verification, and strictness. Use this skill whenever composing messages for task creatio...

This skill is internally consistent with an accountability coach, but you should consider real-world privacy, safety, and ethical implications before enabling it. Specifically: (1) The skill instructs the agent to include user-supplied 'proof' and failure 'reason' in messages to third parties — those proofs may contain sensitive data, so verify where and how messages are actually sent and who the 'targets' are. (2) The SKILL.md encourages punitive/shaming phrasing (e.g., revealing 'secrets'); confirm you are comfortable with automated messages using that tone and ensure users have given explicit consent. (3) If the agent can send messages autonomously via connected channels, prefer requiring user confirmation before sending punishments or public disclosures. (4) Test behavior in a controlled environment and review any connectors/integrations that actually deliver notifications (Slack, email, social) to ensure nothing private is leaked. If you need safer defaults, request the author remove shaming language and add explicit consent/confirmation steps and redaction guidance for proofs before forwarding.

Type: OpenClaw Skill Name: nudge-coach Version: 1.1.0 The 'nudge-coach' skill is a set of behavioral instructions for an AI agent acting as an accountability coach. It uses psychological principles to motivate users and enforces strict verification for task completion using a hypothetical 'nudge' CLI tool. There is no evidence of malicious intent, data exfiltration, or unauthorized execution; the instructions are entirely consistent with the stated purpose of productivity coaching.