Nudge Coach
AdvisoryAudited by VirusTotal on Mar 28, 2026.
Overview
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.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A completion or failure decision may result in proof or failure reasons being sent to other people configured in Nudge.
The skill documents Nudge task commands that can mark outcomes and send messages to accountability targets. This is aligned with the stated accountability purpose, but it is high-impact enough that users should understand when those commands are run and who receives the messages.
Always include a failure reason when running `nudge task fail`... This reason is included in the punishment message sent to targets.
Before using the skill, confirm the Nudge recipients, punishment settings, and whether you want explicit confirmation before task-complete or task-fail actions are executed.
The agent may use strong pressure language instead of a neutral or supportive tone.
The skill explicitly uses pressure, urgency, and potential social exposure as motivational techniques. This is disclosed and related to accountability coaching, but users should be aware of the tone and psychological framing.
Loss Aversion... GOOD: "Your secret is about to be revealed to everyone"
Use this skill only if you want a firm accountability style; adjust or avoid it if secret-reveal or high-pressure messaging is not acceptable.
The agent may not simply accept cancellation, completion, or negotiation requests without questioning them.
The skill tells the agent to challenge the user’s immediate claim and require verification. This is purpose-aligned for an accountability coach, but it intentionally changes the interaction from simple compliance to enforcement.
Never accept "I'm done" at face value. Ask: "Show me."
Install only if you want the agent to enforce verification and accountability rather than always complying with immediate requests.
Personal motivations, track record, proof, and failure reasons may appear in future coaching messages or messages to targets.
The skill relies on stored task history and personal motivation text as context for future messages. This is expected for accountability coaching, but it means personal history and motivations may be repeatedly reused.
Use `nudge task history` to reference past performance... The `why` field is the most powerful motivational tool. Use it at EVERY touchpoint
Avoid putting highly sensitive information in Nudge fields unless you are comfortable with it being reused in reminders, completion messages, or failure messages.