Stealth

What it does

The stealth skill allows AI agents to operate with reduced visibility and impact. It enables the agent to avoid detection during tasks, minimize unwanted attention, and execute actions discreetly. This is achieved by carefully managing communication patterns and interaction styles.

When to use it

• Data Gathering: When collecting information from sensitive sources where overt querying could trigger alarms or restrictions.
• Automated Reporting: To generate reports without disrupting ongoing processes or alerting individuals involved.
• System Monitoring: For quietly observing system behavior and identifying anomalies without generating noise in logs.
• Negotiation Support: To analyze communication patterns during negotiations and suggest subtle adjustments for improved outcomes.

Key capabilities

• Reduced verbosity in communications
• Mimicry of natural language patterns
• Discreet data retrieval
• Minimized interaction footprint

Example prompts

• "Analyze this email thread and summarize the key decisions, but do so without alerting any participants."
• "Monitor server logs for unusual activity, but avoid generating excessive log entries yourself."
• "Draft a response to this customer complaint that is polite and helpful, while avoiding language that might escalate the situation."

Tips & gotchas

The effectiveness of stealth depends on careful prompt engineering. Overly aggressive attempts at concealment can be counterproductive and raise suspicion.