voice-update_skill

Overview

This skill provides a quick spoken voice update to users using the pocket-tts-based say script. It’s designed for short, conversational summaries of what the agent accomplished or important status changes. Use it whenever audio feedback improves clarity or confirms completion.

How this skill works

Compose a 1–2 sentence conversational summary of the outcome you want to communicate. Call the bundled say script to send that text to pocket-tts; the script will auto-start the server if needed and play audio via the system audio tool. Optional flags let you select a voice variant when desired.

When to use it

• After finishing a task when a Stop hook requests audio feedback
• When the user explicitly asks for a spoken summary or confirmation
• For brief audible status updates during long-running workflows
• When hands-free or attention-grabbing feedback is helpful
• To confirm high-level outcomes to non-technical stakeholders

Best practices

• Keep the update to 1–2 short sentences focused on outcomes, not implementation details
• Match the user’s tone—be casual if they are casual, professional if they expect formality
• Avoid code, file paths, and technical jargon in the spoken text
• Use the --voice option only when a distinct voice helps clarity or accessibility
• Remember first use may take 30–60s while pocket-tts starts; indicate potential delay if relevant

Example use cases

• "I've updated the configuration and restarted the service." after deploying a change
• Announcing test results: "The test suite is green; I fixed three type errors."
• Confirming task completion in a hands-free environment: "Done! I created the new component and merged it."
• Providing audible alerts for long operations: "Backup complete. All files uploaded."
• Giving stakeholders a non-technical summary after a code refactor: "Refactor finished—performance improved and no API changes."