settings

Configure assistant voice settings and navigate system preference panes.

1|Updated Mar 30, 2026
One-click install
npx skills add https://github.com/Logarn/Worklin-ai --skill settings-logarn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: settings
Source: https://github.com/Logarn/Worklin-ai/tree/main/assistant/src/config/bundled-skills/settings
Command: npx skills add https://github.com/Logarn/Worklin-ai --skill settings-logarn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Users need a conversational way to adjust their assistant's voice behavior and reach the right settings screens without hunting through menus or editing configuration files by hand. ## Core Features & Use Cases - Voice Configuration Updates: Change the TTS provider (ElevenLabs, Fish Audio, Deepgram, xAI), set voice IDs, adjust the push-to-talk activation key, and set the conversation timeout, with changes persisted to config and broadcast to the desktop client. - System Settings Navigation: Open macOS System Settings panes directly (Microphone or Speech Recognition privacy) to guide users through granting permissions. - In-App Settings Navigation: Jump the Vellum settings panel to a specific tab such as Voice, Models & Services, or Permissions & Privacy. - Use Case: A user says "switch my voice to Fish Audio" and the assistant validates the provider, updates the config, and applies the change immediately. ## Quick Start Ask the assistant to change the TTS provider to Deepgram and set the conversation timeout to 30 seconds.

Frequently Asked Questions about settings

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I change the TTS provider for my voice assistant?▼

Use the voice_config_update tool with the tts_provider setting and a value of elevenlabs, fish-audio, deepgram, or xai. The change is validated against the provider catalog, persisted to services.tts.provider, and takes effect immediately.

How do I set an ElevenLabs voice ID for speech output?▼

Call voice_config_update with the tts_voice_id setting and an alphanumeric ElevenLabs voice ID. The value is validated for format, saved to services.tts.providers.elevenlabs.voiceId, and broadcast to the desktop client.

What conversation timeout values are supported?▼

The conversation_timeout setting accepts only 5, 10, 15, 30, or 60 seconds. Any other numeric value is rejected with a validation error listing the valid options.

Can the assistant open macOS privacy settings for microphone access?▼

Yes, the open_system_settings tool opens the Microphone or Speech Recognition privacy pane using the x-apple.systempreferences URL scheme. The user must still toggle the permission on manually in System Settings.

Why does a voice setting update fail with a validation error?▼

Updates fail when the setting name is unknown, the voice ID contains non-alphanumeric characters, the timeout is not an allowed value, or the provider is not in the catalog. The error message lists the valid options for correction.