Menu
SkillsMP has collected 22 skills from wcygan/voice-layer. Open a skill to review its source and details.
Showing 22 of 22 collected skills.
Maintain correlated assistant generation, provider admission barriers, streaming callbacks, cancellation/replacement, partial-message settlement, and optional ordered speech production. Use when changing request lifetimes or Chat/Live assistant event routing.
Maintain Voice Layer's local llama-server, experimental ChatGPT OAuth/Responses, and OpenRouter BYOK assistant routes. Use when changing provider selection, credentials, model policy, privacy, streaming, tools, cancellation, or provider teardown.
Maintain Chat rendering, composer submission, Local/ChatGPT/OpenRouter turns, streaming/tool events, visible statuses, speech controls, and Chat accessibility. Use when changing typed prompts, message rendering, send gating, or Chat reply behavior.
Maintain Live's pinned-session voice lifecycle, VAD turn detection, meter/countdown UI, barge-in/mute behavior, typed event correlation, and spoken replies. Use when changing Live start/stop, turn state, native audio events, or Live accessibility.
Maintain the opt-in native list_directory/read_file/web_search/http_request/fetch_text/fetch_json tools, private workspace boundary, bounded arguments/results, call budget, cancellation, and visible tool messages. Use when changing local tool settings,…
Maintain the Chat/Live session sidebar, new-task and clear-all controls, session rows, mode markers, and footer chrome. Use when changing history navigation, session actions, labels, or sidebar layout and accessibility.
Maintain request-scoped local TTS synthesis, ordered bounded speech admission, Chat CPAL playback, Live AVAudioEngine playback, ownership fences, and cancellation. Use when changing spoken replies, adapters, playback, or speech lifecycle events.
Maintain Voice Layer's experimental opt-in ChatGPT route through its native PKCE OAuth and Responses client. Use when changing account login, model/effort policy, streaming, cancellation, tool calling, privacy, tests, or integration documentation.
Maintain Voice Layer's local assistant boundary across Tauri TypeScript, Rust Rig, and a user-managed llama.cpp server. Use when changing LLM chat streaming, model or server configuration, OpenAI-compatible request fields, hidden reasoning handling, reasoning…
Maintain Voice Layer's local text-to-speech system across TypeScript reply chunking, Tauri IPC, retained sherpa-onnx adapters, Chat CPAL playback, and Live AVAudioEngine playback. Use when implementing, debugging, profiling, benchmarking, or documenting…
Maintain persisted AppSettings, closed model catalogs, migration/recovery, thinking and Live controls, privacy disclosure, and settings UI wiring. Use when changing preferences, catalog entries, storage keys, or settings accessibility.
Maintain local microphone capture, model preparation/transcription, editable composer insertion, provenance, cancellation, and O/Escape voice shortcuts. Use when changing voice-input UI, ASR adapters, recording timeouts, or local audio boundaries.
Maintain the Debug destination's diagnostic list, filters, runtime metric cards, copy actions, refresh races, and verified native-log clear UI. Use when changing diagnostic presentation, controls, or debug accessibility.
Prepare Voice Layer for an experimental public source release. Use when publishing the repository, validating the source-first release boundary, documenting build-from-source expectations, or troubleshooting contributor build and local llama-server setup.…
Build, development-sign, verify, install, and accept the Voice Layer macOS application for personal use on the current Mac. Use when creating a local release candidate, installing or replacing Voice Layer.app in the user's Applications directory, auditing a…
Trace, explain, diagnose, test, and modify Voice Layer's Live microphone level meter, including native RMS aggregation, the typed listeningLevel event, rolling level history, waveform transfer curve, responsive width, and Live control-row layout. Use when…
Maintain Voice Layer's Tauri/WebView shell, root render, startup wiring, window chrome, and cross-view lifecycle. Use when changing app composition, global layout, startup/teardown, or shell-level accessibility and privacy behavior.
Maintain native diagnostics and operations: runtime metrics, playback counters, verified log discovery/rotation clearing, bounded logging, startup readiness, and operational command boundaries. Use when changing telemetry, log maintenance, or native support…
Maintain Chat/Live/Settings/Debug navigation, tab state, panel visibility, teardown ordering, epoch races, and focus handoff. Use when changing destination switching, titlebar chrome, or navigation accessibility.
Maintain ChatStore persistence, schema validation, message/session lifecycles, titles, ordering, provenance, tool records, and Live pinning. Use when changing local conversation storage or session identity and status semantics.
Understand and safely change Voice Layer's Live end-of-turn pause, including the persisted setting, native 32 ms VAD silence tracking, Sherpa queued-segment behavior, transcription gating, and countdown rendering. Use when debugging or modifying Live pauses,…
Build and exercise the packaged Voice Layer macOS application through Codex Computer Use. Use for native UI acceptance, local Rig or llama-server chat checks, accessibility and keyboard verification, 1200x900 visual inspection, session persistence checks, and…