alfred

Application control — open/launch, close/quit, and switch-to a running app by name. Mock backend. Pure execution.

Drive the user's real browser (Chromium/Brave/Chrome) — open url, web search, read page text, click, type, screenshot, list/switch tabs. Real backend = Playwright connect_over_cdp (attaches to your existing browser); mock for the binding benchmark. Pure execution (slot-filled, no LLM).

Telephony actions — dial a contact/number, redial, hang up, answer. Mock backend (no real telephony). Pure execution.

Unified time control — countdown timers, absolute-time alarms (with optional repeat), and current/world time. The one skill that ACTUALLY fires (systemd-run --user) when ALFRED_CLOCK_REAL=1; mock for the binding benchmark. Pure execution.

Connectivity + UI toggles — wifi, bluetooth, airplane mode, do-not-disturb, dark mode, each on/off. Mock backend. Pure execution.

Manage Docker containers — start/stop/restart, remove, show logs, list running containers. Pure execution, no communication. Mock backend (binding-only) for the thesis benchmark.

Local media processing with ffmpeg — extract audio to MP3, transcode formats, trim segments, capture frames, resize, and concatenate. Real ffmpeg binary; deterministic, offline, no network. Binding-only in the thesis benchmark.

Named focus profiles — turn work/sleep/personal focus on, turn it off, check status. Mock backend. Pure execution.

Control Home Assistant devices — turn entities on/off/toggle, read state, set thermostat temperature and light brightness, and activate scenes. Pure execution, no communication. Mock backend (binding-only) for the thesis benchmark.

Generic OS media transport — play/pause/next/previous and player volume (playerctl). Mock backend for binding-only. Pure execution.

Manage systemd service units — start/stop/restart, check status, enable/disable on boot. Pure execution, no communication. Mock backend (binding-only) for the thesis benchmark.

Control Spotify playback — play/pause, next/previous track, search the catalog, add tracks to playlists, and set volume. Mock backend (binding-only) for the thesis benchmark; no device required.

Control the local machine — volume up/down/mute/set, screen brightness, lock screen, suspend. Pure execution, no communication. Mock backend (binding-only) for the thesis benchmark.

Download from YouTube with yt-dlp — full video, audio-only MP3, subtitles/transcript, metadata JSON, whole playlists, and thumbnails. Real yt-dlp binary (network). Binding-only in the thesis benchmark.

Read and change the phone's settings (Pixel-style) — connectivity, display, device, and per-app settings — through the `settings` script. Pure execution: explore, then set the value the user asked for.

Change Android device settings via the `settings` script (adb-style put/get/list across system/secure/global namespaces). Inspect with list/get, then put the value.