メニュー
Send a Jarvis-voiced TTS announcement to a Sonos speaker in the house. Uses Chatterbox for voice generation. Use when the user wants to send a spoken message to someone in another room via a Sonos speaker.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/lancejames221b/stark-skills --skill sonos-announceコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Mark a logical phase completion in haivemind. More formal than /snapshot — used at step/phase boundaries in multi-phase work. Creates a named, resumable point that /continue can restore from. Triggered by /checkpoint, "checkpoint this", "mark this as a checkpoint", or at phase boundaries in long-running tasks.
Run the Qwen Code CLI as a one-shot bounded executor in a plan/do/verify loop. A frontier model (or you) plans the next bounded step and verifies the result; qwen-do makes a local model do exactly that one step, smoke-test first, then stop. Use when you want a cheap local model to do grunt coding while a smarter orchestrator keeps it on rails.
Scan git commits for PII, credentials, API keys, and passwords before they are pushed. Automatically gates commits via a pre-commit hook. Use when installing PII scanning on a repo, manually scanning a file or diff for credentials, or when a commit is blocked by the hook and remediation is needed. Triggers on "scan for PII", "check for credentials", "install PII guard", "pii hook", or when a commit is blocked by a PII check.
SOC 職業分類に基づく
SKILL.md を表示中
| name | sonos-announce |
| description | Send a Jarvis-voiced TTS announcement to a Sonos speaker in the house. Uses Chatterbox for voice generation. Use when the user wants to send a spoken message to someone in another room via a Sonos speaker. |
| category | voice |
| runtimes | ["claude"] |
| pii_safe | true |
| tier | FRIDAY |
| triggers | ["tell [name] to","announce","say on the sonos","send a message to the kitchen","send a message to the bedroom","let her know","let him know","message the speaker","play on sonos","say upstairs","say downstairs"] |
Send a spoken message to any Sonos speaker in the house using the Jarvis (Chatterbox) voice.
"Jarvis, tell [name] to check their phone." "Say on the kitchen speaker: dinner is ready." "Announce upstairs that I'm heading out." "Send a message to the bedroom."
Speakers are configured in .env:
| Variable | Description |
|---|---|
SONOS_DOWN_IP | Downstairs speaker IP (e.g. kitchen) |
SONOS_UP_IP | Upstairs speaker IP (e.g. bedroom) |
SONOS_DEFAULT | Default target: up, down, or all |
GAMEZ_IP | IP of the machine serving the audio file |
GAMEZ_PORT | Port for the audio HTTP server (default: 8765) |
CHATTERBOX_HOST | SSH alias for the machine running Chatterbox TTS |
CHATTERBOX_URL | Chatterbox endpoint (default: http://localhost:3340/tts) |
Location is inferred from natural language:
| User says | Target |
|---|---|
| "upstairs", "bedroom", "bathroom" | up |
| "downstairs", "kitchen", "living room" | down |
| "everywhere", "all speakers", "the whole house" | all |
| (no location) | $SONOS_DEFAULT (default: down) |
sonos-say <up|down|all> "message"
See SETUP.md for installation.
| User says | Jarvis announces |
|---|---|
| "Tell [name] to check their phone" | "Hey [name], [user] was wondering if you would check your phone." |
| "Let her know dinner is ready" | "Hey [name], [user] wanted to let you know that dinner is ready." |
| "Tell her I'll be there in 5" | "Hey [name], [user] will be there in about five minutes." |