菜单
Send voice messages and text to Telegram chats via the telegram CLI. Use when sending audio as a Telegram voice message or checking chat config.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Schedules and runs cron jobs and the nanika publishing pipeline via scheduler CLI. Use when scheduling jobs, managing cron tasks, running the daemon, checking job history, or setting up the daily publishing pipeline.
Obsidian vault CLI — read, write, search, capture, triage, enrich, and ingest into the vault at ~/.alluka/vault/. Prefer this CLI over the Write tool for vault paths so the search index, frontmatter schema, and triage hooks stay in sync — plain Write still works and the memory system reads any valid markdown at the canonical paths regardless of how it was produced. Use when user asks about notes, vault, captures, inbox triage, note search, or importing scout/learnings data.
Full article pipeline — from topic research to Substack draft. Scouts trending intel, writes or selects an article, generates intaglio art via Google Flow, creates manifest, and cross-posts to Substack. Use when creating, illustrating, or publishing articles.
Telegram and Discord channel integration for the orchestrator. Handles inbound messages as orchestrator commands and pushes mission lifecycle events back.
Handles inbound Telegram messages as orchestrator commands when running with --channels plugin:telegram@claude-plugins-official
Send native voice messages and text to Discord channels via the discord CLI. Use when sending audio as a Discord voice message or checking channel config.
| name | telegram |
| description | Send voice messages and text to Telegram chats via the telegram CLI. Use when sending audio as a Telegram voice message or checking chat config. |
| allowed-tools | Bash(telegram:*) |
| argument-hint | send-voice-message --chat <id> --audio <path> | reply --chat <id> --message <text> |
Sends audio files as Telegram voice messages (OGG/Opus with duration) and text messages to configured chats.
Config: ~/.alluka/channels/telegram.json — bot token and optional chat ID list.
elevenlabs generate, pass the output as a voice messageSend an audio file as a Telegram voice message. Handles conversion to OGG/Opus, waveform generation, and duration extraction automatically.
telegram send-voice-message --chat <chat-id> --audio /path/to/audio.mp3
telegram send-voice-message --chat <chat-id> --audio /path/to/audio.ogg --json
Supported input formats: mp3, ogg, wav, m4a, webm (any format ffmpeg can decode)
Requirements: ffmpeg in PATH (brew install ffmpeg)
Send a plain text message to a Telegram chat.
telegram reply --chat <chat-id> --message "Hello from nanika"
telegram reply --chat <chat-id> --message "Mission complete" --json
JSON-native subcommands for dashboard and agent use.
telegram query status --json # bot token status, chat count
telegram query items --json # list configured chat IDs
telegram query actions --json # available CLI actions
Verify ffmpeg availability, config, and bot API reachability.
telegram doctor
telegram doctor --json
~/.alluka/channels/telegram.json:
{
"bot_token": "<your-bot-token>",
"chat_ids": ["<chat-id>"]
}
Get your bot token from @BotFather. Chat IDs can be found via @userinfobot or the Telegram API.
User: "send this audio to Telegram"
Action: telegram send-voice-message --chat <id> --audio /path/to/audio.mp3
User: "generate a voice message and send to Telegram" Action:
elevenlabs generate narration.txt --output /tmp/
telegram send-voice-message --chat <id> --audio /tmp/narration.mp3